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, 39 insertions, 44 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 5487912befe8..3866b6c4cd88 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -59,13 +59,12 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(block_split);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_insert);
 
-DEFINE_IDA(blk_queue_ida);
+static DEFINE_IDA(blk_queue_ida);
 
 /*
  * For queue allocation
  */
-struct kmem_cache *blk_requestq_cachep;
-struct kmem_cache *blk_requestq_srcu_cachep;
+static struct kmem_cache *blk_requestq_cachep;
 
 /*
  * Controlling structure to kblockd
@@ -253,19 +252,44 @@ void blk_clear_pm_only(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_clear_pm_only);
 
+static void blk_free_queue_rcu(struct rcu_head *rcu_head)
+{
+	kmem_cache_free(blk_requestq_cachep,
+			container_of(rcu_head, struct request_queue, rcu_head));
+}
+
+static void blk_free_queue(struct request_queue *q)
+{
+	percpu_ref_exit(&q->q_usage_counter);
+
+	if (q->poll_stat)
+		blk_stat_remove_callback(q, q->poll_cb);
+	blk_stat_free_callback(q->poll_cb);
+
+	blk_free_queue_stats(q->stats);
+	kfree(q->poll_stat);
+
+	if (queue_is_mq(q))
+		blk_mq_release(q);
+
+	ida_free(&blk_queue_ida, q->id);
+	call_rcu(&q->rcu_head, blk_free_queue_rcu);
+}
+
 /**
  * blk_put_queue - decrement the request_queue refcount
  * @q: the request_queue structure to decrement the refcount for
  *
- * Decrements the refcount of the request_queue kobject. When this reaches 0
- * we'll have blk_release_queue() called.
+ * Decrements the refcount of the request_queue and free it when the refcount
+ * reaches 0.
  *
- * Context: Any context, but the last reference must not be dropped from
- *          atomic context.
+ * Context: Can sleep.
  */
 void blk_put_queue(struct request_queue *q)
 {
-	kobject_put(&q->kobj);
+	might_sleep();
+	if (refcount_dec_and_test(&q->refs))
+		blk_free_queue(q);
 }
 EXPORT_SYMBOL(blk_put_queue);
 
@@ -373,26 +397,20 @@ static void blk_timeout_work(struct work_struct *work)
 {
 }
 
-struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
+struct request_queue *blk_alloc_queue(int node_id)
 {
 	struct request_queue *q;
 
-	q = kmem_cache_alloc_node(blk_get_queue_kmem_cache(alloc_srcu),
-			GFP_KERNEL | __GFP_ZERO, node_id);
+	q = kmem_cache_alloc_node(blk_requestq_cachep, GFP_KERNEL | __GFP_ZERO,
+				  node_id);
 	if (!q)
 		return NULL;
 
-	if (alloc_srcu) {
-		blk_queue_flag_set(QUEUE_FLAG_HAS_SRCU, q);
-		if (init_srcu_struct(q->srcu) != 0)
-			goto fail_q;
-	}
-
 	q->last_merge = NULL;
 
 	q->id = ida_alloc(&blk_queue_ida, GFP_KERNEL);
 	if (q->id < 0)
-		goto fail_srcu;
+		goto fail_q;
 
 	q->stats = blk_alloc_queue_stats();
 	if (!q->stats)
@@ -406,8 +424,7 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
 	INIT_WORK(&q->timeout_work, blk_timeout_work);
 	INIT_LIST_HEAD(&q->icq_list);
 
-	kobject_init(&q->kobj, &blk_queue_ktype);
-
+	refcount_set(&q->refs, 1);
 	mutex_init(&q->debugfs_mutex);
 	mutex_init(&q->sysfs_lock);
 	mutex_init(&q->sysfs_dir_lock);
@@ -434,11 +451,8 @@ fail_stats:
 	blk_free_queue_stats(q->stats);
 fail_id:
 	ida_free(&blk_queue_ida, q->id);
-fail_srcu:
-	if (alloc_srcu)
-		cleanup_srcu_struct(q->srcu);
 fail_q:
-	kmem_cache_free(blk_get_queue_kmem_cache(alloc_srcu), q);
+	kmem_cache_free(blk_requestq_cachep, q);
 	return NULL;
 }
 
@@ -454,7 +468,7 @@ bool blk_get_queue(struct request_queue *q)
 {
 	if (unlikely(blk_queue_dying(q)))
 		return false;
-	kobject_get(&q->kobj);
+	refcount_inc(&q->refs);
 	return true;
 }
 EXPORT_SYMBOL(blk_get_queue);
@@ -945,18 +959,6 @@ unsigned long bdev_start_io_acct(struct block_device *bdev,
 EXPORT_SYMBOL(bdev_start_io_acct);
 
 /**
- * bio_start_io_acct_time - start I/O accounting for bio based drivers
- * @bio:	bio to start account for
- * @start_time:	start time that should be passed back to bio_end_io_acct().
- */
-void bio_start_io_acct_time(struct bio *bio, unsigned long start_time)
-{
-	bdev_start_io_acct(bio->bi_bdev, bio_sectors(bio),
-			   bio_op(bio), start_time);
-}
-EXPORT_SYMBOL_GPL(bio_start_io_acct_time);
-
-/**
  * bio_start_io_acct - start I/O accounting for bio based drivers
  * @bio:	bio to start account for
  *
@@ -1183,9 +1185,6 @@ int __init blk_dev_init(void)
 			sizeof_field(struct request, cmd_flags));
 	BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 *
 			sizeof_field(struct bio, bi_opf));
-	BUILD_BUG_ON(ALIGN(offsetof(struct request_queue, srcu),
-			   __alignof__(struct request_queue)) !=
-		     sizeof(struct request_queue));
 
 	/* used for unplugging and affects IO latency/throughput - HIGHPRI */
 	kblockd_workqueue = alloc_workqueue("kblockd",
@@ -1196,10 +1195,6 @@ int __init blk_dev_init(void)
 	blk_requestq_cachep = kmem_cache_create("request_queue",
 			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
 
-	blk_requestq_srcu_cachep = kmem_cache_create("request_queue_srcu",
-			sizeof(struct request_queue) +
-			sizeof(struct srcu_struct), 0, SLAB_PANIC, NULL);
-
 	blk_debugfs_root = debugfs_create_dir("block", NULL);
 
 	return 0;