Merge branch 'for-4.7/drivers' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "On top of the core pull request, this is the drivers pull request for
  this merge window.  This contains:

   - Switch drivers to the new write back cache API, and kill off the
     flush flags.  From me.

   - Kill the discard support for the STEC pci-e flash driver.  It's
     trivially broken, and apparently unmaintained, so it's safer to
     just remove it.  From Jeff Moyer.

   - A set of lightnvm updates from the usual suspects (Matias/Javier,
     and Simon), and fixes from Arnd, Jeff Mahoney, Sagi, and Wenwei
     Tao.

   - A set of updates for NVMe:

        - Turn the controller state management into a proper state
          machine.  From Christoph.

        - Shuffling of code in preparation for NVMe-over-fabrics, also
          from Christoph.

        - Cleanup of the command prep part from Ming Lin.

        - Rewrite of the discard support from Ming Lin.

        - Deadlock fix for namespace removal from Ming Lin.

        - Use the now exported blk-mq tag helper for IO termination.
          From Sagi.

        - Various little fixes from Christoph, Guilherme, Keith, Ming
          Lin, Wang Sheng-Hui.

   - Convert mtip32xx to use the now exported blk-mq tag iter function,
     from Keith"

* 'for-4.7/drivers' of git://git.kernel.dk/linux-block: (74 commits)
  lightnvm: reserved space calculation incorrect
  lightnvm: rename nr_pages to nr_ppas on nvm_rq
  lightnvm: add is_cached entry to struct ppa_addr
  lightnvm: expose gennvm_mark_blk to targets
  lightnvm: remove mgt targets on mgt removal
  lightnvm: pass dma address to hardware rather than pointer
  lightnvm: do not assume sequential lun alloc.
  nvme/lightnvm: Log using the ctrl named device
  lightnvm: rename dma helper functions
  lightnvm: enable metadata to be sent to device
  lightnvm: do not free unused metadata on rrpc
  lightnvm: fix out of bound ppa lun id on bb tbl
  lightnvm: refactor set_bb_tbl for accepting ppa list
  lightnvm: move responsibility for bad blk mgmt to target
  lightnvm: make nvm_set_rqd_ppalist() aware of vblks
  lightnvm: remove struct factory_blks
  lightnvm: refactor device ops->get_bb_tbl()
  lightnvm: introduce nvm_for_each_lun_ppa() macro
  lightnvm: refactor dev->online_target to global nvm_targets
  lightnvm: rename nvm_targets to nvm_tgt_type
  ...

5 files changed, 397 insertions, 299 deletions

diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index c894841c6456..d296fc3ae06e 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -18,7 +18,7 @@ config BLK_DEV_NVME_SCSI
 	depends on NVME_CORE
 	---help---
 	  This adds support for the SG_IO ioctl on the NVMe character
-	  and block devices nodes, as well a a translation for a small
+	  and block devices nodes, as well as a translation for a small
 	  number of selected SCSI commands to NVMe commands to the NVMe
 	  driver.  If you don't know what this means you probably want
 	  to say N here, unless you run a distro that abuses the SCSI
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 643f457131c2..2de248bd462b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -58,6 +58,55 @@ static DEFINE_SPINLOCK(dev_list_lock);
 
 static struct class *nvme_class;
 
+bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
+		enum nvme_ctrl_state new_state)
+{
+	enum nvme_ctrl_state old_state = ctrl->state;
+	bool changed = false;
+
+	spin_lock_irq(&ctrl->lock);
+	switch (new_state) {
+	case NVME_CTRL_LIVE:
+		switch (old_state) {
+		case NVME_CTRL_RESETTING:
+			changed = true;
+			/* FALLTHRU */
+		default:
+			break;
+		}
+		break;
+	case NVME_CTRL_RESETTING:
+		switch (old_state) {
+		case NVME_CTRL_NEW:
+		case NVME_CTRL_LIVE:
+			changed = true;
+			/* FALLTHRU */
+		default:
+			break;
+		}
+		break;
+	case NVME_CTRL_DELETING:
+		switch (old_state) {
+		case NVME_CTRL_LIVE:
+		case NVME_CTRL_RESETTING:
+			changed = true;
+			/* FALLTHRU */
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+	spin_unlock_irq(&ctrl->lock);
+
+	if (changed)
+		ctrl->state = new_state;
+
+	return changed;
+}
+EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
+
 static void nvme_free_ns(struct kref *kref)
 {
 	struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref);
@@ -138,6 +187,111 @@ struct request *nvme_alloc_request(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(nvme_alloc_request);
 
