Merge tag 'for-5.18/drivers-2022-04-01' of git://git.kernel.dk/linux-block

Pull block driver fixes from Jens Axboe:
 "Followup block driver updates and fixes for the 5.18-rc1 merge window.
  In detail:

   - NVMe pull request
       - Fix multipath hang when disk goes live over reconnect (Anton
         Eidelman)
       - fix RCU hole that allowed for endless looping in multipath
         round robin (Chris Leech)
       - remove redundant assignment after left shift (Colin Ian King)
       - add quirks for Samsung X5 SSDs (Monish Kumar R)
       - fix the read-only state for zoned namespaces with unsupposed
         features (Pankaj Raghav)
       - use a private workqueue instead of the system workqueue in
         nvmet (Sagi Grimberg)
       - allow duplicate NSIDs for private namespaces (Sungup Moon)
       - expose use_threaded_interrupts read-only in sysfs (Xin Hao)"

   - nbd minor allocation fix (Zhang)

   - drbd fixes and maintainer addition (Lars, Jakob, Christoph)

   - n64cart build fix (Jackie)

   - loop compat ioctl fix (Carlos)

   - misc fixes (Colin, Dongli)"

* tag 'for-5.18/drivers-2022-04-01' of git://git.kernel.dk/linux-block:
  drbd: remove check of list iterator against head past the loop body
  drbd: remove usage of list iterator variable after loop
  nbd: fix possible overflow on 'first_minor' in nbd_dev_add()
  MAINTAINERS: add drbd co-maintainer
  drbd: fix potential silent data corruption
  loop: fix ioctl calls using compat_loop_info
  nvme-multipath: fix hang when disk goes live over reconnect
  nvme: fix RCU hole that allowed for endless looping in multipath round robin
  nvme: allow duplicate NSIDs for private namespaces
  nvmet: remove redundant assignment after left shift
  nvmet: use a private workqueue instead of the system workqueue
  nvme-pci: add quirks for Samsung X5 SSDs
  nvme-pci: expose use_threaded_interrupts read-only in sysfs
  nvme: fix the read-only state for zoned namespaces with unsupposed features
  n64cart: convert bi_disk to bi_bdev->bd_disk fix build
  xen/blkfront: fix comment for need_copy
  xen-blkback: remove redundant assignment to variable i

22 files changed, 182 insertions, 90 deletions

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 96881d5babd9..9676a1d214bc 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -171,7 +171,7 @@ void tl_release(struct drbd_connection *connection, unsigned int barrier_nr,
 		unsigned int set_size)
 {
 	struct drbd_request *r;
-	struct drbd_request *req = NULL;
+	struct drbd_request *req = NULL, *tmp = NULL;
 	int expect_epoch = 0;
 	int expect_size = 0;
 
@@ -225,8 +225,11 @@ void tl_release(struct drbd_connection *connection, unsigned int barrier_nr,
 	 * to catch requests being barrier-acked "unexpectedly".
 	 * It usually should find the same req again, or some READ preceding it. */
 	list_for_each_entry(req, &connection->transfer_log, tl_requests)
-		if (req->epoch == expect_epoch)
+		if (req->epoch == expect_epoch) {
+			tmp = req;
 			break;
+		}
+	req = list_prepare_entry(tmp, &connection->transfer_log, tl_requests);
 	list_for_each_entry_safe_from(req, r, &connection->transfer_log, tl_requests) {
 		if (req->epoch != expect_epoch)
 			break;
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index c04394518b07..75be0e16770a 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -180,7 +180,8 @@ void start_new_tl_epoch(struct drbd_connection *connection)
 void complete_master_bio(struct drbd_device *device,
 		struct bio_and_error *m)
 {
-	m->bio->bi_status = errno_to_blk_status(m->error);
+	if (unlikely(m->error))
+		m->bio->bi_status = errno_to_blk_status(m->error);
 	bio_endio(m->bio);
 	dec_ap_bio(device);
 }
@@ -332,17 +333,21 @@ static void set_if_null_req_next(struct drbd_peer_device *peer_device, struct dr
 static void advance_conn_req_next(struct drbd_peer_device *peer_device, struct drbd_request *req)
 {
 	struct drbd_connection *connection = peer_device ? peer_device->connection : NULL;
+	struct drbd_request *iter = req;
 	if (!connection)
 		return;
 	if (connection->req_next != req)
 		return;
-	list_for_each_entry_continue(req, &connection->transfer_log, tl_requests) {
-		const unsigned s = req->rq_state;
-		if (s & RQ_NET_QUEUED)
+
+	req = NULL;
+	list_for_each_entry_continue(iter, &connection->transfer_log, tl_requests) {
+		const unsigned int s = iter->rq_state;
+
+		if (s & RQ_NET_QUEUED) {
+			req = iter;
 			break;
+		}
 	}
-	if (&req->tl_requests == &connection->transfer_log)
-		req = NULL;
 	connection->req_next = req;
 }
 
