Merge tag 'for-5.2/block-20190507' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "Nothing major in this series, just fixes and improvements all over the
  map. This contains:

   - Series of fixes for sed-opal (David, Jonas)

   - Fixes and performance tweaks for BFQ (via Paolo)

   - Set of fixes for bcache (via Coly)

   - Set of fixes for md (via Song)

   - Enabling multi-page for passthrough requests (Ming)

   - Queue release fix series (Ming)

   - Device notification improvements (Martin)

   - Propagate underlying device rotational status in loop (Holger)

   - Removal of mtip32xx trim support, which has been disabled for years
     (Christoph)

   - Improvement and cleanup of nvme command handling (Christoph)

   - Add block SPDX tags (Christoph)

   - Cleanup/hardening of bio/bvec iteration (Christoph)

   - A few NVMe pull requests (Christoph)

   - Removal of CONFIG_LBDAF (Christoph)

   - Various little fixes here and there"

* tag 'for-5.2/block-20190507' of git://git.kernel.dk/linux-block: (164 commits)
  block: fix mismerge in bvec_advance
  block: don't drain in-progress dispatch in blk_cleanup_queue()
  blk-mq: move cancel of hctx->run_work into blk_mq_hw_sysfs_release
  blk-mq: always free hctx after request queue is freed
  blk-mq: split blk_mq_alloc_and_init_hctx into two parts
  blk-mq: free hw queue's resource in hctx's release handler
  blk-mq: move cancel of requeue_work into blk_mq_release
  blk-mq: grab .q_usage_counter when queuing request from plug code path
  block: fix function name in comment
  nvmet: protect discovery change log event list iteration
  nvme: mark nvme_core_init and nvme_core_exit static
  nvme: move command size checks to the core
  nvme-fabrics: check more command sizes
  nvme-pci: check more command sizes
  nvme-pci: remove an unneeded variable initialization
  nvme-pci: unquiesce admin queue on shutdown
  nvme-pci: shutdown on timeout during deletion
  nvme-pci: fix psdt field for single segment sgls
  nvme-multipath: don't print ANA group state by default
  nvme-multipath: split bios with the ns_head bio_set before submitting
  ...

63 files changed, 1495 insertions, 1289 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 028bc085dac8..1b220101a9cb 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -26,30 +26,6 @@ menuconfig BLOCK
 
 if BLOCK
 
-config LBDAF
-	bool "Support for large (2TB+) block devices and files"
-	depends on !64BIT
-	default y
-	help
-	  Enable block devices or files of size 2TB and larger.
-
-	  This option is required to support the full capacity of large
-	  (2TB+) block devices, including RAID, disk, Network Block Device,
-	  Logical Volume Manager (LVM) and loopback.
-	
-	  This option also enables support for single files larger than
-	  2TB.
-
-	  The ext4 filesystem requires that this feature be enabled in
-	  order to support filesystems that have the huge_file feature
-	  enabled.  Otherwise, it will refuse to mount in the read-write
-	  mode any filesystems that use the huge_file feature, which is
-	  enabled by default by mke2fs.ext4.
-
-	  The GFS2 filesystem also requires this feature.
-
-	  If unsure, say Y.
-
 config BLK_SCSI_REQUEST
 	bool
 
diff --git a/block/badblocks.c b/block/badblocks.c
index 91f7bcf979d3..2e5f5697db35 100644
--- a/block/badblocks.c
+++ b/block/badblocks.c
@@ -1,18 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Bad block management
  *
  * - Heavily based on MD badblocks code from Neil Brown
  *
  * Copyright (c) 2015, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 
 #include <linux/badblocks.h>
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index c6113af31960..b3796a40a61a 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -1,15 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * cgroups support for the BFQ I/O scheduler.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License as
- *  published by the Free Software Foundation; either version 2 of the
- *  License, or (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- *  General Public License for more details.
  */
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -578,7 +569,8 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	bfqg_and_blkg_get(bfqg);
 
 	if (bfq_bfqq_busy(bfqq)) {
-		bfq_pos_tree_add_move(bfqd, bfqq);
+		if (unlikely(!bfqd->nonrot_with_queueing))
+			bfq_pos_tree_add_move(bfqd, bfqq);
 		bfq_activate_bfqq(bfqd, bfqq);
 	}
 
@@ -1102,7 +1094,7 @@ struct cftype bfq_blkcg_legacy_files[] = {
 	},
 #endif /* CONFIG_DEBUG_BLK_CGROUP */
 
-	/* the same statictics which cover the bfqg and its descendants */
+	/* the same statistics which cover the bfqg and its descendants */
 	{
 		.name = "bfq.io_service_bytes_recursive",
 		.private = (unsigned long)&blkcg_policy_bfq,
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 5ba1e0d841b4..f8d430f88d25 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Budget Fair Queueing (BFQ) I/O scheduler.
  *
@@ -12,16 +13,6 @@
  *
  * Copyright (C) 2017 Paolo Valente <paolo.valente@linaro.org>
  *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License as
- *  published by the Free Software Foundation; either version 2 of the
- *  License, or (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- *  General Public License for more details.
- *
  * BFQ is a proportional-share I/O scheduler, with some extra
  * low-latency capabilities. BFQ also supports full hierarchical
  * scheduling through cgroups. Next paragraphs provide an introduction
@@ -189,7 +180,7 @@ static const int bfq_default_max_budget = 16 * 1024;
 /*
  * When a sync request is dispatched, the queue that contains that
  * request, and all the ancestor entities of that queue, are charged
- * with the number of sectors of the request. In constrast, if the
+ * with the number of sectors of the request. In contrast, if the
  * request is async, then the queue and its ancestor entities are
  * charged with the number of sectors of the request, multiplied by
  * the factor below. This throttles the bandwidth for async I/O,
@@ -217,7 +208,7 @@ const int bfq_timeout = HZ / 8;
  * queue merging.
  *
  * As can be deduced from the low time limit below, queue merging, if
- * successful, happens at the very beggining of the I/O of the involved
+ * successful, happens at the very beginning of the I/O of the involved
  * cooperating processes, as a consequence of the arrival of the very
  * first requests from each cooperator.  After that, there is very
  * little chance to find cooperators.
@@ -242,6 +233,14 @@ static struct kmem_cache *bfq_pool;
 	  blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT))
 #define BFQQ_CLOSE_THR		(sector_t)(8 * 1024)
 #define BFQQ_SEEKY(bfqq)	(hweight32(bfqq->seek_history) > 19)
+/*
+ * Sync random I/O is likely to be confused with soft real-time I/O,
+ * because it is characterized by limited throughput and apparently
+ * isochronous arrival pattern. To avoid false positives, queues
+ * containing only random (seeky) I/O are prevented from being tagged
+ * as soft real-time.
+ */
+#define BFQQ_TOTALLY_SEEKY(bfqq)	(bfqq->seek_history & -1)
 
 /* Min number of samples required to perform peak-rate update */
 #define BFQ_RATE_MIN_SAMPLES	32
@@ -433,7 +432,7 @@ void bfq_schedule_dispatch(struct bfq_data *bfqd)
 
 /*
  * Lifted from AS - choose which of rq1 and rq2 that is best served now.
- * We choose the request that is closesr to the head right now.  Distance
+ * We choose the request that is closer to the head right now.  Distance
  * behind the head is penalized and only allowed to a certain extent.
  */
 static struct request *bfq_choose_req(struct bfq_data *bfqd,
@@ -595,7 +594,16 @@ static bool bfq_too_late_for_merging(struct bfq_queue *bfqq)
 				       bfq_merge_time_limit);
 }
 
-void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+/*
+ * The following function is not marked as __cold because it is
+ * actually cold, but for the same performance goal described in the
+ * comments on the likely() at the beginning of
+ * bfq_setup_cooperator(). Unexpectedly, to reach an even lower
+ * execution time for the case where this function is not invoked, we
+ * had to add an unlikely() in each involved if().
+ */
+void __cold
+bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 {
 	struct rb_node **p, *parent;
 	struct bfq_queue *__bfqq;
@@ -629,12 +637,19 @@ void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 }
 
 /*
- * The following function returns true if every queue must receive the
- * same share of the throughput (this condition is used when deciding
- * whether idling may be disabled, see the comments in the function
- * bfq_better_to_idle()).
+ * The following function returns false either if every active queue
+ * must receive the same share of the throughput (symmetric scenario),
+ * or, as a special case, if bfqq must receive a share of the
+ * throughput lower than or equal to the share that every other active
+ * queue must receive.  If bfqq does sync I/O, then these are the only
+ * two cases where bfqq happens to be guaranteed its share of the
+ * throughput even if I/O dispatching is not plugged when bfqq remains
+ * temporarily empty (for more details, see the comments in the
+ * function bfq_better_to_idle()). For this reason, the return value
+ * of this function is used to check whether I/O-dispatch plugging can
+ * be avoided.
  *
- * Such a scenario occurs when:
+ * The above first case (symmetric scenario) occurs when:
  * 1) all active queues have the same weight,
  * 2) all active queues belong to the same I/O-priority class,
  * 3) all active groups at the same level in the groups tree have the same
@@ -654,30 +669,36 @@ void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
  * support or the cgroups interface are not enabled, thus no state
  * needs to be maintained in this case.
  */
-static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
+static bool bfq_asymmetric_scenario(struct bfq_data *bfqd,
+				   struct bfq_queue *bfqq)
 {
+	bool smallest_weight = bfqq &&
+		bfqq->weight_counter &&
+		bfqq->weight_counter ==
+		container_of(
+			rb_first_cached(&bfqd->queue_weights_tree),
+			struct bfq_weight_counter,
+			weights_node);
+
 	/*
 	 * For queue weights to differ, queue_weights_tree must contain
 	 * at least two nodes.
 	 */
-	bool varied_queue_weights = !RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
-		(bfqd->queue_weights_tree.rb_node->rb_left ||
-		 bfqd->queue_weights_tree.rb_node->rb_right);
+	bool varied_queue_weights = !smallest_weight &&
+		!RB_EMPTY_ROOT(&bfqd->queue_weights_tree.rb_root) &&
+		(bfqd->queue_weights_tree.rb_root.rb_node->rb_left ||
+		 bfqd->queue_weights_tree.rb_root.rb_node->rb_right);
 
 	bool multiple_classes_busy =
 		(bfqd->busy_queues[0] && bfqd->busy_queues[1]) ||
 		(bfqd->busy_queues[0] && bfqd->busy_queues[2]) ||
 		(bfqd->busy_queues[1] && bfqd->busy_queues[2]);
 
-	/*
-	 * For queue weights to differ, queue_weights_tree must contain
-	 * at least two nodes.
-	 */
-	return !(varied_queue_weights || multiple_classes_busy
+	return varied_queue_weights || multiple_classes_busy
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 	       || bfqd->num_groups_with_pending_reqs > 0
 #endif
-		);
+		;
 }
 
 /*
@@ -694,10 +715,11 @@ static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
  * should be low too.
  */
 void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq,
-			  struct rb_root *root)
+			  struct rb_root_cached *root)
 {
 	struct bfq_entity *entity = &bfqq->entity;
-	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct rb_node **new = &(root->rb_root.rb_node), *parent = NULL;
+	bool leftmost = true;
 
 	/*
 	 * Do not insert if the queue is already associated with a
@@ -726,8 +748,10 @@ void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		}
 		if (entity->weight < __counter->weight)
 			new = &((*new)->rb_left);
-		else
+		else {
 			new = &((*new)->rb_right);
+			leftmost = false;
+		}
 	}
 
 	bfqq->weight_counter = kzalloc(sizeof(struct bfq_weight_counter),
@@ -736,7 +760,7 @@ void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	/*
 	 * In the unlucky event of an allocation failure, we just
 	 * exit. This will cause the weight of queue to not be
-	 * considered in bfq_symmetric_scenario, which, in its turn,
+	 * considered in bfq_asymmetric_scenario, which, in its turn,
 	 * causes the scenario to be deemed wrongly symmetric in case
 	 * bfqq's weight would have been the only weight making the
 	 * scenario asymmetric.  On the bright side, no unbalance will
@@ -750,7 +774,8 @@ void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 
 	bfqq->weight_counter->weight = entity->weight;
 	rb_link_node(&bfqq->weight_counter->weights_node, parent, new);
-	rb_insert_color(&bfqq->weight_counter->weights_node, root);
+	rb_insert_color_cached(&bfqq->weight_counter->weights_node, root,
+				leftmost);
 
 inc_counter:
 	bfqq->weight_counter->num_active++;
@@ -765,7 +790,7 @@ inc_counter:
  */
 void __bfq_weights_tree_remove(struct bfq_data *bfqd,
 			       struct bfq_queue *bfqq,
-			       struct rb_root *root)
+			       struct rb_root_cached *root)
 {
 	if (!bfqq->weight_counter)
 		return;
@@ -774,7 +799,7 @@ void __bfq_weights_tree_remove(struct bfq_data *bfqd,
 	if (bfqq->weight_counter->num_active > 0)
 		goto reset_entity_pointer;
 
-	rb_erase(&bfqq->weight_counter->weights_node, root);
+	rb_erase_cached(&bfqq->weight_counter->weights_node, root);
 	kfree(bfqq->weight_counter);
 
 reset_entity_pointer:
@@ -889,7 +914,7 @@ static unsigned long bfq_serv_to_charge(struct request *rq,
 					struct bfq_queue *bfqq)
 {
 	if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1 ||
-	    !bfq_symmetric_scenario(bfqq->bfqd))
+	    bfq_asymmetric_scenario(bfqq->bfqd, bfqq))
 		return blk_rq_sectors(rq);
 
 	return blk_rq_sectors(rq) * bfq_async_charge_factor;
@@ -955,7 +980,7 @@ static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
 	 *   of several files
 	 * mplayer took 23 seconds to start, if constantly weight-raised.
 	 *
-	 * As for higher values than that accomodating the above bad
+	 * As for higher values than that accommodating the above bad
 	 * scenario, tests show that higher values would often yield
 	 * the opposite of the desired result, i.e., would worsen
 	 * responsiveness by allowing non-interactive applications to
@@ -994,6 +1019,7 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 	else
 		bfq_clear_bfqq_IO_bound(bfqq);
 
+	bfqq->entity.new_weight = bic->saved_weight;
 	bfqq->ttime = bic->saved_ttime;
 	bfqq->wr_coeff = bic->saved_wr_coeff;
 	bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt;
@@ -1041,8 +1067,18 @@ static void bfq_reset_burst_list(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 
 	hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node)
 		hlist_del_init(&item->burst_list_node);
-	hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
-	bfqd->burst_size = 1;
+
+	/*
+	 * Start the creation of a new burst list only if there is no
+	 * active queue. See comments on the conditional invocation of
+	 * bfq_handle_burst().
+	 */
+	if (bfq_tot_busy_queues(bfqd) == 0) {
+		hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+		bfqd->burst_size = 1;
+	} else
+		bfqd->burst_size = 0;
+
 	bfqd->burst_parent_entity = bfqq->entity.parent;
 }
 
@@ -1098,7 +1134,8 @@ static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
  * many parallel threads/processes. Examples are systemd during boot,
  * or git grep. To help these processes get their job done as soon as
  * possible, it is usually better to not grant either weight-raising
- * or device idling to their queues.
+ * or device idling to their queues, unless these queues must be
+ * protected from the I/O flowing through other active queues.
  *
  * In this comment we describe, firstly, the reasons why this fact
  * holds, and, secondly, the next function, which implements the main
@@ -1110,7 +1147,10 @@ static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
  * cumulatively served, the sooner the target job of these queues gets
  * completed. As a consequence, weight-raising any of these queues,
  * which also implies idling the device for it, is almost always
- * counterproductive. In most cases it just lowers throughput.
+ * counterproductive, unless there are other active queues to isolate
+ * these new queues from. If there no other active queues, then
+ * weight-raising these new queues just lowers throughput in most
+ * cases.
  *
  * On the other hand, a burst of queue creations may be caused also by
  * the start of an application that does not consist of a lot of
@@ -1144,14 +1184,16 @@ static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
  * are very rare. They typically occur if some service happens to
  * start doing I/O exactly when the interactive task starts.
  *
- * Turning back to the next function, it implements all the steps
- * needed to detect the occurrence of a large burst and to properly
- * mark all the queues belonging to it (so that they can then be
- * treated in a different way). This goal is achieved by maintaining a
- * "burst list" that holds, temporarily, the queues that belong to the
- * burst in progress. The list is then used to mark these queues as
- * belonging to a large burst if the burst does become large. The main
- * steps are the following.
+ * Turning back to the next function, it is invoked only if there are
+ * no active queues (apart from active queues that would belong to the
+ * same, possible burst bfqq would belong to), and it implements all
+ * the steps needed to detect the occurrence of a large burst and to
+ * properly mark all the queues belonging to it (so that they can then
+ * be treated in a different way). This goal is achieved by
+ * maintaining a "burst list" that holds, temporarily, the queues that
+ * belong to the burst in progress. The list is then used to mark
+ * these queues as belonging to a large burst if the burst does become
+ * large. The main steps are the following.
  *
  * . when the very first queue is created, the queue is inserted into the
  *   list (as it could be the first queue in a possible burst)
@@ -1596,6 +1638,7 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
 	 */
 	in_burst = bfq_bfqq_in_large_burst(bfqq);
 	soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
+		!BFQQ_TOTALLY_SEEKY(bfqq) &&
 		!in_burst &&
 		time_is_before_jiffies(bfqq->soft_rt_next_start) &&
 		bfqq->dispatched == 0;
@@ -1704,6 +1747,123 @@ static void bfq_add_request(struct request *rq)
 	bfqq->queued[rq_is_sync(rq)]++;
 	bfqd->queued++;
 
+	if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) {
+		/*
+		 * Periodically reset inject limit, to make sure that
+		 * the latter eventually drops in case workload
+		 * changes, see step (3) in the comments on
+		 * bfq_update_inject_limit().
+		 */
+		if (time_is_before_eq_jiffies(bfqq->decrease_time_jif +
+					     msecs_to_jiffies(1000))) {
+			/* invalidate baseline total service time */
+			bfqq->last_serv_time_ns = 0;
+
+			/*
+			 * Reset pointer in case we are waiting for
+			 * some request completion.
+			 */
+			bfqd->waited_rq = NULL;
+
+			/*
+			 * If bfqq has a short think time, then start
+			 * by setting the inject limit to 0
+			 * prudentially, because the service time of
+			 * an injected I/O request may be higher than
+			 * the think time of bfqq, and therefore, if
+			 * one request was injected when bfqq remains
+			 * empty, this injected request might delay
+			 * the service of the next I/O request for
+			 * bfqq significantly. In case bfqq can
+			 * actually tolerate some injection, then the
+			 * adaptive update will however raise the
+			 * limit soon. This lucky circumstance holds
+			 * exactly because bfqq has a short think
+			 * time, and thus, after remaining empty, is
+			 * likely to get new I/O enqueued---and then
+			 * completed---before being expired. This is
+			 * the very pattern that gives the
+			 * limit-update algorithm the chance to
+			 * measure the effect of injection on request
+			 * service times, and then to update the limit
+			 * accordingly.
+			 *
+			 * On the opposite end, if bfqq has a long
+			 * think time, then start directly by 1,
+			 * because:
+			 * a) on the bright side, keeping at most one
+			 * request in service in the drive is unlikely
+			 * to cause any harm to the latency of bfqq's
+			 * requests, as the service time of a single
+			 * request is likely to be lower than the
+			 * think time of bfqq;
+			 * b) on the downside, after becoming empty,
+			 * bfqq is likely to expire before getting its
+			 * next request. With this request arrival
+			 * pattern, it is very hard to sample total
+			 * service times and update the inject limit
+			 * accordingly (see comments on
+			 * bfq_update_inject_limit()). So the limit is
+			 * likely to be never, or at least seldom,
+			 * updated.  As a consequence, by setting the
+			 * limit to 1, we avoid that no injection ever
+			 * occurs with bfqq. On the downside, this
+			 * proactive step further reduces chances to
+			 * actually compute the baseline total service
+			 * time. Thus it reduces chances to execute the
+			 * limit-update algorithm and possibly raise the
+			 * limit to more than 1.
+			 */
+			if (bfq_bfqq_has_short_ttime(bfqq))
+				bfqq->inject_limit = 0;
+			else
+				bfqq->inject_limit = 1;
+			bfqq->decrease_time_jif = jiffies;
+		}
+
+		/*
+		 * The following conditions must hold to setup a new
+		 * sampling of total service time, and then a new
+		 * update of the inject limit:
+		 * - bfqq is in service, because the total service
+		 *   time is evaluated only for the I/O requests of
+		 *   the queues in service;
+		 * - this is the right occasion to compute or to
+		 *   lower the baseline total service time, because
+		 *   there are actually no requests in the drive,
+		 *   or
+		 *   the baseline total service time is available, and
+		 *   this is the right occasion to compute the other
+		 *   quantity needed to update the inject limit, i.e.,
+		 *   the total service time caused by the amount of
+		 *   injection allowed by the current value of the
+		 *   limit. It is the right occasion because injection
+		 *   has actually been performed during the service
+		 *   hole, and there are still in-flight requests,
+		 *   which are very likely to be exactly the injected
+		 *   requests, or part of them;
+		 * - the minimum interval for sampling the total
+		 *   service time and updating the inject limit has
+		 *   elapsed.
+		 */
+		if (bfqq == bfqd->in_service_queue &&
+		    (bfqd->rq_in_driver == 0 ||
+		     (bfqq->last_serv_time_ns > 0 &&
+		      bfqd->rqs_injected && bfqd->rq_in_driver > 0)) &&
+		    time_is_before_eq_jiffies(bfqq->decrease_time_jif +
+					      msecs_to_jiffies(100))) {
+			bfqd->last_empty_occupied_ns = ktime_get_ns();
+			/*
+			 * Start the state machine for measuring the
+			 * total service time of rq: setting
+			 * wait_dispatch will cause bfqd->waited_rq to
+			 * be set when rq will be dispatched.
+			 */
+			bfqd->wait_dispatch = true;
+			bfqd->rqs_injected = false;
+		}
+	}
+
 	elv_rb_add(&bfqq->sort_list, rq);
 
 	/*
@@ -1715,8 +1875,9 @@ static void bfq_add_request(struct request *rq)
 