+static inline void nvme_setup_flush(struct nvme_ns *ns,
+		struct nvme_command *cmnd)
+{
+	memset(cmnd, 0, sizeof(*cmnd));
+	cmnd->common.opcode = nvme_cmd_flush;
+	cmnd->common.nsid = cpu_to_le32(ns->ns_id);
+}
+
+static inline int nvme_setup_discard(struct nvme_ns *ns, struct request *req,
+		struct nvme_command *cmnd)
+{
+	struct nvme_dsm_range *range;
+	struct page *page;
+	int offset;
+	unsigned int nr_bytes = blk_rq_bytes(req);
+
+	range = kmalloc(sizeof(*range), GFP_ATOMIC);
+	if (!range)
+		return BLK_MQ_RQ_QUEUE_BUSY;
+
+	range->cattr = cpu_to_le32(0);
+	range->nlb = cpu_to_le32(nr_bytes >> ns->lba_shift);
+	range->slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
+
+	memset(cmnd, 0, sizeof(*cmnd));
+	cmnd->dsm.opcode = nvme_cmd_dsm;
+	cmnd->dsm.nsid = cpu_to_le32(ns->ns_id);
+	cmnd->dsm.nr = 0;
+	cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
+
+	req->completion_data = range;
+	page = virt_to_page(range);
+	offset = offset_in_page(range);
+	blk_add_request_payload(req, page, offset, sizeof(*range));
+
+	/*
+	 * we set __data_len back to the size of the area to be discarded
+	 * on disk. This allows us to report completion on the full amount
+	 * of blocks described by the request.
+	 */
+	req->__data_len = nr_bytes;
+
+	return 0;
+}
+
+static inline void nvme_setup_rw(struct nvme_ns *ns, struct request *req,
+		struct nvme_command *cmnd)
+{
+	u16 control = 0;
+	u32 dsmgmt = 0;
+
+	if (req->cmd_flags & REQ_FUA)
+		control |= NVME_RW_FUA;
+	if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD))
+		control |= NVME_RW_LR;
+
+	if (req->cmd_flags & REQ_RAHEAD)
+		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
+
+	memset(cmnd, 0, sizeof(*cmnd));
+	cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
+	cmnd->rw.command_id = req->tag;
+	cmnd->rw.nsid = cpu_to_le32(ns->ns_id);
+	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
+	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
+
+	if (ns->ms) {
+		switch (ns->pi_type) {
+		case NVME_NS_DPS_PI_TYPE3:
+			control |= NVME_RW_PRINFO_PRCHK_GUARD;
+			break;
+		case NVME_NS_DPS_PI_TYPE1:
+		case NVME_NS_DPS_PI_TYPE2:
+			control |= NVME_RW_PRINFO_PRCHK_GUARD |
+					NVME_RW_PRINFO_PRCHK_REF;
+			cmnd->rw.reftag = cpu_to_le32(
+					nvme_block_nr(ns, blk_rq_pos(req)));
+			break;
+		}
+		if (!blk_integrity_rq(req))
+			control |= NVME_RW_PRINFO_PRACT;
+	}
+
+	cmnd->rw.control = cpu_to_le16(control);
+	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
+}
+
+int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
+		struct nvme_command *cmd)
+{
+	int ret = 0;
+
+	if (req->cmd_type == REQ_TYPE_DRV_PRIV)
+		memcpy(cmd, req->cmd, sizeof(*cmd));
+	else if (req->cmd_flags & REQ_FLUSH)
+		nvme_setup_flush(ns, cmd);
+	else if (req->cmd_flags & REQ_DISCARD)
+		ret = nvme_setup_discard(ns, req, cmd);
+	else
+		nvme_setup_rw(ns, req, cmd);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvme_setup_cmd);
+
 /*
  * Returns 0 on success.  If the result is negative, it's a Linux error code;
  * if the result is positive, it's an NVM Express status code
@@ -894,6 +1048,8 @@ EXPORT_SYMBOL_GPL(nvme_shutdown_ctrl);
 static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
 		struct request_queue *q)
 {
+	bool vwc = false;
+
 	if (ctrl->max_hw_sectors) {
 		u32 max_segments =
 			(ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1;
@@ -903,9 +1059,10 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
 	}
 	if (ctrl->stripe_size)
 		blk_queue_chunk_sectors(q, ctrl->stripe_size >> 9);
-	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
-		blk_queue_flush(q, REQ_FLUSH | REQ_FUA);
 	blk_queue_virt_boundary(q, ctrl->page_size - 1);
+	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
+		vwc = true;
+	blk_queue_write_cache(q, vwc, vwc);
 }
 
 /*
@@ -1272,7 +1429,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	if (nvme_revalidate_disk(ns->disk))
 		goto out_free_disk;
 
-	list_add_tail(&ns->list, &ctrl->namespaces);
+	list_add_tail_rcu(&ns->list, &ctrl->namespaces);
 	kref_get(&ctrl->kref);
 	if (ns->type == NVME_NS_LIGHTNVM)
 		return;
@@ -1295,6 +1452,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 static void nvme_ns_remove(struct nvme_ns *ns)
 {
+	lockdep_assert_held(&ns->ctrl->namespaces_mutex);
+
 	if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
 		return;
 
@@ -1307,9 +1466,8 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 		blk_mq_abort_requeue_list(ns->queue);
 		blk_cleanup_queue(ns->queue);
 	}
-	mutex_lock(&ns->ctrl->namespaces_mutex);
 	list_del_init(&ns->list);
-	mutex_unlock(&ns->ctrl->namespaces_mutex);
+	synchronize_rcu();
 	nvme_put_ns(ns);
 }
 
@@ -1361,7 +1519,7 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn)
 	return ret;
 }
 
-static void __nvme_scan_namespaces(struct nvme_ctrl *ctrl, unsigned nn)
+static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl, unsigned nn)
 {
 	struct nvme_ns *ns, *next;
 	unsigned i;
@@ -1377,11 +1535,16 @@ static void __nvme_scan_namespaces(struct nvme_ctrl *ctrl, unsigned nn)
 	}
 }
 
-void nvme_scan_namespaces(struct nvme_ctrl *ctrl)
+static void nvme_scan_work(struct work_struct *work)
 {
+	struct nvme_ctrl *ctrl =
+		container_of(work, struct nvme_ctrl, scan_work);
 	struct nvme_id_ctrl *id;
 	unsigned nn;
 
+	if (ctrl->state != NVME_CTRL_LIVE)
+		return;
+
 	if (nvme_identify_ctrl(ctrl, &id))
 		return;
 
@@ -1392,23 +1555,86 @@ void nvme_scan_namespaces(struct nvme_ctrl *ctrl)
 		if (!nvme_scan_ns_list(ctrl, nn))
 			goto done;
 	}
-	__nvme_scan_namespaces(ctrl, le32_to_cpup(&id->nn));
+	nvme_scan_ns_sequential(ctrl, nn);
  done:
 	list_sort(NULL, &ctrl->namespaces, ns_cmp);
 	mutex_unlock(&ctrl->namespaces_mutex);
 	kfree(id);
+
+	if (ctrl->ops->post_scan)
+		ctrl->ops->post_scan(ctrl);
+}
+
+void nvme_queue_scan(struct nvme_ctrl *ctrl)
+{
+	/*
+	 * Do not queue new scan work when a controller is reset during
+	 * removal.
+	 */
+	if (ctrl->state == NVME_CTRL_LIVE)
+		schedule_work(&ctrl->scan_work);
 }
-EXPORT_SYMBOL_GPL(nvme_scan_namespaces);
+EXPORT_SYMBOL_GPL(nvme_queue_scan);
 
 void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns, *next;
 
+	mutex_lock(&ctrl->namespaces_mutex);
 	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list)
 		nvme_ns_remove(ns);
+	mutex_unlock(&ctrl->namespaces_mutex);
 }
 EXPORT_SYMBOL_GPL(nvme_remove_namespaces);
 