@@ -358,17 +363,21 @@ static void set_if_null_req_ack_pending(struct drbd_peer_device *peer_device, st
 static void advance_conn_req_ack_pending(struct drbd_peer_device *peer_device, struct drbd_request *req)
 {
 	struct drbd_connection *connection = peer_device ? peer_device->connection : NULL;
+	struct drbd_request *iter = req;
 	if (!connection)
 		return;
 	if (connection->req_ack_pending != req)
 		return;
-	list_for_each_entry_continue(req, &connection->transfer_log, tl_requests) {
-		const unsigned s = req->rq_state;
-		if ((s & RQ_NET_SENT) && (s & RQ_NET_PENDING))
+
+	req = NULL;
+	list_for_each_entry_continue(iter, &connection->transfer_log, tl_requests) {
+		const unsigned int s = iter->rq_state;
+
+		if ((s & RQ_NET_SENT) && (s & RQ_NET_PENDING)) {
+			req = iter;
 			break;
+		}
 	}
-	if (&req->tl_requests == &connection->transfer_log)
-		req = NULL;
 	connection->req_ack_pending = req;
 }
 
@@ -384,17 +393,21 @@ static void set_if_null_req_not_net_done(struct drbd_peer_device *peer_device, s
 static void advance_conn_req_not_net_done(struct drbd_peer_device *peer_device, struct drbd_request *req)
 {
 	struct drbd_connection *connection = peer_device ? peer_device->connection : NULL;
+	struct drbd_request *iter = req;
 	if (!connection)
 		return;
 	if (connection->req_not_net_done != req)
 		return;
-	list_for_each_entry_continue(req, &connection->transfer_log, tl_requests) {
-		const unsigned s = req->rq_state;
-		if ((s & RQ_NET_SENT) && !(s & RQ_NET_DONE))
+
+	req = NULL;
+	list_for_each_entry_continue(iter, &connection->transfer_log, tl_requests) {
+		const unsigned int s = iter->rq_state;
+
+		if ((s & RQ_NET_SENT) && !(s & RQ_NET_DONE)) {
+			req = iter;
 			break;
+		}
 	}
-	if (&req->tl_requests == &connection->transfer_log)
-		req = NULL;
 	connection->req_not_net_done = req;
 }
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 3e636a75c83a..a58595f5ee2c 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1591,6 +1591,7 @@ struct compat_loop_info {
 	compat_ulong_t	lo_inode;       /* ioctl r/o */
 	compat_dev_t	lo_rdevice;     /* ioctl r/o */
 	compat_int_t	lo_offset;
+	compat_int_t	lo_encrypt_type;        /* obsolete, ignored */
 	compat_int_t	lo_encrypt_key_size;    /* ioctl w/o */
 	compat_int_t	lo_flags;       /* ioctl r/o */
 	char		lo_name[LO_NAME_SIZE];
diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c
index 4db9a8c244af..e094d2b8b5a9 100644
--- a/drivers/block/n64cart.c
+++ b/drivers/block/n64cart.c
@@ -88,7 +88,7 @@ static void n64cart_submit_bio(struct bio *bio)
 {
 	struct bio_vec bvec;
 	struct bvec_iter iter;
-	struct device *dev = bio->bi_disk->private_data;
+	struct device *dev = bio->bi_bdev->bd_disk->private_data;
 	u32 pos = bio->bi_iter.bi_sector << SECTOR_SHIFT;
 
