Merge tag 'for-6.3/block-2023-02-16' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe updates via Christoph:
      - Small improvements to the logging functionality (Amit Engel)
      - Authentication cleanups (Hannes Reinecke)
      - Cleanup and optimize the DMA mapping cod in the PCIe driver
        (Keith Busch)
      - Work around the command effects for Format NVM (Keith Busch)
      - Misc cleanups (Keith Busch, Christoph Hellwig)
      - Fix and cleanup freeing single sgl (Keith Busch)

 - MD updates via Song:
      - Fix a rare crash during the takeover process
      - Don't update recovery_cp when curr_resync is ACTIVE
      - Free writes_pending in md_stop
      - Change active_io to percpu

 - Updates to drbd, inching us closer to unifying the out-of-tree driver
   with the in-tree one (Andreas, Christoph, Lars, Robert)

 - BFQ update adding support for multi-actuator drives (Paolo, Federico,
   Davide)

 - Make brd compliant with REQ_NOWAIT (me)

 - Fix for IOPOLL and queue entering, fixing stalled IO waiting on
   timeouts (me)

 - Fix for REQ_NOWAIT with multiple bios (me)

 - Fix memory leak in blktrace cleanup (Greg)

 - Clean up sbitmap and fix a potential hang (Kemeng)

 - Clean up some bits in BFQ, and fix a bug in the request injection
   (Kemeng)

 - Clean up the request allocation and issue code, and fix some bugs
   related to that (Kemeng)

 - ublk updates and fixes:
      - Add support for unprivileged ublk (Ming)
      - Improve device deletion handling (Ming)
      - Misc (Liu, Ziyang)

 - s390 dasd fixes (Alexander, Qiheng)

 - Improve utility of request caching and fixes (Anuj, Xiao)

 - zoned cleanups (Pankaj)

 - More constification for kobjs (Thomas)

 - blk-iocost cleanups (Yu)

 - Remove bio splitting from drivers that don't need it (Christoph)

 - Switch blk-cgroups to use struct gendisk. Some of this is now
   incomplete as select late reverts were done. (Christoph)

 - Add bvec initialization helpers, and convert callers to use that
   rather than open-coding it (Christoph)

 - Misc fixes and cleanups (Jinke, Keith, Arnd, Bart, Li, Martin,
   Matthew, Ulf, Zhong)

* tag 'for-6.3/block-2023-02-16' of git://git.kernel.dk/linux: (169 commits)
  brd: use radix_tree_maybe_preload instead of radix_tree_preload
  block: use proper return value from bio_failfast()
  block: bio-integrity: Copy flags when bio_integrity_payload is cloned
  block: Fix io statistics for cgroup in throttle path
  brd: mark as nowait compatible
  brd: check for REQ_NOWAIT and set correct page allocation mask
  brd: return 0/-error from brd_insert_page()
  block: sync mixed merged request's failfast with 1st bio's
  Revert "blk-cgroup: pin the gendisk in struct blkcg_gq"
  Revert "blk-cgroup: pass a gendisk to blkg_lookup"
  Revert "blk-cgroup: delay blk-cgroup initialization until add_disk"
  Revert "blk-cgroup: delay calling blkcg_exit_disk until disk_release"
  Revert "blk-cgroup: move the cgroup information to struct gendisk"
  nvme-pci: remove iod use_sgls
  nvme-pci: fix freeing single sgl
  block: ublk: check IO buffer based on flag need_get_data
  s390/dasd: Fix potential memleak in dasd_eckd_init()
  s390/dasd: sort out physical vs virtual pointers usage
  block: Remove the ALLOC_CACHE_SLACK constant
  block: make kobj_type structures constant
  ...