 	/*
 	 * Adjust priority tree position, if next_rq changes.
+	 * See comments on bfq_pos_tree_add_move() for the unlikely().
 	 */
-	if (prev != bfqq->next_rq)
+	if (unlikely(!bfqd->nonrot_with_queueing && prev != bfqq->next_rq))
 		bfq_pos_tree_add_move(bfqd, bfqq);
 
 	if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */
@@ -1856,7 +2017,9 @@ static void bfq_remove_request(struct request_queue *q,
 			bfqq->pos_root = NULL;
 		}
 	} else {
-		bfq_pos_tree_add_move(bfqd, bfqq);
+		/* see comments on bfq_pos_tree_add_move() for the unlikely() */
+		if (unlikely(!bfqd->nonrot_with_queueing))
+			bfq_pos_tree_add_move(bfqd, bfqq);
 	}
 
 	if (rq->cmd_flags & REQ_META)
@@ -1941,7 +2104,12 @@ static void bfq_request_merged(struct request_queue *q, struct request *req,
 		 */
 		if (prev != bfqq->next_rq) {
 			bfq_updated_next_req(bfqd, bfqq);
-			bfq_pos_tree_add_move(bfqd, bfqq);
+			/*
+			 * See comments on bfq_pos_tree_add_move() for
+			 * the unlikely().
+			 */
+			if (unlikely(!bfqd->nonrot_with_queueing))
+				bfq_pos_tree_add_move(bfqd, bfqq);
 		}
 	}
 }
@@ -2224,6 +2392,46 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	struct bfq_queue *in_service_bfqq, *new_bfqq;
 
 	/*
+	 * 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
+	 * and pipelining. This means that, to reach a high
+	 * throughput, it must have many requests enqueued at the same
+	 * time. But, in this configuration, the internal scheduling
+	 * algorithm of the device does exactly the job of queue
+	 * merging: it reorders requests so as to obtain as much as
+	 * possible a sequential I/O pattern. As a consequence, with
+	 * the workload generated by processes doing interleaved I/O,
+	 * the throughput reached by the device is likely to be the
+	 * same, with and without queue merging.
+	 *
+	 * Disabling merging also provides a remarkable benefit in
+	 * terms of throughput. Merging tends to make many workloads
+	 * artificially more uneven, because of shared queues
+	 * remaining non empty for incomparably more time than
+	 * non-merged queues. This may accentuate workload
+	 * asymmetries. For example, if one of the queues in a set of
+	 * merged queues has a higher weight than a normal queue, then
+	 * the shared queue may inherit such a high weight and, by
+	 * staying almost always active, may force BFQ to perform I/O
+	 * plugging most of the time. This evidently makes it harder
+	 * for BFQ to let the device reach a high throughput.
+	 *
+	 * Finally, the likely() macro below is not used because one
+	 * of the two branches is more likely than the other, but to
+	 * have the code path after the following if() executed as
+	 * fast as possible for the case of a non rotational device
+	 * with queueing. We want it because this is the fastest kind
+	 * of device. On the opposite end, the likely() may lengthen
+	 * the execution time of BFQ for the case of slower devices
+	 * (rotational or at least without queueing). But in this case
+	 * the execution time of BFQ matters very little, if not at
+	 * all.
+	 */
+	if (likely(bfqd->nonrot_with_queueing))
+		return NULL;
+
+	/*
 	 * Prevent bfqq from being merged if it has been created too
 	 * long ago. The idea is that true cooperating processes, and
 	 * thus their associated bfq_queues, are supposed to be
@@ -2286,6 +2494,7 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	if (!bic)
 		return;
 
+	bic->saved_weight = bfqq->entity.orig_weight;
 	bic->saved_ttime = bfqq->ttime;
 	bic->saved_has_short_ttime = bfq_bfqq_has_short_ttime(bfqq);
 	bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
@@ -2374,6 +2583,16 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 	 *   assignment causes no harm).
 	 */
 	new_bfqq->bic = NULL;
+	/*
+	 * If the queue is shared, the pid is the pid of one of the associated
+	 * processes. Which pid depends on the exact sequence of merge events
+	 * the queue underwent. So printing such a pid is useless and confusing
+	 * because it reports a random pid between those of the associated
+	 * processes.
+	 * We mark such a queue with a pid -1, and then print SHARED instead of
+	 * a pid in logging messages.
+	 */
+	new_bfqq->pid = -1;
 	bfqq->bic = NULL;
 	/* release process reference to bfqq */
 	bfq_put_queue(bfqq);
@@ -2408,8 +2627,8 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
 		/*
 		 * bic still points to bfqq, then it has not yet been
 		 * redirected to some other bfq_queue, and a queue
-		 * merge beween bfqq and new_bfqq can be safely
-		 * fulfillled, i.e., bic can be redirected to new_bfqq
+		 * merge between bfqq and new_bfqq can be safely
+		 * fulfilled, i.e., bic can be redirected to new_bfqq
 		 * and bfqq can be put.
 		 */
 		bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq,
@@ -2543,10 +2762,14 @@ static void bfq_arm_slice_timer(struct bfq_data *bfqd)
 	 * queue).
 	 */
 	if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
-	    bfq_symmetric_scenario(bfqd))
+	    !bfq_asymmetric_scenario(bfqd, bfqq))
 		sl = min_t(u64, sl, BFQ_MIN_TT);
+	else if (bfqq->wr_coeff > 1)
+		sl = max_t(u32, sl, 20ULL * NSEC_PER_MSEC);
 
 	bfqd->last_idling_start = ktime_get();
+	bfqd->last_idling_start_jiffies = jiffies;
+
 	hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),
 		      HRTIMER_MODE_REL);
 	bfqg_stats_set_start_idle_time(bfqq_group(bfqq));
@@ -2848,8 +3071,10 @@ static bool __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 		bfq_requeue_bfqq(bfqd, bfqq, true);
 		/*
 		 * Resort priority tree of potential close cooperators.
+		 * See comments on bfq_pos_tree_add_move() for the unlikely().
 		 */
-		bfq_pos_tree_add_move(bfqd, bfqq);
+		if (unlikely(!bfqd->nonrot_with_queueing))
+			bfq_pos_tree_add_move(bfqd, bfqq);
 	}
 
 	/*
@@ -3223,13 +3448,6 @@ static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
 		    jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
 }
 
-static bool bfq_bfqq_injectable(struct bfq_queue *bfqq)
-{
-	return BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
-		blk_queue_nonrot(bfqq->bfqd->queue) &&
-		bfqq->bfqd->hw_tag;
-}
-
 /**
  * bfq_bfqq_expire - expire a queue.
  * @bfqd: device owning the queue.
@@ -3344,6 +3562,14 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 		slow, bfqq->dispatched, bfq_bfqq_has_short_ttime(bfqq));
 
 	/*
+	 * bfqq expired, so no total service time needs to be computed
+	 * any longer: reset state machine for measuring total service
+	 * times.
+	 */
+	bfqd->rqs_injected = bfqd->wait_dispatch = false;
+	bfqd->waited_rq = NULL;
+
+	/*
 	 * Increase, decrease or leave budget unchanged according to
 	 * reason.
 	 */
@@ -3352,8 +3578,6 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 		/* bfqq is gone, no more actions on it */
 		return;
 
-	bfqq->injected_service = 0;
-
 	/* mark bfqq as waiting a request only if a bic still points to it */
 	if (!bfq_bfqq_busy(bfqq) &&
 	    reason != BFQQE_BUDGET_TIMEOUT &&
@@ -3497,8 +3721,9 @@ static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd,
 }
 
 /*
- * There is a case where idling must be performed not for
- * throughput concerns, but to preserve service guarantees.
+ * There is a case where idling does not have to be performed for
+ * throughput concerns, but to preserve the throughput share of
+ * the process associated with bfqq.
  *
  * To introduce this case, we can note that allowing the drive
  * to enqueue more than one request at a time, and hence
@@ -3514,77 +3739,83 @@ static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd,
  * concern about per-process throughput distribution, and
  * makes its decisions only on a per-request basis. Therefore,
  * the service distribution enforced by the drive's internal
- * scheduler is likely to coincide with the desired
- * device-throughput distribution only in a completely
- * symmetric scenario where:
- * (i)  each of these processes must get the same throughput as
- *      the others;
- * (ii) the I/O of each process has the same properties, in
- *      terms of locality (sequential or random), direction
- *      (reads or writes), request sizes, greediness
- *      (from I/O-bound to sporadic), and so on.
- * In fact, in such a scenario, the drive tends to treat
- * the requests of each of these processes in about the same
- * way as the requests of the others, and thus to provide
- * each of these processes with about the same throughput
- * (which is exactly the desired throughput distribution). In
- * contrast, in any asymmetric scenario, device idling is
- * certainly needed to guarantee that bfqq receives its
- * assigned fraction of the device throughput (see [1] for
- * details).
- * The problem is that idling may significantly reduce
- * throughput with certain combinations of types of I/O and
- * devices. An important example is sync random I/O, on flash
- * storage with command queueing. So, unless bfqq falls in the
- * above cases where idling also boosts throughput, it would
- * be important to check conditions (i) and (ii) accurately,
- * so as to avoid idling when not strictly needed for service
- * guarantees.
+ * scheduler is likely to coincide with the desired throughput
+ * distribution only in a completely symmetric, or favorably
+ * skewed scenario where:
+ * (i-a) each of these processes must get the same throughput as
+ *	 the others,
+ * (i-b) in case (i-a) does not hold, it holds that the process
+ *       associated with bfqq must receive a lower or equal
+ *	 throughput than any of the other processes;
+ * (ii)  the I/O of each process has the same properties, in
+ *       terms of locality (sequential or random), direction
+ *       (reads or writes), request sizes, greediness
+ *       (from I/O-bound to sporadic), and so on;
+
+ * In fact, in such a scenario, the drive tends to treat the requests
+ * of each process in about the same way as the requests of the
+ * others, and thus to provide each of these processes with about the
+ * same throughput.  This is exactly the desired throughput
+ * distribution if (i-a) holds, or, if (i-b) holds instead, this is an
+ * even more convenient distribution for (the process associated with)
+ * bfqq.
+ *
+ * In contrast, in any asymmetric or unfavorable scenario, device
+ * idling (I/O-dispatch plugging) is certainly needed to guarantee
+ * that bfqq receives its assigned fraction of the device throughput
+ * (see [1] for details).
  *
- * Unfortunately, it is extremely difficult to thoroughly
- * check condition (ii). And, in case there are active groups,
- * it becomes very difficult to check condition (i) too. In
- * fact, if there are active groups, then, for condition (i)
- * to become false, it is enough that an active group contains
- * more active processes or sub-groups than some other active
- * group. More precisely, for condition (i) to hold because of
- * such a group, it is not even necessary that the group is
- * (still) active: it is sufficient that, even if the group
- * has become inactive, some of its descendant processes still
- * have some request already dispatched but still waiting for
- * completion. In fact, requests have still to be guaranteed
- * their share of the throughput even after being
- * dispatched. In this respect, it is easy to show that, if a
- * group frequently becomes inactive while still having
- * in-flight requests, and if, when this happens, the group is
- * not considered in the calculation of whether the scenario
- * is asymmetric, then the group may fail to be guaranteed its
- * fair share of the throughput (basically because idling may
- * not be performed for the descendant processes of the group,
- * but it had to be).  We address this issue with the
- * following bi-modal behavior, implemented in the function
- * bfq_symmetric_scenario().
+ * The problem is that idling may significantly reduce throughput with
+ * certain combinations of types of I/O and devices. An important
+ * example is sync random I/O on flash storage with command
+ * queueing. So, unless bfqq falls in cases where idling also boosts
+ * throughput, it is important to check conditions (i-a), i(-b) and
+ * (ii) accurately, so as to avoid idling when not strictly needed for
+ * service guarantees.
+ *
+ * Unfortunately, it is extremely difficult to thoroughly check
+ * condition (ii). And, in case there are active groups, it becomes
+ * very difficult to check conditions (i-a) and (i-b) too.  In fact,
+ * if there are active groups, then, for conditions (i-a) or (i-b) to
+ * become false 'indirectly', it is enough that an active group
+ * contains more active processes or sub-groups than some other active
+ * group. More precisely, for conditions (i-a) or (i-b) to become
+ * false because of such a group, it is not even necessary that the
+ * group is (still) active: it is sufficient that, even if the group
+ * has become inactive, some of its descendant processes still have
+ * some request already dispatched but still waiting for
+ * completion. In fact, requests have still to be guaranteed their
+ * share of the throughput even after being dispatched. In this
+ * respect, it is easy to show that, if a group frequently becomes
+ * inactive while still having in-flight requests, and if, when this
+ * happens, the group is not considered in the calculation of whether
+ * the scenario is asymmetric, then the group may fail to be
+ * guaranteed its fair share of the throughput (basically because
+ * idling may not be performed for the descendant processes of the
+ * group, but it had to be).  We address this issue with the following
+ * bi-modal behavior, implemented in the function
+ * bfq_asymmetric_scenario().
  *
  * If there are groups with requests waiting for completion
  * (as commented above, some of these groups may even be
  * already inactive), then the scenario is tagged as
  * asymmetric, conservatively, without checking any of the
- * conditions (i) and (ii). So the device is idled for bfqq.
+ * conditions (i-a), (i-b) or (ii). So the device is idled for bfqq.
  * This behavior matches also the fact that groups are created
  * exactly if controlling I/O is a primary concern (to
  * preserve bandwidth and latency guarantees).
  *
- * On the opposite end, if there are no groups with requests
- * waiting for completion, then only condition (i) is actually
- * controlled, i.e., provided that condition (i) holds, idling
- * is not performed, regardless of whether condition (ii)
- * holds. In other words, only if condition (i) does not hold,
- * then idling is allowed, and the device tends to be
- * prevented from queueing many requests, possibly of several
- * processes. Since there are no groups with requests waiting
- * for completion, then, to control condition (i) it is enough
- * to check just whether all the queues with requests waiting
- * for completion also have the same weight.
+ * On the opposite end, if there are no groups with requests waiting
+ * for completion, then only conditions (i-a) and (i-b) are actually
+ * controlled, i.e., provided that conditions (i-a) or (i-b) holds,
+ * idling is not performed, regardless of whether condition (ii)
+ * holds.  In other words, only if conditions (i-a) and (i-b) do not
+ * hold, then idling is allowed, and the device tends to be prevented
+ * from queueing many requests, possibly of several processes. Since
+ * there are no groups with requests waiting for completion, then, to
+ * control conditions (i-a) and (i-b) it is enough to check just
+ * whether all the queues with requests waiting for completion also
+ * have the same weight.
  *
  * Not checking condition (ii) evidently exposes bfqq to the
  * risk of getting less throughput than its fair share.
@@ -3636,7 +3867,7 @@ static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd,
  * compound condition that is checked below for deciding
  * whether the scenario is asymmetric. To explain this
  * compound condition, we need to add that the function
- * bfq_symmetric_scenario checks the weights of only
+ * bfq_asymmetric_scenario checks the weights of only
  * non-weight-raised queues, for efficiency reasons (see
  * comments on bfq_weights_tree_add()). Then the fact that
  * bfqq is weight-raised is checked explicitly here. More
@@ -3664,7 +3895,7 @@ static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd,
 	return (bfqq->wr_coeff > 1 &&
 		bfqd->wr_busy_queues <
 		bfq_tot_busy_queues(bfqd)) ||
-		!bfq_symmetric_scenario(bfqd);
+		bfq_asymmetric_scenario(bfqd, bfqq);
 }
 
 /*
@@ -3740,26 +3971,98 @@ static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
 	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_better_to_idle(bfqq);
 }
 
-static struct bfq_queue *bfq_choose_bfqq_for_injection(struct bfq_data *bfqd)
+/*
+ * This function chooses the queue from which to pick the next extra
+ * I/O request to inject, if it finds a compatible queue. See the
+ * comments on bfq_update_inject_limit() for details on the injection
+ * mechanism, and for the definitions of the quantities mentioned
+ * below.
+ */
+static struct bfq_queue *
+bfq_choose_bfqq_for_injection(struct bfq_data *bfqd)
 {
-	struct bfq_queue *bfqq;
+	struct bfq_queue *bfqq, *in_serv_bfqq = bfqd->in_service_queue;
+	unsigned int limit = in_serv_bfqq->inject_limit;
+	/*
+	 * If
+	 * - bfqq is not weight-raised and therefore does not carry
+	 *   time-critical I/O,
+	 * or
+	 * - regardless of whether bfqq is weight-raised, bfqq has
+	 *   however a long think time, during which it can absorb the
+	 *   effect of an appropriate number of extra I/O requests
+	 *   from other queues (see bfq_update_inject_limit for
+	 *   details on the computation of this number);
+	 * then injection can be performed without restrictions.
+	 */
+	bool in_serv_always_inject = in_serv_bfqq->wr_coeff == 1 ||
+		!bfq_bfqq_has_short_ttime(in_serv_bfqq);
+
+	/*
+	 * If
+	 * - the baseline total service time could not be sampled yet,
+	 *   so the inject limit happens to be still 0, and
+	 * - a lot of time has elapsed since the plugging of I/O
+	 *   dispatching started, so drive speed is being wasted
+	 *   significantly;
+	 * then temporarily raise inject limit to one request.
+	 */
+	if (limit == 0 && in_serv_bfqq->last_serv_time_ns == 0 &&
+	    bfq_bfqq_wait_request(in_serv_bfqq) &&
+	    time_is_before_eq_jiffies(bfqd->last_idling_start_jiffies +
+				      bfqd->bfq_slice_idle)
+		)
+		limit = 1;
+
+	if (bfqd->rq_in_driver >= limit)
+		return NULL;
 
 	/*
-	 * A linear search; but, with a high probability, very few
-	 * steps are needed to find a candidate queue, i.e., a queue
-	 * with enough budget left for its next request. In fact:
+	 * Linear search of the source queue for injection; but, with
+	 * a high probability, very few steps are needed to find a
+	 * candidate queue, i.e., a queue with enough budget left for
+	 * its next request. In fact:
 	 * - BFQ dynamically updates the budget of every queue so as
 	 *   to accommodate the expected backlog of the queue;
 	 * - if a queue gets all its requests dispatched as injected
 	 *   service, then the queue is removed from the active list
-	 *   (and re-added only if it gets new requests, but with
-	 *   enough budget for its new backlog).
+	 *   (and re-added only if it gets new requests, but then it
+	 *   is assigned again enough budget for its new backlog).
 	 */
 	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
 		if (!RB_EMPTY_ROOT(&bfqq->sort_list) &&
+		    (in_serv_always_inject || bfqq->wr_coeff > 1) &&
 		    bfq_serv_to_charge(bfqq->next_rq, bfqq) <=
-		    bfq_bfqq_budget_left(bfqq))
-			return bfqq;
+		    bfq_bfqq_budget_left(bfqq)) {
+			/*
+			 * Allow for only one large in-flight request
+			 * on non-rotational devices, for the
+			 * following reason. On non-rotationl drives,
+			 * large requests take much longer than
+			 * smaller requests to be served. In addition,
+			 * the drive prefers to serve large requests
+			 * w.r.t. to small ones, if it can choose. So,
+			 * having more than one large requests queued
+			 * in the drive may easily make the next first
+			 * request of the in-service queue wait for so
+			 * long to break bfqq's service guarantees. On
+			 * the bright side, large requests let the
+			 * drive reach a very high throughput, even if
+			 * there is only one in-flight large request
+			 * at a time.
+			 */
+			if (blk_queue_nonrot(bfqd->queue) &&
+			    blk_rq_sectors(bfqq->next_rq) >=
+			    BFQQ_SECT_THR_NONROT)
+				limit = min_t(unsigned int, 1, limit);
+			else
+				limit = in_serv_bfqq->inject_limit;
+
+			if (bfqd->rq_in_driver < limit) {
+				bfqd->rqs_injected = true;
+				return bfqq;
+			}
+		}
 
 	return NULL;
 }
@@ -3846,14 +4149,32 @@ check_queue:
 	 * for a new request, or has requests waiting for a completion and
 	 * may idle after their completion, then keep it anyway.
 	 *
-	 * Yet, to boost throughput, inject service from other queues if
-	 * possible.
+	 * Yet, inject service from other queues if it boosts
+	 * throughput and is possible.
 	 */
 	if (bfq_bfqq_wait_request(bfqq) ||
 	    (bfqq->dispatched != 0 && bfq_better_to_idle(bfqq))) {
-		if (bfq_bfqq_injectable(bfqq) &&
-		    bfqq->injected_service * bfqq->inject_coeff <
-		    bfqq->entity.service * 10)
+		struct bfq_queue *async_bfqq =
+			bfqq->bic && bfqq->bic->bfqq[0] &&
+			bfq_bfqq_busy(bfqq->bic->bfqq[0]) ?
+			bfqq->bic->bfqq[0] : NULL;
+
+		/*
+		 * If the process associated with bfqq has also async
+		 * I/O pending, then inject it
+		 * unconditionally. Injecting I/O from the same
+		 * process can cause no harm to the process. On the
+		 * contrary, it can only increase bandwidth and reduce
+		 * latency for the process.
+		 */
+		if (async_bfqq &&
+		    icq_to_bic(async_bfqq->next_rq->elv.icq) == bfqq->bic &&
+		    bfq_serv_to_charge(async_bfqq->next_rq, async_bfqq) <=
+		    bfq_bfqq_budget_left(async_bfqq))
+			bfqq = bfqq->bic->bfqq[0];
+		else if (!idling_boosts_thr_without_issues(bfqd, bfqq) &&
+			 (bfqq->wr_coeff == 1 || bfqd->wr_busy_queues > 1 ||
+			  !bfq_bfqq_has_short_ttime(bfqq)))
 			bfqq = bfq_choose_bfqq_for_injection(bfqd);
 		else
 			bfqq = NULL;
@@ -3945,15 +4266,15 @@ static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
 
 	bfq_bfqq_served(bfqq, service_to_charge);
 
-	bfq_dispatch_remove(bfqd->queue, rq);
+	if (bfqq == bfqd->in_service_queue && bfqd->wait_dispatch) {
+		bfqd->wait_dispatch = false;
+		bfqd->waited_rq = rq;
+	}
 
-	if (bfqq != bfqd->in_service_queue) {
-		if (likely(bfqd->in_service_queue))
-			bfqd->in_service_queue->injected_service +=
-				bfq_serv_to_charge(rq, bfqq);
+	bfq_dispatch_remove(bfqd->queue, rq);
 
+	if (bfqq != bfqd->in_service_queue)
 		goto return_rq;
-	}
 
 	/*
 	 * If weight raising has to terminate for bfqq, then next
@@ -4384,13 +4705,6 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 			bfq_mark_bfqq_has_short_ttime(bfqq);
 		bfq_mark_bfqq_sync(bfqq);
 		bfq_mark_bfqq_just_created(bfqq);
-		/*
-		 * Aggressively inject a lot of service: up to 90%.
-		 * This coefficient remains constant during bfqq life,
-		 * but this behavior might be changed, after enough
-		 * testing and tuning.
-		 */
-		bfqq->inject_coeff = 1;
 	} else
 		bfq_clear_bfqq_sync(bfqq);
 
