Merge tag 'for-5.13/block-2021-04-27' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "Pretty quiet round this time, which is nice. In detail:

   - Series revamping bounce buffer support (Christoph)

   - Dead code removal (Christoph, Bart)

   - Partition iteration revamp, now using xarray (Christoph)

   - Passthrough request scheduler improvements (Lin)

   - Series of BFQ improvements (Paolo)

   - Fix ioprio task iteration (Peter)

   - Various little tweaks and fixes (Tejun, Saravanan, Bhaskar, Max,
     Nikolay)"

* tag 'for-5.13/block-2021-04-27' of git://git.kernel.dk/linux-block: (41 commits)
  blk-iocost: don't ignore vrate_min on QD contention
  blk-mq: Fix spurious debugfs directory creation during initialization
  bfq/mq-deadline: remove redundant check for passthrough request
  blk-mq: bypass IO scheduler's limit_depth for passthrough request
  block: Remove an obsolete comment from sg_io()
  block: move bio_list_copy_data to pktcdvd
  block: remove zero_fill_bio_iter
  block: add queue_to_disk() to get gendisk from request_queue
  block: remove an incorrect check from blk_rq_append_bio
  block: initialize ret in bdev_disk_changed
  block: Fix sys_ioprio_set(.which=IOPRIO_WHO_PGRP) task iteration
  block: remove disk_part_iter
  block: simplify diskstats_show
  block: simplify show_partition
  block: simplify printk_all_partitions
  block: simplify partition_overlaps
  block: simplify partition removal
  block: take bd_mutex around delete_partitions in del_gendisk
  block: refactor blk_drop_partitions
  block: move more syncing and invalidation to delete_partition
  ...

23 files changed, 585 insertions, 522 deletions

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index b791e2041e49..e2f14508f2d6 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -547,6 +547,8 @@ static void bfq_pd_init(struct blkg_policy_data *pd)
 
 	entity->orig_weight = entity->weight = entity->new_weight = d->weight;
 	entity->my_sched_data = &bfqg->sched_data;
+	entity->last_bfqq_created = NULL;
+
 	bfqg->my_entity = entity; /*
 				   * the root_group's will be set to NULL
 				   * in bfq_init_queue()
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 95586137194e..0270cd7ca165 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -1012,7 +1012,7 @@ static void
 bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 		      struct bfq_io_cq *bic, bool bfq_already_existing)
 {
-	unsigned int old_wr_coeff = bfqq->wr_coeff;
+	unsigned int old_wr_coeff = 1;
 	bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq);
 
 	if (bic->saved_has_short_ttime)
@@ -1033,7 +1033,13 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 	bfqq->ttime = bic->saved_ttime;
 	bfqq->io_start_time = bic->saved_io_start_time;
 	bfqq->tot_idle_time = bic->saved_tot_idle_time;
-	bfqq->wr_coeff = bic->saved_wr_coeff;
+	/*
+	 * Restore weight coefficient only if low_latency is on
+	 */
+	if (bfqd->low_latency) {
+		old_wr_coeff = bfqq->wr_coeff;
+		bfqq->wr_coeff = bic->saved_wr_coeff;
+	}
 	bfqq->service_from_wr = bic->saved_service_from_wr;
 	bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt;
 	bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish;
@@ -1069,7 +1075,7 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 static int bfqq_process_refs(struct bfq_queue *bfqq)
 {
 	return bfqq->ref - bfqq->allocated - bfqq->entity.on_st_or_in_serv -
-		(bfqq->weight_counter != NULL);
+		(bfqq->weight_counter != NULL) - bfqq->stable_ref;
 }
 
 /* Empty burst list and add just bfqq (see comments on bfq_handle_burst) */
@@ -2622,6 +2628,11 @@ static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq,
 	return true;
 }
 
+static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd,
+					     struct bfq_queue *bfqq);
+
+static void bfq_put_stable_ref(struct bfq_queue *bfqq);
+
 /*
  * Attempt to schedule a merge of bfqq with the currently in-service
  * queue or with a close queue among the scheduled queues.  Return
@@ -2644,11 +2655,50 @@ static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq,
  */
 static struct bfq_queue *
 bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
-		     void *io_struct, bool request)
+		     void *io_struct, bool request, struct bfq_io_cq *bic)
 {
 	struct bfq_queue *in_service_bfqq, *new_bfqq;
 
 	/*
+	 * Check delayed stable merge for rotational or non-queueing
+	 * devs. For this branch to be executed, bfqq must not be
+	 * currently merged with some other queue (i.e., bfqq->bic
+	 * must be non null). If we considered also merged queues,
+	 * then we should also check whether bfqq has already been
+	 * merged with bic->stable_merge_bfqq. But this would be
+	 * costly and complicated.
+	 */
+	if (unlikely(!bfqd->nonrot_with_queueing)) {
+		if (bic->stable_merge_bfqq &&
+		    !bfq_bfqq_just_created(bfqq) &&
+		    time_is_after_jiffies(bfqq->split_time +
+					  msecs_to_jiffies(200))) {
+			struct bfq_queue *stable_merge_bfqq =
+				bic->stable_merge_bfqq;
+			int proc_ref = min(bfqq_process_refs(bfqq),
+					   bfqq_process_refs(stable_merge_bfqq));
+
+			/* deschedule stable merge, because done or aborted here */
+			bfq_put_stable_ref(stable_merge_bfqq);
+
+			bic->stable_merge_bfqq = NULL;
+
+			if (!idling_boosts_thr_without_issues(bfqd, bfqq) &&
+			    proc_ref > 0) {
+				/* next function will take at least one ref */
+				struct bfq_queue *new_bfqq =
+					bfq_setup_merge(bfqq, stable_merge_bfqq);
+
+				bic->stably_merged = true;
+				if (new_bfqq && new_bfqq->bic)
+					new_bfqq->bic->stably_merged = true;
+				return new_bfqq;
+			} else
+				return NULL;
+		}
+	}
+
+	/*
 	 * Do not perform queue merging if the device is non
 	 * rotational and performs internal queueing. In fact, such a
 	 * device reaches a high speed through internal parallelism
@@ -2789,6 +2839,17 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	}
 }
 
+
+static void
+bfq_reassign_last_bfqq(struct bfq_queue *cur_bfqq, struct bfq_queue *new_bfqq)
+{
+	if (cur_bfqq->entity.parent &&
+	    cur_bfqq->entity.parent->last_bfqq_created == cur_bfqq)
+		cur_bfqq->entity.parent->last_bfqq_created = new_bfqq;
+	else if (cur_bfqq->bfqd && cur_bfqq->bfqd->last_bfqq_created == cur_bfqq)
+		cur_bfqq->bfqd->last_bfqq_created = new_bfqq;
+}
+
 void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 {
 	/*
@@ -2806,6 +2867,8 @@ void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 	    bfqq != bfqd->in_service_queue)
 		bfq_del_bfqq_busy(bfqd, bfqq, false);
 
+	bfq_reassign_last_bfqq(bfqq, NULL);
+
 	bfq_put_queue(bfqq);
 }
 
@@ -2823,6 +2886,29 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 	bfq_clear_bfqq_IO_bound(bfqq);
 
 	/*
+	 * The processes associated with bfqq are cooperators of the
+	 * processes associated with new_bfqq. So, if bfqq has a
+	 * waker, then assume that all these processes will be happy
+	 * to let bfqq's waker freely inject I/O when they have no
+	 * I/O.
+	 */
+	if (bfqq->waker_bfqq && !new_bfqq->waker_bfqq &&
+	    bfqq->waker_bfqq != new_bfqq) {
+		new_bfqq->waker_bfqq = bfqq->waker_bfqq;
+		new_bfqq->tentative_waker_bfqq = NULL;
+
+		/*
+		 * If the waker queue disappears, then
+		 * new_bfqq->waker_bfqq must be reset. So insert
+		 * new_bfqq into the woken_list of the waker. See
+		 * bfq_check_waker for details.
+		 */
+		hlist_add_head(&new_bfqq->woken_list_node,
+			       &new_bfqq->waker_bfqq->woken_list);
+
+	}
+
+	/*
 	 * If bfqq is weight-raised, then let new_bfqq inherit
 	 * weight-raising. To reduce false positives, neglect the case
 	 * where bfqq has just been created, but has not yet made it
@@ -2879,6 +2965,9 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 	 */
 	new_bfqq->pid = -1;
 	bfqq->bic = NULL;
+
+	bfq_reassign_last_bfqq(bfqq, new_bfqq);
+
 	bfq_release_process_ref(bfqd, bfqq);
 }
 
@@ -2906,7 +2995,7 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
 	 * We take advantage of this function to perform an early merge
 	 * of the queues of possible cooperating processes.
 	 */
-	new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
+	new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false, bfqd->bio_bic);
 	if (new_bfqq) {
 		/*
 		 * bic still points to bfqq, then it has not yet been
@@ -4491,9 +4580,15 @@ check_queue:
 			bfq_bfqq_busy(bfqq->bic->bfqq[0]) &&
 			bfqq->bic->bfqq[0]->next_rq ?
 			bfqq->bic->bfqq[0] : NULL;
+		struct bfq_queue *blocked_bfqq =
+			!hlist_empty(&bfqq->woken_list) ?
+			container_of(bfqq->woken_list.first,
+				     struct bfq_queue,
+				     woken_list_node)
+			: NULL;
 