34 files changed, 1128 insertions, 780 deletions

diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 615516146086..27f11320b8d1 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -30,6 +30,7 @@ config IOSCHED_BFQ
 config BFQ_GROUP_IOSCHED
        bool "BFQ hierarchical scheduling support"
        depends on IOSCHED_BFQ && BLK_CGROUP
+       default y
        select BLK_CGROUP_RWSTAT
 	help
 
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 0fbde0fc0628..89ffb3aa992c 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -513,12 +513,12 @@ static void bfq_cpd_free(struct blkcg_policy_data *cpd)
 	kfree(cpd_to_bfqgd(cpd));
 }
 
-static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, struct request_queue *q,
-					     struct blkcg *blkcg)
+static struct blkg_policy_data *bfq_pd_alloc(struct gendisk *disk,
+		struct blkcg *blkcg, gfp_t gfp)
 {
 	struct bfq_group *bfqg;
 
-	bfqg = kzalloc_node(sizeof(*bfqg), gfp, q->node);
+	bfqg = kzalloc_node(sizeof(*bfqg), gfp, disk->node_id);
 	if (!bfqg)
 		return NULL;
 
@@ -551,7 +551,6 @@ static void bfq_pd_init(struct blkg_policy_data *pd)
 	bfqg->bfqd = bfqd;
 	bfqg->active_entities = 0;
 	bfqg->num_queues_with_pending_reqs = 0;
-	bfqg->online = true;
 	bfqg->rq_pos_tree = RB_ROOT;
 }
 
@@ -614,7 +613,7 @@ struct bfq_group *bfq_bio_bfqg(struct bfq_data *bfqd, struct bio *bio)
 			continue;
 		}
 		bfqg = blkg_to_bfqg(blkg);
-		if (bfqg->online) {
+		if (bfqg->pd.online) {
 			bio_associate_blkg_from_css(bio, &blkg->blkcg->css);
 			return bfqg;
 		}
@@ -706,12 +705,52 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		bfq_activate_bfqq(bfqd, bfqq);
 	}
 
-	if (!bfqd->in_service_queue && !bfqd->rq_in_driver)
+	if (!bfqd->in_service_queue && !bfqd->tot_rq_in_driver)
 		bfq_schedule_dispatch(bfqd);
 	/* release extra ref taken above, bfqq may happen to be freed now */
 	bfq_put_queue(bfqq);
 }
 
+static void bfq_sync_bfqq_move(struct bfq_data *bfqd,
+			       struct bfq_queue *sync_bfqq,
+			       struct bfq_io_cq *bic,
+			       struct bfq_group *bfqg,
+			       unsigned int act_idx)
+{
+	struct bfq_queue *bfqq;
+
+	if (!sync_bfqq->new_bfqq && !bfq_bfqq_coop(sync_bfqq)) {
+		/* We are the only user of this bfqq, just move it */
+		if (sync_bfqq->entity.sched_data != &bfqg->sched_data)
+			bfq_bfqq_move(bfqd, sync_bfqq, bfqg);
+		return;
+	}
+
+	/*
+	 * The queue was merged to a different queue. Check
+	 * that the merge chain still belongs to the same
+	 * cgroup.
+	 */
+	for (bfqq = sync_bfqq; bfqq; bfqq = bfqq->new_bfqq)
+		if (bfqq->entity.sched_data != &bfqg->sched_data)
+			break;
+	if (bfqq) {
+		/*
+		 * Some queue changed cgroup so the merge is not valid
+		 * anymore. We cannot easily just cancel the merge (by
+		 * clearing new_bfqq) as there may be other processes
+		 * using this queue and holding refs to all queues
+		 * below sync_bfqq->new_bfqq. Similarly if the merge
+		 * already happened, we need to detach from bfqq now
+		 * so that we cannot merge bio to a request from the
+		 * old cgroup.
+		 */
+		bfq_put_cooperator(sync_bfqq);
+		bic_set_bfqq(bic, NULL, true, act_idx);
+		bfq_release_process_ref(bfqd, sync_bfqq);
+	}
+}
+
 /**
  * __bfq_bic_change_cgroup - move @bic to @bfqg.
  * @bfqd: the queue descriptor.
@@ -726,53 +765,20 @@ static void __bfq_bic_change_cgroup(struct bfq_data *bfqd,
 				    struct bfq_io_cq *bic,
 				    struct bfq_group *bfqg)
 {
-	struct bfq_queue *async_bfqq = bic_to_bfqq(bic, false);
-	struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, true);
-	struct bfq_entity *entity;
+	unsigned int act_idx;
 