@@ -4529,6 +4843,11 @@ bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 {
 	bfqq->seek_history <<= 1;
 	bfqq->seek_history |= BFQ_RQ_SEEKY(bfqd, bfqq->last_request_pos, rq);
+
+	if (bfqq->wr_coeff > 1 &&
+	    bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
+	    BFQQ_TOTALLY_SEEKY(bfqq))
+		bfq_bfqq_end_wr(bfqq);
 }
 
 static void bfq_update_has_short_ttime(struct bfq_data *bfqd,
@@ -4823,6 +5142,9 @@ static void bfq_update_hw_tag(struct bfq_data *bfqd)
 	bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD;
 	bfqd->max_rq_in_driver = 0;
 	bfqd->hw_tag_samples = 0;
+
+	bfqd->nonrot_with_queueing =
+		blk_queue_nonrot(bfqd->queue) && bfqd->hw_tag;
 }
 
 static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
@@ -4950,6 +5272,147 @@ static void bfq_finish_requeue_request_body(struct bfq_queue *bfqq)
 }
 
 /*
+ * The processes associated with bfqq may happen to generate their
+ * cumulative I/O at a lower rate than the rate at which the device
+ * could serve the same I/O. This is rather probable, e.g., if only
+ * one process is associated with bfqq and the device is an SSD. It
+ * results in bfqq becoming often empty while in service. In this
+ * respect, if BFQ is allowed to switch to another queue when bfqq
+ * remains empty, then the device goes on being fed with I/O requests,
+ * and the throughput is not affected. In contrast, if BFQ is not
+ * allowed to switch to another queue---because bfqq is sync and
+ * I/O-dispatch needs to be plugged while bfqq is temporarily
+ * empty---then, during the service of bfqq, there will be frequent
+ * "service holes", i.e., time intervals during which bfqq gets empty
+ * and the device can only consume the I/O already queued in its
+ * hardware queues. During service holes, the device may even get to
+ * remaining idle. In the end, during the service of bfqq, the device
+ * is driven at a lower speed than the one it can reach with the kind
+ * of I/O flowing through bfqq.
+ *
+ * To counter this loss of throughput, BFQ implements a "request
+ * injection mechanism", which tries to fill the above service holes
+ * with I/O requests taken from other queues. The hard part in this
+ * mechanism is finding the right amount of I/O to inject, so as to
+ * both boost throughput and not break bfqq's bandwidth and latency
+ * guarantees. In this respect, the mechanism maintains a per-queue
+ * inject limit, computed as below. While bfqq is empty, the injection
+ * mechanism dispatches extra I/O requests only until the total number
+ * of I/O requests in flight---i.e., already dispatched but not yet
+ * completed---remains lower than this limit.
+ *
+ * A first definition comes in handy to introduce the algorithm by
+ * which the inject limit is computed.  We define as first request for
+ * bfqq, an I/O request for bfqq that arrives while bfqq is in
+ * service, and causes bfqq to switch from empty to non-empty. The
+ * algorithm updates the limit as a function of the effect of
+ * injection on the service times of only the first requests of
+ * bfqq. The reason for this restriction is that these are the
+ * requests whose service time is affected most, because they are the
+ * first to arrive after injection possibly occurred.
+ *
+ * To evaluate the effect of injection, the algorithm measures the
+ * "total service time" of first requests. We define as total service
+ * time of an I/O request, the time that elapses since when the
+ * request is enqueued into bfqq, to when it is completed. This
+ * quantity allows the whole effect of injection to be measured. It is
+ * easy to see why. Suppose that some requests of other queues are
+ * actually injected while bfqq is empty, and that a new request R
+ * then arrives for bfqq. If the device does start to serve all or
+ * part of the injected requests during the service hole, then,
+ * because of this extra service, it may delay the next invocation of
+ * the dispatch hook of BFQ. Then, even after R gets eventually
+ * dispatched, the device may delay the actual service of R if it is
+ * still busy serving the extra requests, or if it decides to serve,
+ * before R, some extra request still present in its queues. As a
+ * conclusion, the cumulative extra delay caused by injection can be
+ * easily evaluated by just comparing the total service time of first
+ * requests with and without injection.
+ *
+ * The limit-update algorithm works as follows. On the arrival of a
+ * first request of bfqq, the algorithm measures the total time of the
+ * request only if one of the three cases below holds, and, for each
+ * case, it updates the limit as described below:
+ *
+ * (1) If there is no in-flight request. This gives a baseline for the
+ *     total service time of the requests of bfqq. If the baseline has
+ *     not been computed yet, then, after computing it, the limit is
+ *     set to 1, to start boosting throughput, and to prepare the
+ *     ground for the next case. If the baseline has already been
+ *     computed, then it is updated, in case it results to be lower
+ *     than the previous value.
+ *
+ * (2) If the limit is higher than 0 and there are in-flight
+ *     requests. By comparing the total service time in this case with
+ *     the above baseline, it is possible to know at which extent the
+ *     current value of the limit is inflating the total service
+ *     time. If the inflation is below a certain threshold, then bfqq
+ *     is assumed to be suffering from no perceivable loss of its
+ *     service guarantees, and the limit is even tentatively
+ *     increased. If the inflation is above the threshold, then the
+ *     limit is decreased. Due to the lack of any hysteresis, this
+ *     logic makes the limit oscillate even in steady workload
+ *     conditions. Yet we opted for it, because it is fast in reaching
+ *     the best value for the limit, as a function of the current I/O
+ *     workload. To reduce oscillations, this step is disabled for a
+ *     short time interval after the limit happens to be decreased.
+ *
+ * (3) Periodically, after resetting the limit, to make sure that the
+ *     limit eventually drops in case the workload changes. This is
+ *     needed because, after the limit has gone safely up for a
+ *     certain workload, it is impossible to guess whether the
+ *     baseline total service time may have changed, without measuring
+ *     it again without injection. A more effective version of this
+ *     step might be to just sample the baseline, by interrupting
+ *     injection only once, and then to reset/lower the limit only if
+ *     the total service time with the current limit does happen to be
+ *     too large.
+ *
+ * More details on each step are provided in the comments on the
+ * pieces of code that implement these steps: the branch handling the
+ * transition from empty to non empty in bfq_add_request(), the branch
+ * handling injection in bfq_select_queue(), and the function
+ * bfq_choose_bfqq_for_injection(). These comments also explain some
+ * exceptions, made by the injection mechanism in some special cases.
+ */
+static void bfq_update_inject_limit(struct bfq_data *bfqd,
+				    struct bfq_queue *bfqq)
+{
+	u64 tot_time_ns = ktime_get_ns() - bfqd->last_empty_occupied_ns;
+	unsigned int old_limit = bfqq->inject_limit;
+
+	if (bfqq->last_serv_time_ns > 0) {
+		u64 threshold = (bfqq->last_serv_time_ns * 3)>>1;
+
+		if (tot_time_ns >= threshold && old_limit > 0) {
+			bfqq->inject_limit--;
+			bfqq->decrease_time_jif = jiffies;
+		} else if (tot_time_ns < threshold &&
+			   old_limit < bfqd->max_rq_in_driver<<1)
+			bfqq->inject_limit++;
+	}
+
+	/*
+	 * Either we still have to compute the base value for the
+	 * total service time, and there seem to be the right
+	 * conditions to do it, or we can lower the last base value
+	 * computed.
+	 */
+	if ((bfqq->last_serv_time_ns == 0 && bfqd->rq_in_driver == 0) ||
+	    tot_time_ns < bfqq->last_serv_time_ns) {
+		bfqq->last_serv_time_ns = tot_time_ns;
+		/*
+		 * Now we certainly have a base value: make sure we
+		 * start trying injection.
+		 */
+		bfqq->inject_limit = max_t(unsigned int, 1, old_limit);
+	}
+
+	/* update complete, not waiting for any request completion any longer */
+	bfqd->waited_rq = NULL;
+}
+
+/*
  * Handle either a requeue or a finish for rq. The things to do are
  * the same in both cases: all references to rq are to be dropped. In
  * particular, rq is considered completed from the point of view of
@@ -4993,6 +5456,9 @@ static void bfq_finish_requeue_request(struct request *rq)
 
 		spin_lock_irqsave(&bfqd->lock, flags);
 
+		if (rq == bfqd->waited_rq)
+			bfq_update_inject_limit(bfqd, bfqq);
+
 		bfq_completed_request(bfqq, bfqd);
 		bfq_finish_requeue_request_body(bfqq);
 
@@ -5156,7 +5622,7 @@ static void bfq_prepare_request(struct request *rq, struct bio *bio)
  * preparation is that, after the prepare_request hook is invoked for
  * rq, rq may still be transformed into a request with no icq, i.e., a
  * request not associated with any queue. No bfq hook is invoked to
- * signal this tranformation. As a consequence, should these
+ * signal this transformation. As a consequence, should these
  * preparation operations be performed when the prepare_request hook
  * is invoked, and should rq be transformed one moment later, bfq
  * would end up in an inconsistent state, because it would have
@@ -5247,7 +5713,29 @@ static struct bfq_queue *bfq_init_rq(struct request *rq)
 		}
 	}
 
-	if (unlikely(bfq_bfqq_just_created(bfqq)))
+	/*
+	 * Consider bfqq as possibly belonging to a burst of newly
+	 * created queues only if:
+	 * 1) A burst is actually happening (bfqd->burst_size > 0)
+	 * or
+	 * 2) There is no other active queue. In fact, if, in
+	 *    contrast, there are active queues not belonging to the
+	 *    possible burst bfqq may belong to, then there is no gain
+	 *    in considering bfqq as belonging to a burst, and
+	 *    therefore in not weight-raising bfqq. See comments on
+	 *    bfq_handle_burst().
+	 *
+	 * This filtering also helps eliminating false positives,
+	 * occurring when bfqq does not belong to an actual large
+	 * burst, but some background task (e.g., a service) happens
+	 * to trigger the creation of new queues very close to when
+	 * bfqq and its possible companion queues are created. See
+	 * comments on bfq_handle_burst() for further details also on
+	 * this issue.
+	 */
+	if (unlikely(bfq_bfqq_just_created(bfqq) &&
+		     (bfqd->burst_size > 0 ||
+		      bfq_tot_busy_queues(bfqd) == 0)))
 		bfq_handle_burst(bfqd, bfqq);
 
 	return bfqq;
@@ -5507,7 +5995,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 		     HRTIMER_MODE_REL);
 	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
 
-	bfqd->queue_weights_tree = RB_ROOT;
+	bfqd->queue_weights_tree = RB_ROOT_CACHED;
 	bfqd->num_groups_with_pending_reqs = 0;
 
 	INIT_LIST_HEAD(&bfqd->active_list);
@@ -5515,6 +6003,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	INIT_HLIST_HEAD(&bfqd->burst_list);
 
 	bfqd->hw_tag = -1;
+	bfqd->nonrot_with_queueing = blk_queue_nonrot(bfqd->queue);
 
 	bfqd->bfq_max_budget = bfq_default_max_budget;
 
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 86394e503ca9..c2faa77824f8 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Header file for the BFQ I/O scheduler: data structures and
  * prototypes of interface functions among BFQ components.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License as
- *  published by the Free Software Foundation; either version 2 of the
- *  License, or (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- *  General Public License for more details.
  */
 #ifndef _BFQ_H
 #define _BFQ_H
@@ -32,6 +23,8 @@
 #define BFQ_DEFAULT_GRP_IOPRIO	0
 #define BFQ_DEFAULT_GRP_CLASS	IOPRIO_CLASS_BE
 
+#define MAX_PID_STR_LENGTH 12
+
 /*
  * Soft real-time applications are extremely more latency sensitive
  * than interactive ones. Over-raise the weight of the former to
@@ -89,7 +82,7 @@ struct bfq_service_tree {
  * expiration. This peculiar definition allows for the following
  * optimization, not yet exploited: while a given entity is still in
  * service, we already know which is the best candidate for next
- * service among the other active entitities in the same parent
+ * service among the other active entities in the same parent
  * entity. We can then quickly compare the timestamps of the
  * in-service entity with those of such best candidate.
  *
@@ -140,7 +133,7 @@ struct bfq_weight_counter {
  *
  * Unless cgroups are used, the weight value is calculated from the
  * ioprio to export the same interface as CFQ.  When dealing with
- * ``well-behaved'' queues (i.e., queues that do not spend too much
+ * "well-behaved" queues (i.e., queues that do not spend too much
  * time to consume their budget and have true sequential behavior, and
  * when there are no external factors breaking anticipation) the
  * relative weights at each level of the cgroups hierarchy should be
@@ -240,6 +233,13 @@ struct bfq_queue {
 	/* next ioprio and ioprio class if a change is in progress */
 	unsigned short new_ioprio, new_ioprio_class;
 
+	/* last total-service-time sample, see bfq_update_inject_limit() */
+	u64 last_serv_time_ns;
+	/* limit for request injection */
+	unsigned int inject_limit;
+	/* last time the inject limit has been decreased, in jiffies */
+	unsigned long decrease_time_jif;
+
 	/*
 	 * Shared bfq_queue if queue is cooperating with one or more
 	 * other queues.
@@ -357,29 +357,6 @@ struct bfq_queue {
 
 	/* max service rate measured so far */
 	u32 max_service_rate;
-	/*
-	 * Ratio between the service received by bfqq while it is in
-	 * service, and the cumulative service (of requests of other
-	 * queues) that may be injected while bfqq is empty but still
-	 * in service. To increase precision, the coefficient is
-	 * measured in tenths of unit. Here are some example of (1)
-	 * ratios, (2) resulting percentages of service injected
-	 * w.r.t. to the total service dispatched while bfqq is in
-	 * service, and (3) corresponding values of the coefficient:
-	 * 1 (50%) -> 10
-	 * 2 (33%) -> 20
-	 * 10 (9%) -> 100
-	 * 9.9 (9%) -> 99
-	 * 1.5 (40%) -> 15
-	 * 0.5 (66%) -> 5
-	 * 0.1 (90%) -> 1
-	 *
-	 * So, if the coefficient is lower than 10, then
-	 * injected service is more than bfqq service.
-	 */
-	unsigned int inject_coeff;
-	/* amount of service injected in current service slot */
-	unsigned int injected_service;
 };
 
 /**
@@ -419,6 +396,15 @@ struct bfq_io_cq {
 	bool was_in_burst_list;
 
 	/*
+	 * Save the weight when a merge occurs, to be able
+	 * to restore it in case of split. If the weight is not
+	 * correctly resumed when the queue is recycled,
+	 * then the weight of the recycled queue could differ
+	 * from the weight of the original queue.
+	 */
+	unsigned int saved_weight;
+
+	/*
 	 * Similar to previous fields: save wr information.
 	 */
 	unsigned long saved_wr_coeff;
@@ -450,7 +436,7 @@ struct bfq_data {
 	 * weight-raised @bfq_queue (see the comments to the functions
 	 * bfq_weights_tree_[add|remove] for further details).
 	 */
-	struct rb_root queue_weights_tree;
+	struct rb_root_cached queue_weights_tree;
 
 	/*
 	 * Number of groups with at least one descendant process that
@@ -513,6 +499,9 @@ struct bfq_data {
 	/* number of requests dispatched and waiting for completion */
 	int rq_in_driver;
 
+	/* true if the device is non rotational and performs queueing */
+	bool nonrot_with_queueing;
+
 	/*
 	 * Maximum number of requests in driver in the last
 	 * @hw_tag_samples completed requests.
@@ -544,6 +533,26 @@ struct bfq_data {
 	/* time of last request completion (ns) */
 	u64 last_completion;
 
+	/* time of last transition from empty to non-empty (ns) */
+	u64 last_empty_occupied_ns;
+
+	/*
+	 * Flag set to activate the sampling of the total service time
+	 * of a just-arrived first I/O request (see
+	 * bfq_update_inject_limit()). This will cause the setting of
+	 * waited_rq when the request is finally dispatched.
+	 */
+	bool wait_dispatch;
+	/*
+	 *  If set, then bfq_update_inject_limit() is invoked when
+	 *  waited_rq is eventually completed.
+	 */
+	struct request *waited_rq;
+	/*
+	 * True if some request has been injected during the last service hole.
+	 */
+	bool rqs_injected;
+
 	/* time of first rq dispatch in current observation interval (ns) */
 	u64 first_dispatch;
 	/* time of last rq dispatch in current observation interval (ns) */
@@ -553,6 +562,7 @@ struct bfq_data {
 	ktime_t last_budget_start;
 	/* beginning of the last idle slice */
 	ktime_t last_idling_start;
+	unsigned long last_idling_start_jiffies;
 
 	/* number of samples in current observation interval */
 	int peak_rate_samples;
@@ -898,10 +908,10 @@ void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync);
 struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic);
 void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq);
 void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq,
-			  struct rb_root *root);
+			  struct rb_root_cached *root);
 void __bfq_weights_tree_remove(struct bfq_data *bfqd,
 			       struct bfq_queue *bfqq,
-			       struct rb_root *root);
+			       struct rb_root_cached *root);
 void bfq_weights_tree_remove(struct bfq_data *bfqd,
 			     struct bfq_queue *bfqq);
 void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
@@ -1008,13 +1018,23 @@ void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq);
 /* --------------- end of interface of B-WF2Q+ ---------------- */
 
 /* Logging facilities. */
+static inline void bfq_pid_to_str(int pid, char *str, int len)
+{
+	if (pid != -1)
+		snprintf(str, len, "%d", pid);
+	else
+		snprintf(str, len, "SHARED-");
+}
+
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	do {			\
+	char pid_str[MAX_PID_STR_LENGTH];	\
+	bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH);	\
 	blk_add_cgroup_trace_msg((bfqd)->queue,				\
 			bfqg_to_blkg(bfqq_group(bfqq))->blkcg,		\
-			"bfq%d%c " fmt, (bfqq)->pid,			\
+			"bfq%s%c " fmt, pid_str,			\
 			bfq_bfqq_sync((bfqq)) ? 'S' : 'A', ##args);	\
 } while (0)
 
@@ -1025,10 +1045,13 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 
 #else /* CONFIG_BFQ_GROUP_IOSCHED */
 
-#define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	\
-	blk_add_trace_msg((bfqd)->queue, "bfq%d%c " fmt, (bfqq)->pid,	\
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do {	\
+	char pid_str[MAX_PID_STR_LENGTH];	\
+	bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH);	\
+	blk_add_trace_msg((bfqd)->queue, "bfq%s%c " fmt, pid_str,	\
 			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
-				##args)
+				##args);	\
+} while (0)
 #define bfq_log_bfqg(bfqd, bfqg, fmt, args...)		do {} while (0)
 
 #endif /* CONFIG_BFQ_GROUP_IOSCHED */
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index ae4d000ac0af..c9ba225081ce 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -1,19 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Hierarchical Budget Worst-case Fair Weighted Fair Queueing
  * (B-WF2Q+): hierarchical scheduling algorithm by which the BFQ I/O
  * scheduler schedules generic entities. The latter can represent
  * either single bfq queues (associated with processes) or groups of
  * bfq queues (associated with cgroups).
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License as
- *  published by the Free Software Foundation; either version 2 of the
- *  License, or (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- *  General Public License for more details.
  */
 #include "bfq-iosched.h"
 
@@ -59,7 +50,7 @@ static bool bfq_update_parent_budget(struct bfq_entity *next_in_service);
  * bfq_update_next_in_service - update sd->next_in_service
  * @sd: sched_data for which to perform the update.
  * @new_entity: if not NULL, pointer to the entity whose activation,
- *		requeueing or repositionig triggered the invocation of
+ *		requeueing or repositioning triggered the invocation of
  *		this function.
  * @expiration: id true, this function is being invoked after the
  *             expiration of the in-service entity
@@ -90,7 +81,7 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 
 	/*
 	 * If this update is triggered by the activation, requeueing
-	 * or repositiong of an entity that does not coincide with
+	 * or repositioning of an entity that does not coincide with
 	 * sd->next_in_service, then a full lookup in the active tree
 	 * can be avoided. In fact, it is enough to check whether the
 	 * just-modified entity has the same priority as
@@ -737,7 +728,7 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
 		struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
 		unsigned int prev_weight, new_weight;
 		struct bfq_data *bfqd = NULL;
-		struct rb_root *root;
+		struct rb_root_cached *root;
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 		struct bfq_sched_data *sd;
 		struct bfq_group *bfqg;
@@ -1396,7 +1387,7 @@ left:
  * In this first case, update the virtual time in @st too (see the
  * comments on this update inside the function).
  *
- * In constrast, if there is an in-service entity, then return the
+ * In contrast, if there is an in-service entity, then return the
  * entity that would be set in service if not only the above
  * conditions, but also the next one held true: the currently
  * in-service entity, on expiration,
@@ -1479,12 +1470,12 @@ static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
 		 * is being invoked as a part of the expiration path
 		 * of the in-service queue. In this case, even if
 		 * sd->in_service_entity is not NULL,
-		 * sd->in_service_entiy at this point is actually not
+		 * sd->in_service_entity at this point is actually not
 		 * in service any more, and, if needed, has already
 		 * been properly queued or requeued into the right
 		 * tree. The reason why sd->in_service_entity is still
 		 * not NULL here, even if expiration is true, is that
-		 * sd->in_service_entiy is reset as a last step in the
+		 * sd->in_service_entity is reset as a last step in the
 		 * expiration path. So, if expiration is true, tell
 		 * __bfq_lookup_next_entity that there is no
 		 * sd->in_service_entity.
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 1b633a3526d4..42536674020a 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -1,23 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * bio-integrity.c - bio data integrity extensions
  *
  * Copyright (C) 2007, 2008, 2009 Oracle Corporation
  * Written by: Martin K. Petersen <martin.petersen@oracle.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; see the file COPYING.  If not, write to
- * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139,
- * USA.
- *
  */
 
 #include <linux/blkdev.h>
diff --git a/block/bio.c b/block/bio.c
index 716510ecd7ff..683cbb40f051 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1,19 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2001 Jens Axboe <axboe@kernel.dk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public Licens
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
- *
  */
 #include <linux/mm.h>
 #include <linux/swap.h>
@@ -647,25 +634,72 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
 }
 EXPORT_SYMBOL(bio_clone_fast);
 