 		/*
-		 * The next three mutually-exclusive ifs decide
+		 * The next four mutually-exclusive ifs decide
 		 * whether to try injection, and choose the queue to
 		 * pick an I/O request from.
 		 *
@@ -4526,7 +4621,15 @@ check_queue:
 		 * next bfqq's I/O is brought forward dramatically,
 		 * for it is not blocked for milliseconds.
 		 *
-		 * The third if checks whether bfqq is a queue for
+		 * The third if checks whether there is a queue woken
+		 * by bfqq, and currently with pending I/O. Such a
+		 * woken queue does not steal bandwidth from bfqq,
+		 * because it remains soon without I/O if bfqq is not
+		 * served. So there is virtually no risk of loss of
+		 * bandwidth for bfqq if this woken queue has I/O
+		 * dispatched while bfqq is waiting for new I/O.
+		 *
+		 * The fourth if checks whether bfqq is a queue for
 		 * which it is better to avoid injection. It is so if
 		 * bfqq delivers more throughput when served without
 		 * any further I/O from other queues in the middle, or
@@ -4546,11 +4649,11 @@ check_queue:
 		 * bfq_update_has_short_ttime(), it is rather likely
 		 * that, if I/O is being plugged for bfqq and the
 		 * waker queue has pending I/O requests that are
-		 * blocking bfqq's I/O, then the third alternative
+		 * blocking bfqq's I/O, then the fourth alternative
 		 * above lets the waker queue get served before the
 		 * I/O-plugging timeout fires. So one may deem the
 		 * second alternative superfluous. It is not, because
-		 * the third alternative may be way less effective in
+		 * the fourth alternative may be way less effective in
 		 * case of a synchronization. For two main
 		 * reasons. First, throughput may be low because the
 		 * inject limit may be too low to guarantee the same
@@ -4559,7 +4662,7 @@ check_queue:
 		 * guarantees (the second alternative unconditionally
 		 * injects a pending I/O request of the waker queue
 		 * for each bfq_dispatch_request()). Second, with the
-		 * third alternative, the duration of the plugging,
+		 * fourth alternative, the duration of the plugging,
 		 * i.e., the time before bfqq finally receives new I/O,
 		 * may not be minimized, because the waker queue may
 		 * happen to be served only after other queues.
@@ -4577,6 +4680,14 @@ check_queue:
 			   bfq_bfqq_budget_left(bfqq->waker_bfqq)
 			)
 			bfqq = bfqq->waker_bfqq;
+		else if (blocked_bfqq &&
+			   bfq_bfqq_busy(blocked_bfqq) &&
+			   blocked_bfqq->next_rq &&
+			   bfq_serv_to_charge(blocked_bfqq->next_rq,
+					      blocked_bfqq) <=
+			   bfq_bfqq_budget_left(blocked_bfqq)
+			)
+			bfqq = blocked_bfqq;
 		else if (!idling_boosts_thr_without_issues(bfqd, bfqq) &&
 			 (bfqq->wr_coeff == 1 || bfqd->wr_busy_queues > 1 ||
 			  !bfq_bfqq_has_short_ttime(bfqq)))
@@ -4983,6 +5094,12 @@ void bfq_put_queue(struct bfq_queue *bfqq)
 	bfqg_and_blkg_put(bfqg);
 }
 
+static void bfq_put_stable_ref(struct bfq_queue *bfqq)
+{
+	bfqq->stable_ref--;
+	bfq_put_queue(bfqq);
+}
+
 static void bfq_put_cooperator(struct bfq_queue *bfqq)
 {
 	struct bfq_queue *__bfqq, *next;
@@ -5039,6 +5156,24 @@ static void bfq_exit_icq(struct io_cq *icq)
 {
 	struct bfq_io_cq *bic = icq_to_bic(icq);
 
+	if (bic->stable_merge_bfqq) {
+		struct bfq_data *bfqd = bic->stable_merge_bfqq->bfqd;
+
+		/*
+		 * bfqd is NULL if scheduler already exited, and in
+		 * that case this is the last time bfqq is accessed.
+		 */
+		if (bfqd) {
+			unsigned long flags;
+
+			spin_lock_irqsave(&bfqd->lock, flags);
+			bfq_put_stable_ref(bic->stable_merge_bfqq);
+			spin_unlock_irqrestore(&bfqd->lock, flags);
+		} else {
+			bfq_put_stable_ref(bic->stable_merge_bfqq);
+		}
+	}
+
 	bfq_exit_icq_bfqq(bic, true);
 	bfq_exit_icq_bfqq(bic, false);
 }
@@ -5099,7 +5234,8 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
 
 static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
 				       struct bio *bio, bool is_sync,
-				       struct bfq_io_cq *bic);
+				       struct bfq_io_cq *bic,
+				       bool respawn);
 
 static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio)
 {
@@ -5119,7 +5255,7 @@ static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio)
 	bfqq = bic_to_bfqq(bic, false);
 	if (bfqq) {
 		bfq_release_process_ref(bfqd, bfqq);
-		bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic);
+		bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic, true);
 		bic_set_bfqq(bic, bfqq, false);
 	}
 
@@ -5162,6 +5298,8 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	/* set end request to minus infinity from now */
 	bfqq->ttime.last_end_request = now_ns + 1;
 
+	bfqq->creation_time = jiffies;
+
 	bfqq->io_start_time = now_ns;
 
 	bfq_mark_bfqq_IO_bound(bfqq);
@@ -5211,9 +5349,156 @@ static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd,
 	}
 }
 
+static struct bfq_queue *
+bfq_do_early_stable_merge(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			  struct bfq_io_cq *bic,
+			  struct bfq_queue *last_bfqq_created)
+{
+	struct bfq_queue *new_bfqq =
+		bfq_setup_merge(bfqq, last_bfqq_created);
+
+	if (!new_bfqq)
+		return bfqq;
+
+	if (new_bfqq->bic)
+		new_bfqq->bic->stably_merged = true;
+	bic->stably_merged = true;
+
+	/*
+	 * Reusing merge functions. This implies that
+	 * bfqq->bic must be set too, for
+	 * bfq_merge_bfqqs to correctly save bfqq's
+	 * state before killing it.
+	 */
+	bfqq->bic = bic;
+	bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq);
+
+	return new_bfqq;
+}
+
+/*
+ * Many throughput-sensitive workloads are made of several parallel
+ * I/O flows, with all flows generated by the same application, or
+ * more generically by the same task (e.g., system boot). The most
+ * counterproductive action with these workloads is plugging I/O
+ * dispatch when one of the bfq_queues associated with these flows
+ * remains temporarily empty.
+ *
+ * To avoid this plugging, BFQ has been using a burst-handling
+ * mechanism for years now. This mechanism has proven effective for
+ * throughput, and not detrimental for service guarantees. The
+ * following function pushes this mechanism a little bit further,
+ * basing on the following two facts.
+ *
+ * First, all the I/O flows of a the same application or task
+ * contribute to the execution/completion of that common application
+ * or task. So the performance figures that matter are total
+ * throughput of the flows and task-wide I/O latency.  In particular,
+ * these flows do not need to be protected from each other, in terms
+ * of individual bandwidth or latency.
+ *
+ * Second, the above fact holds regardless of the number of flows.
+ *
+ * Putting these two facts together, this commits merges stably the
+ * bfq_queues associated with these I/O flows, i.e., with the
+ * processes that generate these IO/ flows, regardless of how many the
+ * involved processes are.
+ *
+ * To decide whether a set of bfq_queues is actually associated with
+ * the I/O flows of a common application or task, and to merge these
+ * queues stably, this function operates as follows: given a bfq_queue,
+ * say Q2, currently being created, and the last bfq_queue, say Q1,
+ * created before Q2, Q2 is merged stably with Q1 if
+ * - very little time has elapsed since when Q1 was created
+ * - Q2 has the same ioprio as Q1
+ * - Q2 belongs to the same group as Q1
+ *
+ * Merging bfq_queues also reduces scheduling overhead. A fio test
+ * with ten random readers on /dev/nullb shows a throughput boost of
+ * 40%, with a quadcore. Since BFQ's execution time amounts to ~50% of
+ * the total per-request processing time, the above throughput boost
+ * implies that BFQ's overhead is reduced by more than 50%.
+ *
+ * This new mechanism most certainly obsoletes the current
+ * burst-handling heuristics. We keep those heuristics for the moment.
+ */
+static struct bfq_queue *bfq_do_or_sched_stable_merge(struct bfq_data *bfqd,
+						      struct bfq_queue *bfqq,
+						      struct bfq_io_cq *bic)
+{
+	struct bfq_queue **source_bfqq = bfqq->entity.parent ?
+		&bfqq->entity.parent->last_bfqq_created :
+		&bfqd->last_bfqq_created;
+
+	struct bfq_queue *last_bfqq_created = *source_bfqq;
+
+	/*
+	 * If last_bfqq_created has not been set yet, then init it. If
+	 * it has been set already, but too long ago, then move it
+	 * forward to bfqq. Finally, move also if bfqq belongs to a
+	 * different group than last_bfqq_created, or if bfqq has a
+	 * different ioprio or ioprio_class. If none of these
+	 * conditions holds true, then try an early stable merge or
+	 * schedule a delayed stable merge.
+	 *
+	 * A delayed merge is scheduled (instead of performing an
+	 * early merge), in case bfqq might soon prove to be more
+	 * throughput-beneficial if not merged. Currently this is
+	 * possible only if bfqd is rotational with no queueing. For
+	 * such a drive, not merging bfqq is better for throughput if
+	 * bfqq happens to contain sequential I/O. So, we wait a
+	 * little bit for enough I/O to flow through bfqq. After that,
+	 * if such an I/O is sequential, then the merge is
+	 * canceled. Otherwise the merge is finally performed.
+	 */
+	if (!last_bfqq_created ||
+	    time_before(last_bfqq_created->creation_time +
+			bfqd->bfq_burst_interval,
+			bfqq->creation_time) ||
+		bfqq->entity.parent != last_bfqq_created->entity.parent ||
+		bfqq->ioprio != last_bfqq_created->ioprio ||
+		bfqq->ioprio_class != last_bfqq_created->ioprio_class)
+		*source_bfqq = bfqq;
+	else if (time_after_eq(last_bfqq_created->creation_time +
+				 bfqd->bfq_burst_interval,
+				 bfqq->creation_time)) {
+		if (likely(bfqd->nonrot_with_queueing))
+			/*
+			 * With this type of drive, leaving
+			 * bfqq alone may provide no
+			 * throughput benefits compared with
+			 * merging bfqq. So merge bfqq now.
+			 */
+			bfqq = bfq_do_early_stable_merge(bfqd, bfqq,
+							 bic,
+							 last_bfqq_created);
+		else { /* schedule tentative stable merge */
+			/*
+			 * get reference on last_bfqq_created,
+			 * to prevent it from being freed,
+			 * until we decide whether to merge
+			 */
+			last_bfqq_created->ref++;
+			/*
+			 * need to keep track of stable refs, to
+			 * compute process refs correctly
+			 */
+			last_bfqq_created->stable_ref++;
+			/*
+			 * Record the bfqq to merge to.
+			 */
+			bic->stable_merge_bfqq = last_bfqq_created;
+		}
+	}
+
+	return bfqq;
+}
+
+
 static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
 				       struct bio *bio, bool is_sync,
-				       struct bfq_io_cq *bic)
+				       struct bfq_io_cq *bic,
+				       bool respawn)
 {
 	const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
 	const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
@@ -5271,7 +5556,10 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
 