-	if (async_bfqq) {
-		entity = &async_bfqq->entity;
+	for (act_idx = 0; act_idx < bfqd->num_actuators; act_idx++) {
+		struct bfq_queue *async_bfqq = bic_to_bfqq(bic, false, act_idx);
+		struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, true, act_idx);
 
-		if (entity->sched_data != &bfqg->sched_data) {
-			bic_set_bfqq(bic, NULL, false);
+		if (async_bfqq &&
+		    async_bfqq->entity.sched_data != &bfqg->sched_data) {
+			bic_set_bfqq(bic, NULL, false, act_idx);
 			bfq_release_process_ref(bfqd, async_bfqq);
 		}
-	}
 
-	if (sync_bfqq) {
-		if (!sync_bfqq->new_bfqq && !bfq_bfqq_coop(sync_bfqq)) {
-			/* We are the only user of this bfqq, just move it */
-			if (sync_bfqq->entity.sched_data != &bfqg->sched_data)
-				bfq_bfqq_move(bfqd, sync_bfqq, bfqg);
-		} else {
-			struct bfq_queue *bfqq;
-
-			/*
-			 * The queue was merged to a different queue. Check
-			 * that the merge chain still belongs to the same
-			 * cgroup.
-			 */
-			for (bfqq = sync_bfqq; bfqq; bfqq = bfqq->new_bfqq)
-				if (bfqq->entity.sched_data !=
-				    &bfqg->sched_data)
-					break;
-			if (bfqq) {
-				/*
-				 * Some queue changed cgroup so the merge is
-				 * not valid anymore. We cannot easily just
-				 * cancel the merge (by clearing new_bfqq) as
-				 * there may be other processes using this
-				 * queue and holding refs to all queues below
-				 * sync_bfqq->new_bfqq. Similarly if the merge
-				 * already happened, we need to detach from
-				 * bfqq now so that we cannot merge bio to a
-				 * request from the old cgroup.
-				 */
-				bfq_put_cooperator(sync_bfqq);
-				bic_set_bfqq(bic, NULL, true);
-				bfq_release_process_ref(bfqd, sync_bfqq);
-			}
-		}
+		if (sync_bfqq)
+			bfq_sync_bfqq_move(bfqd, sync_bfqq, bic, bfqg, act_idx);
 	}
 }
 
@@ -978,7 +984,6 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 
 put_async_queues:
 	bfq_put_async_queues(bfqd, bfqg);
-	bfqg->online = false;
 
 	spin_unlock_irqrestore(&bfqd->lock, flags);
 	/*
@@ -1284,7 +1289,7 @@ struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
 {
 	int ret;
 
-	ret = blkcg_activate_policy(bfqd->queue, &blkcg_policy_bfq);
+	ret = blkcg_activate_policy(bfqd->queue->disk, &blkcg_policy_bfq);
 	if (ret)
 		return NULL;
 
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 380e9bda2e57..8a8d4441519c 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -377,20 +377,23 @@ static const unsigned long bfq_late_stable_merging = 600;
 #define RQ_BIC(rq)		((struct bfq_io_cq *)((rq)->elv.priv[0]))
 #define RQ_BFQQ(rq)		((rq)->elv.priv[1])
 
-struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync)
+struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync,
+			      unsigned int actuator_idx)
 {
-	return bic->bfqq[is_sync];
+	if (is_sync)
+		return bic->bfqq[1][actuator_idx];
+
+	return bic->bfqq[0][actuator_idx];
 }
 
 static void bfq_put_stable_ref(struct bfq_queue *bfqq);
 
-void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync)
+void bic_set_bfqq(struct bfq_io_cq *bic,
+		  struct bfq_queue *bfqq,
+		  bool is_sync,
+		  unsigned int actuator_idx)
 {
-	struct bfq_queue *old_bfqq = bic->bfqq[is_sync];
-
-	/* Clear bic pointer if bfqq is detached from this bic */
-	if (old_bfqq && old_bfqq->bic == bic)
-		old_bfqq->bic = NULL;
+	struct bfq_queue *old_bfqq = bic->bfqq[is_sync][actuator_idx];
 