+static inline bool page_is_mergeable(const struct bio_vec *bv,
+		struct page *page, unsigned int len, unsigned int off,
+		bool same_page)
+{
+	phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) +
+		bv->bv_offset + bv->bv_len - 1;
+	phys_addr_t page_addr = page_to_phys(page);
+
+	if (vec_end_addr + 1 != page_addr + off)
+		return false;
+	if (xen_domain() && !xen_biovec_phys_mergeable(bv, page))
+		return false;
+
+	if ((vec_end_addr & PAGE_MASK) != page_addr) {
+		if (same_page)
+			return false;
+		if (pfn_to_page(PFN_DOWN(vec_end_addr)) + 1 != page)
+			return false;
+	}
+
+	WARN_ON_ONCE(same_page && (len + off) > PAGE_SIZE);
+
+	return true;
+}
+
+/*
+ * Check if the @page can be added to the current segment(@bv), and make
+ * sure to call it only if page_is_mergeable(@bv, @page) is true
+ */
+static bool can_add_page_to_seg(struct request_queue *q,
+		struct bio_vec *bv, struct page *page, unsigned len,
+		unsigned offset)
+{
+	unsigned long mask = queue_segment_boundary(q);
+	phys_addr_t addr1 = page_to_phys(bv->bv_page) + bv->bv_offset;
+	phys_addr_t addr2 = page_to_phys(page) + offset + len - 1;
+
+	if ((addr1 | mask) != (addr2 | mask))
+		return false;
+
+	if (bv->bv_len + len > queue_max_segment_size(q))
+		return false;
+
+	return true;
+}
+
 /**
- *	bio_add_pc_page	-	attempt to add page to bio
+ *	__bio_add_pc_page	- attempt to add page to passthrough bio
  *	@q: the target queue
  *	@bio: destination bio
  *	@page: page to add
  *	@len: vec entry length
  *	@offset: vec entry offset
+ *	@put_same_page: put the page if it is same with last added page
  *
  *	Attempt to add a page to the bio_vec maplist. This can fail for a
  *	number of reasons, such as the bio being full or target block device
  *	limitations. The target block device must allow bio's up to PAGE_SIZE,
  *	so it is always possible to add a single page to an empty bio.
  *
- *	This should only be used by REQ_PC bios.
+ *	This should only be used by passthrough bios.
  */
-int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
-		    *page, unsigned int len, unsigned int offset)
+static int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
+		struct page *page, unsigned int len, unsigned int offset,
+		bool put_same_page)
 {
-	int retried_segments = 0;
 	struct bio_vec *bvec;
 
 	/*
@@ -677,18 +711,14 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
 	if (((bio->bi_iter.bi_size + len) >> 9) > queue_max_hw_sectors(q))
 		return 0;
 
-	/*
-	 * For filesystems with a blocksize smaller than the pagesize
-	 * we will often be called with the same page as last time and
-	 * a consecutive offset.  Optimize this special case.
-	 */
 	if (bio->bi_vcnt > 0) {
-		struct bio_vec *prev = &bio->bi_io_vec[bio->bi_vcnt - 1];
+		bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
 
-		if (page == prev->bv_page &&
-		    offset == prev->bv_offset + prev->bv_len) {
-			prev->bv_len += len;
-			bio->bi_iter.bi_size += len;
+		if (page == bvec->bv_page &&
+		    offset == bvec->bv_offset + bvec->bv_len) {
+			if (put_same_page)
+				put_page(page);
+			bvec->bv_len += len;
 			goto done;
 		}
 
@@ -696,63 +726,47 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
 		 * If the queue doesn't support SG gaps and adding this
 		 * offset would create a gap, disallow it.
 		 */
-		if (bvec_gap_to_prev(q, prev, offset))
+		if (bvec_gap_to_prev(q, bvec, offset))
 			return 0;
+
+		if (page_is_mergeable(bvec, page, len, offset, false) &&
+		    can_add_page_to_seg(q, bvec, page, len, offset)) {
+			bvec->bv_len += len;
+			goto done;
+		}
 	}
 
 	if (bio_full(bio))
 		return 0;
 
-	/*
-	 * setup the new entry, we might clear it again later if we
-	 * cannot add the page
-	 */
+	if (bio->bi_phys_segments >= queue_max_segments(q))
+		return 0;
+
 	bvec = &bio->bi_io_vec[bio->bi_vcnt];
 	bvec->bv_page = page;
 	bvec->bv_len = len;
 	bvec->bv_offset = offset;
 	bio->bi_vcnt++;
-	bio->bi_phys_segments++;
-	bio->bi_iter.bi_size += len;
-
-	/*
-	 * Perform a recount if the number of segments is greater
-	 * than queue_max_segments(q).
-	 */
-
-	while (bio->bi_phys_segments > queue_max_segments(q)) {
-
-		if (retried_segments)
-			goto failed;
-
-		retried_segments = 1;
-		blk_recount_segments(q, bio);
-	}
-
-	/* If we may be able to merge these biovecs, force a recount */
-	if (bio->bi_vcnt > 1 && biovec_phys_mergeable(q, bvec - 1, bvec))
-		bio_clear_flag(bio, BIO_SEG_VALID);
-
  done:
+	bio->bi_iter.bi_size += len;
+	bio->bi_phys_segments = bio->bi_vcnt;
+	bio_set_flag(bio, BIO_SEG_VALID);
 	return len;
+}
 
- failed:
-	bvec->bv_page = NULL;
-	bvec->bv_len = 0;
-	bvec->bv_offset = 0;
-	bio->bi_vcnt--;
-	bio->bi_iter.bi_size -= len;
-	blk_recount_segments(q, bio);
-	return 0;
+int bio_add_pc_page(struct request_queue *q, struct bio *bio,
+		struct page *page, unsigned int len, unsigned int offset)
+{
+	return __bio_add_pc_page(q, bio, page, len, offset, false);
 }
 EXPORT_SYMBOL(bio_add_pc_page);
 
 /**
  * __bio_try_merge_page - try appending data to an existing bvec.
  * @bio: destination bio
- * @page: page to add
+ * @page: start page to add
  * @len: length of the data to add
- * @off: offset of the data in @page
+ * @off: offset of the data relative to @page
  * @same_page: if %true only merge if the new data is in the same physical
  *		page as the last segment of the bio.
  *
@@ -760,6 +774,8 @@ EXPORT_SYMBOL(bio_add_pc_page);
  * a useful optimisation for file systems with a block size smaller than the
  * page size.
  *
+ * Warn if (@len, @off) crosses pages in case that @same_page is true.
+ *
  * Return %true on success or %false on failure.
  */
 bool __bio_try_merge_page(struct bio *bio, struct page *page,
@@ -770,29 +786,23 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page,
 
 	if (bio->bi_vcnt > 0) {
 		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
-		phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) +
-			bv->bv_offset + bv->bv_len - 1;
-		phys_addr_t page_addr = page_to_phys(page);
 
-		if (vec_end_addr + 1 != page_addr + off)
-			return false;
-		if (same_page && (vec_end_addr & PAGE_MASK) != page_addr)
-			return false;
-
-		bv->bv_len += len;
-		bio->bi_iter.bi_size += len;
-		return true;
+		if (page_is_mergeable(bv, page, len, off, same_page)) {
+			bv->bv_len += len;
+			bio->bi_iter.bi_size += len;
+			return true;
+		}
 	}
 	return false;
 }
 EXPORT_SYMBOL_GPL(__bio_try_merge_page);
 
 /**
- * __bio_add_page - add page to a bio in a new segment
+ * __bio_add_page - add page(s) to a bio in a new segment
  * @bio: destination bio
- * @page: page to add
- * @len: length of the data to add
- * @off: offset of the data in @page
+ * @page: start page to add
+ * @len: length of the data to add, may cross pages
+ * @off: offset of the data relative to @page, may cross pages
  *
  * Add the data at @page + @off to @bio as a new bvec.  The caller must ensure
  * that @bio has space for another bvec.
@@ -815,13 +825,13 @@ void __bio_add_page(struct bio *bio, struct page *page,
 EXPORT_SYMBOL_GPL(__bio_add_page);
 
 /**
- *	bio_add_page	-	attempt to add page to bio
+ *	bio_add_page	-	attempt to add page(s) to bio
  *	@bio: destination bio
- *	@page: page to add
- *	@len: vec entry length
- *	@offset: vec entry offset
+ *	@page: start page to add
+ *	@len: vec entry length, may cross pages
+ *	@offset: vec entry offset relative to @page, may cross pages
  *
- *	Attempt to add a page to the bio_vec maplist. This will only fail
+ *	Attempt to add page(s) to the bio_vec maplist. This will only fail
  *	if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio.
  */
 int bio_add_page(struct bio *bio, struct page *page,
@@ -836,6 +846,24 @@ int bio_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_add_page);
 
+static void bio_get_pages(struct bio *bio)
+{
+	struct bvec_iter_all iter_all;
+	struct bio_vec *bvec;
+
+	bio_for_each_segment_all(bvec, bio, iter_all)
+		get_page(bvec->bv_page);
+}
+
+static void bio_release_pages(struct bio *bio)
+{
+	struct bvec_iter_all iter_all;
+	struct bio_vec *bvec;
+
+	bio_for_each_segment_all(bvec, bio, iter_all)
+		put_page(bvec->bv_page);
+}
+
 static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter)
 {
 	const struct bio_vec *bv = iter->bvec;
@@ -848,20 +876,10 @@ static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter)
 	len = min_t(size_t, bv->bv_len - iter->iov_offset, iter->count);
 	size = bio_add_page(bio, bv->bv_page, len,
 				bv->bv_offset + iter->iov_offset);
-	if (size == len) {
-		if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
-			struct page *page;
-			int i;
-
-			mp_bvec_for_each_page(page, bv, i)
-				get_page(page);
-		}
-
-		iov_iter_advance(iter, size);
-		return 0;
-	}
-
-	return -EINVAL;
+	if (unlikely(size != len))
+		return -EINVAL;
+	iov_iter_advance(iter, size);
+	return 0;
 }
 
 #define PAGE_PTRS_PER_BVEC     (sizeof(struct bio_vec) / sizeof(struct page *))
@@ -934,29 +952,24 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 {
 	const bool is_bvec = iov_iter_is_bvec(iter);
-	unsigned short orig_vcnt = bio->bi_vcnt;
+	int ret;
 
-	/*
-	 * If this is a BVEC iter, then the pages are kernel pages. Don't
-	 * release them on IO completion, if the caller asked us to.
-	 */
-	if (is_bvec && iov_iter_bvec_no_ref(iter))
-		bio_set_flag(bio, BIO_NO_PAGE_REF);
+	if (WARN_ON_ONCE(bio->bi_vcnt))
+		return -EINVAL;
 
 	do {
-		int ret;
-
 		if (is_bvec)
 			ret = __bio_iov_bvec_add_pages(bio, iter);
 		else
 			ret = __bio_iov_iter_get_pages(bio, iter);
+	} while (!ret && iov_iter_count(iter) && !bio_full(bio));
 
-		if (unlikely(ret))
-			return bio->bi_vcnt > orig_vcnt ? 0 : ret;
-
-	} while (iov_iter_count(iter) && !bio_full(bio));
+	if (iov_iter_bvec_no_ref(iter))
+		bio_set_flag(bio, BIO_NO_PAGE_REF);
+	else if (is_bvec)
+		bio_get_pages(bio);
 
-	return 0;
+	return bio->bi_vcnt ? 0 : ret;
 }
 
 static void submit_bio_wait_endio(struct bio *bio)
@@ -1127,11 +1140,10 @@ static struct bio_map_data *bio_alloc_map_data(struct iov_iter *data,
  */
 static int bio_copy_from_iter(struct bio *bio, struct iov_iter *iter)
 {
-	int i;
 	struct bio_vec *bvec;
 	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bvec, bio, i, iter_all) {
+	bio_for_each_segment_all(bvec, bio, iter_all) {
 		ssize_t ret;
 
 		ret = copy_page_from_iter(bvec->bv_page,
@@ -1159,11 +1171,10 @@ static int bio_copy_from_iter(struct bio *bio, struct iov_iter *iter)
  */
 static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter)
 {
-	int i;
 	struct bio_vec *bvec;
 	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bvec, bio, i, iter_all) {
+	bio_for_each_segment_all(bvec, bio, iter_all) {
 		ssize_t ret;
 
 		ret = copy_page_to_iter(bvec->bv_page,
@@ -1184,10 +1195,9 @@ static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter)
 void bio_free_pages(struct bio *bio)
 {
 	struct bio_vec *bvec;
-	int i;
 	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bvec, bio, i, iter_all)
+	bio_for_each_segment_all(bvec, bio, iter_all)
 		__free_page(bvec->bv_page);
 }
 EXPORT_SYMBOL(bio_free_pages);
@@ -1388,21 +1398,14 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 			for (j = 0; j < npages; j++) {
 				struct page *page = pages[j];
 				unsigned int n = PAGE_SIZE - offs;
-				unsigned short prev_bi_vcnt = bio->bi_vcnt;
 
 				if (n > bytes)
 					n = bytes;
 
-				if (!bio_add_pc_page(q, bio, page, n, offs))
+				if (!__bio_add_pc_page(q, bio, page, n, offs,
+							true))
 					break;
 
-				/*
-				 * check if vector was merged with previous
-				 * drop page reference if needed
-				 */
-				if (bio->bi_vcnt == prev_bi_vcnt)
-					put_page(page);
-
 				added += n;
 				bytes -= n;
 				offs = 0;
@@ -1432,7 +1435,7 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 	return bio;
 
  out_unmap:
-	bio_for_each_segment_all(bvec, bio, j, iter_all) {
+	bio_for_each_segment_all(bvec, bio, iter_all) {
 		put_page(bvec->bv_page);
 	}
 	bio_put(bio);
@@ -1442,13 +1445,12 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 static void __bio_unmap_user(struct bio *bio)
 {
 	struct bio_vec *bvec;
-	int i;
 	struct bvec_iter_all iter_all;
 
 	/*
 	 * make sure we dirty pages we wrote to
 	 */
-	bio_for_each_segment_all(bvec, bio, i, iter_all) {
+	bio_for_each_segment_all(bvec, bio, iter_all) {
 		if (bio_data_dir(bio) == READ)
 			set_page_dirty_lock(bvec->bv_page);
 
@@ -1539,10 +1541,9 @@ static void bio_copy_kern_endio_read(struct bio *bio)
 {
 	char *p = bio->bi_private;
 	struct bio_vec *bvec;
-	int i;
 	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bvec, bio, i, iter_all) {
+	bio_for_each_segment_all(bvec, bio, iter_all) {
 		memcpy(p, page_address(bvec->bv_page), bvec->bv_len);
 		p += bvec->bv_len;
 	}
@@ -1650,25 +1651,14 @@ cleanup:
 void bio_set_pages_dirty(struct bio *bio)
 {
 	struct bio_vec *bvec;
-	int i;
 	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bvec, bio, i, iter_all) {
+	bio_for_each_segment_all(bvec, bio, iter_all) {
 		if (!PageCompound(bvec->bv_page))
 			set_page_dirty_lock(bvec->bv_page);
 	}
 }
 
-static void bio_release_pages(struct bio *bio)
-{
-	struct bio_vec *bvec;
-	int i;
-	struct bvec_iter_all iter_all;
-
-	bio_for_each_segment_all(bvec, bio, i, iter_all)
-		put_page(bvec->bv_page);
-}
-
 /*
  * bio_check_pages_dirty() will check that all the BIO's pages are still dirty.
  * If they are, then fine.  If, however, some pages are clean then they must
@@ -1712,10 +1702,9 @@ void bio_check_pages_dirty(struct bio *bio)
 {
 	struct bio_vec *bvec;
 	unsigned long flags;
-	int i;
 	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bvec, bio, i, iter_all) {
+	bio_for_each_segment_all(bvec, bio, iter_all) {
 		if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page))
 			goto defer;
 	}
@@ -2203,6 +2192,9 @@ static int __init init_bio(void)
 	bio_slab_nr = 0;
 	bio_slabs = kcalloc(bio_slab_max, sizeof(struct bio_slab),
 			    GFP_KERNEL);
+
+	BUILD_BUG_ON(BIO_FLAG_LAST > BVEC_POOL_OFFSET);
+
 	if (!bio_slabs)
 		panic("bio: can't allocate bios\n");
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 617a2b3f7582..b97b479e4f64 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Common Block IO controller cgroup interface
  *
diff --git a/block/blk-core.c b/block/blk-core.c
index a55389ba8779..419d600e6637 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 1991, 1992 Linus Torvalds
  * Copyright (C) 1994,      Karl Keyte: Added support for disk statistics
@@ -232,15 +233,6 @@ void blk_sync_queue(struct request_queue *q)
 {
 	del_timer_sync(&q->timeout);
 	cancel_work_sync(&q->timeout_work);
-
-	if (queue_is_mq(q)) {
-		struct blk_mq_hw_ctx *hctx;
-		int i;
-
-		cancel_delayed_work_sync(&q->requeue_work);
-		queue_for_each_hw_ctx(q, hctx, i)
-			cancel_delayed_work_sync(&hctx->run_work);
-	}
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
@@ -347,18 +339,6 @@ void blk_cleanup_queue(struct request_queue *q)
 
 	blk_queue_flag_set(QUEUE_FLAG_DEAD, q);
 
-	/*
-	 * make sure all in-progress dispatch are completed because
-	 * blk_freeze_queue() can only complete all requests, and
-	 * dispatch may still be in-progress since we dispatch requests
-	 * from more than one contexts.
-	 *
-	 * We rely on driver to deal with the race in case that queue
-	 * initialization isn't done.
-	 */
-	if (queue_is_mq(q) && blk_queue_init_done(q))
-		blk_mq_quiesce_queue(q);
-
 	/* for synchronous bio-based driver finish in-flight integrity i/o */
 	blk_flush_integrity();
 
@@ -375,7 +355,7 @@ void blk_cleanup_queue(struct request_queue *q)
 	blk_exit_queue(q);
 
 	if (queue_is_mq(q))
-		blk_mq_free_queue(q);
+		blk_mq_exit_queue(q);
 
 	percpu_ref_exit(&q->q_usage_counter);
 
diff --git a/block/blk-exec.c b/block/blk-exec.c
index a34b7d918742..1db44ca0f4a6 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Functions related to setting various queue properties from drivers
  */
diff --git a/block/blk-flush.c b/block/blk-flush.c
index d95f94892015..aedd9320e605 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -1,11 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Functions to sequence PREFLUSH and FUA writes.
  *
  * Copyright (C) 2011		Max Planck Institute for Gravitational Physics
  * Copyright (C) 2011		Tejun Heo <tj@kernel.org>
  *
- * This file is released under the GPLv2.
- *
  * REQ_{PREFLUSH|FUA} requests are decomposed to sequences consisted of three
  * optional steps - PREFLUSH, DATA and POSTFLUSH - according to the request
  * properties and hardware capability.
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 85864c71e858..825c9c070458 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -1,23 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * blk-integrity.c - Block layer data integrity extensions
  *
  * Copyright (C) 2007, 2008 Oracle Corporation
  * Written by: Martin K. Petersen <martin.petersen@oracle.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; see the file COPYING.  If not, write to
- * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139,
- * USA.
- *
  */
 
 #include <linux/blkdev.h>
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index 507212d75ee2..d22e61bced86 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Block rq-qos base io controller
  *
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 1c9d4f0f96ea..21e87a714a73 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -267,23 +267,6 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 			goto split;
 		}
 
-		if (bvprvp) {
-			if (seg_size + bv.bv_len > queue_max_segment_size(q))
-				goto new_segment;
-			if (!biovec_phys_mergeable(q, bvprvp, &bv))
-				goto new_segment;
-
-			seg_size += bv.bv_len;
-			bvprv = bv;
-			bvprvp = &bvprv;
-			sectors += bv.bv_len >> 9;
-
-			if (nsegs == 1 && seg_size > front_seg_size)
-				front_seg_size = seg_size;
-
-			continue;
-		}
-new_segment:
 		if (nsegs == max_segs)
 			goto split;
 
@@ -370,12 +353,12 @@ EXPORT_SYMBOL(blk_queue_split);
 static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 					     struct bio *bio)
 {
-	struct bio_vec bv, bvprv = { NULL };
-	int prev = 0;
+	struct bio_vec uninitialized_var(bv), bvprv = { NULL };
 	unsigned int seg_size, nr_phys_segs;
 	unsigned front_seg_size;
 	struct bio *fbio, *bbio;
 	struct bvec_iter iter;
+	bool new_bio = false;
 
 	if (!bio)
 		return 0;
@@ -396,7 +379,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	nr_phys_segs = 0;
 	for_each_bio(bio) {
 		bio_for_each_bvec(bv, bio, iter) {
-			if (prev) {
+			if (new_bio) {
 				if (seg_size + bv.bv_len
 				    > queue_max_segment_size(q))
 					goto new_segment;
@@ -404,7 +387,6 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 					goto new_segment;
 
 				seg_size += bv.bv_len;
-				bvprv = bv;
 
 				if (nr_phys_segs == 1 && seg_size >
 						front_seg_size)
@@ -413,12 +395,15 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 				continue;
 			}
 new_segment:
-			bvprv = bv;
-			prev = 1;
 			bvec_split_segs(q, &bv, &nr_phys_segs, &seg_size,
 					&front_seg_size, NULL, UINT_MAX);
+			new_bio = false;
 		}
 		bbio = bio;
+		if (likely(bio->bi_iter.bi_size)) {
+			bvprv = bv;
+			new_bio = true;
+		}
 	}
 
 	fbio->bi_seg_front_size = front_seg_size;
@@ -484,79 +469,97 @@ static unsigned blk_bvec_map_sg(struct request_queue *q,
 		struct scatterlist **sg)
 {
 	unsigned nbytes = bvec->bv_len;
-	unsigned nsegs = 0, total = 0, offset = 0;
+	unsigned nsegs = 0, total = 0;
 
 	while (nbytes > 0) {
-		unsigned seg_size;
-		struct page *pg;
-		unsigned idx;
-
-		*sg = blk_next_sg(sg, sglist);
+		unsigned offset = bvec->bv_offset + total;
+		unsigned len = min(get_max_segment_size(q, offset), nbytes);
+		struct page *page = bvec->bv_page;
 
-		seg_size = get_max_segment_size(q, bvec->bv_offset + total);
-		seg_size = min(nbytes, seg_size);
-
-		offset = (total + bvec->bv_offset) % PAGE_SIZE;
-		idx = (total + bvec->bv_offset) / PAGE_SIZE;
-		pg = bvec_nth_page(bvec->bv_page, idx);
+		/*
+		 * Unfortunately a fair number of drivers barf on scatterlists
+		 * that have an offset larger than PAGE_SIZE, despite other
+		 * subsystems dealing with that invariant just fine.  For now
+		 * stick to the legacy format where we never present those from
+		 * the block layer, but the code below should be removed once
+		 * these offenders (mostly MMC/SD drivers) are fixed.
+		 */
+		page += (offset >> PAGE_SHIFT);
+		offset &= ~PAGE_MASK;
 