 out:
 	bfqq->ref++; /* get a process reference to this queue */
-	bfq_log_bfqq(bfqd, bfqq, "get_queue, at end: %p, %d", bfqq, bfqq->ref);
+
+	if (bfqq != &bfqd->oom_bfqq && is_sync && !respawn)
+		bfqq = bfq_do_or_sched_stable_merge(bfqd, bfqq, bic);
+
 	rcu_read_unlock();
 	return bfqq;
 }
@@ -5521,7 +5809,8 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 {
 	struct bfq_queue *bfqq = RQ_BFQQ(rq),
-		*new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true);
+		*new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true,
+						 RQ_BIC(rq));
 	bool waiting, idle_timer_disabled = false;
 
 	if (new_bfqq) {
@@ -5627,7 +5916,48 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	spin_lock_irq(&bfqd->lock);
 	bfqq = bfq_init_rq(rq);
-	if (!bfqq || at_head || blk_rq_is_passthrough(rq)) {
+
+	/*
+	 * Reqs with at_head or passthrough flags set are to be put
+	 * directly into dispatch list. Additional case for putting rq
+	 * directly into the dispatch queue: the only active
+	 * bfq_queues are bfqq and either its waker bfq_queue or one
+	 * of its woken bfq_queues. The rationale behind this
+	 * additional condition is as follows:
+	 * - consider a bfq_queue, say Q1, detected as a waker of
+	 *   another bfq_queue, say Q2
+	 * - by definition of a waker, Q1 blocks the I/O of Q2, i.e.,
+	 *   some I/O of Q1 needs to be completed for new I/O of Q2
+	 *   to arrive.  A notable example of waker is journald
+	 * - so, Q1 and Q2 are in any respect the queues of two
+	 *   cooperating processes (or of two cooperating sets of
+	 *   processes): the goal of Q1's I/O is doing what needs to
+	 *   be done so that new Q2's I/O can finally be
+	 *   issued. Therefore, if the service of Q1's I/O is delayed,
+	 *   then Q2's I/O is delayed too.  Conversely, if Q2's I/O is
+	 *   delayed, the goal of Q1's I/O is hindered.
+	 * - as a consequence, if some I/O of Q1/Q2 arrives while
+	 *   Q2/Q1 is the only queue in service, there is absolutely
+	 *   no point in delaying the service of such an I/O. The
+	 *   only possible result is a throughput loss
+	 * - so, when the above condition holds, the best option is to
+	 *   have the new I/O dispatched as soon as possible
+	 * - the most effective and efficient way to attain the above
+	 *   goal is to put the new I/O directly in the dispatch
+	 *   list
+	 * - as an additional restriction, Q1 and Q2 must be the only
+	 *   busy queues for this commit to put the I/O of Q2/Q1 in
+	 *   the dispatch list.  This is necessary, because, if also
+	 *   other queues are waiting for service, then putting new
+	 *   I/O directly in the dispatch list may evidently cause a
+	 *   violation of service guarantees for the other queues
+	 */
+	if (!bfqq ||
+	    (bfqq != bfqd->in_service_queue &&
+	     bfqd->in_service_queue != NULL &&
+	     bfq_tot_busy_queues(bfqd) == 1 + bfq_bfqq_busy(bfqq) &&
+	     (bfqq->waker_bfqq == bfqd->in_service_queue ||
+	      bfqd->in_service_queue->waker_bfqq == bfqq)) || at_head) {
 		if (at_head)
 			list_add(&rq->queuelist, &bfqd->dispatch);
 		else
@@ -5767,7 +6097,17 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 			1UL<<(BFQ_RATE_SHIFT - 10))
 		bfq_update_rate_reset(bfqd, NULL);
 	bfqd->last_completion = now_ns;
-	bfqd->last_completed_rq_bfqq = bfqq;
+	/*
+	 * Shared queues are likely to receive I/O at a high
+	 * rate. This may deceptively let them be considered as wakers
+	 * of other queues. But a false waker will unjustly steal
+	 * bandwidth to its supposedly woken queue. So considering
+	 * also shared queues in the waking mechanism may cause more
+	 * control troubles than throughput benefits. Then do not set
+	 * last_completed_rq_bfqq to bfqq if bfqq is a shared queue.
+	 */
+	if (!bfq_bfqq_coop(bfqq))
+		bfqd->last_completed_rq_bfqq = bfqq;
 
 	/*
 	 * If we are waiting to discover whether the request pattern
@@ -6124,7 +6464,7 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
 
 	if (bfqq)
 		bfq_put_queue(bfqq);
-	bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);
+	bfqq = bfq_get_queue(bfqd, bio, is_sync, bic, split);
 
 	bic_set_bfqq(bic, bfqq, is_sync);
 	if (split && is_sync) {
@@ -6245,8 +6585,9 @@ static struct bfq_queue *bfq_init_rq(struct request *rq)
 
 	if (likely(!new_queue)) {
 		/* If the queue was seeky for too long, break it apart. */
-		if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
-			bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
+		if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq) &&
+			!bic->stably_merged) {
+			struct bfq_queue *old_bfqq = bfqq;
 
 			/* Update bic before losing reference to bfqq */
 			if (bfq_bfqq_in_large_burst(bfqq))
@@ -6255,11 +6596,24 @@ static struct bfq_queue *bfq_init_rq(struct request *rq)
 			bfqq = bfq_split_bfqq(bic, bfqq);
 			split = true;
 
-			if (!bfqq)
+			if (!bfqq) {
 				bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,
 								 true, is_sync,
 								 NULL);
-			else
+				bfqq->waker_bfqq = old_bfqq->waker_bfqq;
+				bfqq->tentative_waker_bfqq = NULL;
+
+				/*
+				 * If the waker queue disappears, then
+				 * new_bfqq->waker_bfqq must be
+				 * reset. So insert new_bfqq into the
+				 * woken_list of the waker. See
+				 * bfq_check_waker for details.
+				 */
+				if (bfqq->waker_bfqq)
+					hlist_add_head(&bfqq->woken_list_node,
+						       &bfqq->waker_bfqq->woken_list);
+			} else
 				bfqq_already_existing = true;
 		}
 	}
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index b8e793c34ff1..99c2a3cb081e 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -197,6 +197,9 @@ struct bfq_entity {
 
 	/* flag, set if the entity is counted in groups_with_pending_reqs */
 	bool in_groups_with_pending_reqs;
+
+	/* last child queue of entity created (for non-leaf entities) */
+	struct bfq_queue *last_bfqq_created;
 };
 
 struct bfq_group;
@@ -230,6 +233,8 @@ struct bfq_ttime {
 struct bfq_queue {
 	/* reference counter */
 	int ref;
+	/* counter of references from other queues for delayed stable merge */
+	int stable_ref;
 	/* parent bfq_data */
 	struct bfq_data *bfqd;
 
@@ -365,6 +370,8 @@ struct bfq_queue {
 
 	unsigned long first_IO_time; /* time of first I/O for this queue */
 
+	unsigned long creation_time; /* when this queue is created */
+
 	/* max service rate measured so far */
 	u32 max_service_rate;
 
@@ -454,6 +461,11 @@ struct bfq_io_cq {
 	u64 saved_last_serv_time_ns;
 	unsigned int saved_inject_limit;
 	unsigned long saved_decrease_time_jif;
+
+	/* candidate queue for a stable merge (due to close creation time) */
+	struct bfq_queue *stable_merge_bfqq;
+
+	bool stably_merged;	/* non splittable if true */
 };
 
