Merge tag 'for-6.2/block-2022-12-08' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull requests via Christoph:
      - Support some passthrough commands without CAP_SYS_ADMIN (Kanchan
        Joshi)
      - Refactor PCIe probing and reset (Christoph Hellwig)
      - Various fabrics authentication fixes and improvements (Sagi
        Grimberg)
      - Avoid fallback to sequential scan due to transient issues (Uday
        Shankar)
      - Implement support for the DEAC bit in Write Zeroes (Christoph
        Hellwig)
      - Allow overriding the IEEE OUI and firmware revision in configfs
        for nvmet (Aleksandr Miloserdov)
      - Force reconnect when number of queue changes in nvmet (Daniel
        Wagner)
      - Minor fixes and improvements (Uros Bizjak, Joel Granados, Sagi
        Grimberg, Christoph Hellwig, Christophe JAILLET)
      - Fix and cleanup nvme-fc req allocation (Chaitanya Kulkarni)
      - Use the common tagset helpers in nvme-pci driver (Christoph
        Hellwig)
      - Cleanup the nvme-pci removal path (Christoph Hellwig)
      - Use kstrtobool() instead of strtobool (Christophe JAILLET)
      - Allow unprivileged passthrough of Identify Controller (Joel
        Granados)
      - Support io stats on the mpath device (Sagi Grimberg)
      - Minor nvmet cleanup (Sagi Grimberg)

 - MD pull requests via Song:
      - Code cleanups (Christoph)
      - Various fixes

 - Floppy pull request from Denis:
      - Fix a memory leak in the init error path (Yuan)

 - Series fixing some batch wakeup issues with sbitmap (Gabriel)

 - Removal of the pktcdvd driver that was deprecated more than 5 years
   ago, and subsequent removal of the devnode callback in struct
   block_device_operations as no users are now left (Greg)

 - Fix for partition read on an exclusively opened bdev (Jan)

 - Series of elevator API cleanups (Jinlong, Christoph)

 - Series of fixes and cleanups for blk-iocost (Kemeng)

 - Series of fixes and cleanups for blk-throttle (Kemeng)

 - Series adding concurrent support for sync queues in BFQ (Yu)

 - Series bringing drbd a bit closer to the out-of-tree maintained
   version (Christian, Joel, Lars, Philipp)

 - Misc drbd fixes (Wang)

 - blk-wbt fixes and tweaks for enable/disable (Yu)

 - Fixes for mq-deadline for zoned devices (Damien)

 - Add support for read-only and offline zones for null_blk
   (Shin'ichiro)

 - Series fixing the delayed holder tracking, as used by DM (Yu,
   Christoph)

 - Series enabling bio alloc caching for IRQ based IO (Pavel)

 - Series enabling userspace peer-to-peer DMA (Logan)

 - BFQ waker fixes (Khazhismel)

 - Series fixing elevator refcount issues (Christoph, Jinlong)

 - Series cleaning up references around queue destruction (Christoph)

 - Series doing quiesce by tagset, enabling cleanups in drivers
   (Christoph, Chao)

 - Series untangling the queue kobject and queue references (Christoph)

 - Misc fixes and cleanups (Bart, David, Dawei, Jinlong, Kemeng, Ye,
   Yang, Waiman, Shin'ichiro, Randy, Pankaj, Christoph)

* tag 'for-6.2/block-2022-12-08' of git://git.kernel.dk/linux: (247 commits)
  blktrace: Fix output non-blktrace event when blk_classic option enabled
  block: sed-opal: Don't include <linux/kernel.h>
  sed-opal: allow using IOC_OPAL_SAVE for locking too
  blk-cgroup: Fix typo in comment
  block: remove bio_set_op_attrs
  nvmet: don't open-code NVME_NS_ATTR_RO enumeration
  nvme-pci: use the tagset alloc/free helpers
  nvme: add the Apple shared tag workaround to nvme_alloc_io_tag_set
  nvme: only set reserved_tags in nvme_alloc_io_tag_set for fabrics controllers
  nvme: consolidate setting the tagset flags
  nvme: pass nr_maps explicitly to nvme_alloc_io_tag_set
  block: bio_copy_data_iter
  nvme-pci: split out a nvme_pci_ctrl_is_dead helper
  nvme-pci: return early on ctrl state mismatch in nvme_reset_work
  nvme-pci: rename nvme_disable_io_queues
  nvme-pci: cleanup nvme_suspend_queue
  nvme-pci: remove nvme_pci_disable
  nvme-pci: remove nvme_disable_admin_queue
  nvme: merge nvme_shutdown_ctrl into nvme_disable_ctrl
  nvme: use nvme_wait_ready in nvme_shutdown_ctrl
  ...