 	bio_for_each_segment(bvec, bio, iter) {
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 5a1f98494ddd..b3cdfc0ffb98 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1800,17 +1800,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 	refcount_set(&nbd->refs, 0);
 	INIT_LIST_HEAD(&nbd->list);
 	disk->major = NBD_MAJOR;
-
-	/* Too big first_minor can cause duplicate creation of
-	 * sysfs files/links, since index << part_shift might overflow, or
-	 * MKDEV() expect that the max bits of first_minor is 20.
-	 */
-	disk->first_minor = index << part_shift;
-	if (disk->first_minor < index || disk->first_minor > MINORMASK) {
-		err = -EINVAL;
-		goto out_free_work;
-	}
-
 	disk->minors = 1 << part_shift;
 	disk->fops = &nbd_fops;
 	disk->private_data = nbd;
@@ -1915,8 +1904,19 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 	if (!netlink_capable(skb, CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (info->attrs[NBD_ATTR_INDEX])
+	if (info->attrs[NBD_ATTR_INDEX]) {
 		index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+
+		/*
+		 * Too big first_minor can cause duplicate creation of
+		 * sysfs files/links, since index << part_shift might overflow, or
+		 * MKDEV() expect that the max bits of first_minor is 20.
+		 */
+		if (index < 0 || index > MINORMASK >> part_shift) {
+			printk(KERN_ERR "nbd: illegal input index %d\n", index);
+			return -EINVAL;
+		}
+	}
 	if (!info->attrs[NBD_ATTR_SOCKETS]) {
 		printk(KERN_ERR "nbd: must specify at least one socket\n");
 		return -EINVAL;
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index d1e26461a64e..de42458195bc 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -931,7 +931,7 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req,
 	if (rc)
 		goto unmap;
 
-	for (n = 0, i = 0; n < nseg; n++) {
+	for (n = 0; n < nseg; n++) {
 		uint8_t first_sect, last_sect;
 
 		if ((n % SEGS_PER_INDIRECT_FRAME) == 0) {
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 378262ec47ae..003056d4f7f5 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -576,7 +576,7 @@ struct setup_rw_req {
 	struct blkif_request *ring_req;
 	grant_ref_t gref_head;
 	unsigned int id;
-	/* Only used when persistent grant is used and it's a read request */
+	/* Only used when persistent grant is used and it's a write request */
 	bool need_copy;
 	unsigned int bvec_off;
 	char *bvec_data;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 677fa4bf76d3..efb85c6d8e2d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1830,9 +1830,6 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	nvme_config_discard(disk, ns);
 	blk_queue_max_write_zeroes_sectors(disk->queue,
 					   ns->ctrl->max_zeroes_sectors);
-
-	set_disk_ro(disk, (id->nsattr & NVME_NS_ATTR_RO) ||
-		test_bit(NVME_NS_FORCE_RO, &ns->flags));
 }
 
 static inline bool nvme_first_scan(struct gendisk *disk)
@@ -1891,6 +1888,8 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 			goto out_unfreeze;
 	}
 
+	set_disk_ro(ns->disk, (id->nsattr & NVME_NS_ATTR_RO) ||
+		test_bit(NVME_NS_FORCE_RO, &ns->flags));
 	set_bit(NVME_NS_READY, &ns->flags);
 	blk_mq_unfreeze_queue(ns->disk->queue);
 
@@ -1903,6 +1902,9 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 	if (nvme_ns_head_multipath(ns->head)) {
 		blk_mq_freeze_queue(ns->head->disk->queue);
 		nvme_update_disk_info(ns->head->disk, ns, id);
+		set_disk_ro(ns->head->disk,
+			    (id->nsattr & NVME_NS_ATTR_RO) ||
+				    test_bit(NVME_NS_FORCE_RO, &ns->flags));
 		nvme_mpath_revalidate_paths(ns);
 		blk_stack_limits(&ns->head->disk->queue->limits,
 				 &ns->queue->limits, 0);
@@ -3589,15 +3591,20 @@ static const struct attribute_group *nvme_dev_attr_groups[] = {
 	NULL,
 };
 
-static struct nvme_ns_head *nvme_find_ns_head(struct nvme_subsystem *subsys,
+static struct nvme_ns_head *nvme_find_ns_head(struct nvme_ctrl *ctrl,
 		unsigned nsid)
 {
 	struct nvme_ns_head *h;
 
-	lockdep_assert_held(&subsys->lock);
+	lockdep_assert_held(&ctrl->subsys->lock);
 
-	list_for_each_entry(h, &subsys->nsheads, entry) {
-		if (h->ns_id != nsid)
+	list_for_each_entry(h, &ctrl->subsys->nsheads, entry) {
+		/*
+		 * Private namespaces can share NSIDs under some conditions.
+		 * In that case we can't use the same ns_head for namespaces
+		 * with the same NSID.
+		 */
+		if (h->ns_id != nsid || !nvme_is_unique_nsid(ctrl, h))
 			continue;
 		if (!list_empty(&h->list) && nvme_tryget_ns_head(h))
 			return h;
@@ -3791,7 +3798,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
 	}
 
 	mutex_lock(&ctrl->subsys->lock);
-	head = nvme_find_ns_head(ctrl->subsys, nsid);
+	head = nvme_find_ns_head(ctrl, nsid);
 	if (!head) {
 		ret = nvme_subsys_check_duplicate_ids(ctrl->subsys, ids);
 		if (ret) {
@@ -3988,6 +3995,16 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	set_capacity(ns->disk, 0);
 	nvme_fault_inject_fini(&ns->fault_inject);
 