 	/*
 	 * If bfqq != NULL, then a non-stable queue merge between
@@ -405,9 +408,18 @@ void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync)
 	 * we cancel the stable merge if
 	 * bic->stable_merge_bfqq == bfqq.
 	 */
-	bic->bfqq[is_sync] = bfqq;
+	struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[actuator_idx];
+
+	/* Clear bic pointer if bfqq is detached from this bic */
+	if (old_bfqq && old_bfqq->bic == bic)
+		old_bfqq->bic = NULL;
 
-	if (bfqq && bic->stable_merge_bfqq == bfqq) {
+	if (is_sync)
+		bic->bfqq[1][actuator_idx] = bfqq;
+	else
+		bic->bfqq[0][actuator_idx] = bfqq;
+
+	if (bfqq && bfqq_data->stable_merge_bfqq == bfqq) {
 		/*
 		 * Actually, these same instructions are executed also
 		 * in bfq_setup_cooperator, in case of abort or actual
@@ -416,9 +428,9 @@ void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync)
 		 * did so, we would nest even more complexity in this
 		 * function.
 		 */
-		bfq_put_stable_ref(bic->stable_merge_bfqq);
+		bfq_put_stable_ref(bfqq_data->stable_merge_bfqq);
 
-		bic->stable_merge_bfqq = NULL;
+		bfqq_data->stable_merge_bfqq = NULL;
 	}
 }
 
@@ -678,9 +690,9 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 {
 	struct bfq_data *bfqd = data->q->elevator->elevator_data;
 	struct bfq_io_cq *bic = bfq_bic_lookup(data->q);
-	struct bfq_queue *bfqq = bic ? bic_to_bfqq(bic, op_is_sync(opf)) : NULL;
 	int depth;
 	unsigned limit = data->q->nr_requests;
+	unsigned int act_idx;
 
 	/* Sync reads have full depth available */
 	if (op_is_sync(opf) && !op_is_write(opf)) {
@@ -690,14 +702,21 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 		limit = (limit * depth) >> bfqd->full_depth_shift;
 	}
 
-	/*
-	 * Does queue (or any parent entity) exceed number of requests that
-	 * should be available to it? Heavily limit depth so that it cannot
-	 * consume more available requests and thus starve other entities.
-	 */
-	if (bfqq && bfqq_request_over_limit(bfqq, limit))
-		depth = 1;
+	for (act_idx = 0; bic && act_idx < bfqd->num_actuators; act_idx++) {
+		struct bfq_queue *bfqq =
+			bic_to_bfqq(bic, op_is_sync(opf), act_idx);
 
+		/*
+		 * Does queue (or any parent entity) exceed number of
+		 * requests that should be available to it? Heavily
+		 * limit depth so that it cannot consume more
+		 * available requests and thus starve other entities.
+		 */
+		if (bfqq && bfqq_request_over_limit(bfqq, limit)) {
+			depth = 1;
+			break;
+		}
+	}
 	bfq_log(bfqd, "[%s] wr_busy %d sync %d depth %u",
 		__func__, bfqd->wr_busy_queues, op_is_sync(opf), depth);
 	if (depth)
@@ -1074,9 +1093,6 @@ static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
 {
 	u64 dur;
 
-	if (bfqd->bfq_wr_max_time > 0)
-		return bfqd->bfq_wr_max_time;
-
 	dur = bfqd->rate_dur_prod;
 	do_div(dur, bfqd->peak_rate);
 
@@ -1118,36 +1134,39 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 {
 	unsigned int old_wr_coeff = 1;
 	bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq);
+	unsigned int a_idx = bfqq->actuator_idx;
+	struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[a_idx];
 
-	if (bic->saved_has_short_ttime)
+	if (bfqq_data->saved_has_short_ttime)
 		bfq_mark_bfqq_has_short_ttime(bfqq);
 	else
 		bfq_clear_bfqq_has_short_ttime(bfqq);
 
-	if (bic->saved_IO_bound)
+	if (bfqq_data->saved_IO_bound)
 		bfq_mark_bfqq_IO_bound(bfqq);
 	else
 		bfq_clear_bfqq_IO_bound(bfqq);
 