+static void nvme_async_event_work(struct work_struct *work)
+{
+	struct nvme_ctrl *ctrl =
+		container_of(work, struct nvme_ctrl, async_event_work);
+
+	spin_lock_irq(&ctrl->lock);
+	while (ctrl->event_limit > 0) {
+		int aer_idx = --ctrl->event_limit;
+
+		spin_unlock_irq(&ctrl->lock);
+		ctrl->ops->submit_async_event(ctrl, aer_idx);
+		spin_lock_irq(&ctrl->lock);
+	}
+	spin_unlock_irq(&ctrl->lock);
+}
+
+void nvme_complete_async_event(struct nvme_ctrl *ctrl,
+		struct nvme_completion *cqe)
+{
+	u16 status = le16_to_cpu(cqe->status) >> 1;
+	u32 result = le32_to_cpu(cqe->result);
+
+	if (status == NVME_SC_SUCCESS || status == NVME_SC_ABORT_REQ) {
+		++ctrl->event_limit;
+		schedule_work(&ctrl->async_event_work);
+	}
+
+	if (status != NVME_SC_SUCCESS)
+		return;
+
+	switch (result & 0xff07) {
+	case NVME_AER_NOTICE_NS_CHANGED:
+		dev_info(ctrl->device, "rescanning\n");
+		nvme_queue_scan(ctrl);
+		break;
+	default:
+		dev_warn(ctrl->device, "async event result %08x\n", result);
+	}
+}
+EXPORT_SYMBOL_GPL(nvme_complete_async_event);
+
+void nvme_queue_async_events(struct nvme_ctrl *ctrl)
+{
+	ctrl->event_limit = NVME_NR_AERS;
+	schedule_work(&ctrl->async_event_work);
+}
+EXPORT_SYMBOL_GPL(nvme_queue_async_events);
+
 static DEFINE_IDA(nvme_instance_ida);
 
 static int nvme_set_instance(struct nvme_ctrl *ctrl)
@@ -1440,6 +1666,10 @@ static void nvme_release_instance(struct nvme_ctrl *ctrl)
 
 void nvme_uninit_ctrl(struct nvme_ctrl *ctrl)
 {
+	flush_work(&ctrl->async_event_work);
+	flush_work(&ctrl->scan_work);
+	nvme_remove_namespaces(ctrl);
+
 	device_destroy(nvme_class, MKDEV(nvme_char_major, ctrl->instance));
 
 	spin_lock(&dev_list_lock);
@@ -1475,12 +1705,16 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 {
 	int ret;
 
+	ctrl->state = NVME_CTRL_NEW;
+	spin_lock_init(&ctrl->lock);
 	INIT_LIST_HEAD(&ctrl->namespaces);
 	mutex_init(&ctrl->namespaces_mutex);
 	kref_init(&ctrl->kref);
 	ctrl->dev = dev;
 	ctrl->ops = ops;
 	ctrl->quirks = quirks;
+	INIT_WORK(&ctrl->scan_work, nvme_scan_work);
+	INIT_WORK(&ctrl->async_event_work, nvme_async_event_work);
 
 	ret = nvme_set_instance(ctrl);
 	if (ret)
@@ -1520,8 +1754,8 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
-	mutex_lock(&ctrl->namespaces_mutex);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		if (!kref_get_unless_zero(&ns->kref))
 			continue;
 
@@ -1538,7 +1772,7 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
 
 		nvme_put_ns(ns);
 	}
-	mutex_unlock(&ctrl->namespaces_mutex);
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(nvme_kill_queues);
 
@@ -1546,8 +1780,8 @@ void nvme_stop_queues(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
-	mutex_lock(&ctrl->namespaces_mutex);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		spin_lock_irq(ns->queue->queue_lock);
 		queue_flag_set(QUEUE_FLAG_STOPPED, ns->queue);
 		spin_unlock_irq(ns->queue->queue_lock);
@@ -1555,7 +1789,7 @@ void nvme_stop_queues(struct nvme_ctrl *ctrl)
 		blk_mq_cancel_requeue_work(ns->queue);
 		blk_mq_stop_hw_queues(ns->queue);
 	}
-	mutex_unlock(&ctrl->namespaces_mutex);
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(nvme_stop_queues);
 
@@ -1563,13 +1797,13 @@ void nvme_start_queues(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
-	mutex_lock(&ctrl->namespaces_mutex);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		queue_flag_clear_unlocked(QUEUE_FLAG_STOPPED, ns->queue);
 		blk_mq_start_stopped_hw_queues(ns->queue, true);
 		blk_mq_kick_requeue_list(ns->queue);
 	}
-	mutex_unlock(&ctrl->namespaces_mutex);
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(nvme_start_queues);
 
@@ -1607,9 +1841,9 @@ int __init nvme_core_init(void)
 
 void nvme_core_exit(void)
 {
-	unregister_blkdev(nvme_major, "nvme");
 	class_destroy(nvme_class);
 	__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
+	unregister_blkdev(nvme_major, "nvme");
 }
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 9461dd639acd..a0af0558354c 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -367,8 +367,8 @@ static int nvme_nvm_get_l2p_tbl(struct nvm_dev *nvmdev, u64 slba, u32 nlb,
 		ret = nvme_submit_sync_cmd(ns->ctrl->admin_q,
 				(struct nvme_command *)&c, entries, len);
 		if (ret) {
-			dev_err(ns->ctrl->dev, "L2P table transfer failed (%d)\n",
-									ret);
+			dev_err(ns->ctrl->device,
+				"L2P table transfer failed (%d)\n", ret);
 			ret = -EIO;
 			goto out;
 		}
@@ -387,41 +387,16 @@ out:
 	return ret;
 }
 
-static void nvme_nvm_bb_tbl_fold(struct nvm_dev *nvmdev,
-						int nr_dst_blks, u8 *dst_blks,
-						int nr_src_blks, u8 *src_blks)
-{
-	int blk, offset, pl, blktype;
-
-	for (blk = 0; blk < nr_dst_blks; blk++) {
-		offset = blk * nvmdev->plane_mode;
-		blktype = src_blks[offset];
-
-		/* Bad blocks on any planes take precedence over other types */
-		for (pl = 0; pl < nvmdev->plane_mode; pl++) {
-			if (src_blks[offset + pl] &
-					(NVM_BLK_T_BAD|NVM_BLK_T_GRWN_BAD)) {
-				blktype = src_blks[offset + pl];
-				break;
-			}
-		}
-
-		dst_blks[blk] = blktype;
-	}
-}
-
 static int nvme_nvm_get_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr ppa,
-				int nr_dst_blks, nvm_bb_update_fn *update_bbtbl,
-				void *priv)
+								u8 *blks)
 {
 	struct request_queue *q = nvmdev->q;
 	struct nvme_ns *ns = q->queuedata;
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	struct nvme_nvm_command c = {};
 	struct nvme_nvm_bb_tbl *bb_tbl;
-	u8 *dst_blks = NULL;
-	int nr_src_blks = nr_dst_blks * nvmdev->plane_mode;
-	int tblsz = sizeof(struct nvme_nvm_bb_tbl) + nr_src_blks;
+	int nr_blks = nvmdev->blks_per_lun * nvmdev->plane_mode;
+	int tblsz = sizeof(struct nvme_nvm_bb_tbl) + nr_blks;
 	int ret = 0;
 
 	c.get_bb.opcode = nvme_nvm_admin_get_bb_tbl;
@@ -432,54 +407,43 @@ static int nvme_nvm_get_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr ppa,
 	if (!bb_tbl)
 		return -ENOMEM;
 