 /**
@@ -578,6 +590,9 @@ struct bfq_data {
 	/* bfqq owning the last completed rq */
 	struct bfq_queue *last_completed_rq_bfqq;
 
+	/* last bfqq created, among those in the root group */
+	struct bfq_queue *last_bfqq_created;
+
 	/* time of last transition from empty to non-empty (ns) */
 	u64 last_empty_occupied_ns;
 
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index 070e34a7feb1..7a462df71f68 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -1706,4 +1706,12 @@ void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 
 	if (bfqq->wr_coeff > 1)
 		bfqd->wr_busy_queues++;
+
+	/* Move bfqq to the head of the woken list of its waker */
+	if (!hlist_unhashed(&bfqq->woken_list_node) &&
+	    &bfqq->woken_list_node != bfqq->waker_bfqq->woken_list.first) {
+		hlist_del_init(&bfqq->woken_list_node);
+		hlist_add_head(&bfqq->woken_list_node,
+			       &bfqq->waker_bfqq->woken_list);
+	}
 }
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index dfa652122a2d..4b4eb8964a6f 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -204,7 +204,6 @@ bool bio_integrity_prep(struct bio *bio)
 {
 	struct bio_integrity_payload *bip;
 	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
-	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
 	void *buf;
 	unsigned long start, end;
 	unsigned int len, nr_pages;
@@ -238,7 +237,7 @@ bool bio_integrity_prep(struct bio *bio)
 
 	/* Allocate kernel buffer for protection data */
 	len = intervals * bi->tuple_size;
-	buf = kmalloc(len, GFP_NOIO | q->bounce_gfp);
+	buf = kmalloc(len, GFP_NOIO);
 	status = BLK_STS_RESOURCE;
 	if (unlikely(buf == NULL)) {
 		printk(KERN_ERR "could not allocate integrity buffer\n");
diff --git a/block/bio.c b/block/bio.c
index 50e579088aca..44205dfb6b60 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -493,20 +493,20 @@ struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs)
 }
 EXPORT_SYMBOL(bio_kmalloc);
 
-void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start)
+void zero_fill_bio(struct bio *bio)
 {
 	unsigned long flags;
 	struct bio_vec bv;
 	struct bvec_iter iter;
 
-	__bio_for_each_segment(bv, bio, iter, start) {
+	bio_for_each_segment(bv, bio, iter) {
 		char *data = bvec_kmap_irq(&bv, &flags);
 		memset(data, 0, bv.bv_len);
 		flush_dcache_page(bv.bv_page);
 		bvec_kunmap_irq(data, &flags);
 	}
 }
-EXPORT_SYMBOL(zero_fill_bio_iter);
+EXPORT_SYMBOL(zero_fill_bio);
 
 /**
  * bio_truncate - truncate the bio to small size of @new_size
@@ -1236,43 +1236,6 @@ void bio_copy_data(struct bio *dst, struct bio *src)
 }
 EXPORT_SYMBOL(bio_copy_data);
 
-/**
- * bio_list_copy_data - copy contents of data buffers from one chain of bios to
- * another
- * @src: source bio list
- * @dst: destination bio list
- *
- * Stops when it reaches the end of either the @src list or @dst list - that is,
- * copies min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of
- * bios).
- */
-void bio_list_copy_data(struct bio *dst, struct bio *src)
-{
-	struct bvec_iter src_iter = src->bi_iter;
-	struct bvec_iter dst_iter = dst->bi_iter;
-
-	while (1) {
-		if (!src_iter.bi_size) {
-			src = src->bi_next;
-			if (!src)
-				break;
-
-			src_iter = src->bi_iter;
-		}
-
-		if (!dst_iter.bi_size) {
-			dst = dst->bi_next;
-			if (!dst)
-				break;
-
-			dst_iter = dst->bi_iter;
-		}
-
-		bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
-	}
-}
-EXPORT_SYMBOL(bio_list_copy_data);
-
 void bio_free_pages(struct bio *bio)
 {
 	struct bio_vec *bvec;
diff --git a/block/blk-core.c b/block/blk-core.c
index fc60ff208497..9bcdae93f6d4 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1161,10 +1161,8 @@ static blk_status_t blk_cloned_rq_check_limits(struct request_queue *q,
 	}
 
 	/*
-	 * queue's settings related to segment counting like q->bounce_pfn
-	 * may differ from that of other stacking queues.
-	 * Recalculate it to check the request correctly on this queue's
-	 * limitation.
+	 * The queue settings related to segment counting may differ from the
+	 * original queue.
 	 */
 	rq->nr_phys_segments = blk_recalc_rq_segments(rq);
 	if (rq->nr_phys_segments > queue_max_segments(q)) {
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 98d656bdb42b..e0c4baa01857 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -987,10 +987,6 @@ static void ioc_adjust_base_vrate(struct ioc *ioc, u32 rq_wait_pct,
 		return;
 	}
 
-	/* rq_wait signal is always reliable, ignore user vrate_min */
-	if (rq_wait_pct > RQ_WAIT_BUSY_PCT)
-		vrate_min = VRATE_MIN;
-
 	/*
 	 * If vrate is out of bounds, apply clamp gradually as the
 	 * bounds can change abruptly.  Otherwise, apply busy_level
diff --git a/block/blk-map.c b/block/blk-map.c
index 1ffef782fcf2..3743158ddaeb 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -123,7 +123,6 @@ static int bio_uncopy_user(struct bio *bio)
 			bio_free_pages(bio);
 	}
 	kfree(bmd);
-	bio_put(bio);
 	return ret;
 }
 
@@ -132,7 +131,7 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data,
 {
 	struct bio_map_data *bmd;
 	struct page *page;
-	struct bio *bio, *bounce_bio;
+	struct bio *bio;
 	int i = 0, ret;
 	int nr_pages;
 	unsigned int len = iter->count;
@@ -181,7 +180,7 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data,
 
 			i++;
 		} else {
-			page = alloc_page(rq->q->bounce_gfp | gfp_mask);
+			page = alloc_page(GFP_NOIO | gfp_mask);
 			if (!page) {
 				ret = -ENOMEM;
 				goto cleanup;
@@ -218,16 +217,9 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data,
 
 	bio->bi_private = bmd;
 
-	bounce_bio = bio;
-	ret = blk_rq_append_bio(rq, &bounce_bio);
+	ret = blk_rq_append_bio(rq, bio);
 	if (ret)
 		goto cleanup;
-
-	/*
-	 * We link the bounce buffer in and could have to traverse it later, so
-	 * we have to get a ref to prevent it from being freed
-	 */
-	bio_get(bounce_bio);
 	return 0;
 cleanup:
 	if (!map_data)
@@ -242,7 +234,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 		gfp_t gfp_mask)
 {
 	unsigned int max_sectors = queue_max_hw_sectors(rq->q);
-	struct bio *bio, *bounce_bio;
+	struct bio *bio;
 	int ret;
 	int j;
 
@@ -304,49 +296,17 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 			break;
 	}
 
-	/*
-	 * Subtle: if we end up needing to bounce a bio, it would normally
-	 * disappear when its bi_end_io is run.  However, we need the original
-	 * bio for the unmap, so grab an extra reference to it
-	 */
-	bio_get(bio);
-
-	bounce_bio = bio;
-	ret = blk_rq_append_bio(rq, &bounce_bio);
+	ret = blk_rq_append_bio(rq, bio);
 	if (ret)
-		goto out_put_orig;
-
-	/*
-	 * We link the bounce buffer in and could have to traverse it
-	 * later, so we have to get a ref to prevent it from being freed
-	 */
-	bio_get(bounce_bio);
+		goto out_unmap;
 	return 0;
 
- out_put_orig:
-	bio_put(bio);
  out_unmap:
 	bio_release_pages(bio, false);
 	bio_put(bio);
 	return ret;
 }
 
-/**
- *	bio_unmap_user	-	unmap a bio
- *	@bio:		the bio being unmapped
- *
- *	Unmap a bio previously mapped by bio_map_user_iov(). Must be called from
- *	process context.
- *
- *	bio_unmap_user() may sleep.
- */
-static void bio_unmap_user(struct bio *bio)
-{
-	bio_release_pages(bio, bio_data_dir(bio) == READ);
-	bio_put(bio);
-	bio_put(bio);
-}
-
 static void bio_invalidate_vmalloc_pages(struct bio *bio)
 {
 #ifdef ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
@@ -486,7 +446,7 @@ static struct bio *bio_copy_kern(struct request_queue *q, void *data,
 		if (bytes > len)
 			bytes = len;
 
-		page = alloc_page(q->bounce_gfp | gfp_mask);
+		page = alloc_page(GFP_NOIO | gfp_mask);
 		if (!page)
 			goto cleanup;
 
@@ -519,33 +479,24 @@ cleanup:
  * Append a bio to a passthrough request.  Only works if the bio can be merged
  * into the request based on the driver constraints.
  */
-int blk_rq_append_bio(struct request *rq, struct bio **bio)
+int blk_rq_append_bio(struct request *rq, struct bio *bio)
 {
-	struct bio *orig_bio = *bio;
 	struct bvec_iter iter;
 	struct bio_vec bv;
 	unsigned int nr_segs = 0;
 