+	/*
+	 * Ensure that !NVME_NS_READY is seen by other threads to prevent
+	 * this ns going back into current_path.
+	 */
+	synchronize_srcu(&ns->head->srcu);
+
+	/* wait for concurrent submissions */
+	if (nvme_mpath_clear_current_path(ns))
+		synchronize_srcu(&ns->head->srcu);
+
 	mutex_lock(&ns->ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);
 	if (list_empty(&ns->head->list)) {
@@ -3999,10 +4016,6 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	/* guarantee not available in head->list */
 	synchronize_rcu();
 
-	/* wait for concurrent submissions */
-	if (nvme_mpath_clear_current_path(ns))
-		synchronize_srcu(&ns->head->srcu);
-
 	if (!nvme_ns_head_multipath(ns->head))
 		nvme_cdev_del(&ns->cdev, &ns->cdev_device);
 	del_gendisk(ns->disk);
@@ -4480,6 +4493,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
 	if (ctrl->queue_count > 1) {
 		nvme_queue_scan(ctrl);
 		nvme_start_queues(ctrl);
+		nvme_mpath_update(ctrl);
 	}
 
 	nvme_change_uevent(ctrl, "NVME_EVENT=connected");
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 1b31f19e1053..d464fdf978fb 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -482,10 +482,11 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 
 	/*
 	 * Add a multipath node if the subsystems supports multiple controllers.
-	 * We also do this for private namespaces as the namespace sharing data could
-	 * change after a rescan.
+	 * We also do this for private namespaces as the namespace sharing flag
+	 * could change after a rescan.
 	 */
-	if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || !multipath)
+	if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) ||
+	    !nvme_is_unique_nsid(ctrl, head) || !multipath)
 		return 0;
 
 	head->disk = blk_alloc_disk(ctrl->numa_node);
@@ -612,8 +613,17 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 	ns->ana_grpid = le32_to_cpu(desc->grpid);
 	ns->ana_state = desc->state;
 	clear_bit(NVME_NS_ANA_PENDING, &ns->flags);
-
-	if (nvme_state_is_live(ns->ana_state))
+	/*
+	 * nvme_mpath_set_live() will trigger I/O to the multipath path device
+	 * and in turn to this path device.  However we cannot accept this I/O
+	 * if the controller is not live.  This may deadlock if called from
+	 * nvme_mpath_init_identify() and the ctrl will never complete
+	 * initialization, preventing I/O from completing.  For this case we
+	 * will reprocess the ANA log page in nvme_mpath_update() once the
+	 * controller is ready.
+	 */
+	if (nvme_state_is_live(ns->ana_state) &&
+	    ns->ctrl->state == NVME_CTRL_LIVE)
 		nvme_mpath_set_live(ns);
 }
 
@@ -700,6 +710,18 @@ static void nvme_ana_work(struct work_struct *work)
 	nvme_read_ana_log(ctrl);
 }
 
+void nvme_mpath_update(struct nvme_ctrl *ctrl)
+{
+	u32 nr_change_groups = 0;
+
+	if (!ctrl->ana_log_buf)
+		return;
+
+	mutex_lock(&ctrl->ana_lock);
+	nvme_parse_ana_log(ctrl, &nr_change_groups, nvme_update_ana_state);
+	mutex_unlock(&ctrl->ana_lock);
+}
+
 static void nvme_anatt_timeout(struct timer_list *t)
 {
 	struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index f4b674a8ce20..1393bbf82d71 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -723,6 +723,25 @@ static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		return queue_live;
 	return __nvme_check_ready(ctrl, rq, queue_live);
 }
+
+/*
+ * NSID shall be unique for all shared namespaces, or if at least one of the
+ * following conditions is met:
+ *   1. Namespace Management is supported by the controller
+ *   2. ANA is supported by the controller
+ *   3. NVM Set are supported by the controller
+ *
+ * In other case, private namespace are not required to report a unique NSID.
+ */
+static inline bool nvme_is_unique_nsid(struct nvme_ctrl *ctrl,
+		struct nvme_ns_head *head)
+{
+	return head->shared ||
+		(ctrl->oacs & NVME_CTRL_OACS_NS_MNGT_SUPP) ||
+		(ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA) ||
+		(ctrl->ctratt & NVME_CTRL_CTRATT_NVM_SETS);
+}
+
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buf, unsigned bufflen);
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
@@ -782,6 +801,7 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id);
 void nvme_mpath_remove_disk(struct nvme_ns_head *head);
 int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id);
 void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl);
+void nvme_mpath_update(struct nvme_ctrl *ctrl);
 void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
 void nvme_mpath_stop(struct nvme_ctrl *ctrl);
 bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
@@ -853,6 +873,9 @@ static inline int nvme_mpath_init_identify(struct nvme_ctrl *ctrl,
 "Please enable CONFIG_NVME_MULTIPATH for full support of multi-port devices.\n");
 	return 0;
 }
+static inline void nvme_mpath_update(struct nvme_ctrl *ctrl)
+{
+}
 static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
 {
 }
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 2e98ac3f3ad6..d817ca17463e 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -45,7 +45,7 @@
 #define NVME_MAX_SEGS	127
 