-	dst_blks = kzalloc(nr_dst_blks, GFP_KERNEL);
-	if (!dst_blks) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
 	ret = nvme_submit_sync_cmd(ctrl->admin_q, (struct nvme_command *)&c,
 								bb_tbl, tblsz);
 	if (ret) {
-		dev_err(ctrl->dev, "get bad block table failed (%d)\n", ret);
+		dev_err(ctrl->device, "get bad block table failed (%d)\n", ret);
 		ret = -EIO;
 		goto out;
 	}
 
 	if (bb_tbl->tblid[0] != 'B' || bb_tbl->tblid[1] != 'B' ||
 		bb_tbl->tblid[2] != 'L' || bb_tbl->tblid[3] != 'T') {
-		dev_err(ctrl->dev, "bbt format mismatch\n");
+		dev_err(ctrl->device, "bbt format mismatch\n");
 		ret = -EINVAL;
 		goto out;
 	}
 
 	if (le16_to_cpu(bb_tbl->verid) != 1) {
 		ret = -EINVAL;
-		dev_err(ctrl->dev, "bbt version not supported\n");
+		dev_err(ctrl->device, "bbt version not supported\n");
 		goto out;
 	}
 
-	if (le32_to_cpu(bb_tbl->tblks) != nr_src_blks) {
+	if (le32_to_cpu(bb_tbl->tblks) != nr_blks) {
 		ret = -EINVAL;
-		dev_err(ctrl->dev, "bbt unsuspected blocks returned (%u!=%u)",
-				le32_to_cpu(bb_tbl->tblks), nr_src_blks);
+		dev_err(ctrl->device,
+				"bbt unsuspected blocks returned (%u!=%u)",
+				le32_to_cpu(bb_tbl->tblks), nr_blks);
 		goto out;
 	}
 
-	nvme_nvm_bb_tbl_fold(nvmdev, nr_dst_blks, dst_blks,
-						nr_src_blks, bb_tbl->blk);
-
-	ppa = dev_to_generic_addr(nvmdev, ppa);
-	ret = update_bbtbl(ppa, nr_dst_blks, dst_blks, priv);
-
+	memcpy(blks, bb_tbl->blk, nvmdev->blks_per_lun * nvmdev->plane_mode);
 out:
-	kfree(dst_blks);
 	kfree(bb_tbl);
 	return ret;
 }
 
-static int nvme_nvm_set_bb_tbl(struct nvm_dev *nvmdev, struct nvm_rq *rqd,
-								int type)
+static int nvme_nvm_set_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr *ppas,
+							int nr_ppas, int type)
 {
 	struct nvme_ns *ns = nvmdev->q->queuedata;
 	struct nvme_nvm_command c = {};
@@ -487,14 +451,15 @@ static int nvme_nvm_set_bb_tbl(struct nvm_dev *nvmdev, struct nvm_rq *rqd,
 
 	c.set_bb.opcode = nvme_nvm_admin_set_bb_tbl;
 	c.set_bb.nsid = cpu_to_le32(ns->ns_id);
-	c.set_bb.spba = cpu_to_le64(rqd->ppa_addr.ppa);
-	c.set_bb.nlb = cpu_to_le16(rqd->nr_pages - 1);
+	c.set_bb.spba = cpu_to_le64(ppas->ppa);
+	c.set_bb.nlb = cpu_to_le16(nr_ppas - 1);
 	c.set_bb.value = type;
 
 	ret = nvme_submit_sync_cmd(ns->ctrl->admin_q, (struct nvme_command *)&c,
 								NULL, 0);
 	if (ret)
-		dev_err(ns->ctrl->dev, "set bad block table failed (%d)\n", ret);
+		dev_err(ns->ctrl->device, "set bad block table failed (%d)\n",
+									ret);
 	return ret;
 }
 
@@ -504,8 +469,9 @@ static inline void nvme_nvm_rqtocmd(struct request *rq, struct nvm_rq *rqd,
 	c->ph_rw.opcode = rqd->opcode;
 	c->ph_rw.nsid = cpu_to_le32(ns->ns_id);
 	c->ph_rw.spba = cpu_to_le64(rqd->ppa_addr.ppa);
+	c->ph_rw.metadata = cpu_to_le64(rqd->dma_meta_list);
 	c->ph_rw.control = cpu_to_le16(rqd->flags);
-	c->ph_rw.length = cpu_to_le16(rqd->nr_pages - 1);
+	c->ph_rw.length = cpu_to_le16(rqd->nr_ppas - 1);
 
 	if (rqd->opcode == NVM_OP_HBWRITE || rqd->opcode == NVM_OP_HBREAD)
 		c->hb_rw.slba = cpu_to_le64(nvme_block_nr(ns,
@@ -576,7 +542,7 @@ static int nvme_nvm_erase_block(struct nvm_dev *dev, struct nvm_rq *rqd)
 	c.erase.opcode = NVM_OP_ERASE;
 	c.erase.nsid = cpu_to_le32(ns->ns_id);
 	c.erase.spba = cpu_to_le64(rqd->ppa_addr.ppa);
-	c.erase.length = cpu_to_le16(rqd->nr_pages - 1);
+	c.erase.length = cpu_to_le16(rqd->nr_ppas - 1);
 
 	return nvme_submit_sync_cmd(q, (struct nvme_command *)&c, NULL, 0);
 }
@@ -601,10 +567,10 @@ static void *nvme_nvm_dev_dma_alloc(struct nvm_dev *dev, void *pool,
 	return dma_pool_alloc(pool, mem_flags, dma_handler);
 }
 