-	blk_queue_bounce(rq->q, bio);
-
-	bio_for_each_bvec(bv, *bio, iter)
+	bio_for_each_bvec(bv, bio, iter)
 		nr_segs++;
 
 	if (!rq->bio) {
-		blk_rq_bio_prep(rq, *bio, nr_segs);
+		blk_rq_bio_prep(rq, bio, nr_segs);
 	} else {
-		if (!ll_back_merge_fn(rq, *bio, nr_segs)) {
-			if (orig_bio != *bio) {
-				bio_put(*bio);
-				*bio = orig_bio;
-			}
+		if (!ll_back_merge_fn(rq, bio, nr_segs))
 			return -EINVAL;
-		}
-
-		rq->biotail->bi_next = *bio;
-		rq->biotail = *bio;
-		rq->__data_len += (*bio)->bi_iter.bi_size;
-		bio_crypt_free_ctx(*bio);
+		rq->biotail->bi_next = bio;
+		rq->biotail = bio;
+		rq->__data_len += (bio)->bi_iter.bi_size;
+		bio_crypt_free_ctx(bio);
 	}
 
 	return 0;
@@ -566,12 +517,6 @@ EXPORT_SYMBOL(blk_rq_append_bio);
  *
  *    A matching blk_rq_unmap_user() must be issued at the end of I/O, while
  *    still in process context.
- *
- *    Note: The mapped bio may need to be bounced through blk_queue_bounce()
- *    before being submitted to the device, as pages mapped may be out of
- *    reach. It's the callers responsibility to make sure this happens. The
- *    original bio must be passed back in to blk_rq_unmap_user() for proper
- *    unmapping.
  */
 int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 			struct rq_map_data *map_data,
@@ -588,6 +533,8 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 
 	if (map_data)
 		copy = true;
+	else if (blk_queue_may_bounce(q))
+		copy = true;
 	else if (iov_iter_alignment(iter) & align)
 		copy = true;
 	else if (queue_virt_boundary(q))
@@ -641,25 +588,21 @@ EXPORT_SYMBOL(blk_rq_map_user);
  */
 int blk_rq_unmap_user(struct bio *bio)
 {
-	struct bio *mapped_bio;
+	struct bio *next_bio;
 	int ret = 0, ret2;
 
 	while (bio) {
-		mapped_bio = bio;
-		if (unlikely(bio_flagged(bio, BIO_BOUNCED)))
-			mapped_bio = bio->bi_private;
-
 		if (bio->bi_private) {
-			ret2 = bio_uncopy_user(mapped_bio);
+			ret2 = bio_uncopy_user(bio);
 			if (ret2 && !ret)
 				ret = ret2;
 		} else {
-			bio_unmap_user(mapped_bio);
+			bio_release_pages(bio, bio_data_dir(bio) == READ);
 		}
 
-		mapped_bio = bio;
+		next_bio = bio;
 		bio = bio->bi_next;
-		bio_put(mapped_bio);
+		bio_put(next_bio);
 	}
 
 	return ret;
@@ -684,7 +627,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 {
 	int reading = rq_data_dir(rq) == READ;
 	unsigned long addr = (unsigned long) kbuf;
-	struct bio *bio, *orig_bio;
+	struct bio *bio;
 	int ret;
 
 	if (len > (queue_max_hw_sectors(q) << 9))
@@ -692,7 +635,8 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	if (!len || !kbuf)
 		return -EINVAL;
 
-	if (!blk_rq_aligned(q, addr, len) || object_is_on_stack(kbuf))
+	if (!blk_rq_aligned(q, addr, len) || object_is_on_stack(kbuf) ||
+	    blk_queue_may_bounce(q))
 		bio = bio_copy_kern(q, kbuf, len, gfp_mask, reading);
 	else
 		bio = bio_map_kern(q, kbuf, len, gfp_mask);
@@ -703,14 +647,9 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	bio->bi_opf &= ~REQ_OP_MASK;
 	bio->bi_opf |= req_op(rq);
 
-	orig_bio = bio;
-	ret = blk_rq_append_bio(rq, &bio);
-	if (unlikely(ret)) {
-		/* request is too big */
-		bio_put(orig_bio);
-		return ret;
-	}
-
-	return 0;
+	ret = blk_rq_append_bio(rq, bio);
+	if (unlikely(ret))
+		bio_put(bio);
+	return ret;
 }
 EXPORT_SYMBOL(blk_rq_map_kern);
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 271f6596435b..2a75bc7401df 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -972,6 +972,14 @@ void blk_mq_debugfs_register_sched_hctx(struct request_queue *q,
 {
 	struct elevator_type *e = q->elevator->type;
 
+	/*
+	 * If the parent debugfs directory has not been created yet, return;
+	 * We will be called again later on with appropriate parent debugfs
+	 * directory from blk_register_queue()
+	 */
+	if (!hctx->debugfs_dir)
+		return;
+
 	if (!e->hctx_debugfs_attrs)
 		return;
 
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 9c92053e704d..2a37731e8244 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -373,8 +373,8 @@ static bool blk_mq_tagset_count_completed_rqs(struct request *rq,
 }
 
 /**
- * blk_mq_tagset_wait_completed_request - wait until all completed req's
- * complete funtion is run
+ * blk_mq_tagset_wait_completed_request - Wait until all scheduled request
+ * completions have finished.
  * @tagset:	Tag set to drain completed request
  *
  * Note: This function has to be run after all IO queues are shutdown
@@ -517,7 +517,7 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	tags->nr_tags = total_tags;
 	tags->nr_reserved_tags = reserved_tags;
 
-	if (flags & BLK_MQ_F_TAG_HCTX_SHARED)
+	if (blk_mq_is_sbitmap_shared(flags))
 		return tags;
 
 	if (blk_mq_init_bitmap_tags(tags, node, alloc_policy) < 0) {
@@ -529,7 +529,7 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 
 void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags)
 {
-	if (!(flags & BLK_MQ_F_TAG_HCTX_SHARED)) {
+	if (!blk_mq_is_sbitmap_shared(flags)) {
 		sbitmap_queue_free(tags->bitmap_tags);
 		sbitmap_queue_free(tags->breserved_tags);
 	}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4e3a70ab5be1..cd4ad58c88a5 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -361,11 +361,12 @@ static struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data)
 
 	if (e) {
 		/*
-		 * Flush requests are special and go directly to the
+		 * Flush/passthrough requests are special and go directly to the
 		 * dispatch list. Don't include reserved tags in the
 		 * limiting, as it isn't useful.
 		 */
 		if (!op_is_flush(data->cmd_flags) &&
+		    !blk_op_is_passthrough(data->cmd_flags) &&
 		    e->type->ops.limit_depth &&
 		    !(data->flags & BLK_MQ_REQ_RESERVED))
 			e->type->ops.limit_depth(data->cmd_flags, data);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index b4aa2f37fab6..9c009090c4b5 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -7,7 +7,6 @@
 #include <linux/init.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
-#include <linux/memblock.h>	/* for max_pfn/max_low_pfn */
 #include <linux/gcd.h>
 #include <linux/lcm.h>
 #include <linux/jiffies.h>
@@ -17,11 +16,6 @@
 #include "blk.h"
 #include "blk-wbt.h"
 
-unsigned long blk_max_low_pfn;
-EXPORT_SYMBOL(blk_max_low_pfn);
-
-unsigned long blk_max_pfn;
-
 void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout)
 {
 	q->rq_timeout = timeout;
@@ -55,7 +49,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->discard_alignment = 0;
 	lim->discard_misaligned = 0;
 	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
-	lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT);
+	lim->bounce = BLK_BOUNCE_NONE;
 	lim->alignment_offset = 0;
 	lim->io_opt = 0;
 	lim->misaligned = 0;
@@ -92,39 +86,16 @@ EXPORT_SYMBOL(blk_set_stacking_limits);
 /**
  * blk_queue_bounce_limit - set bounce buffer limit for queue
  * @q: the request queue for the device
- * @max_addr: the maximum address the device can handle
+ * @bounce: bounce limit to enforce
  *
  * Description:
- *    Different hardware can have different requirements as to what pages
- *    it can do I/O directly to. A low level driver can call
- *    blk_queue_bounce_limit to have lower memory pages allocated as bounce
- *    buffers for doing I/O to pages residing above @max_addr.
+ *    Force bouncing for ISA DMA ranges or highmem.
+ *
+ *    DEPRECATED, don't use in new code.
  **/
-void blk_queue_bounce_limit(struct request_queue *q, u64 max_addr)
+void blk_queue_bounce_limit(struct request_queue *q, enum blk_bounce bounce)
 {
-	unsigned long b_pfn = max_addr >> PAGE_SHIFT;
-	int dma = 0;
-
-	q->bounce_gfp = GFP_NOIO;
-#if BITS_PER_LONG == 64
-	/*
-	 * Assume anything <= 4GB can be handled by IOMMU.  Actually
-	 * some IOMMUs can handle everything, but I don't know of a
-	 * way to test this here.
-	 */
-	if (b_pfn < (min_t(u64, 0xffffffffUL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
-		dma = 1;
-	q->limits.bounce_pfn = max(max_low_pfn, b_pfn);
-#else
-	if (b_pfn < blk_max_low_pfn)
-		dma = 1;
-	q->limits.bounce_pfn = b_pfn;
-#endif
-	if (dma) {
-		init_emergency_isa_pool();
-		q->bounce_gfp = GFP_NOIO | GFP_DMA;
-		q->limits.bounce_pfn = b_pfn;
-	}
+	q->limits.bounce = bounce;
 }
 EXPORT_SYMBOL(blk_queue_bounce_limit);
 
@@ -547,7 +518,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 					b->max_write_zeroes_sectors);
 	t->max_zone_append_sectors = min(t->max_zone_append_sectors,
 					b->max_zone_append_sectors);
-	t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
+	t->bounce = max(t->bounce, b->bounce);
 