-		sg_set_page(*sg, pg, seg_size, offset);
+		*sg = blk_next_sg(sg, sglist);
+		sg_set_page(*sg, page, len, offset);
 
-		total += seg_size;
-		nbytes -= seg_size;
+		total += len;
+		nbytes -= len;
 		nsegs++;
 	}
 
 	return nsegs;
 }
 
-static inline void
-__blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
-		     struct scatterlist *sglist, struct bio_vec *bvprv,
-		     struct scatterlist **sg, int *nsegs)
+static inline int __blk_bvec_map_sg(struct bio_vec bv,
+		struct scatterlist *sglist, struct scatterlist **sg)
+{
+	*sg = blk_next_sg(sg, sglist);
+	sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset);
+	return 1;
+}
+
+/* only try to merge bvecs into one sg if they are from two bios */
+static inline bool
+__blk_segment_map_sg_merge(struct request_queue *q, struct bio_vec *bvec,
+			   struct bio_vec *bvprv, struct scatterlist **sg)
 {
 
 	int nbytes = bvec->bv_len;
 
-	if (*sg) {
-		if ((*sg)->length + nbytes > queue_max_segment_size(q))
-			goto new_segment;
-		if (!biovec_phys_mergeable(q, bvprv, bvec))
-			goto new_segment;
+	if (!*sg)
+		return false;
 
-		(*sg)->length += nbytes;
-	} else {
-new_segment:
-		if (bvec->bv_offset + bvec->bv_len <= PAGE_SIZE) {
-			*sg = blk_next_sg(sg, sglist);
-			sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset);
-			(*nsegs) += 1;
-		} else
-			(*nsegs) += blk_bvec_map_sg(q, bvec, sglist, sg);
-	}
-	*bvprv = *bvec;
-}
+	if ((*sg)->length + nbytes > queue_max_segment_size(q))
+		return false;
 
-static inline int __blk_bvec_map_sg(struct request_queue *q, struct bio_vec bv,
-		struct scatterlist *sglist, struct scatterlist **sg)
-{
-	*sg = sglist;
-	sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset);
-	return 1;
+	if (!biovec_phys_mergeable(q, bvprv, bvec))
+		return false;
+
+	(*sg)->length += nbytes;
+
+	return true;
 }
 
 static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 			     struct scatterlist *sglist,
 			     struct scatterlist **sg)
 {
-	struct bio_vec bvec, bvprv = { NULL };
+	struct bio_vec uninitialized_var(bvec), bvprv = { NULL };
 	struct bvec_iter iter;
 	int nsegs = 0;
+	bool new_bio = false;
 
-	for_each_bio(bio)
-		bio_for_each_bvec(bvec, bio, iter)
-			__blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg,
-					     &nsegs);
+	for_each_bio(bio) {
+		bio_for_each_bvec(bvec, bio, iter) {
+			/*
+			 * Only try to merge bvecs from two bios given we
+			 * have done bio internal merge when adding pages
+			 * to bio
+			 */
+			if (new_bio &&
+			    __blk_segment_map_sg_merge(q, &bvec, &bvprv, sg))
+				goto next_bvec;
+
+			if (bvec.bv_offset + bvec.bv_len <= PAGE_SIZE)
+				nsegs += __blk_bvec_map_sg(bvec, sglist, sg);
+			else
+				nsegs += blk_bvec_map_sg(q, &bvec, sglist, sg);
+ next_bvec:
+			new_bio = false;
+		}
+		if (likely(bio->bi_iter.bi_size)) {
+			bvprv = bvec;
+			new_bio = true;
+		}
+	}
 
 	return nsegs;
 }
@@ -572,9 +575,9 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	int nsegs = 0;
 
 	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
-		nsegs = __blk_bvec_map_sg(q, rq->special_vec, sglist, &sg);
+		nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, &sg);
 	else if (rq->bio && bio_op(rq->bio) == REQ_OP_WRITE_SAME)
-		nsegs = __blk_bvec_map_sg(q, bio_iovec(rq->bio), sglist, &sg);
+		nsegs = __blk_bvec_map_sg(bio_iovec(rq->bio), sglist, &sg);
 	else if (rq->bio)
 		nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg);
 
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 03a534820271..48bebf00a5f3 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * CPU <-> hardware queue mapping helpers
  *
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index ec1d18cb643c..6aea0ebc3a73 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2017 Facebook
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public
- * License v2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
 #include <linux/kernel.h>
diff --git a/block/blk-mq-pci.c b/block/blk-mq-pci.c
index 1dce18553984..ad4545a2a98b 100644
--- a/block/blk-mq-pci.c
+++ b/block/blk-mq-pci.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2016 Christoph Hellwig.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 #include <linux/kobject.h>
 #include <linux/blkdev.h>
diff --git a/block/blk-mq-rdma.c b/block/blk-mq-rdma.c
index 45030a81a1ed..cc921e6ba709 100644
--- a/block/blk-mq-rdma.c
+++ b/block/blk-mq-rdma.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2017 Sagi Grimberg.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 #include <linux/blk-mq.h>
 #include <linux/blk-mq-rdma.h>
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index aa6bc5c02643..74c6bb871f7e 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * blk-mq scheduling framework
  *
@@ -413,6 +414,14 @@ void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx,
 				  struct list_head *list, bool run_queue_async)
 {
 	struct elevator_queue *e;
+	struct request_queue *q = hctx->queue;
+
+	/*
+	 * blk_mq_sched_insert_requests() is called from flush plug
+	 * context only, and hold one usage counter to prevent queue
+	 * from being released.
+	 */
+	percpu_ref_get(&q->q_usage_counter);
 
 	e = hctx->queue->elevator;
 	if (e && e->type->ops.insert_requests)
@@ -426,12 +435,14 @@ void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx,
 		if (!hctx->dispatch_busy && !e && !run_queue_async) {
 			blk_mq_try_issue_list_directly(hctx, list);
 			if (list_empty(list))
-				return;
+				goto out;
 		}
 		blk_mq_insert_requests(hctx, ctx, list);
 	}
 
 	blk_mq_run_hw_queue(hctx, run_queue_async);
+ out:
+	percpu_ref_put(&q->q_usage_counter);
 }
 
 static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set,
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 5315e538b3b1..d6e1a9bd7131 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/backing-dev.h>
@@ -10,6 +11,7 @@
 #include <linux/smp.h>
 
 #include <linux/blk-mq.h>
+#include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
 
@@ -33,6 +35,13 @@ static void blk_mq_hw_sysfs_release(struct kobject *kobj)
 {
 	struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx,
 						  kobj);
+
+	cancel_delayed_work_sync(&hctx->run_work);
+
+	if (hctx->flags & BLK_MQ_F_BLOCKING)
+		cleanup_srcu_struct(hctx->srcu);
+	blk_free_flush_queue(hctx->fq);
+	sbitmap_free(&hctx->ctx_map);
 	free_cpumask_var(hctx->cpumask);
 	kfree(hctx->ctxs);
 	kfree(hctx);
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index a4931fc7be8a..7513c8eaabee 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Tag allocation using scalable bitmaps. Uses active queue tracking to support
  * fairer distribution of tags between multiple submitters when a shared tag map
diff --git a/block/blk-mq-virtio.c b/block/blk-mq-virtio.c
index 370827163835..75a52c18a8f6 100644
--- a/block/blk-mq-virtio.c
+++ b/block/blk-mq-virtio.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2016 Christoph Hellwig.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 #include <linux/device.h>
 #include <linux/blk-mq.h>
diff --git a/block/blk-mq.c b/block/blk-mq.c
index fc60ed7e940e..08a6248d8536 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Block multiqueue core code
  *
@@ -2062,7 +2063,7 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 		list_del_init(&page->lru);
 		/*
 		 * Remove kmemleak object previously allocated in
-		 * blk_mq_init_rq_map().
+		 * blk_mq_alloc_rqs().
 		 */
 		kmemleak_free(page_address(page));
 		__free_pages(page, page->private);
@@ -2267,12 +2268,11 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
 
-	if (hctx->flags & BLK_MQ_F_BLOCKING)
-		cleanup_srcu_struct(hctx->srcu);
-
 	blk_mq_remove_cpuhp(hctx);
-	blk_free_flush_queue(hctx->fq);
-	sbitmap_free(&hctx->ctx_map);
+
+	spin_lock(&q->unused_hctx_lock);
+	list_add(&hctx->hctx_list, &q->unused_hctx_list);
+	spin_unlock(&q->unused_hctx_lock);
 }
 
 static void blk_mq_exit_hw_queues(struct request_queue *q,
@@ -2289,15 +2289,65 @@ static void blk_mq_exit_hw_queues(struct request_queue *q,
 	}
 }
 
+static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
+{
+	int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
+
+	BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu),
+			   __alignof__(struct blk_mq_hw_ctx)) !=
+		     sizeof(struct blk_mq_hw_ctx));
+
+	if (tag_set->flags & BLK_MQ_F_BLOCKING)
+		hw_ctx_size += sizeof(struct srcu_struct);
+
+	return hw_ctx_size;
+}
+
 static int blk_mq_init_hctx(struct request_queue *q,
 		struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
 {
-	int node;
+	hctx->queue_num = hctx_idx;
+
+	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
+
+	hctx->tags = set->tags[hctx_idx];
+
+	if (set->ops->init_hctx &&
+	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
+		goto unregister_cpu_notifier;
+
+	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx,
+				hctx->numa_node))
+		goto exit_hctx;
+	return 0;
+
+ exit_hctx:
+	if (set->ops->exit_hctx)
+		set->ops->exit_hctx(hctx, hctx_idx);
+ unregister_cpu_notifier:
+	blk_mq_remove_cpuhp(hctx);
+	return -1;
+}
+
+static struct blk_mq_hw_ctx *
+blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
+		int node)
+{
+	struct blk_mq_hw_ctx *hctx;
+	gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY;
+
+	hctx = kzalloc_node(blk_mq_hw_ctx_size(set), gfp, node);
+	if (!hctx)
+		goto fail_alloc_hctx;
 
-	node = hctx->numa_node;
+	if (!zalloc_cpumask_var_node(&hctx->cpumask, gfp, node))
+		goto free_hctx;
+
+	atomic_set(&hctx->nr_active, 0);
 	if (node == NUMA_NO_NODE)
-		node = hctx->numa_node = set->numa_node;
+		node = set->numa_node;
+	hctx->numa_node = node;
 
 	INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
 	spin_lock_init(&hctx->lock);
@@ -2305,58 +2355,47 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	hctx->queue = q;
 	hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
 
-	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
-
-	hctx->tags = set->tags[hctx_idx];
+	INIT_LIST_HEAD(&hctx->hctx_list);
 
 	/*
 	 * Allocate space for all possible cpus to avoid allocation at
 	 * runtime
 	 */
 	hctx->ctxs = kmalloc_array_node(nr_cpu_ids, sizeof(void *),
-			GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node);
+			gfp, node);
 	if (!hctx->ctxs)
-		goto unregister_cpu_notifier;
+		goto free_cpumask;
 
 	if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8),
-				GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node))
+				gfp, node))
 		goto free_ctxs;
-
 	hctx->nr_ctx = 0;
 
 	spin_lock_init(&hctx->dispatch_wait_lock);
 	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
 	INIT_LIST_HEAD(&hctx->dispatch_wait.entry);
 
-	if (set->ops->init_hctx &&
-	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
-		goto free_bitmap;
-
 	hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size,
-			GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY);
+			gfp);
 	if (!hctx->fq)
-		goto exit_hctx;
-
-	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, node))
-		goto free_fq;
+		goto free_bitmap;
 
 	if (hctx->flags & BLK_MQ_F_BLOCKING)
 		init_srcu_struct(hctx->srcu);
+	blk_mq_hctx_kobj_init(hctx);
 
-	return 0;
+	return hctx;
 
- free_fq:
-	blk_free_flush_queue(hctx->fq);
- exit_hctx:
-	if (set->ops->exit_hctx)
-		set->ops->exit_hctx(hctx, hctx_idx);
  free_bitmap:
 	sbitmap_free(&hctx->ctx_map);
  free_ctxs:
 	kfree(hctx->ctxs);
- unregister_cpu_notifier:
-	blk_mq_remove_cpuhp(hctx);
-	return -1;
+ free_cpumask:
+	free_cpumask_var(hctx->cpumask);
+ free_hctx:
+	kfree(hctx);
+ fail_alloc_hctx:
+	return NULL;
 }
 
 static void blk_mq_init_cpu_queues(struct request_queue *q,
@@ -2631,13 +2670,17 @@ static int blk_mq_alloc_ctxs(struct request_queue *q)
  */
 void blk_mq_release(struct request_queue *q)
 {
-	struct blk_mq_hw_ctx *hctx;
-	unsigned int i;
+	struct blk_mq_hw_ctx *hctx, *next;
+	int i;
 
-	/* hctx kobj stays in hctx */
-	queue_for_each_hw_ctx(q, hctx, i) {
-		if (!hctx)
-			continue;
+	cancel_delayed_work_sync(&q->requeue_work);
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		WARN_ON_ONCE(hctx && list_empty(&hctx->hctx_list));
+
+	/* all hctx are in .unused_hctx_list now */
+	list_for_each_entry_safe(hctx, next, &q->unused_hctx_list, hctx_list) {
+		list_del_init(&hctx->hctx_list);
 		kobject_put(&hctx->kobj);
 	}
 
@@ -2700,51 +2743,38 @@ struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set,
 }
 EXPORT_SYMBOL(blk_mq_init_sq_queue);
 
-static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
-{
-	int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
-
-	BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu),
-			   __alignof__(struct blk_mq_hw_ctx)) !=
-		     sizeof(struct blk_mq_hw_ctx));
-
-	if (tag_set->flags & BLK_MQ_F_BLOCKING)
-		hw_ctx_size += sizeof(struct srcu_struct);
-
-	return hw_ctx_size;
-}
-
 static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx(
 		struct blk_mq_tag_set *set, struct request_queue *q,
 		int hctx_idx, int node)
 {
-	struct blk_mq_hw_ctx *hctx;
-
-	hctx = kzalloc_node(blk_mq_hw_ctx_size(set),
-			GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
-			node);
-	if (!hctx)
-		return NULL;
+	struct blk_mq_hw_ctx *hctx = NULL, *tmp;
 
-	if (!zalloc_cpumask_var_node(&hctx->cpumask,
-				GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
-				node)) {
-		kfree(hctx);
-		return NULL;
+	/* reuse dead hctx first */
+	spin_lock(&q->unused_hctx_lock);
+	list_for_each_entry(tmp, &q->unused_hctx_list, hctx_list) {
+		if (tmp->numa_node == node) {
+			hctx = tmp;
+			break;
+		}
 	}
+	if (hctx)
+		list_del_init(&hctx->hctx_list);
+	spin_unlock(&q->unused_hctx_lock);
 
-	atomic_set(&hctx->nr_active, 0);
-	hctx->numa_node = node;
-	hctx->queue_num = hctx_idx;
+	if (!hctx)
+		hctx = blk_mq_alloc_hctx(q, set, node);
+	if (!hctx)
+		goto fail;
 
-	if (blk_mq_init_hctx(q, set, hctx, hctx_idx)) {
-		free_cpumask_var(hctx->cpumask);
-		kfree(hctx);
-		return NULL;
-	}
-	blk_mq_hctx_kobj_init(hctx);
+	if (blk_mq_init_hctx(q, set, hctx, hctx_idx))
+		goto free_hctx;
 
 	return hctx;
+
+ free_hctx:
+	kobject_put(&hctx->kobj);
+ fail:
+	return NULL;
 }
 
 static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
@@ -2770,10 +2800,8 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 
 		hctx = blk_mq_alloc_and_init_hctx(set, q, i, node);
 		if (hctx) {
-			if (hctxs[i]) {
+			if (hctxs[i])
 				blk_mq_exit_hctx(q, set, hctxs[i], i);
-				kobject_put(&hctxs[i]->kobj);
-			}
 			hctxs[i] = hctx;
 		} else {
 			if (hctxs[i])
@@ -2804,9 +2832,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 			if (hctx->tags)
 				blk_mq_free_map_and_requests(set, j);
 			blk_mq_exit_hctx(q, set, hctx, j);
-			kobject_put(&hctx->kobj);
 			hctxs[j] = NULL;
-
 		}
 	}
 	mutex_unlock(&q->sysfs_lock);
@@ -2849,6 +2875,9 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	if (!q->queue_hw_ctx)
 		goto err_sys_init;
 
+	INIT_LIST_HEAD(&q->unused_hctx_list);
+	spin_lock_init(&q->unused_hctx_lock);
+
 	blk_mq_realloc_hw_ctxs(set, q);
 	if (!q->nr_hw_queues)
 		goto err_hctxs;
@@ -2905,7 +2934,8 @@ err_exit:
 }
 EXPORT_SYMBOL(blk_mq_init_allocated_queue);
 
-void blk_mq_free_queue(struct request_queue *q)
+/* tags can _not_ be used after returning from blk_mq_exit_queue */
+void blk_mq_exit_queue(struct request_queue *q)
 {
 	struct blk_mq_tag_set	*set = q->tag_set;
 
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 423ea88ab6fb..633a5a77ee8b 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -37,7 +37,7 @@ struct blk_mq_ctx {
 	struct kobject		kobj;
 } ____cacheline_aligned_in_smp;
 
-void blk_mq_free_queue(struct request_queue *q);
+void blk_mq_exit_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
 bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);
diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
index d169d7188fa6..3f55b56f24bc 100644
--- a/block/blk-rq-qos.c
+++ b/block/blk-rq-qos.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+
 #include "blk-rq-qos.h"
 
 /*
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index 564851889550..2300e038b9fa 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef RQ_QOS_H
 #define RQ_QOS_H
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 6375afaedcec..3facc41476be 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Functions related to setting various queue properties from drivers
  */
@@ -663,22 +664,6 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 EXPORT_SYMBOL(disk_stack_limits);
 
 /**
- * blk_queue_dma_pad - set pad mask
- * @q:     the request queue for the device
- * @mask:  pad mask
- *
- * Set dma pad mask.
- *
- * Appending pad buffer to a request modifies the last entry of a
- * scatter list such that it includes the pad buffer.
- **/
-void blk_queue_dma_pad(struct request_queue *q, unsigned int mask)
-{
-	q->dma_pad_mask = mask;
-}
-EXPORT_SYMBOL(blk_queue_dma_pad);
-
-/**
  * blk_queue_update_dma_pad - update pad mask
  * @q:     the request queue for the device
  * @mask:  pad mask
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 696a04176e4d..940f15d600f8 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Block stat tracking code
  *
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 7a95a1eb27e1..a16a02c52a85 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -728,7 +728,7 @@ static struct queue_sysfs_entry throtl_sample_time_entry = {
 };
 #endif
 
-static struct attribute *default_attrs[] = {
+static struct attribute *queue_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
 	&queue_max_hw_sectors_entry.attr,
@@ -769,7 +769,25 @@ static struct attribute *default_attrs[] = {
 #endif
 	NULL,
 };
-ATTRIBUTE_GROUPS(default);
+
+static umode_t queue_attr_visible(struct kobject *kobj, struct attribute *attr,
+				int n)
+{
+	struct request_queue *q =
+		container_of(kobj, struct request_queue, kobj);
+
+	if (attr == &queue_io_timeout_entry.attr &&
+		(!q->mq_ops || !q->mq_ops->timeout))
+			return 0;
+
+	return attr->mode;
+}
+
+static struct attribute_group queue_attr_group = {
+	.attrs = queue_attrs,
+	.is_visible = queue_attr_visible,
+};
+
 
 #define to_queue(atr) container_of((atr), struct queue_sysfs_entry, attr)
 
@@ -891,7 +909,6 @@ static const struct sysfs_ops queue_sysfs_ops = {
 
 struct kobj_type blk_queue_ktype = {
 	.sysfs_ops	= &queue_sysfs_ops,
-	.default_groups = default_groups,
 	.release	= blk_release_queue,
 };
 
@@ -940,6 +957,14 @@ int blk_register_queue(struct gendisk *disk)
 		goto unlock;
 	}
 
+	ret = sysfs_create_group(&q->kobj, &queue_attr_group);
+	if (ret) {
+		blk_trace_remove_sysfs(dev);
+		kobject_del(&q->kobj);
+		kobject_put(&dev->kobj);
+		goto unlock;
+	}
+
 	if (queue_is_mq(q)) {
 		__blk_mq_register_dev(dev, q);
 		blk_mq_debugfs_register(q);
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 124c26128bf6..8aa68fae96ad 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Functions related to generic timeout handling of requests.
  */
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index fd166fbb0f65..313f45a37e9d 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * buffered writeback throttling. loosely based on CoDel. We can't drop
  * packets for IO scheduling, so the logic is something like this:
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 2d98803faec2..ae7e91bd0618 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Zoned block device handling
  *
diff --git a/block/blk.h b/block/blk.h
index 5d636ee41663..e27fd1512e4b 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -75,7 +75,7 @@ static inline bool biovec_phys_mergeable(struct request_queue *q,
 
 	if (addr1 + vec1->bv_len != addr2)
 		return false;
-	if (xen_domain() && !xen_biovec_phys_mergeable(vec1, vec2))
+	if (xen_domain() && !xen_biovec_phys_mergeable(vec1, vec2->bv_page))
 		return false;
 	if ((addr1 | mask) != ((addr2 + vec2->bv_len - 1) | mask))
 		return false;
diff --git a/block/bounce.c b/block/bounce.c
index 47eb7e936e22..f8ed677a1bf7 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -163,14 +163,13 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool)
 {
 	struct bio *bio_orig = bio->bi_private;
 	struct bio_vec *bvec, orig_vec;
-	int i;
 	struct bvec_iter orig_iter = bio_orig->bi_iter;
 	struct bvec_iter_all iter_all;
 