-	bfqq->last_serv_time_ns = bic->saved_last_serv_time_ns;
-	bfqq->inject_limit = bic->saved_inject_limit;
-	bfqq->decrease_time_jif = bic->saved_decrease_time_jif;
+	bfqq->last_serv_time_ns = bfqq_data->saved_last_serv_time_ns;
+	bfqq->inject_limit = bfqq_data->saved_inject_limit;
+	bfqq->decrease_time_jif = bfqq_data->saved_decrease_time_jif;
 
-	bfqq->entity.new_weight = bic->saved_weight;
-	bfqq->ttime = bic->saved_ttime;
-	bfqq->io_start_time = bic->saved_io_start_time;
-	bfqq->tot_idle_time = bic->saved_tot_idle_time;
+	bfqq->entity.new_weight = bfqq_data->saved_weight;
+	bfqq->ttime = bfqq_data->saved_ttime;
+	bfqq->io_start_time = bfqq_data->saved_io_start_time;
+	bfqq->tot_idle_time = bfqq_data->saved_tot_idle_time;
 	/*
 	 * Restore weight coefficient only if low_latency is on
 	 */
 	if (bfqd->low_latency) {
 		old_wr_coeff = bfqq->wr_coeff;
-		bfqq->wr_coeff = bic->saved_wr_coeff;
+		bfqq->wr_coeff = bfqq_data->saved_wr_coeff;
 	}
-	bfqq->service_from_wr = bic->saved_service_from_wr;
-	bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt;
-	bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish;
-	bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time;
+	bfqq->service_from_wr = bfqq_data->saved_service_from_wr;
+	bfqq->wr_start_at_switch_to_srt =
+		bfqq_data->saved_wr_start_at_switch_to_srt;
+	bfqq->last_wr_start_finish = bfqq_data->saved_last_wr_start_finish;
+	bfqq->wr_cur_max_time = bfqq_data->saved_wr_cur_max_time;
 
 	if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
 	    time_is_before_jiffies(bfqq->last_wr_start_finish +
@@ -1766,6 +1785,33 @@ static bool bfq_bfqq_higher_class_or_weight(struct bfq_queue *bfqq,
 	return bfqq_weight > in_serv_weight;
 }
 
+/*
+ * Get the index of the actuator that will serve bio.
+ */
+static unsigned int bfq_actuator_index(struct bfq_data *bfqd, struct bio *bio)
+{
+	unsigned int i;
+	sector_t end;
+
+	/* no search needed if one or zero ranges present */
+	if (bfqd->num_actuators == 1)
+		return 0;
+
+	/* bio_end_sector(bio) gives the sector after the last one */
+	end = bio_end_sector(bio) - 1;
+
+	for (i = 0; i < bfqd->num_actuators; i++) {
+		if (end >= bfqd->sector[i] &&
+		    end < bfqd->sector[i] + bfqd->nr_sectors[i])
+			return i;
+	}
+
+	WARN_ONCE(true,
+		  "bfq_actuator_index: bio sector out of ranges: end=%llu\n",
+		  end);
+	return 0;
+}
+
 static bool bfq_better_to_idle(struct bfq_queue *bfqq);
 
 static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
@@ -1785,7 +1831,9 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
 		arrived_in_time =  ktime_get_ns() <=
 			bfqq->ttime.last_end_request +
 			bfqd->bfq_slice_idle * 3;
-
+	unsigned int act_idx = bfq_actuator_index(bfqd, rq->bio);
+	bool bfqq_non_merged_or_stably_merged =
+		bfqq->bic || RQ_BIC(rq)->bfqq_data[act_idx].stably_merged;
 
 	/*
 	 * bfqq deserves to be weight-raised if:
@@ -1819,9 +1867,8 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
 	 */
 	wr_or_deserves_wr = bfqd->low_latency &&
 		(bfqq->wr_coeff > 1 ||
-		 (bfq_bfqq_sync(bfqq) &&
-		  (bfqq->bic || RQ_BIC(rq)->stably_merged) &&
-		   (*interactive || soft_rt)));
+		 (bfq_bfqq_sync(bfqq) && bfqq_non_merged_or_stably_merged &&
+		  (*interactive || soft_rt)));
 