-static void nvme_nvm_dev_dma_free(void *pool, void *ppa_list,
+static void nvme_nvm_dev_dma_free(void *pool, void *addr,
 							dma_addr_t dma_handler)
 {
-	dma_pool_free(pool, ppa_list, dma_handler);
+	dma_pool_free(pool, addr, dma_handler);
 }
 
 static struct nvm_dev_ops nvme_nvm_dev_ops = {
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index f846da4eb338..114b92873894 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -67,7 +67,16 @@ enum nvme_quirks {
 	NVME_QUIRK_DISCARD_ZEROES		= (1 << 2),
 };
 
+enum nvme_ctrl_state {
+	NVME_CTRL_NEW,
+	NVME_CTRL_LIVE,
+	NVME_CTRL_RESETTING,
+	NVME_CTRL_DELETING,
+};
+
 struct nvme_ctrl {
+	enum nvme_ctrl_state state;
+	spinlock_t lock;
 	const struct nvme_ctrl_ops *ops;
 	struct request_queue *admin_q;
 	struct device *dev;
@@ -84,7 +93,7 @@ struct nvme_ctrl {
 	char serial[20];
 	char model[40];
 	char firmware_rev[8];
-	int cntlid;
+	u16 cntlid;
 
 	u32 ctrl_config;
 
@@ -99,6 +108,8 @@ struct nvme_ctrl {
 	u32 vs;
 	bool subsystem;
 	unsigned long quirks;
+	struct work_struct scan_work;
+	struct work_struct async_event_work;
 };
 
 /*
@@ -136,9 +147,10 @@ struct nvme_ctrl_ops {
 	int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val);
 	int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val);
 	int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
-	bool (*io_incapable)(struct nvme_ctrl *ctrl);
 	int (*reset_ctrl)(struct nvme_ctrl *ctrl);
 	void (*free_ctrl)(struct nvme_ctrl *ctrl);
+	void (*post_scan)(struct nvme_ctrl *ctrl);
+	void (*submit_async_event)(struct nvme_ctrl *ctrl, int aer_idx);
 };
 
 static inline bool nvme_ctrl_ready(struct nvme_ctrl *ctrl)
@@ -150,17 +162,6 @@ static inline bool nvme_ctrl_ready(struct nvme_ctrl *ctrl)
 	return val & NVME_CSTS_RDY;
 }
 
-static inline bool nvme_io_incapable(struct nvme_ctrl *ctrl)
-{
-	u32 val = 0;
-
-	if (ctrl->ops->io_incapable(ctrl))
-		return true;
-	if (ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &val))
-		return true;
-	return val & NVME_CSTS_CFS;
-}
-
 static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl)
 {
 	if (!ctrl->subsystem)
@@ -173,57 +174,20 @@ static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector)
 	return (sector >> (ns->lba_shift - 9));
 }
 
-static inline void nvme_setup_flush(struct nvme_ns *ns,
-		struct nvme_command *cmnd)
+static inline unsigned nvme_map_len(struct request *rq)
 {
-	memset(cmnd, 0, sizeof(*cmnd));
-	cmnd->common.opcode = nvme_cmd_flush;
-	cmnd->common.nsid = cpu_to_le32(ns->ns_id);
+	if (rq->cmd_flags & REQ_DISCARD)
+		return sizeof(struct nvme_dsm_range);
+	else
+		return blk_rq_bytes(rq);
 }
 
-static inline void nvme_setup_rw(struct nvme_ns *ns, struct request *req,
-		struct nvme_command *cmnd)
+static inline void nvme_cleanup_cmd(struct request *req)
 {
-	u16 control = 0;
-	u32 dsmgmt = 0;
-
-	if (req->cmd_flags & REQ_FUA)
-		control |= NVME_RW_FUA;
-	if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD))
-		control |= NVME_RW_LR;
-
-	if (req->cmd_flags & REQ_RAHEAD)
-		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
-
-	memset(cmnd, 0, sizeof(*cmnd));
-	cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
-	cmnd->rw.command_id = req->tag;
-	cmnd->rw.nsid = cpu_to_le32(ns->ns_id);
-	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
-	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
-
-	if (ns->ms) {
-		switch (ns->pi_type) {
-		case NVME_NS_DPS_PI_TYPE3:
-			control |= NVME_RW_PRINFO_PRCHK_GUARD;
-			break;
-		case NVME_NS_DPS_PI_TYPE1:
-		case NVME_NS_DPS_PI_TYPE2:
-			control |= NVME_RW_PRINFO_PRCHK_GUARD |
-					NVME_RW_PRINFO_PRCHK_REF;
-			cmnd->rw.reftag = cpu_to_le32(
-					nvme_block_nr(ns, blk_rq_pos(req)));
-			break;
-		}
-		if (!blk_integrity_rq(req))
-			control |= NVME_RW_PRINFO_PRACT;
-	}
-
-	cmnd->rw.control = cpu_to_le16(control);
-	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
+	if (req->cmd_flags & REQ_DISCARD)
+		kfree(req->completion_data);
 }
 
-
 static inline int nvme_error_status(u16 status)
 {
 	switch (status & 0x7ff) {
@@ -242,6 +206,8 @@ static inline bool nvme_req_needs_retry(struct request *req, u16 status)
 		(jiffies - req->start_time) < req->timeout;
 }
 
+bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
+		enum nvme_ctrl_state new_state);
 int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap);
 int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap);
 int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl);
@@ -251,9 +217,14 @@ void nvme_uninit_ctrl(struct nvme_ctrl *ctrl);
 void nvme_put_ctrl(struct nvme_ctrl *ctrl);
 int nvme_init_identify(struct nvme_ctrl *ctrl);
 
-void nvme_scan_namespaces(struct nvme_ctrl *ctrl);
+void nvme_queue_scan(struct nvme_ctrl *ctrl);
 void nvme_remove_namespaces(struct nvme_ctrl *ctrl);
 