 static int use_threaded_interrupts;
-module_param(use_threaded_interrupts, int, 0);
+module_param(use_threaded_interrupts, int, 0444);
 
 static bool use_cmb_sqes = true;
 module_param(use_cmb_sqes, bool, 0444);
@@ -3467,7 +3467,10 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_128_BYTES_SQES |
 				NVME_QUIRK_SHARED_TAGS |
 				NVME_QUIRK_SKIP_CID_GEN },
-
+	{ PCI_DEVICE(0x144d, 0xa808),   /* Samsung X5 */
+		.driver_data =  NVME_QUIRK_DELAY_BEFORE_CHK_RDY|
+				NVME_QUIRK_NO_DEEPEST_PS |
+				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ 0, }
 };
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 46d0dab686dd..397daaf51f1b 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -988,7 +988,7 @@ void nvmet_execute_async_event(struct nvmet_req *req)
 	ctrl->async_event_cmds[ctrl->nr_async_event_cmds++] = req;
 	mutex_unlock(&ctrl->lock);
 
-	schedule_work(&ctrl->async_event_work);
+	queue_work(nvmet_wq, &ctrl->async_event_work);
 }
 
 void nvmet_execute_keep_alive(struct nvmet_req *req)
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 8fedd1e052fe..e44b2988759e 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -1555,7 +1555,7 @@ static void nvmet_port_release(struct config_item *item)
 	struct nvmet_port *port = to_nvmet_port(item);
 
 	/* Let inflight controllers teardown complete */
-	flush_scheduled_work();
+	flush_workqueue(nvmet_wq);
 	list_del(&port->global_entry);
 
 	kfree(port->ana_state);
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 64c2d2f3e25c..90e75324dae0 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -20,6 +20,9 @@ struct workqueue_struct *zbd_wq;
 static const struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
 static DEFINE_IDA(cntlid_ida);
 
+struct workqueue_struct *nvmet_wq;
+EXPORT_SYMBOL_GPL(nvmet_wq);
+
 /*
  * This read/write semaphore is used to synchronize access to configuration
  * information on a target system that will result in discovery log page
@@ -205,7 +208,7 @@ void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
 	list_add_tail(&aen->entry, &ctrl->async_events);
 	mutex_unlock(&ctrl->lock);
 
-	schedule_work(&ctrl->async_event_work);
+	queue_work(nvmet_wq, &ctrl->async_event_work);
 }
 
 static void nvmet_add_to_changed_ns_log(struct nvmet_ctrl *ctrl, __le32 nsid)
@@ -385,7 +388,7 @@ static void nvmet_keep_alive_timer(struct work_struct *work)
 	if (reset_tbkas) {
 		pr_debug("ctrl %d reschedule traffic based keep-alive timer\n",
 			ctrl->cntlid);
-		schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+		queue_delayed_work(nvmet_wq, &ctrl->ka_work, ctrl->kato * HZ);
 		return;
 	}
 
@@ -403,7 +406,7 @@ void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 	pr_debug("ctrl %d start keep-alive timer for %d secs\n",
 		ctrl->cntlid, ctrl->kato);
 
-	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+	queue_delayed_work(nvmet_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl)
@@ -1120,7 +1123,7 @@ static inline u8 nvmet_cc_iocqes(u32 cc)
 
 static inline bool nvmet_css_supported(u8 cc_css)
 {
-	switch (cc_css <<= NVME_CC_CSS_SHIFT) {
+	switch (cc_css << NVME_CC_CSS_SHIFT) {
 	case NVME_CC_CSS_NVM:
 	case NVME_CC_CSS_CSI:
 		return true;
@@ -1478,7 +1481,7 @@ void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl)
 	mutex_lock(&ctrl->lock);
 	if (!(ctrl->csts & NVME_CSTS_CFS)) {
 		ctrl->csts |= NVME_CSTS_CFS;
-		schedule_work(&ctrl->fatal_err_work);
+		queue_work(nvmet_wq, &ctrl->fatal_err_work);
 	}
 	mutex_unlock(&ctrl->lock);
 }
@@ -1619,9 +1622,15 @@ static int __init nvmet_init(void)
 		goto out_free_zbd_work_queue;
 	}
 