 	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
 					    b->seg_boundary_mask);
@@ -927,11 +898,3 @@ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
 	}
 }
 EXPORT_SYMBOL_GPL(blk_queue_set_zoned);
-
-static int __init blk_settings_init(void)
-{
-	blk_max_low_pfn = max_low_pfn - 1;
-	blk_max_pfn = max_pfn - 1;
-	return 0;
-}
-subsys_initcall(blk_settings_init);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 0f4f0c8a7825..e03bedf180ab 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -60,7 +60,7 @@ static ssize_t queue_var_store64(s64 *var, const char *page)
 
 static ssize_t queue_requests_show(struct request_queue *q, char *page)
 {
-	return queue_var_show(q->nr_requests, (page));
+	return queue_var_show(q->nr_requests, page);
 }
 
 static ssize_t
@@ -264,6 +264,11 @@ static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
 	return queue_var_show(max_hw_sectors_kb, (page));
 }
 
+static ssize_t queue_virt_boundary_mask_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(q->limits.virt_boundary_mask, (page));
+}
+
 #define QUEUE_SYSFS_BIT_FNS(name, flag, neg)				\
 static ssize_t								\
 queue_##name##_show(struct request_queue *q, char *page)		\
@@ -610,6 +615,7 @@ QUEUE_RO_ENTRY(queue_fua, "fua");
 QUEUE_RO_ENTRY(queue_dax, "dax");
 QUEUE_RW_ENTRY(queue_io_timeout, "io_timeout");
 QUEUE_RW_ENTRY(queue_wb_lat, "wbt_lat_usec");
+QUEUE_RO_ENTRY(queue_virt_boundary_mask, "virt_boundary_mask");
 
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 QUEUE_RW_ENTRY(blk_throtl_sample_time, "throttle_sample_time");
@@ -670,6 +676,7 @@ static struct attribute *queue_attrs[] = {
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 	&blk_throtl_sample_time_entry.attr,
 #endif
+	&queue_virt_boundary_mask_entry.attr,
 	NULL,
 };
 
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index c0276b42d9fb..250cb76ee615 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -52,14 +52,6 @@ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond)
 }
 EXPORT_SYMBOL_GPL(blk_zone_cond_str);
 
-static inline sector_t blk_zone_start(struct request_queue *q,
-				      sector_t sector)
-{
-	sector_t zone_mask = blk_queue_zone_sectors(q) - 1;
-
-	return sector & ~zone_mask;
-}
-
 /*
  * Return true if a request is a write requests that needs zone write locking.
  */
diff --git a/block/blk.h b/block/blk.h
index 3b53e44b967e..8b3591aee0a5 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -6,6 +6,7 @@
 #include <linux/blk-mq.h>
 #include <linux/part_stat.h>
 #include <linux/blk-crypto.h>
+#include <linux/memblock.h>	/* for max_pfn/max_low_pfn */
 #include <xen/xen.h>
 #include "blk-crypto-internal.h"
 #include "blk-mq.h"
@@ -311,18 +312,20 @@ static inline void blk_throtl_bio_endio(struct bio *bio) { }
 static inline void blk_throtl_stat_add(struct request *rq, u64 time) { }
 #endif
 
-#ifdef CONFIG_BOUNCE
-extern int init_emergency_isa_pool(void);
-extern void blk_queue_bounce(struct request_queue *q, struct bio **bio);
-#else
-static inline int init_emergency_isa_pool(void)
+void __blk_queue_bounce(struct request_queue *q, struct bio **bio);
+
+static inline bool blk_queue_may_bounce(struct request_queue *q)
 {
-	return 0;
+	return IS_ENABLED(CONFIG_BOUNCE) &&
+		q->limits.bounce == BLK_BOUNCE_HIGH &&
+		max_low_pfn >= max_pfn;
 }
+
 static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
 {
+	if (unlikely(blk_queue_may_bounce(q) && bio_has_data(*bio)))
+		__blk_queue_bounce(q, bio);	
 }
-#endif /* CONFIG_BOUNCE */
 
 #ifdef CONFIG_BLK_CGROUP_IOLATENCY
 extern int blk_iolatency_init(struct request_queue *q);
@@ -346,7 +349,6 @@ char *disk_name(struct gendisk *hd, int partno, char *buf);
 #define ADDPART_FLAG_NONE	0
 #define ADDPART_FLAG_RAID	1
 #define ADDPART_FLAG_WHOLEDISK	2
-void delete_partition(struct block_device *part);
 int bdev_add_partition(struct block_device *bdev, int partno,
 		sector_t start, sector_t length);
 int bdev_del_partition(struct block_device *bdev, int partno);
diff --git a/block/bounce.c b/block/bounce.c
index 6c441f4f1cd4..94081e013c58 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -18,7 +18,6 @@
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/highmem.h>
-#include <linux/memblock.h>
 #include <linux/printk.h>
 #include <asm/tlbflush.h>
 
@@ -29,7 +28,7 @@
 #define ISA_POOL_SIZE	16
 
 static struct bio_set bounce_bio_set, bounce_bio_split;
-static mempool_t page_pool, isa_page_pool;
+static mempool_t page_pool;
 
 static void init_bounce_bioset(void)
 {
@@ -49,11 +48,11 @@ static void init_bounce_bioset(void)
 	bounce_bs_setup = true;
 }
 
-#if defined(CONFIG_HIGHMEM)
 static __init int init_emergency_pool(void)
 {
 	int ret;
-#if defined(CONFIG_HIGHMEM) && !defined(CONFIG_MEMORY_HOTPLUG)
+
+#ifndef CONFIG_MEMORY_HOTPLUG
 	if (max_pfn <= max_low_pfn)
 		return 0;
 #endif
@@ -67,9 +66,7 @@ static __init int init_emergency_pool(void)
 }
 
 __initcall(init_emergency_pool);
-#endif
 
-#ifdef CONFIG_HIGHMEM
 /*
  * highmem version, map in to vec
  */
@@ -82,48 +79,6 @@ static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
 	kunmap_atomic(vto);
 }
 
-#else /* CONFIG_HIGHMEM */
-
-#define bounce_copy_vec(to, vfrom)	\
-	memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len)
-
-#endif /* CONFIG_HIGHMEM */
-
-/*
- * allocate pages in the DMA region for the ISA pool
- */
-static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
-{
-	return mempool_alloc_pages(gfp_mask | GFP_DMA, data);
-}
-
-static DEFINE_MUTEX(isa_mutex);
-
-/*
- * gets called "every" time someone init's a queue with BLK_BOUNCE_ISA
- * as the max address, so check if the pool has already been created.
- */
-int init_emergency_isa_pool(void)
-{
-	int ret;
-
-	mutex_lock(&isa_mutex);
-
-	if (mempool_initialized(&isa_page_pool)) {
-		mutex_unlock(&isa_mutex);
-		return 0;
-	}
-
-	ret = mempool_init(&isa_page_pool, ISA_POOL_SIZE, mempool_alloc_pages_isa,
-			   mempool_free_pages, (void *) 0);
-	BUG_ON(ret);
-
-	pr_info("isa pool size: %d pages\n", ISA_POOL_SIZE);
-	init_bounce_bioset();
-	mutex_unlock(&isa_mutex);
-	return 0;
-}
-
 /*
  * Simple bounce buffer support for highmem pages. Depending on the
  * queue gfp mask set, *to may or may not be a highmem page. kmap it
@@ -159,7 +114,7 @@ static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
 	}
 }
 
-static void bounce_end_io(struct bio *bio, mempool_t *pool)
+static void bounce_end_io(struct bio *bio)
 {
 	struct bio *bio_orig = bio->bi_private;
 	struct bio_vec *bvec, orig_vec;
@@ -173,7 +128,7 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool)
 		orig_vec = bio_iter_iovec(bio_orig, orig_iter);
 		if (bvec->bv_page != orig_vec.bv_page) {
 			dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
-			mempool_free(bvec->bv_page, pool);
+			mempool_free(bvec->bv_page, &page_pool);
 		}
 		bio_advance_iter(bio_orig, &orig_iter, orig_vec.bv_len);
 	}
@@ -185,33 +140,17 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool)
 
 static void bounce_end_io_write(struct bio *bio)
 {
-	bounce_end_io(bio, &page_pool);
+	bounce_end_io(bio);
 }
 
-static void bounce_end_io_write_isa(struct bio *bio)
-{
-
-	bounce_end_io(bio, &isa_page_pool);
-}
-
-static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
+static void bounce_end_io_read(struct bio *bio)
 {
 	struct bio *bio_orig = bio->bi_private;
 
 	if (!bio->bi_status)
 		copy_to_high_bio_irq(bio_orig, bio);
 
-	bounce_end_io(bio, pool);
-}
-
-static void bounce_end_io_read(struct bio *bio)
-{
-	__bounce_end_io_read(bio, &page_pool);
-}
-
-static void bounce_end_io_read_isa(struct bio *bio)
-{
-	__bounce_end_io_read(bio, &isa_page_pool);
+	bounce_end_io(bio);
 }
 
 static struct bio *bounce_clone_bio(struct bio *bio_src)
@@ -241,12 +180,8 @@ static struct bio *bounce_clone_bio(struct bio *bio_src)
 	 *    asking for trouble and would force extra work on
 	 *    __bio_clone_fast() anyways.
 	 */
-	if (bio_is_passthrough(bio_src))
-		bio = bio_kmalloc(GFP_NOIO | __GFP_NOFAIL,
-				  bio_segments(bio_src));
-	else
-		bio = bio_alloc_bioset(GFP_NOIO, bio_segments(bio_src),
-				       &bounce_bio_set);
+	bio = bio_alloc_bioset(GFP_NOIO, bio_segments(bio_src),
+			       &bounce_bio_set);
 	bio->bi_bdev		= bio_src->bi_bdev;
 	if (bio_flagged(bio_src, BIO_REMAPPED))
 		bio_set_flag(bio, BIO_REMAPPED);
@@ -287,8 +222,7 @@ err_put:
 	return NULL;
 }
 