+#define NVME_NR_AERS	1
+void nvme_complete_async_event(struct nvme_ctrl *ctrl,
+		struct nvme_completion *cqe);
+void nvme_queue_async_events(struct nvme_ctrl *ctrl);
+
 void nvme_stop_queues(struct nvme_ctrl *ctrl);
 void nvme_start_queues(struct nvme_ctrl *ctrl);
 void nvme_kill_queues(struct nvme_ctrl *ctrl);
@@ -261,6 +232,8 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl);
 struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, unsigned int flags);
 void nvme_requeue_req(struct request *req);
+int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
+		struct nvme_command *cmd);
 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,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 4fd733ff72b1..0f093f14d348 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -54,8 +54,7 @@
  * We handle AEN commands ourselves and don't even let the
  * block layer know about them.
  */
-#define NVME_NR_AEN_COMMANDS	1
-#define NVME_AQ_BLKMQ_DEPTH	(NVME_AQ_DEPTH - NVME_NR_AEN_COMMANDS)
+#define NVME_AQ_BLKMQ_DEPTH	(NVME_AQ_DEPTH - NVME_NR_AERS)
 
 static int use_threaded_interrupts;
 module_param(use_threaded_interrupts, int, 0);
@@ -92,9 +91,7 @@ struct nvme_dev {
 	struct msix_entry *entry;
 	void __iomem *bar;
 	struct work_struct reset_work;
-	struct work_struct scan_work;
 	struct work_struct remove_work;
-	struct work_struct async_work;
 	struct timer_list watchdog_timer;
 	struct mutex shutdown_lock;
 	bool subsystem;
@@ -102,11 +99,6 @@ struct nvme_dev {
 	dma_addr_t cmb_dma_addr;
 	u64 cmb_size;
 	u32 cmbsz;
-	unsigned long flags;
-
-#define NVME_CTRL_RESETTING    0
-#define NVME_CTRL_REMOVING     1
-
 	struct nvme_ctrl ctrl;
 	struct completion ioq_wait;
 };
@@ -271,40 +263,6 @@ static int nvme_init_request(void *data, struct request *req,
 	return 0;
 }
 
-static void nvme_queue_scan(struct nvme_dev *dev)
-{
-	/*
-	 * Do not queue new scan work when a controller is reset during
-	 * removal.
-	 */
-	if (test_bit(NVME_CTRL_REMOVING, &dev->flags))
-		return;
-	queue_work(nvme_workq, &dev->scan_work);
-}
-
-static void nvme_complete_async_event(struct nvme_dev *dev,
-		struct nvme_completion *cqe)
-{
-	u16 status = le16_to_cpu(cqe->status) >> 1;
-	u32 result = le32_to_cpu(cqe->result);
-
-	if (status == NVME_SC_SUCCESS || status == NVME_SC_ABORT_REQ) {
-		++dev->ctrl.event_limit;
-		queue_work(nvme_workq, &dev->async_work);
-	}
-
-	if (status != NVME_SC_SUCCESS)
-		return;
-
-	switch (result & 0xff07) {
-	case NVME_AER_NOTICE_NS_CHANGED:
-		dev_info(dev->ctrl.device, "rescanning\n");
-		nvme_queue_scan(dev);
-	default:
-		dev_warn(dev->ctrl.device, "async event result %08x\n", result);
-	}
-}
-
 /**
  * __nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
  * @nvmeq: The queue to use
@@ -334,16 +292,11 @@ static __le64 **iod_list(struct request *req)
 	return (__le64 **)(iod->sg + req->nr_phys_segments);
 }
 
-static int nvme_init_iod(struct request *rq, struct nvme_dev *dev)
+static int nvme_init_iod(struct request *rq, unsigned size,
+		struct nvme_dev *dev)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(rq);
 	int nseg = rq->nr_phys_segments;
-	unsigned size;
-
-	if (rq->cmd_flags & REQ_DISCARD)
-		size = sizeof(struct nvme_dsm_range);
-	else
-		size = blk_rq_bytes(rq);
 
 	if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) {
 		iod->sg = kmalloc(nvme_iod_alloc_size(dev, size, nseg), GFP_ATOMIC);
@@ -368,6 +321,8 @@ static void nvme_free_iod(struct nvme_dev *dev, struct request *req)
 	__le64 **list = iod_list(req);
 	dma_addr_t prp_dma = iod->first_dma;
 
+	nvme_cleanup_cmd(req);
+
 	if (iod->npages == 0)
 		dma_pool_free(dev->prp_small_pool, list[0], prp_dma);
 	for (i = 0; i < iod->npages; i++) {
@@ -529,7 +484,7 @@ static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req,
 }
 
 static int nvme_map_data(struct nvme_dev *dev, struct request *req,
-		struct nvme_command *cmnd)
+		unsigned size, struct nvme_command *cmnd)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct request_queue *q = req->q;
@@ -546,7 +501,7 @@ static int nvme_map_data(struct nvme_dev *dev, struct request *req,
 	if (!dma_map_sg(dev->dev, iod->sg, iod->nents, dma_dir))
 		goto out;
 
-	if (!nvme_setup_prps(dev, req, blk_rq_bytes(req)))
+	if (!nvme_setup_prps(dev, req, size))
 		goto out_unmap;
 
 	ret = BLK_MQ_RQ_QUEUE_ERROR;
@@ -596,37 +551,6 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 }
 
 /*
- * We reuse the small pool to allocate the 16-byte range here as it is not
- * worth having a special pool for these or additional cases to handle freeing
- * the iod.
- */
-static int nvme_setup_discard(struct nvme_queue *nvmeq, struct nvme_ns *ns,
-		struct request *req, struct nvme_command *cmnd)
-{
-	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-	struct nvme_dsm_range *range;
-
-	range = dma_pool_alloc(nvmeq->dev->prp_small_pool, GFP_ATOMIC,
-						&iod->first_dma);
-	if (!range)
-		return BLK_MQ_RQ_QUEUE_BUSY;
-	iod_list(req)[0] = (__le64 *)range;
-	iod->npages = 0;
-
-	range->cattr = cpu_to_le32(0);
-	range->nlb = cpu_to_le32(blk_rq_bytes(req) >> ns->lba_shift);
-	range->slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
-
-	memset(cmnd, 0, sizeof(*cmnd));
-	cmnd->dsm.opcode = nvme_cmd_dsm;
-	cmnd->dsm.nsid = cpu_to_le32(ns->ns_id);
-	cmnd->dsm.prp1 = cpu_to_le64(iod->first_dma);
-	cmnd->dsm.nr = 0;
-	cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
-	return BLK_MQ_RQ_QUEUE_OK;
-}
-
-/*
  * NOTE: ns is NULL when called on the admin queue.
  */
 static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
@@ -637,6 +561,7 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct nvme_dev *dev = nvmeq->dev;
 	struct request *req = bd->rq;
 	struct nvme_command cmnd;
+	unsigned map_len;
 	int ret = BLK_MQ_RQ_QUEUE_OK;
 
 	/*
@@ -652,23 +577,17 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 		}
 	}
 
-	ret = nvme_init_iod(req, dev);
+	map_len = nvme_map_len(req);
+	ret = nvme_init_iod(req, map_len, dev);
 	if (ret)
 		return ret;
 