+	nvmet_wq = alloc_workqueue("nvmet-wq", WQ_MEM_RECLAIM, 0);
+	if (!nvmet_wq) {
+		error = -ENOMEM;
+		goto out_free_buffered_work_queue;
+	}
+
 	error = nvmet_init_discovery();
 	if (error)
-		goto out_free_work_queue;
+		goto out_free_nvmet_work_queue;
 
 	error = nvmet_init_configfs();
 	if (error)
@@ -1630,7 +1639,9 @@ static int __init nvmet_init(void)
 
 out_exit_discovery:
 	nvmet_exit_discovery();
-out_free_work_queue:
+out_free_nvmet_work_queue:
+	destroy_workqueue(nvmet_wq);
+out_free_buffered_work_queue:
 	destroy_workqueue(buffered_io_wq);
 out_free_zbd_work_queue:
 	destroy_workqueue(zbd_wq);
@@ -1642,6 +1653,7 @@ static void __exit nvmet_exit(void)
 	nvmet_exit_configfs();
 	nvmet_exit_discovery();
 	ida_destroy(&cntlid_ida);
+	destroy_workqueue(nvmet_wq);
 	destroy_workqueue(buffered_io_wq);
 	destroy_workqueue(zbd_wq);
 
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index de90001fc5c4..ab2627e17bb9 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -1491,7 +1491,7 @@ __nvmet_fc_free_assocs(struct nvmet_fc_tgtport *tgtport)
 	list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
 		if (!nvmet_fc_tgt_a_get(assoc))
 			continue;
-		if (!schedule_work(&assoc->del_work))
+		if (!queue_work(nvmet_wq, &assoc->del_work))
 			/* already deleting - release local reference */
 			nvmet_fc_tgt_a_put(assoc);
 	}
@@ -1546,7 +1546,7 @@ nvmet_fc_invalidate_host(struct nvmet_fc_target_port *target_port,
 			continue;
 		assoc->hostport->invalid = 1;
 		noassoc = false;
-		if (!schedule_work(&assoc->del_work))
+		if (!queue_work(nvmet_wq, &assoc->del_work))
 			/* already deleting - release local reference */
 			nvmet_fc_tgt_a_put(assoc);
 	}
@@ -1592,7 +1592,7 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl)
 		nvmet_fc_tgtport_put(tgtport);
 
 		if (found_ctrl) {
-			if (!schedule_work(&assoc->del_work))
+			if (!queue_work(nvmet_wq, &assoc->del_work))
 				/* already deleting - release local reference */
 				nvmet_fc_tgt_a_put(assoc);
 			return;
@@ -2060,7 +2060,7 @@ nvmet_fc_rcv_ls_req(struct nvmet_fc_target_port *target_port,
 	iod->rqstdatalen = lsreqbuf_len;
 	iod->hosthandle = hosthandle;
 
-	schedule_work(&iod->work);
+	queue_work(nvmet_wq, &iod->work);
 
 	return 0;
 }
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index 54606f1872b4..5c16372f3b53 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -360,7 +360,7 @@ fcloop_h2t_ls_req(struct nvme_fc_local_port *localport,
 		spin_lock(&rport->lock);
 		list_add_tail(&rport->ls_list, &tls_req->ls_list);
 		spin_unlock(&rport->lock);
-		schedule_work(&rport->ls_work);
+		queue_work(nvmet_wq, &rport->ls_work);
 		return ret;
 	}
 
@@ -393,7 +393,7 @@ fcloop_h2t_xmt_ls_rsp(struct nvmet_fc_target_port *targetport,
 		spin_lock(&rport->lock);
 		list_add_tail(&rport->ls_list, &tls_req->ls_list);
 		spin_unlock(&rport->lock);
-		schedule_work(&rport->ls_work);
+		queue_work(nvmet_wq, &rport->ls_work);
 	}
 
 	return 0;
@@ -448,7 +448,7 @@ fcloop_t2h_ls_req(struct nvmet_fc_target_port *targetport, void *hosthandle,
 		spin_lock(&tport->lock);
 		list_add_tail(&tport->ls_list, &tls_req->ls_list);
 		spin_unlock(&tport->lock);
-		schedule_work(&tport->ls_work);
+		queue_work(nvmet_wq, &tport->ls_work);
 		return ret;
 	}
 