-static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
-			       mempool_t *pool)
+void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 {
 	struct bio *bio;
 	int rw = bio_data_dir(*bio_orig);
@@ -301,14 +235,13 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	bio_for_each_segment(from, *bio_orig, iter) {
 		if (i++ < BIO_MAX_VECS)
 			sectors += from.bv_len >> 9;
-		if (page_to_pfn(from.bv_page) > q->limits.bounce_pfn)
+		if (PageHighMem(from.bv_page))
 			bounce = true;
 	}
 	if (!bounce)
 		return;
 
-	if (!bio_is_passthrough(*bio_orig) &&
-	    sectors < bio_sectors(*bio_orig)) {
+	if (sectors < bio_sectors(*bio_orig)) {
 		bio = bio_split(*bio_orig, sectors, GFP_NOIO, &bounce_bio_split);
 		bio_chain(bio, *bio_orig);
 		submit_bio_noacct(*bio_orig);
@@ -324,10 +257,10 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	for (i = 0, to = bio->bi_io_vec; i < bio->bi_vcnt; to++, i++) {
 		struct page *page = to->bv_page;
 
-		if (page_to_pfn(page) <= q->limits.bounce_pfn)
+		if (!PageHighMem(page))
 			continue;
 
-		to->bv_page = mempool_alloc(pool, q->bounce_gfp);
+		to->bv_page = mempool_alloc(&page_pool, GFP_NOIO);
 		inc_zone_page_state(to->bv_page, NR_BOUNCE);
 
 		if (rw == WRITE) {
@@ -346,46 +279,11 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 
 	bio->bi_flags |= (1 << BIO_BOUNCED);
 
-	if (pool == &page_pool) {
+	if (rw == READ)
+		bio->bi_end_io = bounce_end_io_read;
+	else
 		bio->bi_end_io = bounce_end_io_write;
-		if (rw == READ)
-			bio->bi_end_io = bounce_end_io_read;
-	} else {
-		bio->bi_end_io = bounce_end_io_write_isa;
-		if (rw == READ)
-			bio->bi_end_io = bounce_end_io_read_isa;
-	}
 
 	bio->bi_private = *bio_orig;
 	*bio_orig = bio;
 }
-
-void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
-{
-	mempool_t *pool;
-
-	/*
-	 * Data-less bio, nothing to bounce
-	 */
-	if (!bio_has_data(*bio_orig))
-		return;
-
-	/*
-	 * for non-isa bounce case, just check if the bounce pfn is equal
-	 * to or bigger than the highest pfn in the system -- in that case,
-	 * don't waste time iterating over bio segments
-	 */
-	if (!(q->bounce_gfp & GFP_DMA)) {
-		if (q->limits.bounce_pfn >= blk_max_pfn)
-			return;
-		pool = &page_pool;
-	} else {
-		BUG_ON(!mempool_initialized(&isa_page_pool));
-		pool = &isa_page_pool;
-	}
-
-	/*
-	 * slow path
-	 */
-	__blk_queue_bounce(q, bio_orig, pool);
-}
diff --git a/block/elevator.c b/block/elevator.c
index 293c5c81397a..440699c28119 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -621,7 +621,8 @@ static inline bool elv_support_iosched(struct request_queue *q)
  */
 static struct elevator_type *elevator_get_default(struct request_queue *q)
 {
-	if (q->nr_hw_queues != 1)
+	if (q->nr_hw_queues != 1 &&
+			!blk_mq_is_sbitmap_shared(q->tag_set->flags))
 		return NULL;
 
 	return elevator_get(q, "mq-deadline", false);
diff --git a/block/genhd.c b/block/genhd.c
index 8c8f543572e6..39ca97b0edc6 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -161,81 +161,6 @@ static void part_in_flight_rw(struct block_device *part,
 		inflight[1] = 0;
 }
 
-/**
- * disk_part_iter_init - initialize partition iterator
- * @piter: iterator to initialize
- * @disk: disk to iterate over
- * @flags: DISK_PITER_* flags
- *
- * Initialize @piter so that it iterates over partitions of @disk.
- *
- * CONTEXT:
- * Don't care.
- */
-void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk,
-			  unsigned int flags)
-{
-	piter->disk = disk;
-	piter->part = NULL;
-	if (flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0))
-		piter->idx = 0;
-	else
-		piter->idx = 1;
-	piter->flags = flags;
-}
-
-/**
- * disk_part_iter_next - proceed iterator to the next partition and return it
- * @piter: iterator of interest
- *
- * Proceed @piter to the next partition and return it.
- *
- * CONTEXT:
- * Don't care.
- */
-struct block_device *disk_part_iter_next(struct disk_part_iter *piter)
-{
-	struct block_device *part;
-	unsigned long idx;
-
-	/* put the last partition */
-	disk_part_iter_exit(piter);
-
-	rcu_read_lock();
-	xa_for_each_start(&piter->disk->part_tbl, idx, part, piter->idx) {
-		if (!bdev_nr_sectors(part) &&
-		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
-		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
-		      piter->idx == 0))
-			continue;
-
-		piter->part = bdgrab(part);
-		if (!piter->part)
-			continue;
-		piter->idx = idx + 1;
-		break;
-	}
-	rcu_read_unlock();
-
-	return piter->part;
-}
-
-/**
- * disk_part_iter_exit - finish up partition iteration
- * @piter: iter of interest
- *
- * Called when iteration is over.  Cleans up @piter.
- *
- * CONTEXT:
- * Don't care.
- */
-void disk_part_iter_exit(struct disk_part_iter *piter)
-{
-	if (piter->part)
-		bdput(piter->part);
-	piter->part = NULL;
-}
-
 /*
  * Can be deleted altogether. Later.
  *
@@ -472,13 +397,22 @@ static char *bdevt_str(dev_t devt, char *buf)
 
 void disk_uevent(struct gendisk *disk, enum kobject_action action)
 {
-	struct disk_part_iter piter;
 	struct block_device *part;
+	unsigned long idx;
+
+	rcu_read_lock();
+	xa_for_each(&disk->part_tbl, idx, part) {
+		if (bdev_is_partition(part) && !bdev_nr_sectors(part))
+			continue;
+		if (!bdgrab(part))
+			continue;
 
-	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY_PART0);
-	while ((part = disk_part_iter_next(&piter)))
+		rcu_read_unlock();
 		kobject_uevent(bdev_kobj(part), action);
-	disk_part_iter_exit(&piter);
+		bdput(part);
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(disk_uevent);
 
@@ -646,18 +580,6 @@ void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk)
 }
 EXPORT_SYMBOL(device_add_disk_no_queue_reg);
 
-static void invalidate_partition(struct block_device *bdev)
-{
-	fsync_bdev(bdev);
-	__invalidate_device(bdev, true);
-
-	/*
-	 * Unhash the bdev inode for this device so that it can't be looked
-	 * up any more even if openers still hold references to it.
-	 */
-	remove_inode_hash(bdev->bd_inode);
-}
-
 /**
  * del_gendisk - remove the gendisk
  * @disk: the struct gendisk to remove
@@ -679,9 +601,6 @@ static void invalidate_partition(struct block_device *bdev)
  */
 void del_gendisk(struct gendisk *disk)
 {
-	struct disk_part_iter piter;
-	struct block_device *part;
-
 	might_sleep();
 
 	if (WARN_ON_ONCE(!disk->queue))
@@ -696,15 +615,19 @@ void del_gendisk(struct gendisk *disk)
 	 */
 	down_write(&bdev_lookup_sem);
 
-	/* invalidate stuff */
-	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
-	while ((part = disk_part_iter_next(&piter))) {
-		invalidate_partition(part);
-		delete_partition(part);
-	}
-	disk_part_iter_exit(&piter);
+	mutex_lock(&disk->part0->bd_mutex);
+	blk_drop_partitions(disk);
+	mutex_unlock(&disk->part0->bd_mutex);
+
+	fsync_bdev(disk->part0);
+	__invalidate_device(disk->part0, true);
+
+	/*
+	 * Unhash the bdev inode for this device so that it can't be looked
+	 * up any more even if openers still hold references to it.
+	 */
+	remove_inode_hash(disk->part0->bd_inode);
 
-	invalidate_partition(disk->part0);
 	set_capacity(disk, 0);
 	disk->flags &= ~GENHD_FL_UP;
 	up_write(&bdev_lookup_sem);
@@ -817,10 +740,10 @@ void __init printk_all_partitions(void)
 	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
 	while ((dev = class_dev_iter_next(&iter))) {
 		struct gendisk *disk = dev_to_disk(dev);
-		struct disk_part_iter piter;
 		struct block_device *part;
 		char name_buf[BDEVNAME_SIZE];
 		char devt_buf[BDEVT_SIZE];
+		unsigned long idx;
 