-	if (req->cmd_flags & REQ_DISCARD) {
-		ret = nvme_setup_discard(nvmeq, ns, req, &cmnd);
-	} else {
-		if (req->cmd_type == REQ_TYPE_DRV_PRIV)
-			memcpy(&cmnd, req->cmd, sizeof(cmnd));
-		else if (req->cmd_flags & REQ_FLUSH)
-			nvme_setup_flush(ns, &cmnd);
-		else
-			nvme_setup_rw(ns, req, &cmnd);
+	ret = nvme_setup_cmd(ns, req, &cmnd);
+	if (ret)
+		goto out;
 
-		if (req->nr_phys_segments)
-			ret = nvme_map_data(dev, req, &cmnd);
-	}
+	if (req->nr_phys_segments)
+		ret = nvme_map_data(dev, req, map_len, &cmnd);
 
 	if (ret)
 		goto out;
@@ -764,7 +683,7 @@ static void __nvme_process_cq(struct nvme_queue *nvmeq, unsigned int *tag)
 		 */
 		if (unlikely(nvmeq->qid == 0 &&
 				cqe.command_id >= NVME_AQ_BLKMQ_DEPTH)) {
-			nvme_complete_async_event(nvmeq->dev, &cqe);
+			nvme_complete_async_event(&nvmeq->dev->ctrl, &cqe);
 			continue;
 		}
 
@@ -833,21 +752,18 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
 	return 0;
 }
 
-static void nvme_async_event_work(struct work_struct *work)
+static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl, int aer_idx)
 {
-	struct nvme_dev *dev = container_of(work, struct nvme_dev, async_work);
+	struct nvme_dev *dev = to_nvme_dev(ctrl);
 	struct nvme_queue *nvmeq = dev->queues[0];
 	struct nvme_command c;
 
 	memset(&c, 0, sizeof(c));
 	c.common.opcode = nvme_admin_async_event;
+	c.common.command_id = NVME_AQ_BLKMQ_DEPTH + aer_idx;
 
 	spin_lock_irq(&nvmeq->q_lock);
-	while (dev->ctrl.event_limit > 0) {
-		c.common.command_id = NVME_AQ_BLKMQ_DEPTH +
-			--dev->ctrl.event_limit;
-		__nvme_submit_cmd(nvmeq, &c);
-	}
+	__nvme_submit_cmd(nvmeq, &c);
 	spin_unlock_irq(&nvmeq->q_lock);
 }
 
@@ -939,7 +855,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	 * cancellation error. All outstanding requests are completed on
 	 * shutdown, so we return BLK_EH_HANDLED.
 	 */
-	if (test_bit(NVME_CTRL_RESETTING, &dev->flags)) {
+	if (dev->ctrl.state == NVME_CTRL_RESETTING) {
 		dev_warn(dev->ctrl.device,
 			 "I/O %d QID %d timeout, disable controller\n",
 			 req->tag, nvmeq->qid);
@@ -1003,16 +919,15 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	return BLK_EH_RESET_TIMER;
 }
 
-static void nvme_cancel_queue_ios(struct request *req, void *data, bool reserved)
+static void nvme_cancel_io(struct request *req, void *data, bool reserved)
 {
-	struct nvme_queue *nvmeq = data;
 	int status;
 
 	if (!blk_mq_request_started(req))
 		return;
 
-	dev_dbg_ratelimited(nvmeq->dev->ctrl.device,
-		 "Cancelling I/O %d QID %d\n", req->tag, nvmeq->qid);
+	dev_dbg_ratelimited(((struct nvme_dev *) data)->ctrl.device,
+				"Cancelling I/O %d", req->tag);
 
 	status = NVME_SC_ABORT_REQ;
 	if (blk_queue_dying(req->q))
@@ -1069,14 +984,6 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 	return 0;
 }
 
-static void nvme_clear_queue(struct nvme_queue *nvmeq)
-{
-	spin_lock_irq(&nvmeq->q_lock);
-	if (nvmeq->tags && *nvmeq->tags)
-		blk_mq_all_tag_busy_iter(*nvmeq->tags, nvme_cancel_queue_ios, nvmeq);
-	spin_unlock_irq(&nvmeq->q_lock);
-}
-
 static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
 {
 	struct nvme_queue *nvmeq = dev->queues[0];
@@ -1350,22 +1257,44 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	return result;
 }
 
+static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
+{
+
+	/* If true, indicates loss of adapter communication, possibly by a
+	 * NVMe Subsystem reset.
+	 */
+	bool nssro = dev->subsystem && (csts & NVME_CSTS_NSSRO);
+
+	/* If there is a reset ongoing, we shouldn't reset again. */
+	if (work_busy(&dev->reset_work))
+		return false;
+
+	/* We shouldn't reset unless the controller is on fatal error state
+	 * _or_ if we lost the communication with it.
+	 */
+	if (!(csts & NVME_CSTS_CFS) && !nssro)
+		return false;
+
+	/* If PCI error recovery process is happening, we cannot reset or
+	 * the recovery mechanism will surely fail.
+	 */
+	if (pci_channel_offline(to_pci_dev(dev->dev)))
+		return false;
+
+	return true;
+}
+
 static void nvme_watchdog_timer(unsigned long data)
 {
 	struct nvme_dev *dev = (struct nvme_dev *)data;
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
 
-	/*
-	 * Skip controllers currently under reset.
-	 */
-	if (!work_pending(&dev->reset_work) && !work_busy(&dev->reset_work) &&
-	    ((csts & NVME_CSTS_CFS) ||
-	     (dev->subsystem && (csts & NVME_CSTS_NSSRO)))) {
-		if (queue_work(nvme_workq, &dev->reset_work)) {
+	/* Skip controllers under certain specific conditions. */
+	if (nvme_should_reset(dev, csts)) {
+		if (queue_work(nvme_workq, &dev->reset_work))
 			dev_warn(dev->dev,
 				"Failed status: 0x%x, reset controller.\n",
 				csts);
-		}
 		return;
 	}
 
@@ -1551,8 +1480,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	return result;
 }
 
-static void nvme_set_irq_hints(struct nvme_dev *dev)
+static void nvme_pci_post_scan(struct nvme_ctrl *ctrl)
 {
+	struct nvme_dev *dev = to_nvme_dev(ctrl);
 	struct nvme_queue *nvmeq;
 	int i;
 