@@ -480,7 +480,7 @@ fcloop_t2h_xmt_ls_rsp(struct nvme_fc_local_port *localport,
 		spin_lock(&tport->lock);
 		list_add_tail(&tport->ls_list, &tls_req->ls_list);
 		spin_unlock(&tport->lock);
-		schedule_work(&tport->ls_work);
+		queue_work(nvmet_wq, &tport->ls_work);
 	}
 
 	return 0;
@@ -520,7 +520,7 @@ fcloop_tgt_discovery_evt(struct nvmet_fc_target_port *tgtport)
 	tgt_rscn->tport = tgtport->private;
 	INIT_WORK(&tgt_rscn->work, fcloop_tgt_rscn_work);
 
-	schedule_work(&tgt_rscn->work);
+	queue_work(nvmet_wq, &tgt_rscn->work);
 }
 
 static void
@@ -739,7 +739,7 @@ fcloop_fcp_req(struct nvme_fc_local_port *localport,
 	INIT_WORK(&tfcp_req->tio_done_work, fcloop_tgt_fcprqst_done_work);
 	kref_init(&tfcp_req->ref);
 
-	schedule_work(&tfcp_req->fcp_rcv_work);
+	queue_work(nvmet_wq, &tfcp_req->fcp_rcv_work);
 
 	return 0;
 }
@@ -921,7 +921,7 @@ fcloop_fcp_req_release(struct nvmet_fc_target_port *tgtport,
 {
 	struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq);
 
-	schedule_work(&tfcp_req->tio_done_work);
+	queue_work(nvmet_wq, &tfcp_req->tio_done_work);
 }
 
 static void
@@ -976,7 +976,7 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport,
 
 	if (abortio)
 		/* leave the reference while the work item is scheduled */
-		WARN_ON(!schedule_work(&tfcp_req->abort_rcv_work));
+		WARN_ON(!queue_work(nvmet_wq, &tfcp_req->abort_rcv_work));
 	else  {
 		/*
 		 * as the io has already had the done callback made,
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index 6485dc8eb974..f3d58abf11e0 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -283,7 +283,7 @@ static void nvmet_file_execute_flush(struct nvmet_req *req)
 	if (!nvmet_check_transfer_len(req, 0))
 		return;
 	INIT_WORK(&req->f.work, nvmet_file_flush_work);
-	schedule_work(&req->f.work);
+	queue_work(nvmet_wq, &req->f.work);
 }
 
 static void nvmet_file_execute_discard(struct nvmet_req *req)
@@ -343,7 +343,7 @@ static void nvmet_file_execute_dsm(struct nvmet_req *req)
 	if (!nvmet_check_data_len_lte(req, nvmet_dsm_len(req)))
 		return;
 	INIT_WORK(&req->f.work, nvmet_file_dsm_work);
-	schedule_work(&req->f.work);
+	queue_work(nvmet_wq, &req->f.work);
 }
 
 static void nvmet_file_write_zeroes_work(struct work_struct *w)
@@ -373,7 +373,7 @@ static void nvmet_file_execute_write_zeroes(struct nvmet_req *req)
 	if (!nvmet_check_transfer_len(req, 0))
 		return;
 	INIT_WORK(&req->f.work, nvmet_file_write_zeroes_work);
-	schedule_work(&req->f.work);
+	queue_work(nvmet_wq, &req->f.work);
 }
 
 u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 23f9d6f88804..59024af2da2e 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -166,7 +166,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		iod->req.transfer_len = blk_rq_payload_bytes(req);
 	}
 
-	schedule_work(&iod->work);
+	queue_work(nvmet_wq, &iod->work);
 	return BLK_STS_OK;
 }
 
@@ -187,7 +187,7 @@ static void nvme_loop_submit_async_event(struct nvme_ctrl *arg)
 		return;
 	}
 