 	/*
 	 * free up bounce indirect pages used
 	 */
-	bio_for_each_segment_all(bvec, bio, i, iter_all) {
+	bio_for_each_segment_all(bvec, bio, iter_all) {
 		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);
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 005e2b75d775..b898a1cdf872 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -1,24 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  BSG helper library
  *
  *  Copyright (C) 2008   James Smart, Emulex Corporation
  *  Copyright (C) 2011   Red Hat, Inc.  All rights reserved.
  *  Copyright (C) 2011   Mike Christie
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
  */
 #include <linux/slab.h>
 #include <linux/blk-mq.h>
diff --git a/block/bsg.c b/block/bsg.c
index f306853c6b08..833c44b3d458 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -1,13 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * bsg.c - block layer implementation of the sg v4 interface
- *
- * Copyright (C) 2004 Jens Axboe <axboe@suse.de> SUSE Labs
- * Copyright (C) 2004 Peter M. Jones <pjones@redhat.com>
- *
- *  This file is subject to the terms and conditions of the GNU General Public
- *  License version 2.  See the file "COPYING" in the main directory of this
- *  archive for more details.
- *
  */
 #include <linux/module.h>
 #include <linux/init.h>
diff --git a/block/elevator.c b/block/elevator.c
index d6d835a08de6..ec55d5fc0b3e 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  Block device elevator/IO-scheduler.
  *
@@ -509,8 +510,6 @@ void elv_unregister_queue(struct request_queue *q)
 
 int elv_register(struct elevator_type *e)
 {
-	char *def = "";
-
 	/* create icq_cache if requested */
 	if (e->icq_size) {
 		if (WARN_ON(e->icq_size < sizeof(struct io_cq)) ||
@@ -535,8 +534,8 @@ int elv_register(struct elevator_type *e)
 	list_add_tail(&e->list, &elv_list);
 	spin_unlock(&elv_list_lock);
 
-	printk(KERN_INFO "io scheduler %s registered%s\n", e->elevator_name,
-								def);
+	printk(KERN_INFO "io scheduler %s registered\n", e->elevator_name);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(elv_register);
diff --git a/block/genhd.c b/block/genhd.c
index 703267865f14..ad6826628e79 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  gendisk handling
  */
@@ -531,6 +532,18 @@ void blk_free_devt(dev_t devt)
 	}
 }
 
+/**
+ *	We invalidate devt by assigning NULL pointer for devt in idr.
+ */
+void blk_invalidate_devt(dev_t devt)
+{
+	if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
+		spin_lock_bh(&ext_devt_lock);
+		idr_replace(&ext_devt_idr, NULL, blk_mangle_minor(MINOR(devt)));
+		spin_unlock_bh(&ext_devt_lock);
+	}
+}
+
 static char *bdevt_str(dev_t devt, char *buf)
 {
 	if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) {
@@ -793,6 +806,13 @@ void del_gendisk(struct gendisk *disk)
 
 	if (!(disk->flags & GENHD_FL_HIDDEN))
 		blk_unregister_region(disk_devt(disk), disk->minors);
+	/*
+	 * Remove gendisk pointer from idr so that it cannot be looked up
+	 * while RCU period before freeing gendisk is running to prevent
+	 * use-after-free issues. Note that the device number stays
+	 * "in-use" until we really free the gendisk.
+	 */
+	blk_invalidate_devt(disk_devt(disk));
 
 	kobject_put(disk->part0.holder_dir);
 	kobject_put(disk->slave_dir);
@@ -1628,12 +1648,11 @@ static unsigned long disk_events_poll_jiffies(struct gendisk *disk)
 
 	/*
 	 * If device-specific poll interval is set, always use it.  If
-	 * the default is being used, poll iff there are events which
-	 * can't be monitored asynchronously.
+	 * the default is being used, poll if the POLL flag is set.
 	 */
 	if (ev->poll_msecs >= 0)
 		intv_msecs = ev->poll_msecs;
-	else if (disk->events & ~disk->async_events)
+	else if (disk->event_flags & DISK_EVENT_FLAG_POLL)
 		intv_msecs = disk_events_dfl_poll_msecs;
 
 	return msecs_to_jiffies(intv_msecs);
@@ -1843,11 +1862,13 @@ static void disk_check_events(struct disk_events *ev,
 
 	/*
 	 * Tell userland about new events.  Only the events listed in
-	 * @disk->events are reported.  Unlisted events are processed the
-	 * same internally but never get reported to userland.
+	 * @disk->events are reported, and only if DISK_EVENT_FLAG_UEVENT
+	 * is set. Otherwise, events are processed internally but never
+	 * get reported to userland.
 	 */
 	for (i = 0; i < ARRAY_SIZE(disk_uevents); i++)
-		if (events & disk->events & (1 << i))
+		if ((events & disk->events & (1 << i)) &&
+		    (disk->event_flags & DISK_EVENT_FLAG_UEVENT))
 			envp[nr_events++] = disk_uevents[i];
 
 	if (nr_events)
@@ -1860,6 +1881,7 @@ static void disk_check_events(struct disk_events *ev,
  *
  * events		: list of all supported events
  * events_async		: list of events which can be detected w/o polling
+ *			  (always empty, only for backwards compatibility)
  * events_poll_msecs	: polling interval, 0: disable, -1: system default
  */
 static ssize_t __disk_events_show(unsigned int events, char *buf)
@@ -1884,15 +1906,16 @@ static ssize_t disk_events_show(struct device *dev,
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
+	if (!(disk->event_flags & DISK_EVENT_FLAG_UEVENT))
+		return 0;
+
 	return __disk_events_show(disk->events, buf);
 }
 
 static ssize_t disk_events_async_show(struct device *dev,
 				      struct device_attribute *attr, char *buf)
 {
-	struct gendisk *disk = dev_to_disk(dev);
-
-	return __disk_events_show(disk->async_events, buf);
+	return 0;
 }
 
 static ssize_t disk_events_poll_msecs_show(struct device *dev,
@@ -1901,6 +1924,9 @@ static ssize_t disk_events_poll_msecs_show(struct device *dev,
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
+	if (!disk->ev)
+		return sprintf(buf, "-1\n");
+
 	return sprintf(buf, "%ld\n", disk->ev->poll_msecs);
 }
 
@@ -1917,6 +1943,9 @@ static ssize_t disk_events_poll_msecs_store(struct device *dev,
 	if (intv < 0 && intv != -1)
 		return -EINVAL;
 
+	if (!disk->ev)
+		return -ENODEV;
+
 	disk_block_events(disk);
 	disk->ev->poll_msecs = intv;
 	__disk_unblock_events(disk, true);
@@ -1981,7 +2010,7 @@ static void disk_alloc_events(struct gendisk *disk)
 {
 	struct disk_events *ev;
 
-	if (!disk->fops->check_events)
+	if (!disk->fops->check_events || !disk->events)
 		return;
 
 	ev = kzalloc(sizeof(*ev), GFP_KERNEL);
@@ -2003,14 +2032,14 @@ static void disk_alloc_events(struct gendisk *disk)
 
 static void disk_add_events(struct gendisk *disk)
 {
-	if (!disk->ev)
-		return;
-
 	/* FIXME: error handling */
 	if (sysfs_create_files(&disk_to_dev(disk)->kobj, disk_events_attrs) < 0)
 		pr_warn("%s: failed to create sysfs files for events\n",
 			disk->disk_name);
 
+	if (!disk->ev)
+		return;
+
 	mutex_lock(&disk_events_mutex);
 	list_add_tail(&disk->ev->node, &disk_events);
 	mutex_unlock(&disk_events_mutex);
@@ -2024,14 +2053,13 @@ static void disk_add_events(struct gendisk *disk)
 
 static void disk_del_events(struct gendisk *disk)
 {
-	if (!disk->ev)
-		return;
-
-	disk_block_events(disk);
+	if (disk->ev) {
+		disk_block_events(disk);
 
-	mutex_lock(&disk_events_mutex);
-	list_del_init(&disk->ev->node);
-	mutex_unlock(&disk_events_mutex);
+		mutex_lock(&disk_events_mutex);
+		list_del_init(&disk->ev->node);
+		mutex_unlock(&disk_events_mutex);
+	}
 
 	sysfs_remove_files(&disk_to_dev(disk)->kobj, disk_events_attrs);
 }
diff --git a/block/ioctl.c b/block/ioctl.c
index 4825c78a6baa..15a0eb80ada9 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/capability.h>
 #include <linux/blkdev.h>
 #include <linux/export.h>
diff --git a/block/ioprio.c b/block/ioprio.c
index f9821080c92c..2e0559f157c8 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * fs/ioprio.c
  *
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index ec6a04e01bc1..c3b05119cebd 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * The Kyber I/O scheduler. Controls latency by throttling queue depths using
  * scalable techniques.
  *
  * Copyright (C) 2017 Facebook
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public
- * License v2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
 #include <linux/kernel.h>
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 14288f864e94..1876f5712bfd 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  MQ Deadline i/o scheduler - adaptation of the legacy deadline scheduler,
  *  for the blk-mq scheduling framework
diff --git a/block/opal_proto.h b/block/opal_proto.h
index e20be8258854..d9a05ad02eb5 100644
--- a/block/opal_proto.h
+++ b/block/opal_proto.h
@@ -1,18 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright © 2016 Intel Corporation
  *
  * Authors:
  *    Rafael Antognolli <rafael.antognolli@intel.com>
  *    Scott  Bauer      <scott.bauer@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 #include <linux/types.h>
 
@@ -170,6 +162,8 @@ enum opal_token {
 	OPAL_READLOCKED = 0x07,
 	OPAL_WRITELOCKED = 0x08,
 	OPAL_ACTIVEKEY = 0x0A,
+	/* lockingsp table */
+	OPAL_LIFECYCLE = 0x06,
 	/* locking info table */
 	OPAL_MAXRANGES = 0x04,
 	 /* mbr control */
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 8e596a8dff32..aee643ce13d1 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -285,6 +285,13 @@ void delete_partition(struct gendisk *disk, int partno)
 	kobject_put(part->holder_dir);
 	device_del(part_to_dev(part));
 
+	/*
+	 * Remove gendisk pointer from idr so that it cannot be looked up
+	 * while RCU period before freeing gendisk is running to prevent
+	 * use-after-free issues. Note that the device number stays
+	 * "in-use" until we really free the gendisk.
+	 */
+	blk_invalidate_devt(part_devt(part));
 	hd_struct_kill(part);
 }
 
diff --git a/block/partitions/acorn.c b/block/partitions/acorn.c
index fbeb697374d5..7587700fad4a 100644
--- a/block/partitions/acorn.c
+++ b/block/partitions/acorn.c
@@ -1,12 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- *  linux/fs/partitions/acorn.c
- *
  *  Copyright (c) 1996-2000 Russell King.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  Scan ADFS partitions on hard disk drives.  Unfortunately, there
  *  isn't a standard for partitioning drives on Acorn machines, so
  *  every single manufacturer of SCSI and IDE cards created their own
diff --git a/block/partitions/aix.h b/block/partitions/aix.h
index e0c66a987523..b4449f0b9f2b 100644
--- a/block/partitions/aix.h
+++ b/block/partitions/aix.h
@@ -1 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 extern int aix_partition(struct parsed_partitions *state);
diff --git a/block/partitions/amiga.h b/block/partitions/amiga.h
index d094585cadaa..7e63f4d9d969 100644
--- a/block/partitions/amiga.h
+++ b/block/partitions/amiga.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  *  fs/partitions/amiga.h
  */
diff --git a/block/partitions/efi.c b/block/partitions/efi.c
index 39f70d968754..db2fef7dfc47 100644
--- a/block/partitions/efi.c
+++ b/block/partitions/efi.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /************************************************************
  * EFI GUID Partition Table handling
  *
@@ -7,21 +8,6 @@
  * efi.[ch] by Matt Domsch <Matt_Domsch@dell.com>
  *   Copyright 2000,2001,2002,2004 Dell Inc.
  *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- *
  * TODO:
  *
  * Changelog:
diff --git a/block/partitions/efi.h b/block/partitions/efi.h
index abd0b19288a6..3e8576157575 100644
--- a/block/partitions/efi.h
+++ b/block/partitions/efi.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /************************************************************
  * EFI GUID Partition Table
  * Per Intel EFI Specification v1.02
@@ -5,21 +6,6 @@
  *
  * By Matt Domsch <Matt_Domsch@dell.com>  Fri Sep 22 22:15:56 CDT 2000  
  *   Copyright 2000,2001 Dell Inc.
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- * 
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- * 
  ************************************************************/
 
 #ifndef FS_PART_EFI_H_INCLUDED
diff --git a/block/partitions/ibm.h b/block/partitions/ibm.h
index 08fb0804a812..8bf13febb2b6 100644
--- a/block/partitions/ibm.h
+++ b/block/partitions/ibm.h
@@ -1 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 int ibm_partition(struct parsed_partitions *);
diff --git a/block/partitions/karma.h b/block/partitions/karma.h
index c764b2e9df21..48e074d417fb 100644
--- a/block/partitions/karma.h
+++ b/block/partitions/karma.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  *  fs/partitions/karma.h
  */
diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c
index 16766f267559..6db573f33219 100644
--- a/block/partitions/ldm.c
+++ b/block/partitions/ldm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /**
  * ldm - Support for Windows Logical Disk Manager (Dynamic Disks)
  *
@@ -6,21 +7,6 @@
  * Copyright (C) 2001,2002 Jakob Kemi <jakob.kemi@telia.com>
  *
  * Documentation is available at http://www.linux-ntfs.org/doku.php?id=downloads 
- *
- * This program is free software; you can redistribute it and/or modify it under
- * the terms of the GNU General Public License as published by the Free Software
- * Foundation; either version 2 of the License, or (at your option) any later
- * version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
- * FOR A PARTICULAR PURPOSE.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program (in the main directory of the source in the file COPYING); if
- * not, write to the Free Software Foundation, Inc., 59 Temple Place, Suite 330,
- * Boston, MA  02111-1307  USA
  */
 
 #include <linux/slab.h>
diff --git a/block/partitions/ldm.h b/block/partitions/ldm.h
index f4c6055df956..1ca63e97bccc 100644
--- a/block/partitions/ldm.h
+++ b/block/partitions/ldm.h
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /**
  * ldm - Part of the Linux-NTFS project.
  *
@@ -6,21 +7,6 @@
  * Copyright (C) 2001,2002 Jakob Kemi <jakob.kemi@telia.com>
  *
  * Documentation is available at http://www.linux-ntfs.org/doku.php?id=downloads 
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program (in the main directory of the Linux-NTFS source
- * in the file COPYING); if not, write to the Free Software Foundation,
- * Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #ifndef _FS_PT_LDM_H_
diff --git a/block/partitions/msdos.h b/block/partitions/msdos.h
index 38c781c490b3..fcacfc486092 100644
--- a/block/partitions/msdos.h
+++ b/block/partitions/msdos.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  *  fs/partitions/msdos.h
  */
diff --git a/block/partitions/osf.h b/block/partitions/osf.h
index 20ed2315ec16..4d8088e7ea8c 100644
--- a/block/partitions/osf.h
+++ b/block/partitions/osf.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  *  fs/partitions/osf.h
  */
diff --git a/block/partitions/sgi.h b/block/partitions/sgi.h
index b9553ebdd5a9..a5b77c3987cf 100644
--- a/block/partitions/sgi.h
+++ b/block/partitions/sgi.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  *  fs/partitions/sgi.h
  */
diff --git a/block/partitions/sun.h b/block/partitions/sun.h
index 2424baa8319f..ae1b9eed3fd7 100644
--- a/block/partitions/sun.h
+++ b/block/partitions/sun.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  *  fs/partitions/sun.h
  */
diff --git a/block/partitions/sysv68.h b/block/partitions/sysv68.h
index bf2f5ffa97ac..4fb6b8ec78ae 100644
--- a/block/partitions/sysv68.h
+++ b/block/partitions/sysv68.h
@@ -1 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 extern int sysv68_partition(struct parsed_partitions *state);
diff --git a/block/partitions/ultrix.h b/block/partitions/ultrix.h
index a3cc00b2bded..9f676cead222 100644
--- a/block/partitions/ultrix.h
+++ b/block/partitions/ultrix.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  *  fs/partitions/ultrix.h
  */
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 533f4aee8567..f5e0ad65e86a 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -1,20 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2001 Jens Axboe <axboe@suse.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- *
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public Licens
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
- *
  */
 #include <linux/kernel.h>
 #include <linux/errno.h>
diff --git a/block/sed-opal.c b/block/sed-opal.c
index e0de4dd448b3..a46e8d13e16d 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -1,18 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright © 2016 Intel Corporation
  *
  * Authors:
  *    Scott  Bauer      <scott.bauer@intel.com>
  *    Rafael Antognolli <rafael.antognolli@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ":OPAL: " fmt
@@ -85,7 +77,6 @@ struct opal_dev {
 	void *data;
 	sec_send_recv *send_recv;
 
-	const struct opal_step *steps;
 	struct mutex dev_lock;
 	u16 comid;
 	u32 hsn;
@@ -157,7 +148,7 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = {
 
 	/* C_PIN_TABLE object ID's */
 
-        [OPAL_C_PIN_MSID] =
+	[OPAL_C_PIN_MSID] =
 		{ 0x00, 0x00, 0x00, 0x0B, 0x00, 0x00, 0x84, 0x02},
 	[OPAL_C_PIN_SID] =
 		{ 0x00, 0x00, 0x00, 0x0B, 0x00, 0x00, 0x00, 0x01},
@@ -181,7 +172,7 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = {
  * Derived from: TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
  * Section: 6.3 Assigned UIDs
  */
-static const u8 opalmethod[][OPAL_UID_LENGTH] = {
+static const u8 opalmethod[][OPAL_METHOD_LENGTH] = {
 	[OPAL_PROPERTIES] =
 		{ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x01 },
 	[OPAL_STARTSESSION] =
@@ -217,6 +208,7 @@ static const u8 opalmethod[][OPAL_UID_LENGTH] = {
 };
 
 static int end_opal_session_error(struct opal_dev *dev);
+static int opal_discovery0_step(struct opal_dev *dev);
 
 struct opal_suspend_data {
 	struct opal_lock_unlock unlk;
@@ -382,37 +374,50 @@ static void check_geometry(struct opal_dev *dev, const void *data)
 	dev->lowest_lba = geo->lowest_aligned_lba;
 }
 
-static int next(struct opal_dev *dev)
+static int execute_step(struct opal_dev *dev,
+			const struct opal_step *step, size_t stepIndex)
 {
-	const struct opal_step *step;
-	int state = 0, error = 0;
+	int error = step->fn(dev, step->data);
 
-	do {
-		step = &dev->steps[state];
-		if (!step->fn)
-			break;
+	if (error) {
+		pr_debug("Step %zu (%pS) failed with error %d: %s\n",
+			 stepIndex, step->fn, error,
+			 opal_error_to_human(error));
+	}
 
-		error = step->fn(dev, step->data);
-		if (error) {
-			pr_debug("Error on step function: %d with error %d: %s\n",
-				 state, error,
-				 opal_error_to_human(error));
-
-			/* For each OPAL command we do a discovery0 then we
-			 * start some sort of session.
-			 * If we haven't passed state 1 then there was an error
-			 * on discovery0 or during the attempt to start a
-			 * session. Therefore we shouldn't attempt to terminate
-			 * a session, as one has not yet been created.
-			 */
-			if (state > 1) {
-				end_opal_session_error(dev);
-				return error;
-			}
+	return error;
+}
 
-		}
-		state++;
-	} while (!error);
+static int execute_steps(struct opal_dev *dev,
+			 const struct opal_step *steps, size_t n_steps)
+{
+	size_t state = 0;
+	int error;
+
+	/* first do a discovery0 */
+	error = opal_discovery0_step(dev);
+	if (error)
+		return error;
+
+	for (state = 0; state < n_steps; state++) {
+		error = execute_step(dev, &steps[state], state);
+		if (error)
+			goto out_error;
+	}
+
+	return 0;
+
+out_error:
+	/*
+	 * For each OPAL command the first step in steps starts some sort of
+	 * session. If an error occurred in the initial discovery0 or if an
+	 * error occurred in the first step (and thus stopping the loop with
+	 * state == 0) then there was an error before or during the attempt to
+	 * start a session. Therefore we shouldn't attempt to terminate a
+	 * session, as one has not yet been created.
+	 */
+	if (state > 0)
+		end_opal_session_error(dev);
 
 	return error;
 }
@@ -510,15 +515,32 @@ static int opal_discovery0(struct opal_dev *dev, void *data)
 	return opal_discovery0_end(dev);
 }
 
-static void add_token_u8(int *err, struct opal_dev *cmd, u8 tok)
+static int opal_discovery0_step(struct opal_dev *dev)
+{
+	const struct opal_step discovery0_step = {
+		opal_discovery0,
+	};
+	return execute_step(dev, &discovery0_step, 0);
+}
+
+static bool can_add(int *err, struct opal_dev *cmd, size_t len)
 {
 	if (*err)
-		return;
-	if (cmd->pos >= IO_BUFFER_LENGTH - 1) {
-		pr_debug("Error adding u8: end of buffer.\n");
+		return false;
+
+	if (len > IO_BUFFER_LENGTH || cmd->pos > IO_BUFFER_LENGTH - len) {
+		pr_debug("Error adding %zu bytes: end of buffer.\n", len);
 		*err = -ERANGE;
-		return;
+		return false;
 	}
+
+	return true;
+}
+
+static void add_token_u8(int *err, struct opal_dev *cmd, u8 tok)
+{
+	if (!can_add(err, cmd, 1))
+		return;
 	cmd->cmd[cmd->pos++] = tok;
 }
 
@@ -551,7 +573,6 @@ static void add_medium_atom_header(struct opal_dev *cmd, bool bytestring,
 
 static void add_token_u64(int *err, struct opal_dev *cmd, u64 number)
 {
-
 	size_t len;
 	int msb;
 
@@ -563,9 +584,8 @@ static void add_token_u64(int *err, struct opal_dev *cmd, u64 number)
 	msb = fls64(number);
 	len = DIV_ROUND_UP(msb, 8);
 
-	if (cmd->pos >= IO_BUFFER_LENGTH - len - 1) {
+	if (!can_add(err, cmd, len + 1)) {
 		pr_debug("Error adding u64: end of buffer.\n");
-		*err = -ERANGE;
 		return;
 	}
 	add_short_atom_header(cmd, false, false, len);
@@ -573,24 +593,19 @@ static void add_token_u64(int *err, struct opal_dev *cmd, u64 number)
 		add_token_u8(err, cmd, number >> (len * 8));
 }
 
-static void add_token_bytestring(int *err, struct opal_dev *cmd,
-				 const u8 *bytestring, size_t len)
+static u8 *add_bytestring_header(int *err, struct opal_dev *cmd, size_t len)
 {
 	size_t header_len = 1;
 	bool is_short_atom = true;
 
-	if (*err)
-		return;
-
 	if (len & ~SHORT_ATOM_LEN_MASK) {
 		header_len = 2;
 		is_short_atom = false;
 	}
 
-	if (len >= IO_BUFFER_LENGTH - cmd->pos - header_len) {
+	if (!can_add(err, cmd, header_len + len)) {
 		pr_debug("Error adding bytestring: end of buffer.\n");
-		*err = -ERANGE;
-		return;
+		return NULL;
 	}
 
 	if (is_short_atom)
@@ -598,9 +613,19 @@ static void add_token_bytestring(int *err, struct opal_dev *cmd,
 	else
 		add_medium_atom_header(cmd, true, false, len);
 