@@ -1567,16 +1497,6 @@ static void nvme_set_irq_hints(struct nvme_dev *dev)
 	}
 }
 
-static void nvme_dev_scan(struct work_struct *work)
-{
-	struct nvme_dev *dev = container_of(work, struct nvme_dev, scan_work);
-
-	if (!dev->tagset.tags)
-		return;
-	nvme_scan_namespaces(&dev->ctrl);
-	nvme_set_irq_hints(dev);
-}
-
 static void nvme_del_queue_end(struct request *req, int error)
 {
 	struct nvme_queue *nvmeq = req->end_io_data;
@@ -1592,7 +1512,13 @@ static void nvme_del_cq_end(struct request *req, int error)
 	if (!error) {
 		unsigned long flags;
 
-		spin_lock_irqsave(&nvmeq->q_lock, flags);
+		/*
+		 * We might be called with the AQ q_lock held
+		 * and the I/O queue q_lock should always
+		 * nest inside the AQ one.
+		 */
+		spin_lock_irqsave_nested(&nvmeq->q_lock, flags,
+					SINGLE_DEPTH_NESTING);
 		nvme_process_cq(nvmeq);
 		spin_unlock_irqrestore(&nvmeq->q_lock, flags);
 	}
@@ -1684,7 +1610,6 @@ static int nvme_dev_add(struct nvme_dev *dev)
 		nvme_free_queues(dev, dev->online_queues);
 	}
 
-	nvme_queue_scan(dev);
 	return 0;
 }
 
@@ -1797,8 +1722,8 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	}
 	nvme_pci_disable(dev);
 
-	for (i = dev->queue_count - 1; i >= 0; i--)
-		nvme_clear_queue(dev->queues[i]);
+	blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_io, dev);
+	blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_io, dev);
 	mutex_unlock(&dev->shutdown_lock);
 }
 
@@ -1854,7 +1779,7 @@ static void nvme_reset_work(struct work_struct *work)
 	struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work);
 	int result = -ENODEV;
 
-	if (WARN_ON(test_bit(NVME_CTRL_RESETTING, &dev->flags)))
+	if (WARN_ON(dev->ctrl.state == NVME_CTRL_RESETTING))
 		goto out;
 
 	/*
@@ -1864,11 +1789,9 @@ static void nvme_reset_work(struct work_struct *work)
 	if (dev->ctrl.ctrl_config & NVME_CC_ENABLE)
 		nvme_dev_disable(dev, false);
 
-	if (test_bit(NVME_CTRL_REMOVING, &dev->flags))
+	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING))
 		goto out;
 
-	set_bit(NVME_CTRL_RESETTING, &dev->flags);
-
 	result = nvme_pci_enable(dev);
 	if (result)
 		goto out;
@@ -1890,8 +1813,14 @@ static void nvme_reset_work(struct work_struct *work)
 	if (result)
 		goto out;
 
-	dev->ctrl.event_limit = NVME_NR_AEN_COMMANDS;
-	queue_work(nvme_workq, &dev->async_work);
+	/*
+	 * A controller that can not execute IO typically requires user
+	 * intervention to correct. For such degraded controllers, the driver
+	 * should not submit commands the user did not request, so skip
+	 * registering for asynchronous event notification on this condition.
+	 */
+	if (dev->online_queues > 1)
+		nvme_queue_async_events(&dev->ctrl);
 
 	mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + HZ));
 
@@ -1901,13 +1830,20 @@ static void nvme_reset_work(struct work_struct *work)
 	 */
 	if (dev->online_queues < 2) {
 		dev_warn(dev->ctrl.device, "IO queues not created\n");
+		nvme_kill_queues(&dev->ctrl);
 		nvme_remove_namespaces(&dev->ctrl);
 	} else {
 		nvme_start_queues(&dev->ctrl);
 		nvme_dev_add(dev);
 	}
 
-	clear_bit(NVME_CTRL_RESETTING, &dev->flags);
+	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_LIVE)) {
+		dev_warn(dev->ctrl.device, "failed to mark controller live\n");
+		goto out;
+	}
+
+	if (dev->online_queues > 1)
+		nvme_queue_scan(&dev->ctrl);
 	return;
 
  out:
@@ -1955,13 +1891,6 @@ static int nvme_pci_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 	return 0;
 }
 
-static bool nvme_pci_io_incapable(struct nvme_ctrl *ctrl)
-{
-	struct nvme_dev *dev = to_nvme_dev(ctrl);
-
-	return !dev->bar || dev->online_queues < 2;
-}
-
 static int nvme_pci_reset_ctrl(struct nvme_ctrl *ctrl)
 {
 	return nvme_reset(to_nvme_dev(ctrl));
@@ -1972,9 +1901,10 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.reg_read32		= nvme_pci_reg_read32,
 	.reg_write32		= nvme_pci_reg_write32,
 	.reg_read64		= nvme_pci_reg_read64,
-	.io_incapable		= nvme_pci_io_incapable,
 	.reset_ctrl		= nvme_pci_reset_ctrl,
 	.free_ctrl		= nvme_pci_free_ctrl,
+	.post_scan		= nvme_pci_post_scan,
+	.submit_async_event	= nvme_pci_submit_async_event,
 };
 
 static int nvme_dev_map(struct nvme_dev *dev)
@@ -2026,10 +1956,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (result)
 		goto free;
 
-	INIT_WORK(&dev->scan_work, nvme_dev_scan);
 	INIT_WORK(&dev->reset_work, nvme_reset_work);
 	INIT_WORK(&dev->remove_work, nvme_remove_dead_ctrl_work);
-	INIT_WORK(&dev->async_work, nvme_async_event_work);
 	setup_timer(&dev->watchdog_timer, nvme_watchdog_timer,
 		(unsigned long)dev);
 	mutex_init(&dev->shutdown_lock);
@@ -2086,15 +2014,12 @@ static void nvme_remove(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
 
-	set_bit(NVME_CTRL_REMOVING, &dev->flags);
+	nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
+
 	pci_set_drvdata(pdev, NULL);
-	flush_work(&dev->async_work);
 	flush_work(&dev->reset_work);
-	flush_work(&dev->scan_work);
-	nvme_remove_namespaces(&dev->ctrl);
 	nvme_uninit_ctrl(&dev->ctrl);
 	nvme_dev_disable(dev, true);
-	flush_work(&dev->reset_work);
 	nvme_dev_remove_admin(dev);
 	nvme_free_queues(dev, 0);
 	nvme_release_cmb(dev);