-	schedule_work(&iod->work);
+	queue_work(nvmet_wq, &iod->work);
 }
 
 static int nvme_loop_init_iod(struct nvme_loop_ctrl *ctrl,
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index d910c6aad4b6..69818752a33a 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -366,6 +366,7 @@ struct nvmet_req {
 
 extern struct workqueue_struct *buffered_io_wq;
 extern struct workqueue_struct *zbd_wq;
+extern struct workqueue_struct *nvmet_wq;
 
 static inline void nvmet_set_result(struct nvmet_req *req, u32 result)
 {
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index a4de1e0d518b..5247c24538eb 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -283,7 +283,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
 	if (req->p.use_workqueue || effects) {
 		INIT_WORK(&req->p.work, nvmet_passthru_execute_cmd_work);
 		req->p.rq = rq;
-		schedule_work(&req->p.work);
+		queue_work(nvmet_wq, &req->p.work);
 	} else {
 		rq->end_io_data = req;
 		blk_execute_rq_nowait(rq, false, nvmet_passthru_req_done);
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 2446d0918a41..2fab0b219b25 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -1584,7 +1584,7 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id,
 
 	if (queue->host_qid == 0) {
 		/* Let inflight controller teardown complete */
-		flush_scheduled_work();
+		flush_workqueue(nvmet_wq);
 	}
 
 	ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn);
@@ -1669,7 +1669,7 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue)
 
 	if (disconnect) {
 		rdma_disconnect(queue->cm_id);
-		schedule_work(&queue->release_work);
+		queue_work(nvmet_wq, &queue->release_work);
 	}
 }
 
@@ -1699,7 +1699,7 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id,
 	mutex_unlock(&nvmet_rdma_queue_mutex);
 
 	pr_err("failed to connect queue %d\n", queue->idx);
-	schedule_work(&queue->release_work);
+	queue_work(nvmet_wq, &queue->release_work);
 }
 
 /**
@@ -1773,7 +1773,7 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id,
 		if (!queue) {
 			struct nvmet_rdma_port *port = cm_id->context;
 
-			schedule_delayed_work(&port->repair_work, 0);
+			queue_delayed_work(nvmet_wq, &port->repair_work, 0);
 			break;
 		}
 		fallthrough;
@@ -1903,7 +1903,7 @@ static void nvmet_rdma_repair_port_work(struct work_struct *w)
 	nvmet_rdma_disable_port(port);
 	ret = nvmet_rdma_enable_port(port);
 	if (ret)
-		schedule_delayed_work(&port->repair_work, 5 * HZ);
+		queue_delayed_work(nvmet_wq, &port->repair_work, 5 * HZ);
 }
 
 static int nvmet_rdma_add_port(struct nvmet_port *nport)
@@ -2053,7 +2053,7 @@ static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data
 	}
 	mutex_unlock(&nvmet_rdma_queue_mutex);
 
-	flush_scheduled_work();
+	flush_workqueue(nvmet_wq);
 }
 
 static struct ib_client nvmet_rdma_ib_client = {
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 83ca577f72be..2793554e622e 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1269,7 +1269,7 @@ static void nvmet_tcp_schedule_release_queue(struct nvmet_tcp_queue *queue)
 	spin_lock(&queue->state_lock);
 	if (queue->state != NVMET_TCP_Q_DISCONNECTING) {
 		queue->state = NVMET_TCP_Q_DISCONNECTING;
-		schedule_work(&queue->release_work);
+		queue_work(nvmet_wq, &queue->release_work);
 	}
 	spin_unlock(&queue->state_lock);
 }
@@ -1684,7 +1684,7 @@ static void nvmet_tcp_listen_data_ready(struct sock *sk)
 		goto out;
 
 	if (sk->sk_state == TCP_LISTEN)
-		schedule_work(&port->accept_work);
+		queue_work(nvmet_wq, &port->accept_work);
 out:
 	read_unlock_bh(&sk->sk_callback_lock);
 }
@@ -1815,7 +1815,7 @@ static u16 nvmet_tcp_install_queue(struct nvmet_sq *sq)
 
 	if (sq->qid == 0) {
 		/* Let inflight controller teardown complete */
-		flush_scheduled_work();
+		flush_workqueue(nvmet_wq);
 	}
 
 	queue->nr_cmds = sq->size * 2;
@@ -1876,12 +1876,12 @@ static void __exit nvmet_tcp_exit(void)
 
 	nvmet_unregister_transport(&nvmet_tcp_ops);
 
-	flush_scheduled_work();
+	flush_workqueue(nvmet_wq);
 	mutex_lock(&nvmet_tcp_queue_mutex);
 	list_for_each_entry(queue, &nvmet_tcp_queue_list, queue_list)
 		kernel_sock_shutdown(queue->sock, SHUT_RDWR);
 	mutex_unlock(&nvmet_tcp_queue_mutex);
-	flush_scheduled_work();
+	flush_workqueue(nvmet_wq);
 
 	destroy_workqueue(nvmet_tcp_wq);
 }