 		/*
 		 * Don't show empty devices or things that have been
@@ -831,30 +754,29 @@ void __init printk_all_partitions(void)
 			continue;
 
 		/*
-		 * Note, unlike /proc/partitions, I am showing the
-		 * numbers in hex - the same format as the root=
-		 * option takes.
+		 * Note, unlike /proc/partitions, I am showing the numbers in
+		 * hex - the same format as the root= option takes.
 		 */
-		disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0);
-		while ((part = disk_part_iter_next(&piter))) {
-			bool is_part0 = part == disk->part0;
-
-			printk("%s%s %10llu %s %s", is_part0 ? "" : "  ",
+		rcu_read_lock();
+		xa_for_each(&disk->part_tbl, idx, part) {
+			if (!bdev_nr_sectors(part))
+				continue;
+			printk("%s%s %10llu %s %s",
+			       bdev_is_partition(part) ? "  " : "",
 			       bdevt_str(part->bd_dev, devt_buf),
 			       bdev_nr_sectors(part) >> 1,
 			       disk_name(disk, part->bd_partno, name_buf),
 			       part->bd_meta_info ?
 					part->bd_meta_info->uuid : "");
-			if (is_part0) {
-				if (dev->parent && dev->parent->driver)
-					printk(" driver: %s\n",
-					      dev->parent->driver->name);
-				else
-					printk(" (driver?)\n");
-			} else
+			if (bdev_is_partition(part))
 				printk("\n");
+			else if (dev->parent && dev->parent->driver)
+				printk(" driver: %s\n",
+					dev->parent->driver->name);
+			else
+				printk(" (driver?)\n");
 		}
-		disk_part_iter_exit(&piter);
+		rcu_read_unlock();
 	}
 	class_dev_iter_exit(&iter);
 }
@@ -919,8 +841,8 @@ static void *show_partition_start(struct seq_file *seqf, loff_t *pos)
 static int show_partition(struct seq_file *seqf, void *v)
 {
 	struct gendisk *sgp = v;
-	struct disk_part_iter piter;
 	struct block_device *part;
+	unsigned long idx;
 	char buf[BDEVNAME_SIZE];
 
 	/* Don't show non-partitionable removeable devices or empty devices */
@@ -930,15 +852,16 @@ static int show_partition(struct seq_file *seqf, void *v)
 	if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)
 		return 0;
 
-	/* show the full disk and all non-0 size partitions of it */
-	disk_part_iter_init(&piter, sgp, DISK_PITER_INCL_PART0);
-	while ((part = disk_part_iter_next(&piter)))
+	rcu_read_lock();
+	xa_for_each(&sgp->part_tbl, idx, part) {
+		if (!bdev_nr_sectors(part))
+			continue;
 		seq_printf(seqf, "%4d  %7d %10llu %s\n",
 			   MAJOR(part->bd_dev), MINOR(part->bd_dev),
 			   bdev_nr_sectors(part) >> 1,
 			   disk_name(sgp, part->bd_partno, buf));
-	disk_part_iter_exit(&piter);
-
+	}
+	rcu_read_unlock();
 	return 0;
 }
 
@@ -1247,11 +1170,11 @@ const struct device_type disk_type = {
 static int diskstats_show(struct seq_file *seqf, void *v)
 {
 	struct gendisk *gp = v;
-	struct disk_part_iter piter;
 	struct block_device *hd;
 	char buf[BDEVNAME_SIZE];
 	unsigned int inflight;
 	struct disk_stats stat;
+	unsigned long idx;
 
 	/*
 	if (&disk_to_dev(gp)->kobj.entry == block_class.devices.next)
@@ -1261,8 +1184,10 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 				"\n\n");
 	*/
 
-	disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0);
-	while ((hd = disk_part_iter_next(&piter))) {
+	rcu_read_lock();
+	xa_for_each(&gp->part_tbl, idx, hd) {
+		if (bdev_is_partition(hd) && !bdev_nr_sectors(hd))
+			continue;
 		part_stat_read_all(hd, &stat);
 		if (queue_is_mq(gp->queue))
 			inflight = blk_mq_in_flight(gp->queue, hd);
@@ -1305,7 +1230,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 						 NSEC_PER_MSEC)
 			);
 	}
-	disk_part_iter_exit(&piter);
+	rcu_read_unlock();
 
 	return 0;
 }
diff --git a/block/ioprio.c b/block/ioprio.c
index 364d2294ba90..bee628f9f1b2 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -119,11 +119,17 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
 				pgrp = task_pgrp(current);
 			else
 				pgrp = find_vpid(who);
+
+			read_lock(&tasklist_lock);
 			do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
 				ret = set_task_ioprio(p, ioprio);
-				if (ret)
-					break;
+				if (ret) {
+					read_unlock(&tasklist_lock);
+					goto out;
+				}
 			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+			read_unlock(&tasklist_lock);
+
 			break;
 		case IOPRIO_WHO_USER:
 			uid = make_kuid(current_user_ns(), who);
@@ -153,6 +159,7 @@ free_uid:
 			ret = -EINVAL;
 	}
 
+out:
 	rcu_read_unlock();
 	return ret;
 }
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index f3631a287466..04aded71ead2 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -500,11 +500,8 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	trace_block_rq_insert(rq);
 
-	if (at_head || blk_rq_is_passthrough(rq)) {
-		if (at_head)
-			list_add(&rq->queuelist, &dd->dispatch);
-		else
-			list_add_tail(&rq->queuelist, &dd->dispatch);
+	if (at_head) {
+		list_add(&rq->queuelist, &dd->dispatch);
 	} else {
 		deadline_add_rq_rb(dd, rq);
 
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 46f055bc7ecb..dc60ecf46fe6 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -285,8 +285,11 @@ struct device_type part_type = {
  * Must be called either with bd_mutex held, before a disk can be opened or
  * after all disk users are gone.
  */
-void delete_partition(struct block_device *part)
+static void delete_partition(struct block_device *part)
 {
+	fsync_bdev(part);
+	__invalidate_device(part, true);
+
 	xa_erase(&part->bd_disk->part_tbl, part->bd_partno);
 	kobject_put(part->bd_holder_dir);
 	device_del(&part->bd_device);
@@ -424,21 +427,21 @@ out_put:
 static bool partition_overlaps(struct gendisk *disk, sector_t start,
 		sector_t length, int skip_partno)
 {
-	struct disk_part_iter piter;
 	struct block_device *part;
 	bool overlap = false;
-
-	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
-	while ((part = disk_part_iter_next(&piter))) {
-		if (part->bd_partno == skip_partno ||
-		    start >= part->bd_start_sect + bdev_nr_sectors(part) ||
-		    start + length <= part->bd_start_sect)
-			continue;
-		overlap = true;
-		break;
+	unsigned long idx;
+
+	rcu_read_lock();
+	xa_for_each_start(&disk->part_tbl, idx, part, 1) {
+		if (part->bd_partno != skip_partno &&
+		    start < part->bd_start_sect + bdev_nr_sectors(part) &&
+		    start + length > part->bd_start_sect) {
+			overlap = true;
+			break;
+		}
 	}
+	rcu_read_unlock();
 
-	disk_part_iter_exit(&piter);
 	return overlap;
 }
 
@@ -475,9 +478,6 @@ int bdev_del_partition(struct block_device *bdev, int partno)
 	if (part->bd_openers)
 		goto out_unlock;
 
-	sync_blockdev(part);
-	invalidate_bdev(part);
-
 	delete_partition(part);
 	ret = 0;
 out_unlock:
@@ -533,28 +533,20 @@ static bool disk_unlock_native_capacity(struct gendisk *disk)
 	}
 }
 
-int blk_drop_partitions(struct block_device *bdev)
+void blk_drop_partitions(struct gendisk *disk)
 {
-	struct disk_part_iter piter;
 	struct block_device *part;
+	unsigned long idx;
 
-	if (bdev->bd_part_count)
-		return -EBUSY;
+	lockdep_assert_held(&disk->part0->bd_mutex);
 
-	sync_blockdev(bdev);
-	invalidate_bdev(bdev);
-
-	disk_part_iter_init(&piter, bdev->bd_disk, DISK_PITER_INCL_EMPTY);
-	while ((part = disk_part_iter_next(&piter)))
+	xa_for_each_start(&disk->part_tbl, idx, part, 1) {
+		if (!bdgrab(part))
+			continue;
 		delete_partition(part);
-	disk_part_iter_exit(&piter);
-
-	return 0;
+		bdput(part);
+	}
 }
-#ifdef CONFIG_S390
-/* for historic reasons in the DASD driver */
-EXPORT_SYMBOL_GPL(blk_drop_partitions);
-#endif
 
 static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev,
 		struct parsed_partitions *state, int p)
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 6599bac0a78c..1b3fe99b83a6 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -353,10 +353,6 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 
 	start_time = jiffies;
 
-	/* ignore return value. All information is passed back to caller
-	 * (if he doesn't check that is his problem).
-	 * N.B. a non-zero SCSI status is _not_ necessarily an error.
-	 */
 	blk_execute_rq(bd_disk, rq, at_head);
 
 	hdr->duration = jiffies_to_msecs(jiffies - start_time);
@@ -431,7 +427,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	bytes = max(in_len, out_len);
 	if (bytes) {
-		buffer = kzalloc(bytes, q->bounce_gfp | GFP_USER| __GFP_NOWARN);
+		buffer = kzalloc(bytes, GFP_NOIO | GFP_USER | __GFP_NOWARN);
 		if (!buffer)
 			return -ENOMEM;