 	/*
 	 * Using the last flag, update budget and check whether bfqq
@@ -2098,7 +2145,7 @@ static void bfq_check_waker(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	 * We reset waker detection logic also if too much time has passed
  	 * since the first detection. If wakeups are rare, pointless idling
 	 * doesn't hurt throughput that much. The condition below makes sure
-	 * we do not uselessly idle blocking waker in more than 1/64 cases. 
+	 * we do not uselessly idle blocking waker in more than 1/64 cases.
 	 */
 	if (bfqd->last_completed_rq_bfqq !=
 	    bfqq->tentative_waker_bfqq ||
@@ -2209,9 +2256,9 @@ static void bfq_add_request(struct request *rq)
 		 *   elapsed.
 		 */
 		if (bfqq == bfqd->in_service_queue &&
-		    (bfqd->rq_in_driver == 0 ||
+		    (bfqd->tot_rq_in_driver == 0 ||
 		     (bfqq->last_serv_time_ns > 0 &&
-		      bfqd->rqs_injected && bfqd->rq_in_driver > 0)) &&
+		      bfqd->rqs_injected && bfqd->tot_rq_in_driver > 0)) &&
 		    time_is_before_eq_jiffies(bfqq->decrease_time_jif +
 					      msecs_to_jiffies(10))) {
 			bfqd->last_empty_occupied_ns = ktime_get_ns();
@@ -2235,7 +2282,7 @@ static void bfq_add_request(struct request *rq)
 			 * will be set in case injection is performed
 			 * on bfqq before rq is completed).
 			 */
-			if (bfqd->rq_in_driver == 0)
+			if (bfqd->tot_rq_in_driver == 0)
 				bfqd->rqs_injected = false;
 		}
 	}
@@ -2418,7 +2465,8 @@ static bool bfq_bio_merge(struct request_queue *q, struct bio *bio,
 		 */
 		bfq_bic_update_cgroup(bic, bio);
 
-		bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf));
+		bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf),
+					     bfq_actuator_index(bfqd, bio));
 	} else {
 		bfqd->bio_bfqq = NULL;
 	}
@@ -2584,24 +2632,29 @@ static void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
 void bfq_end_wr_async_queues(struct bfq_data *bfqd,
 			     struct bfq_group *bfqg)
 {
-	int i, j;
+	int i, j, k;
 
-	for (i = 0; i < 2; i++)
-		for (j = 0; j < IOPRIO_NR_LEVELS; j++)
-			if (bfqg->async_bfqq[i][j])
-				bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]);
-	if (bfqg->async_idle_bfqq)
-		bfq_bfqq_end_wr(bfqg->async_idle_bfqq);
+	for (k = 0; k < bfqd->num_actuators; k++) {
+		for (i = 0; i < 2; i++)
+			for (j = 0; j < IOPRIO_NR_LEVELS; j++)
+				if (bfqg->async_bfqq[i][j][k])
+					bfq_bfqq_end_wr(bfqg->async_bfqq[i][j][k]);
+		if (bfqg->async_idle_bfqq[k])
+			bfq_bfqq_end_wr(bfqg->async_idle_bfqq[k]);
+	}
 }
 
 static void bfq_end_wr(struct bfq_data *bfqd)
 {
 	struct bfq_queue *bfqq;
+	int i;
 
 	spin_lock_irq(&bfqd->lock);
 
-	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
-		bfq_bfqq_end_wr(bfqq);
+	for (i = 0; i < bfqd->num_actuators; i++) {
+		list_for_each_entry(bfqq, &bfqd->active_list[i], bfqq_list)
+			bfq_bfqq_end_wr(bfqq);
+	}
 	list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list)
 		bfq_bfqq_end_wr(bfqq);
 	bfq_end_wr_async(bfqd);
@@ -2794,6 +2847,35 @@ static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq,
 static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd,
 					     struct bfq_queue *bfqq);
 