-	memcpy(&cmd->cmd[cmd->pos], bytestring, len);
-	cmd->pos += len;
+	return &cmd->cmd[cmd->pos];
+}
+
+static void add_token_bytestring(int *err, struct opal_dev *cmd,
+				 const u8 *bytestring, size_t len)
+{
+	u8 *start;
 
+	start = add_bytestring_header(err, cmd, len);
+	if (!start)
+		return;
+	memcpy(start, bytestring, len);
+	cmd->pos += len;
 }
 
 static int build_locking_range(u8 *buffer, size_t length, u8 lr)
@@ -623,7 +648,7 @@ static int build_locking_range(u8 *buffer, size_t length, u8 lr)
 static int build_locking_user(u8 *buffer, size_t length, u8 lr)
 {
 	if (length > OPAL_UID_LENGTH) {
-		pr_debug("Can't build locking range user, Length OOB\n");
+		pr_debug("Can't build locking range user. Length OOB\n");
 		return -ERANGE;
 	}
 
@@ -649,6 +674,9 @@ static int cmd_finalize(struct opal_dev *cmd, u32 hsn, u32 tsn)
 	struct opal_header *hdr;
 	int err = 0;
 
+	/* close the parameter list opened from cmd_start */
+	add_token_u8(&err, cmd, OPAL_ENDLIST);
+
 	add_token_u8(&err, cmd, OPAL_ENDOFDATA);
 	add_token_u8(&err, cmd, OPAL_STARTLIST);
 	add_token_u8(&err, cmd, 0);
@@ -687,6 +715,11 @@ static const struct opal_resp_tok *response_get_token(
 {
 	const struct opal_resp_tok *tok;
 
+	if (!resp) {
+		pr_debug("Response is NULL\n");
+		return ERR_PTR(-EINVAL);
+	}
+
 	if (n >= resp->num) {
 		pr_debug("Token number doesn't exist: %d, resp: %d\n",
 			 n, resp->num);
@@ -869,27 +902,19 @@ static size_t response_get_string(const struct parsed_resp *resp, int n,
 				  const char **store)
 {
 	u8 skip;
-	const struct opal_resp_tok *token;
+	const struct opal_resp_tok *tok;
 
 	*store = NULL;
-	if (!resp) {
-		pr_debug("Response is NULL\n");
-		return 0;
-	}
-
-	if (n >= resp->num) {
-		pr_debug("Response has %d tokens. Can't access %d\n",
-			 resp->num, n);
+	tok = response_get_token(resp, n);
+	if (IS_ERR(tok))
 		return 0;
-	}
 
-	token = &resp->toks[n];
-	if (token->type != OPAL_DTA_TOKENID_BYTESTRING) {
+	if (tok->type != OPAL_DTA_TOKENID_BYTESTRING) {
 		pr_debug("Token is not a byte string!\n");
 		return 0;
 	}
 
-	switch (token->width) {
+	switch (tok->width) {
 	case OPAL_WIDTH_TINY:
 	case OPAL_WIDTH_SHORT:
 		skip = 1;
@@ -905,37 +930,29 @@ static size_t response_get_string(const struct parsed_resp *resp, int n,
 		return 0;
 	}
 
-	*store = token->pos + skip;
-	return token->len - skip;
+	*store = tok->pos + skip;
+	return tok->len - skip;
 }
 
 static u64 response_get_u64(const struct parsed_resp *resp, int n)
 {
-	if (!resp) {
-		pr_debug("Response is NULL\n");
-		return 0;
-	}
+	const struct opal_resp_tok *tok;
 
-	if (n >= resp->num) {
-		pr_debug("Response has %d tokens. Can't access %d\n",
-			 resp->num, n);
+	tok = response_get_token(resp, n);
+	if (IS_ERR(tok))
 		return 0;
-	}
 
-	if (resp->toks[n].type != OPAL_DTA_TOKENID_UINT) {
-		pr_debug("Token is not unsigned it: %d\n",
-			 resp->toks[n].type);
+	if (tok->type != OPAL_DTA_TOKENID_UINT) {
+		pr_debug("Token is not unsigned int: %d\n", tok->type);
 		return 0;
 	}
 
-	if (!(resp->toks[n].width == OPAL_WIDTH_TINY ||
-	      resp->toks[n].width == OPAL_WIDTH_SHORT)) {
-		pr_debug("Atom is not short or tiny: %d\n",
-			 resp->toks[n].width);
+	if (tok->width != OPAL_WIDTH_TINY && tok->width != OPAL_WIDTH_SHORT) {
+		pr_debug("Atom is not short or tiny: %d\n", tok->width);
 		return 0;
 	}
 
-	return resp->toks[n].stored.u;
+	return tok->stored.u;
 }
 
 static bool response_token_matches(const struct opal_resp_tok *token, u8 match)
@@ -991,6 +1008,27 @@ static void clear_opal_cmd(struct opal_dev *dev)
 	memset(dev->cmd, 0, IO_BUFFER_LENGTH);
 }
 
+static int cmd_start(struct opal_dev *dev, const u8 *uid, const u8 *method)
+{
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, method, OPAL_METHOD_LENGTH);
+
+	/*
+	 * Every method call is followed by its parameters enclosed within
+	 * OPAL_STARTLIST and OPAL_ENDLIST tokens. We automatically open the
+	 * parameter list here and close it later in cmd_finalize.
+	 */
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+
+	return err;
+}
+
 static int start_opal_session_cont(struct opal_dev *dev)
 {
 	u32 hsn, tsn;
@@ -1050,24 +1088,47 @@ static int finalize_and_send(struct opal_dev *dev, cont_fn cont)
 	return opal_send_recv(dev, cont);
 }
 
+/*
+ * request @column from table @table on device @dev. On success, the column
+ * data will be available in dev->resp->tok[4]
+ */
+static int generic_get_column(struct opal_dev *dev, const u8 *table,
+			      u64 column)
+{
+	int err;
+
+	err = cmd_start(dev, table, opalmethod[OPAL_GET]);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_STARTCOLUMN);
+	add_token_u64(&err, dev, column);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_ENDCOLUMN);
+	add_token_u64(&err, dev, column);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err)
+		return err;
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
 static int gen_key(struct opal_dev *dev, void *data)
 {
 	u8 uid[OPAL_UID_LENGTH];
-	int err = 0;
-
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
+	int err;
 
 	memcpy(uid, dev->prev_data, min(sizeof(uid), dev->prev_d_len));
 	kfree(dev->prev_data);
 	dev->prev_data = NULL;
 
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_GENKEY],
-			     OPAL_UID_LENGTH);
-	add_token_u8(&err, dev, OPAL_STARTLIST);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
+	err = cmd_start(dev, uid, opalmethod[OPAL_GENKEY]);
 
 	if (err) {
 		pr_debug("Error building gen key command\n");
@@ -1105,62 +1166,39 @@ static int get_active_key_cont(struct opal_dev *dev)
 static int get_active_key(struct opal_dev *dev, void *data)
 {
 	u8 uid[OPAL_UID_LENGTH];
-	int err = 0;
+	int err;
 	u8 *lr = data;
 
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
-
 	err = build_locking_range(uid, sizeof(uid), *lr);
 	if (err)
 		return err;
 
-	err = 0;
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_GET], OPAL_UID_LENGTH);
-	add_token_u8(&err, dev, OPAL_STARTLIST);
-	add_token_u8(&err, dev, OPAL_STARTLIST);
-	add_token_u8(&err, dev, OPAL_STARTNAME);
-	add_token_u8(&err, dev, 3); /* startCloumn */
-	add_token_u8(&err, dev, 10); /* ActiveKey */
-	add_token_u8(&err, dev, OPAL_ENDNAME);
-	add_token_u8(&err, dev, OPAL_STARTNAME);
-	add_token_u8(&err, dev, 4); /* endColumn */
-	add_token_u8(&err, dev, 10); /* ActiveKey */
-	add_token_u8(&err, dev, OPAL_ENDNAME);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
-	if (err) {
-		pr_debug("Error building get active key command\n");
+	err = generic_get_column(dev, uid, OPAL_ACTIVEKEY);
+	if (err)
 		return err;
-	}
 
-	return finalize_and_send(dev, get_active_key_cont);
+	return get_active_key_cont(dev);
 }
 
 static int generic_lr_enable_disable(struct opal_dev *dev,
 				     u8 *uid, bool rle, bool wle,
 				     bool rl, bool wl)
 {
-	int err = 0;
+	int err;
 
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
+	err = cmd_start(dev, uid, opalmethod[OPAL_SET]);
 
-	add_token_u8(&err, dev, OPAL_STARTLIST);
 	add_token_u8(&err, dev, OPAL_STARTNAME);
 	add_token_u8(&err, dev, OPAL_VALUES);
 	add_token_u8(&err, dev, OPAL_STARTLIST);
 
 	add_token_u8(&err, dev, OPAL_STARTNAME);
-	add_token_u8(&err, dev, 5); /* ReadLockEnabled */
+	add_token_u8(&err, dev, OPAL_READLOCKENABLED);
 	add_token_u8(&err, dev, rle);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
 
 	add_token_u8(&err, dev, OPAL_STARTNAME);
-	add_token_u8(&err, dev, 6); /* WriteLockEnabled */
+	add_token_u8(&err, dev, OPAL_WRITELOCKENABLED);
 	add_token_u8(&err, dev, wle);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
 
@@ -1176,7 +1214,6 @@ static int generic_lr_enable_disable(struct opal_dev *dev,
 
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
 	return err;
 }
 
@@ -1197,10 +1234,7 @@ static int setup_locking_range(struct opal_dev *dev, void *data)
 	u8 uid[OPAL_UID_LENGTH];
 	struct opal_user_lr_setup *setup = data;
 	u8 lr;
-	int err = 0;
-
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
+	int err;
 
 	lr = setup->session.opal_key.lr;
 	err = build_locking_range(uid, sizeof(uid), lr);
@@ -1210,40 +1244,34 @@ static int setup_locking_range(struct opal_dev *dev, void *data)
 	if (lr == 0)
 		err = enable_global_lr(dev, uid, setup);
 	else {
-		add_token_u8(&err, dev, OPAL_CALL);
-		add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
-		add_token_bytestring(&err, dev, opalmethod[OPAL_SET],
-				     OPAL_UID_LENGTH);
+		err = cmd_start(dev, uid, opalmethod[OPAL_SET]);
 
-		add_token_u8(&err, dev, OPAL_STARTLIST);
 		add_token_u8(&err, dev, OPAL_STARTNAME);
 		add_token_u8(&err, dev, OPAL_VALUES);
 		add_token_u8(&err, dev, OPAL_STARTLIST);
 
 		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, 3); /* Ranges Start */
+		add_token_u8(&err, dev, OPAL_RANGESTART);
 		add_token_u64(&err, dev, setup->range_start);
 		add_token_u8(&err, dev, OPAL_ENDNAME);
 
 		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, 4); /* Ranges length */
+		add_token_u8(&err, dev, OPAL_RANGELENGTH);
 		add_token_u64(&err, dev, setup->range_length);
 		add_token_u8(&err, dev, OPAL_ENDNAME);
 
 		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, 5); /*ReadLockEnabled */
+		add_token_u8(&err, dev, OPAL_READLOCKENABLED);
 		add_token_u64(&err, dev, !!setup->RLE);
 		add_token_u8(&err, dev, OPAL_ENDNAME);
 
 		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, 6); /*WriteLockEnabled*/
+		add_token_u8(&err, dev, OPAL_WRITELOCKENABLED);
 		add_token_u64(&err, dev, !!setup->WLE);
 		add_token_u8(&err, dev, OPAL_ENDNAME);
 
 		add_token_u8(&err, dev, OPAL_ENDLIST);
 		add_token_u8(&err, dev, OPAL_ENDNAME);
-		add_token_u8(&err, dev, OPAL_ENDLIST);
-
 	}
 	if (err) {
 		pr_debug("Error building Setup Locking range command.\n");
@@ -1261,29 +1289,21 @@ static int start_generic_opal_session(struct opal_dev *dev,
 				      u8 key_len)
 {
 	u32 hsn;
-	int err = 0;
+	int err;
 
 	if (key == NULL && auth != OPAL_ANYBODY_UID)
 		return OPAL_INVAL_PARAM;
 
-	clear_opal_cmd(dev);
-
-	set_comid(dev, dev->comid);
 	hsn = GENERIC_HOST_SESSION_NUM;
+	err = cmd_start(dev, opaluid[OPAL_SMUID_UID],
+			opalmethod[OPAL_STARTSESSION]);
 
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, opaluid[OPAL_SMUID_UID],
-			     OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_STARTSESSION],
-			     OPAL_UID_LENGTH);
-	add_token_u8(&err, dev, OPAL_STARTLIST);
 	add_token_u64(&err, dev, hsn);
 	add_token_bytestring(&err, dev, opaluid[sp_type], OPAL_UID_LENGTH);
 	add_token_u8(&err, dev, 1);
 
 	switch (auth) {
 	case OPAL_ANYBODY_UID:
-		add_token_u8(&err, dev, OPAL_ENDLIST);
 		break;
 	case OPAL_ADMIN1_UID:
 	case OPAL_SID_UID:
@@ -1296,7 +1316,6 @@ static int start_generic_opal_session(struct opal_dev *dev,
 		add_token_bytestring(&err, dev, opaluid[auth],
 				     OPAL_UID_LENGTH);
 		add_token_u8(&err, dev, OPAL_ENDNAME);
-		add_token_u8(&err, dev, OPAL_ENDLIST);
 		break;
 	default:
 		pr_debug("Cannot start Admin SP session with auth %d\n", auth);
@@ -1324,6 +1343,7 @@ static int start_SIDASP_opal_session(struct opal_dev *dev, void *data)
 
 	if (!key) {
 		const struct opal_key *okey = data;
+
 		ret = start_generic_opal_session(dev, OPAL_SID_UID,
 						 OPAL_ADMINSP_UID,
 						 okey->key,
@@ -1341,6 +1361,7 @@ static int start_SIDASP_opal_session(struct opal_dev *dev, void *data)
 static int start_admin1LSP_opal_session(struct opal_dev *dev, void *data)
 {
 	struct opal_key *key = data;
+
 	return start_generic_opal_session(dev, OPAL_ADMIN1_UID,
 					  OPAL_LOCKINGSP_UID,
 					  key->key, key->key_len);
@@ -1356,30 +1377,21 @@ static int start_auth_opal_session(struct opal_dev *dev, void *data)
 	u8 *key = session->opal_key.key;
 	u32 hsn = GENERIC_HOST_SESSION_NUM;
 
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
-
-	if (session->sum) {
+	if (session->sum)
 		err = build_locking_user(lk_ul_user, sizeof(lk_ul_user),
 					 session->opal_key.lr);
-		if (err)
-			return err;
-
-	} else if (session->who != OPAL_ADMIN1 && !session->sum) {
+	else if (session->who != OPAL_ADMIN1 && !session->sum)
 		err = build_locking_user(lk_ul_user, sizeof(lk_ul_user),
 					 session->who - 1);
-		if (err)
-			return err;
-	} else
+	else
 		memcpy(lk_ul_user, opaluid[OPAL_ADMIN1_UID], OPAL_UID_LENGTH);
 
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, opaluid[OPAL_SMUID_UID],
-			     OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_STARTSESSION],
-			     OPAL_UID_LENGTH);
+	if (err)
+		return err;
+
+	err = cmd_start(dev, opaluid[OPAL_SMUID_UID],
+			opalmethod[OPAL_STARTSESSION]);
 
-	add_token_u8(&err, dev, OPAL_STARTLIST);
 	add_token_u64(&err, dev, hsn);
 	add_token_bytestring(&err, dev, opaluid[OPAL_LOCKINGSP_UID],
 			     OPAL_UID_LENGTH);
@@ -1392,7 +1404,6 @@ static int start_auth_opal_session(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, 3);
 	add_token_bytestring(&err, dev, lk_ul_user, OPAL_UID_LENGTH);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
 		pr_debug("Error building STARTSESSION command.\n");
@@ -1404,18 +1415,10 @@ static int start_auth_opal_session(struct opal_dev *dev, void *data)
 
 static int revert_tper(struct opal_dev *dev, void *data)
 {
-	int err = 0;
-
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
+	int err;
 
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, opaluid[OPAL_ADMINSP_UID],
-			     OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_REVERT],
-			     OPAL_UID_LENGTH);
-	add_token_u8(&err, dev, OPAL_STARTLIST);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
+	err = cmd_start(dev, opaluid[OPAL_ADMINSP_UID],
+			opalmethod[OPAL_REVERT]);
 	if (err) {
 		pr_debug("Error building REVERT TPER command.\n");
 		return err;
@@ -1428,18 +1431,12 @@ static int internal_activate_user(struct opal_dev *dev, void *data)
 {
 	struct opal_session_info *session = data;
 	u8 uid[OPAL_UID_LENGTH];
-	int err = 0;
-
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
+	int err;
 
 	memcpy(uid, opaluid[OPAL_USER1_UID], OPAL_UID_LENGTH);
 	uid[7] = session->who;
 
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
-	add_token_u8(&err, dev, OPAL_STARTLIST);
+	err = cmd_start(dev, uid, opalmethod[OPAL_SET]);
 	add_token_u8(&err, dev, OPAL_STARTNAME);
 	add_token_u8(&err, dev, OPAL_VALUES);
 	add_token_u8(&err, dev, OPAL_STARTLIST);
@@ -1449,7 +1446,6 @@ static int internal_activate_user(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDNAME);
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
 		pr_debug("Error building Activate UserN command.\n");
@@ -1463,20 +1459,12 @@ static int erase_locking_range(struct opal_dev *dev, void *data)
 {
 	struct opal_session_info *session = data;
 	u8 uid[OPAL_UID_LENGTH];
-	int err = 0;
-
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
+	int err;
 
 	if (build_locking_range(uid, sizeof(uid), session->opal_key.lr) < 0)
 		return -ERANGE;
 
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_ERASE],
-			     OPAL_UID_LENGTH);
-	add_token_u8(&err, dev, OPAL_STARTLIST);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
+	err = cmd_start(dev, uid, opalmethod[OPAL_ERASE]);
 
 	if (err) {
 		pr_debug("Error building Erase Locking Range Command.\n");
@@ -1488,26 +1476,20 @@ static int erase_locking_range(struct opal_dev *dev, void *data)
 static int set_mbr_done(struct opal_dev *dev, void *data)
 {
 	u8 *mbr_done_tf = data;
-	int err = 0;
+	int err;
 
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
+	err = cmd_start(dev, opaluid[OPAL_MBRCONTROL],
+			opalmethod[OPAL_SET]);
 
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, opaluid[OPAL_MBRCONTROL],
-			     OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
-	add_token_u8(&err, dev, OPAL_STARTLIST);
 	add_token_u8(&err, dev, OPAL_STARTNAME);
 	add_token_u8(&err, dev, OPAL_VALUES);
 	add_token_u8(&err, dev, OPAL_STARTLIST);
 	add_token_u8(&err, dev, OPAL_STARTNAME);
-	add_token_u8(&err, dev, 2); /* Done */
+	add_token_u8(&err, dev, OPAL_MBRDONE);
 	add_token_u8(&err, dev, *mbr_done_tf); /* Done T or F */
 	add_token_u8(&err, dev, OPAL_ENDNAME);
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
 		pr_debug("Error Building set MBR Done command\n");
@@ -1520,26 +1502,20 @@ static int set_mbr_done(struct opal_dev *dev, void *data)
 static int set_mbr_enable_disable(struct opal_dev *dev, void *data)
 {
 	u8 *mbr_en_dis = data;
-	int err = 0;
+	int err;
 
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
+	err = cmd_start(dev, opaluid[OPAL_MBRCONTROL],
+			opalmethod[OPAL_SET]);
 
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, opaluid[OPAL_MBRCONTROL],
-			     OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
-	add_token_u8(&err, dev, OPAL_STARTLIST);
 	add_token_u8(&err, dev, OPAL_STARTNAME);
 	add_token_u8(&err, dev, OPAL_VALUES);
 	add_token_u8(&err, dev, OPAL_STARTLIST);
 	add_token_u8(&err, dev, OPAL_STARTNAME);
-	add_token_u8(&err, dev, 1);
+	add_token_u8(&err, dev, OPAL_MBRENABLE);
 	add_token_u8(&err, dev, *mbr_en_dis);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
 		pr_debug("Error Building set MBR done command\n");
@@ -1552,26 +1528,19 @@ static int set_mbr_enable_disable(struct opal_dev *dev, void *data)
 static int generic_pw_cmd(u8 *key, size_t key_len, u8 *cpin_uid,
 			  struct opal_dev *dev)
 {
-	int err = 0;
+	int err;
 
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
+	err = cmd_start(dev, cpin_uid, opalmethod[OPAL_SET]);
 
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, cpin_uid, OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_SET],
-			     OPAL_UID_LENGTH);
-	add_token_u8(&err, dev, OPAL_STARTLIST);
 	add_token_u8(&err, dev, OPAL_STARTNAME);
 	add_token_u8(&err, dev, OPAL_VALUES);
 	add_token_u8(&err, dev, OPAL_STARTLIST);
 	add_token_u8(&err, dev, OPAL_STARTNAME);
-	add_token_u8(&err, dev, 3); /* PIN */
+	add_token_u8(&err, dev, OPAL_PIN);
 	add_token_bytestring(&err, dev, key, key_len);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	return err;
 }
@@ -1619,10 +1588,7 @@ static int add_user_to_lr(struct opal_dev *dev, void *data)
 	u8 lr_buffer[OPAL_UID_LENGTH];
 	u8 user_uid[OPAL_UID_LENGTH];
 	struct opal_lock_unlock *lkul = data;
-	int err = 0;
-
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
+	int err;
 
 	memcpy(lr_buffer, opaluid[OPAL_LOCKINGRANGE_ACE_RDLOCKED],
 	       OPAL_UID_LENGTH);
@@ -1637,12 +1603,8 @@ static int add_user_to_lr(struct opal_dev *dev, void *data)
 
 	user_uid[7] = lkul->session.who;
 
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, lr_buffer, OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_SET],
-			     OPAL_UID_LENGTH);
+	err = cmd_start(dev, lr_buffer, opalmethod[OPAL_SET]);
 
-	add_token_u8(&err, dev, OPAL_STARTLIST);
 	add_token_u8(&err, dev, OPAL_STARTNAME);
 	add_token_u8(&err, dev, OPAL_VALUES);
 