1 files changed, 77 insertions, 80 deletions

diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index 8fc3da4c23bb..b02b53658ed4 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -218,6 +218,24 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
 	return false;
 }
 
+static void bfq_inc_active_entities(struct bfq_entity *entity)
+{
+	struct bfq_sched_data *sd = entity->sched_data;
+	struct bfq_group *bfqg = container_of(sd, struct bfq_group, sched_data);
+
+	if (bfqg != bfqg->bfqd->root_group)
+		bfqg->active_entities++;
+}
+
+static void bfq_dec_active_entities(struct bfq_entity *entity)
+{
+	struct bfq_sched_data *sd = entity->sched_data;
+	struct bfq_group *bfqg = container_of(sd, struct bfq_group, sched_data);
+
+	if (bfqg != bfqg->bfqd->root_group)
+		bfqg->active_entities--;
+}
+
 #else /* CONFIG_BFQ_GROUP_IOSCHED */
 
 static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
@@ -230,6 +248,14 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
 	return true;
 }
 
+static void bfq_inc_active_entities(struct bfq_entity *entity)
+{
+}
+
+static void bfq_dec_active_entities(struct bfq_entity *entity)
+{
+}
+
 #endif /* CONFIG_BFQ_GROUP_IOSCHED */
 
 /*
@@ -456,11 +482,6 @@ static void bfq_active_insert(struct bfq_service_tree *st,
 {
 	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
 	struct rb_node *node = &entity->rb_node;
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-	struct bfq_sched_data *sd = NULL;
-	struct bfq_group *bfqg = NULL;
-	struct bfq_data *bfqd = NULL;
-#endif
 
 	bfq_insert(&st->active, entity);
 
@@ -471,17 +492,10 @@ static void bfq_active_insert(struct bfq_service_tree *st,
 
 	bfq_update_active_tree(node);
 
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-	sd = entity->sched_data;
-	bfqg = container_of(sd, struct bfq_group, sched_data);
-	bfqd = (struct bfq_data *)bfqg->bfqd;
-#endif
 	if (bfqq)
 		list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-	if (bfqg != bfqd->root_group)
-		bfqg->active_entities++;
-#endif
+
+	bfq_inc_active_entities(entity);
 }
 
 /**
@@ -558,29 +572,16 @@ static void bfq_active_extract(struct bfq_service_tree *st,
 {
 	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
 	struct rb_node *node;
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-	struct bfq_sched_data *sd = NULL;
-	struct bfq_group *bfqg = NULL;
-	struct bfq_data *bfqd = NULL;
-#endif
 
 	node = bfq_find_deepest(&entity->rb_node);
 	bfq_extract(&st->active, entity);
 
 	if (node)
 		bfq_update_active_tree(node);
-
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-	sd = entity->sched_data;
-	bfqg = container_of(sd, struct bfq_group, sched_data);
-	bfqd = (struct bfq_data *)bfqg->bfqd;
-#endif
 	if (bfqq)
 		list_del(&bfqq->bfqq_list);
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-	if (bfqg != bfqd->root_group)
-		bfqg->active_entities--;
-#endif
+
+	bfq_dec_active_entities(entity);
 }
 
 /**
@@ -706,22 +707,6 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
 	if (entity->prio_changed) {
 		struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
 		unsigned int prev_weight, new_weight;
-		struct bfq_data *bfqd = NULL;
-		struct rb_root_cached *root;
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-		struct bfq_sched_data *sd;
-		struct bfq_group *bfqg;
-#endif
-
-		if (bfqq)
-			bfqd = bfqq->bfqd;
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-		else {
-			sd = entity->my_sched_data;
-			bfqg = container_of(sd, struct bfq_group, sched_data);
-			bfqd = (struct bfq_data *)bfqg->bfqd;
-		}
-#endif
 
 		/* Matches the smp_wmb() in bfq_group_set_weight. */
 		smp_rmb();
@@ -770,19 +755,15 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
 		 * queue, remove the entity from its old weight counter (if
 		 * there is a counter associated with the entity).
 		 */
-		if (prev_weight != new_weight && bfqq) {
-			root = &bfqd->queue_weights_tree;
-			__bfq_weights_tree_remove(bfqd, bfqq, root);
-		}
+		if (prev_weight != new_weight && bfqq)
+			bfq_weights_tree_remove(bfqq);
 		entity->weight = new_weight;
 		/*
 		 * Add the entity, if it is not a weight-raised queue,
 		 * to the counter associated with its new weight.
 		 */
-		if (prev_weight != new_weight && bfqq && bfqq->wr_coeff == 1) {
-			/* If we get here, root has been initialized. */
-			bfq_weights_tree_add(bfqd, bfqq, root);
-		}
+		if (prev_weight != new_weight && bfqq && bfqq->wr_coeff == 1)
+			bfq_weights_tree_add(bfqq);
 
 		new_st->wsum += entity->weight;
 