+static struct bfq_queue *
+bfq_setup_stable_merge(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		       struct bfq_queue *stable_merge_bfqq,
+		       struct bfq_iocq_bfqq_data *bfqq_data)
+{
+	int proc_ref = min(bfqq_process_refs(bfqq),
+			   bfqq_process_refs(stable_merge_bfqq));
+	struct bfq_queue *new_bfqq;
+
+	if (idling_boosts_thr_without_issues(bfqd, bfqq) ||
+	    proc_ref == 0)
+		return NULL;
+
+	/* next function will take at least one ref */
+	new_bfqq = bfq_setup_merge(bfqq, stable_merge_bfqq);
+
+	if (new_bfqq) {
+		bfqq_data->stably_merged = true;
+		if (new_bfqq->bic) {
+			unsigned int new_a_idx = new_bfqq->actuator_idx;
+			struct bfq_iocq_bfqq_data *new_bfqq_data =
+				&new_bfqq->bic->bfqq_data[new_a_idx];
+
+			new_bfqq_data->stably_merged = true;
+		}
+	}
+	return new_bfqq;
+}
+
 /*
  * Attempt to schedule a merge of bfqq with the currently in-service
  * queue or with a close queue among the scheduled queues.  Return
@@ -2819,6 +2901,8 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		     void *io_struct, bool request, struct bfq_io_cq *bic)
 {
 	struct bfq_queue *in_service_bfqq, *new_bfqq;
+	unsigned int a_idx = bfqq->actuator_idx;
+	struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[a_idx];
 
 	/* if a merge has already been setup, then proceed with that first */
 	if (bfqq->new_bfqq)
@@ -2840,37 +2924,23 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		 * stable merging) also if bic is associated with a
 		 * sync queue, but this bfqq is async
 		 */
-		if (bfq_bfqq_sync(bfqq) && bic->stable_merge_bfqq &&
+		if (bfq_bfqq_sync(bfqq) && bfqq_data->stable_merge_bfqq &&
 		    !bfq_bfqq_just_created(bfqq) &&
 		    time_is_before_jiffies(bfqq->split_time +
 					  msecs_to_jiffies(bfq_late_stable_merging)) &&
 		    time_is_before_jiffies(bfqq->creation_time +
 					   msecs_to_jiffies(bfq_late_stable_merging))) {
 			struct bfq_queue *stable_merge_bfqq =
-				bic->stable_merge_bfqq;
-			int proc_ref = min(bfqq_process_refs(bfqq),
-					   bfqq_process_refs(stable_merge_bfqq));
+				bfqq_data->stable_merge_bfqq;
 
 			/* deschedule stable merge, because done or aborted here */
 			bfq_put_stable_ref(stable_merge_bfqq);
 
-			bic->stable_merge_bfqq = NULL;
-
-			if (!idling_boosts_thr_without_issues(bfqd, bfqq) &&
-			    proc_ref > 0) {
-				/* next function will take at least one ref */
-				struct bfq_queue *new_bfqq =
-					bfq_setup_merge(bfqq, stable_merge_bfqq);
-
-				if (new_bfqq) {
-					bic->stably_merged = true;
-					if (new_bfqq->bic)
-						new_bfqq->bic->stably_merged =
-									true;
-				}
-				return new_bfqq;
-			} else
-				return NULL;
+			bfqq_data->stable_merge_bfqq = NULL;
+
+			return bfq_setup_stable_merge(bfqd, bfqq,
+						      stable_merge_bfqq,
+						      bfqq_data);
 		}
 	}
 
@@ -2965,6 +3035,8 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 {
 	struct bfq_io_cq *bic = bfqq->bic;
+	unsigned int a_idx = bfqq->actuator_idx;
+	struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[a_idx];
 
 	/*
 	 * If !bfqq->bic, the queue is already shared or its requests
@@ -2974,18 +3046,21 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	if (!bic)
 		return;
 