@@ -1680,7 +1642,6 @@ static int add_user_to_lr(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDNAME);
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
 		pr_debug("Error building add user to locking range command.\n");
@@ -1697,9 +1658,6 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 	u8 read_locked = 1, write_locked = 1;
 	int err = 0;
 
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
-
 	if (build_locking_range(lr_buffer, sizeof(lr_buffer),
 				lkul->session.opal_key.lr) < 0)
 		return -ERANGE;
@@ -1714,17 +1672,15 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 		write_locked = 0;
 		break;
 	case OPAL_LK:
-		/* vars are initalized to locked */
+		/* vars are initialized to locked */
 		break;
 	default:
 		pr_debug("Tried to set an invalid locking state... returning to uland\n");
 		return OPAL_INVAL_PARAM;
 	}
 
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, lr_buffer, OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
-	add_token_u8(&err, dev, OPAL_STARTLIST);
+	err = cmd_start(dev, lr_buffer, opalmethod[OPAL_SET]);
+
 	add_token_u8(&err, dev, OPAL_STARTNAME);
 	add_token_u8(&err, dev, OPAL_VALUES);
 	add_token_u8(&err, dev, OPAL_STARTLIST);
@@ -1741,7 +1697,6 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
 		pr_debug("Error building SET command.\n");
@@ -1775,7 +1730,7 @@ static int lock_unlock_locking_range_sum(struct opal_dev *dev, void *data)
 		write_locked = 0;
 		break;
 	case OPAL_LK:
-		/* vars are initalized to locked */
+		/* vars are initialized to locked */
 		break;
 	default:
 		pr_debug("Tried to set an invalid locking state.\n");
@@ -1796,17 +1751,10 @@ static int activate_lsp(struct opal_dev *dev, void *data)
 	struct opal_lr_act *opal_act = data;
 	u8 user_lr[OPAL_UID_LENGTH];
 	u8 uint_3 = 0x83;
-	int err = 0, i;
-
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
-
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, opaluid[OPAL_LOCKINGSP_UID],
-			     OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_ACTIVATE],
-			     OPAL_UID_LENGTH);
+	int err, i;
 
+	err = cmd_start(dev, opaluid[OPAL_LOCKINGSP_UID],
+			opalmethod[OPAL_ACTIVATE]);
 
 	if (opal_act->sum) {
 		err = build_locking_range(user_lr, sizeof(user_lr),
@@ -1814,7 +1762,6 @@ static int activate_lsp(struct opal_dev *dev, void *data)
 		if (err)
 			return err;
 
-		add_token_u8(&err, dev, OPAL_STARTLIST);
 		add_token_u8(&err, dev, OPAL_STARTNAME);
 		add_token_u8(&err, dev, uint_3);
 		add_token_u8(&err, dev, 6);
@@ -1829,11 +1776,6 @@ static int activate_lsp(struct opal_dev *dev, void *data)
 		}
 		add_token_u8(&err, dev, OPAL_ENDLIST);
 		add_token_u8(&err, dev, OPAL_ENDNAME);
-		add_token_u8(&err, dev, OPAL_ENDLIST);
-
-	} else {
-		add_token_u8(&err, dev, OPAL_STARTLIST);
-		add_token_u8(&err, dev, OPAL_ENDLIST);
 	}
 
 	if (err) {
@@ -1844,17 +1786,19 @@ static int activate_lsp(struct opal_dev *dev, void *data)
 	return finalize_and_send(dev, parse_and_check_status);
 }
 
-static int get_lsp_lifecycle_cont(struct opal_dev *dev)
+/* Determine if we're in the Manufactured Inactive or Active state */
+static int get_lsp_lifecycle(struct opal_dev *dev, void *data)
 {
 	u8 lc_status;
-	int error = 0;
+	int err;
 
-	error = parse_and_check_status(dev);
-	if (error)
-		return error;
+	err = generic_get_column(dev, opaluid[OPAL_LOCKINGSP_UID],
+				 OPAL_LIFECYCLE);
+	if (err)
+		return err;
 
 	lc_status = response_get_u64(&dev->parsed, 4);
-	/* 0x08 is Manufacured Inactive */
+	/* 0x08 is Manufactured Inactive */
 	/* 0x09 is Manufactured */
 	if (lc_status != OPAL_MANUFACTURED_INACTIVE) {
 		pr_debug("Couldn't determine the status of the Lifecycle state\n");
@@ -1864,56 +1808,19 @@ static int get_lsp_lifecycle_cont(struct opal_dev *dev)
 	return 0;
 }
 
-/* Determine if we're in the Manufactured Inactive or Active state */
-static int get_lsp_lifecycle(struct opal_dev *dev, void *data)
-{
-	int err = 0;
-
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
-
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, opaluid[OPAL_LOCKINGSP_UID],
-			     OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_GET], OPAL_UID_LENGTH);
-
-	add_token_u8(&err, dev, OPAL_STARTLIST);
-	add_token_u8(&err, dev, OPAL_STARTLIST);
-
-	add_token_u8(&err, dev, OPAL_STARTNAME);
-	add_token_u8(&err, dev, 3); /* Start Column */
-	add_token_u8(&err, dev, 6); /* Lifecycle Column */
-	add_token_u8(&err, dev, OPAL_ENDNAME);
-
-	add_token_u8(&err, dev, OPAL_STARTNAME);
-	add_token_u8(&err, dev, 4); /* End Column */
-	add_token_u8(&err, dev, 6); /* Lifecycle Column */
-	add_token_u8(&err, dev, OPAL_ENDNAME);
-
-	add_token_u8(&err, dev, OPAL_ENDLIST);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
-
-	if (err) {
-		pr_debug("Error Building GET Lifecycle Status command\n");
-		return err;
-	}
-
-	return finalize_and_send(dev, get_lsp_lifecycle_cont);
-}
-
-static int get_msid_cpin_pin_cont(struct opal_dev *dev)
+static int get_msid_cpin_pin(struct opal_dev *dev, void *data)
 {
 	const char *msid_pin;
 	size_t strlen;
-	int error = 0;
+	int err;
 
-	error = parse_and_check_status(dev);
-	if (error)
-		return error;
+	err = generic_get_column(dev, opaluid[OPAL_C_PIN_MSID], OPAL_PIN);
+	if (err)
+		return err;
 
 	strlen = response_get_string(&dev->parsed, 4, &msid_pin);
 	if (!msid_pin) {
-		pr_debug("%s: Couldn't extract PIN from response\n", __func__);
+		pr_debug("Couldn't extract MSID_CPIN from response\n");
 		return OPAL_INVAL_PARAM;
 	}
 
@@ -1926,42 +1833,6 @@ static int get_msid_cpin_pin_cont(struct opal_dev *dev)
 	return 0;
 }
 
-static int get_msid_cpin_pin(struct opal_dev *dev, void *data)
-{
-	int err = 0;
-
-	clear_opal_cmd(dev);
-	set_comid(dev, dev->comid);
-
-	add_token_u8(&err, dev, OPAL_CALL);
-	add_token_bytestring(&err, dev, opaluid[OPAL_C_PIN_MSID],
-			     OPAL_UID_LENGTH);
-	add_token_bytestring(&err, dev, opalmethod[OPAL_GET], OPAL_UID_LENGTH);
-
-	add_token_u8(&err, dev, OPAL_STARTLIST);
-	add_token_u8(&err, dev, OPAL_STARTLIST);
-
-	add_token_u8(&err, dev, OPAL_STARTNAME);
-	add_token_u8(&err, dev, 3); /* Start Column */
-	add_token_u8(&err, dev, 3); /* PIN */
-	add_token_u8(&err, dev, OPAL_ENDNAME);
-
-	add_token_u8(&err, dev, OPAL_STARTNAME);
-	add_token_u8(&err, dev, 4); /* End Column */
-	add_token_u8(&err, dev, 3); /* Lifecycle Column */
-	add_token_u8(&err, dev, OPAL_ENDNAME);
-
-	add_token_u8(&err, dev, OPAL_ENDLIST);
-	add_token_u8(&err, dev, OPAL_ENDLIST);
-
-	if (err) {
-		pr_debug("Error building Get MSID CPIN PIN command.\n");
-		return err;
-	}
-
-	return finalize_and_send(dev, get_msid_cpin_pin_cont);
-}
-
 static int end_opal_session(struct opal_dev *dev, void *data)
 {
 	int err = 0;
@@ -1977,18 +1848,14 @@ static int end_opal_session(struct opal_dev *dev, void *data)
 
 static int end_opal_session_error(struct opal_dev *dev)
 {
-	const struct opal_step error_end_session[] = {
-		{ end_opal_session, },
-		{ NULL, }
+	const struct opal_step error_end_session = {
+		end_opal_session,
 	};
-	dev->steps = error_end_session;
-	return next(dev);
+	return execute_step(dev, &error_end_session, 0);
 }
 
-static inline void setup_opal_dev(struct opal_dev *dev,
-				  const struct opal_step *steps)
+static inline void setup_opal_dev(struct opal_dev *dev)
 {
-	dev->steps = steps;
 	dev->tsn = 0;
 	dev->hsn = 0;
 	dev->prev_data = NULL;
@@ -1996,15 +1863,11 @@ static inline void setup_opal_dev(struct opal_dev *dev,
 
 static int check_opal_support(struct opal_dev *dev)
 {
-	const struct opal_step steps[] = {
-		{ opal_discovery0, },
-		{ NULL, }
-	};
 	int ret;
 
 	mutex_lock(&dev->dev_lock);
-	setup_opal_dev(dev, steps);
-	ret = next(dev);
+	setup_opal_dev(dev);
+	ret = opal_discovery0_step(dev);
 	dev->supported = !ret;
 	mutex_unlock(&dev->dev_lock);
 	return ret;
@@ -2057,18 +1920,16 @@ static int opal_secure_erase_locking_range(struct opal_dev *dev,
 					   struct opal_session_info *opal_session)
 {
 	const struct opal_step erase_steps[] = {
-		{ opal_discovery0, },
 		{ start_auth_opal_session, opal_session },
 		{ get_active_key, &opal_session->opal_key.lr },
 		{ gen_key, },
-		{ end_opal_session, },
-		{ NULL, }
+		{ end_opal_session, }
 	};
 	int ret;
 
 	mutex_lock(&dev->dev_lock);
-	setup_opal_dev(dev, erase_steps);
-	ret = next(dev);
+	setup_opal_dev(dev);
+	ret = execute_steps(dev, erase_steps, ARRAY_SIZE(erase_steps));
 	mutex_unlock(&dev->dev_lock);
 	return ret;
 }
@@ -2077,17 +1938,15 @@ static int opal_erase_locking_range(struct opal_dev *dev,
 				    struct opal_session_info *opal_session)
 {
 	const struct opal_step erase_steps[] = {
-		{ opal_discovery0, },
 		{ start_auth_opal_session, opal_session },
 		{ erase_locking_range, opal_session },
-		{ end_opal_session, },
-		{ NULL, }
+		{ end_opal_session, }
 	};
 	int ret;
 
 	mutex_lock(&dev->dev_lock);
-	setup_opal_dev(dev, erase_steps);
-	ret = next(dev);
+	setup_opal_dev(dev);
+	ret = execute_steps(dev, erase_steps, ARRAY_SIZE(erase_steps));
 	mutex_unlock(&dev->dev_lock);
 	return ret;
 }
@@ -2095,15 +1954,16 @@ static int opal_erase_locking_range(struct opal_dev *dev,
 static int opal_enable_disable_shadow_mbr(struct opal_dev *dev,
 					  struct opal_mbr_data *opal_mbr)
 {
+	u8 enable_disable = opal_mbr->enable_disable == OPAL_MBR_ENABLE ?
+		OPAL_TRUE : OPAL_FALSE;
+
 	const struct opal_step mbr_steps[] = {
-		{ opal_discovery0, },
 		{ start_admin1LSP_opal_session, &opal_mbr->key },
-		{ set_mbr_done, &opal_mbr->enable_disable },
+		{ set_mbr_done, &enable_disable },
 		{ end_opal_session, },
 		{ start_admin1LSP_opal_session, &opal_mbr->key },
-		{ set_mbr_enable_disable, &opal_mbr->enable_disable },
-		{ end_opal_session, },
-		{ NULL, }
+		{ set_mbr_enable_disable, &enable_disable },
+		{ end_opal_session, }
 	};
 	int ret;
 
@@ -2112,8 +1972,8 @@ static int opal_enable_disable_shadow_mbr(struct opal_dev *dev,
 		return -EINVAL;
 
 	mutex_lock(&dev->dev_lock);
-	setup_opal_dev(dev, mbr_steps);
-	ret = next(dev);
+	setup_opal_dev(dev);
+	ret = execute_steps(dev, mbr_steps, ARRAY_SIZE(mbr_steps));
 	mutex_unlock(&dev->dev_lock);
 	return ret;
 }
@@ -2130,7 +1990,7 @@ static int opal_save(struct opal_dev *dev, struct opal_lock_unlock *lk_unlk)
 	suspend->lr = lk_unlk->session.opal_key.lr;
 
 	mutex_lock(&dev->dev_lock);
-	setup_opal_dev(dev, NULL);
+	setup_opal_dev(dev);
 	add_suspend_info(dev, suspend);
 	mutex_unlock(&dev->dev_lock);
 	return 0;
@@ -2140,11 +2000,9 @@ static int opal_add_user_to_lr(struct opal_dev *dev,
 			       struct opal_lock_unlock *lk_unlk)
 {
 	const struct opal_step steps[] = {
-		{ opal_discovery0, },
 		{ start_admin1LSP_opal_session, &lk_unlk->session.opal_key },
 		{ add_user_to_lr, lk_unlk },
-		{ end_opal_session, },
-		{ NULL, }
+		{ end_opal_session, }
 	};
 	int ret;
 
@@ -2166,8 +2024,8 @@ static int opal_add_user_to_lr(struct opal_dev *dev,
 	}
 
 	mutex_lock(&dev->dev_lock);
-	setup_opal_dev(dev, steps);
-	ret = next(dev);
+	setup_opal_dev(dev);
+	ret = execute_steps(dev, steps, ARRAY_SIZE(steps));
 	mutex_unlock(&dev->dev_lock);
 	return ret;
 }
@@ -2175,16 +2033,14 @@ static int opal_add_user_to_lr(struct opal_dev *dev,
 static int opal_reverttper(struct opal_dev *dev, struct opal_key *opal)
 {
 	const struct opal_step revert_steps[] = {
-		{ opal_discovery0, },
 		{ start_SIDASP_opal_session, opal },
-		{ revert_tper, }, /* controller will terminate session */
-		{ NULL, }
+		{ revert_tper, } /* controller will terminate session */
 	};
 	int ret;
 
 	mutex_lock(&dev->dev_lock);
-	setup_opal_dev(dev, revert_steps);
-	ret = next(dev);
+	setup_opal_dev(dev);
+	ret = execute_steps(dev, revert_steps, ARRAY_SIZE(revert_steps));
 	mutex_unlock(&dev->dev_lock);
 
 	/*
@@ -2201,37 +2057,34 @@ static int __opal_lock_unlock(struct opal_dev *dev,
 			      struct opal_lock_unlock *lk_unlk)
 {
 	const struct opal_step unlock_steps[] = {
-		{ opal_discovery0, },
 		{ start_auth_opal_session, &lk_unlk->session },
 		{ lock_unlock_locking_range, lk_unlk },
-		{ end_opal_session, },
-		{ NULL, }
+		{ end_opal_session, }
 	};
 	const struct opal_step unlock_sum_steps[] = {
-		{ opal_discovery0, },
 		{ start_auth_opal_session, &lk_unlk->session },
 		{ lock_unlock_locking_range_sum, lk_unlk },
-		{ end_opal_session, },
-		{ NULL, }
+		{ end_opal_session, }
 	};
 
-	dev->steps = lk_unlk->session.sum ? unlock_sum_steps : unlock_steps;
-	return next(dev);
+	if (lk_unlk->session.sum)
+		return execute_steps(dev, unlock_sum_steps,
+				     ARRAY_SIZE(unlock_sum_steps));
+	else
+		return execute_steps(dev, unlock_steps,
+				     ARRAY_SIZE(unlock_steps));
 }
 
 static int __opal_set_mbr_done(struct opal_dev *dev, struct opal_key *key)
 {
-	u8 mbr_done_tf = 1;
-	const struct opal_step mbrdone_step [] = {
-		{ opal_discovery0, },
+	u8 mbr_done_tf = OPAL_TRUE;
+	const struct opal_step mbrdone_step[] = {
 		{ start_admin1LSP_opal_session, key },
 		{ set_mbr_done, &mbr_done_tf },
-		{ end_opal_session, },
-		{ NULL, }
+		{ end_opal_session, }
 	};
 
-	dev->steps = mbrdone_step;
-	return next(dev);
+	return execute_steps(dev, mbrdone_step, ARRAY_SIZE(mbrdone_step));
 }
 
 static int opal_lock_unlock(struct opal_dev *dev,
@@ -2252,14 +2105,12 @@ static int opal_lock_unlock(struct opal_dev *dev,
 static int opal_take_ownership(struct opal_dev *dev, struct opal_key *opal)
 {
 	const struct opal_step owner_steps[] = {
-		{ opal_discovery0, },
 		{ start_anybodyASP_opal_session, },
 		{ get_msid_cpin_pin, },
 		{ end_opal_session, },
 		{ start_SIDASP_opal_session, opal },
 		{ set_sid_cpin_pin, opal },
-		{ end_opal_session, },
-		{ NULL, }
+		{ end_opal_session, }
 	};
 	int ret;
 
@@ -2267,21 +2118,20 @@ static int opal_take_ownership(struct opal_dev *dev, struct opal_key *opal)
 		return -ENODEV;
 
 	mutex_lock(&dev->dev_lock);
-	setup_opal_dev(dev, owner_steps);
-	ret = next(dev);
+	setup_opal_dev(dev);
+	ret = execute_steps(dev, owner_steps, ARRAY_SIZE(owner_steps));
 	mutex_unlock(&dev->dev_lock);
 	return ret;
 }
 
-static int opal_activate_lsp(struct opal_dev *dev, struct opal_lr_act *opal_lr_act)
+static int opal_activate_lsp(struct opal_dev *dev,
+			     struct opal_lr_act *opal_lr_act)
 {
 	const struct opal_step active_steps[] = {
-		{ opal_discovery0, },
 		{ start_SIDASP_opal_session, &opal_lr_act->key },
 		{ get_lsp_lifecycle, },
 		{ activate_lsp, opal_lr_act },
-		{ end_opal_session, },
-		{ NULL, }
+		{ end_opal_session, }
 	};
 	int ret;
 
@@ -2289,8 +2139,8 @@ static int opal_activate_lsp(struct opal_dev *dev, struct opal_lr_act *opal_lr_a
 		return -EINVAL;
 
 	mutex_lock(&dev->dev_lock);
-	setup_opal_dev(dev, active_steps);
-	ret = next(dev);
+	setup_opal_dev(dev);
+	ret = execute_steps(dev, active_steps, ARRAY_SIZE(active_steps));
 	mutex_unlock(&dev->dev_lock);
 	return ret;
 }
@@ -2299,17 +2149,15 @@ static int opal_setup_locking_range(struct opal_dev *dev,
 				    struct opal_user_lr_setup *opal_lrs)
 {
 	const struct opal_step lr_steps[] = {
-		{ opal_discovery0, },
 		{ start_auth_opal_session, &opal_lrs->session },
 		{ setup_locking_range, opal_lrs },
-		{ end_opal_session, },
-		{ NULL, }
+		{ end_opal_session, }
 	};
 	int ret;
 
 	mutex_lock(&dev->dev_lock);
-	setup_opal_dev(dev, lr_steps);
-	ret = next(dev);
+	setup_opal_dev(dev);
+	ret = execute_steps(dev, lr_steps, ARRAY_SIZE(lr_steps));
 	mutex_unlock(&dev->dev_lock);
 	return ret;
 }
@@ -2317,11 +2165,9 @@ static int opal_setup_locking_range(struct opal_dev *dev,
 static int opal_set_new_pw(struct opal_dev *dev, struct opal_new_pw *opal_pw)
 {
 	const struct opal_step pw_steps[] = {
-		{ opal_discovery0, },
 		{ start_auth_opal_session, &opal_pw->session },
 		{ set_new_pw, &opal_pw->new_user_pw },
-		{ end_opal_session, },
-		{ NULL }
+		{ end_opal_session, }
 	};
 	int ret;
 
@@ -2332,8 +2178,8 @@ static int opal_set_new_pw(struct opal_dev *dev, struct opal_new_pw *opal_pw)
 		return -EINVAL;
 
 	mutex_lock(&dev->dev_lock);
-	setup_opal_dev(dev, pw_steps);
-	ret = next(dev);
+	setup_opal_dev(dev);
+	ret = execute_steps(dev, pw_steps, ARRAY_SIZE(pw_steps));
 	mutex_unlock(&dev->dev_lock);
 	return ret;
 }
@@ -2342,11 +2188,9 @@ static int opal_activate_user(struct opal_dev *dev,
 			      struct opal_session_info *opal_session)
 {
 	const struct opal_step act_steps[] = {
-		{ opal_discovery0, },
 		{ start_admin1LSP_opal_session, &opal_session->opal_key },
 		{ internal_activate_user, opal_session },
-		{ end_opal_session, },
-		{ NULL, }
+		{ end_opal_session, }
 	};
 	int ret;
 
@@ -2358,8 +2202,8 @@ static int opal_activate_user(struct opal_dev *dev,
 	}
 
 	mutex_lock(&dev->dev_lock);
-	setup_opal_dev(dev, act_steps);
-	ret = next(dev);
+	setup_opal_dev(dev);
+	ret = execute_steps(dev, act_steps, ARRAY_SIZE(act_steps));
 	mutex_unlock(&dev->dev_lock);
 	return ret;
 }
@@ -2376,7 +2220,7 @@ bool opal_unlock_from_suspend(struct opal_dev *dev)
 		return false;
 
 	mutex_lock(&dev->dev_lock);
-	setup_opal_dev(dev, NULL);
+	setup_opal_dev(dev);
 
 	list_for_each_entry(suspend, &dev->unlk_lst, node) {
 		dev->tsn = 0;
diff --git a/block/t10-pi.c b/block/t10-pi.c
index 62aed77d0bb9..0c0094609dd6 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -1,24 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * t10_pi.c - Functions for generating and verifying T10 Protection
  *	      Information.
- *
- * Copyright (C) 2007, 2008, 2014 Oracle Corporation
- * Written by: Martin K. Petersen <martin.petersen@oracle.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; see the file COPYING.  If not, write to
- * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139,
- * USA.
- *
  */
 
 #include <linux/t10-pi.h>