@@ -984,19 +965,6 @@ static void __bfq_activate_entity(struct bfq_entity *entity,
 		entity->on_st_or_in_serv = true;
 	}
 
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-	if (!bfq_entity_to_bfqq(entity)) { /* bfq_group */
-		struct bfq_group *bfqg =
-			container_of(entity, struct bfq_group, entity);
-		struct bfq_data *bfqd = bfqg->bfqd;
-
-		if (!entity->in_groups_with_pending_reqs) {
-			entity->in_groups_with_pending_reqs = true;
-			bfqd->num_groups_with_pending_reqs++;
-		}
-	}
-#endif
-
 	bfq_update_fin_time_enqueue(entity, st, backshifted);
 }
 
@@ -1082,12 +1050,12 @@ static void __bfq_requeue_entity(struct bfq_entity *entity)
 }
 
 static void __bfq_activate_requeue_entity(struct bfq_entity *entity,
-					  struct bfq_sched_data *sd,
 					  bool non_blocking_wait_rq)
 {
 	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
 
-	if (sd->in_service_entity == entity || entity->tree == &st->active)
+	if (entity->sched_data->in_service_entity == entity ||
+	    entity->tree == &st->active)
 		 /*
 		  * in service or already queued on the active tree,
 		  * requeue or reposition
@@ -1119,14 +1087,10 @@ static void bfq_activate_requeue_entity(struct bfq_entity *entity,
 					bool non_blocking_wait_rq,
 					bool requeue, bool expiration)
 {
-	struct bfq_sched_data *sd;
-
 	for_each_entity(entity) {
-		sd = entity->sched_data;
-		__bfq_activate_requeue_entity(entity, sd, non_blocking_wait_rq);
-
-		if (!bfq_update_next_in_service(sd, entity, expiration) &&
-		    !requeue)
+		__bfq_activate_requeue_entity(entity, non_blocking_wait_rq);
+		if (!bfq_update_next_in_service(entity->sched_data, entity,
+						expiration) && !requeue)
 			break;
 	}
 }
@@ -1646,6 +1610,32 @@ void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 				    bfqq == bfqd->in_service_queue, expiration);
 }
 
+void bfq_add_bfqq_in_groups_with_pending_reqs(struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	if (!entity->in_groups_with_pending_reqs) {
+		entity->in_groups_with_pending_reqs = true;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+		if (!(bfqq_group(bfqq)->num_queues_with_pending_reqs++))
+			bfqq->bfqd->num_groups_with_pending_reqs++;
+#endif
+	}
+}
+
+void bfq_del_bfqq_in_groups_with_pending_reqs(struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	if (entity->in_groups_with_pending_reqs) {
+		entity->in_groups_with_pending_reqs = false;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+		if (!(--bfqq_group(bfqq)->num_queues_with_pending_reqs))
+			bfqq->bfqd->num_groups_with_pending_reqs--;
+#endif
+	}
+}
+
 /*
  * Called when the bfqq no longer has requests pending, remove it from
  * the service tree. As a special case, it can be invoked during an
@@ -1668,8 +1658,14 @@ void bfq_del_bfqq_busy(struct bfq_queue *bfqq, bool expiration)
 
 	bfq_deactivate_bfqq(bfqd, bfqq, true, expiration);
 
-	if (!bfqq->dispatched)
-		bfq_weights_tree_remove(bfqd, bfqq);
+	if (!bfqq->dispatched) {
+		bfq_del_bfqq_in_groups_with_pending_reqs(bfqq);
+		/*
+		 * Next function is invoked last, because it causes bfqq to be
+		 * freed. DO NOT use bfqq after the next function invocation.
+		 */
+		bfq_weights_tree_remove(bfqq);
+	}
 }
 
 /*
@@ -1686,10 +1682,11 @@ void bfq_add_bfqq_busy(struct bfq_queue *bfqq)
 	bfq_mark_bfqq_busy(bfqq);
 	bfqd->busy_queues[bfqq->ioprio_class - 1]++;
 
-	if (!bfqq->dispatched)
+	if (!bfqq->dispatched) {
+		bfq_add_bfqq_in_groups_with_pending_reqs(bfqq);
 		if (bfqq->wr_coeff == 1)
-			bfq_weights_tree_add(bfqd, bfqq,
-					     &bfqd->queue_weights_tree);
+			bfq_weights_tree_add(bfqq);
+	}
 
 	if (bfqq->wr_coeff > 1)
 		bfqd->wr_busy_queues++;