-	bic->saved_last_serv_time_ns = bfqq->last_serv_time_ns;
-	bic->saved_inject_limit = bfqq->inject_limit;
-	bic->saved_decrease_time_jif = bfqq->decrease_time_jif;
-
-	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);
-	bic->saved_io_start_time = bfqq->io_start_time;
-	bic->saved_tot_idle_time = bfqq->tot_idle_time;
-	bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
-	bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
+	bfqq_data->saved_last_serv_time_ns = bfqq->last_serv_time_ns;
+	bfqq_data->saved_inject_limit =	bfqq->inject_limit;
+	bfqq_data->saved_decrease_time_jif = bfqq->decrease_time_jif;
+
+	bfqq_data->saved_weight = bfqq->entity.orig_weight;
+	bfqq_data->saved_ttime = bfqq->ttime;
+	bfqq_data->saved_has_short_ttime =
+		bfq_bfqq_has_short_ttime(bfqq);
+	bfqq_data->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
+	bfqq_data->saved_io_start_time = bfqq->io_start_time;
+	bfqq_data->saved_tot_idle_time = bfqq->tot_idle_time;
+	bfqq_data->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
+	bfqq_data->was_in_burst_list =
+		!hlist_unhashed(&bfqq->burst_list_node);
+
 	if (unlikely(bfq_bfqq_just_created(bfqq) &&
 		     !bfq_bfqq_in_large_burst(bfqq) &&
 		     bfqq->bfqd->low_latency)) {
@@ -2998,17 +3073,21 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 		 * to bfqq, so that to avoid that bfqq unjustly fails
 		 * to enjoy weight raising if split soon.
 		 */
-		bic->saved_wr_coeff = bfqq->bfqd->bfq_wr_coeff;
-		bic->saved_wr_start_at_switch_to_srt = bfq_smallest_from_now();
-		bic->saved_wr_cur_max_time = bfq_wr_duration(bfqq->bfqd);
-		bic->saved_last_wr_start_finish = jiffies;
+		bfqq_data->saved_wr_coeff = bfqq->bfqd->bfq_wr_coeff;
+		bfqq_data->saved_wr_start_at_switch_to_srt =
+			bfq_smallest_from_now();
+		bfqq_data->saved_wr_cur_max_time =
+			bfq_wr_duration(bfqq->bfqd);
+		bfqq_data->saved_last_wr_start_finish = jiffies;
 	} else {
-		bic->saved_wr_coeff = bfqq->wr_coeff;
-		bic->saved_wr_start_at_switch_to_srt =
+		bfqq_data->saved_wr_coeff = bfqq->wr_coeff;
+		bfqq_data->saved_wr_start_at_switch_to_srt =
 			bfqq->wr_start_at_switch_to_srt;
-		bic->saved_service_from_wr = bfqq->service_from_wr;
-		bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
-		bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
+		bfqq_data->saved_service_from_wr =
+			bfqq->service_from_wr;
+		bfqq_data->saved_last_wr_start_finish =
+			bfqq->last_wr_start_finish;
+		bfqq_data->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
 	}
 }
 
@@ -3114,7 +3193,7 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 	/*
 	 * Merge queues (that is, let bic redirect its requests to new_bfqq)
 	 */
-	bic_set_bfqq(bic, new_bfqq, true);
+	bic_set_bfqq(bic, new_bfqq, true, bfqq->actuator_idx);
 	bfq_mark_bfqq_coop(new_bfqq);
 	/*
 	 * new_bfqq now belongs to at least two bics (it is a shared queue):
@@ -3532,13 +3611,13 @@ static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq)
 	 * - start a new observation interval with this dispatch
 	 */
 	if (now_ns - bfqd->last_dispatch > 100*NSEC_PER_MSEC &&
-	    bfqd->rq_in_driver == 0)
+	    bfqd->tot_rq_in_driver == 0)
 		goto update_rate_and_reset;
 
 	/* Update sampling information */
 	bfqd->peak_rate_samples++;
 
-	if ((bfqd->rq_in_driver > 0 ||
+	if ((bfqd->tot_rq_in_driver > 0 ||
 		now_ns - bfqd->last_completion < BFQ_MIN_TT)
 	    && !BFQ_RQ_SEEKY(bfqd, bfqd->last_position, rq))
 		bfqd->sequential_samples++;
@@ -3803,10 +3882,8 @@ static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd,
 		return false;
 
 	return (bfqq->wr_coeff > 1 &&
-		(bfqd->wr_busy_queues <
-		 tot_busy_queues ||
-		 bfqd->rq_in_driver >=