1 files changed, 430 insertions, 689 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index a5653892d773..b6f7815fa239 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -89,6 +89,10 @@ static dev_t nvme_ctrl_base_chr_devt;
 static struct class *nvme_class;
 static struct class *nvme_subsys_class;
 
+static DEFINE_IDA(nvme_ns_chr_minor_ida);
+static dev_t nvme_ns_chr_devt;
+static struct class *nvme_ns_chr_class;
+
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 					   unsigned nsid);
@@ -112,7 +116,7 @@ static void nvme_set_queue_dying(struct nvme_ns *ns)
 	set_capacity_and_notify(ns->disk, 0);
 }
 
-static void nvme_queue_scan(struct nvme_ctrl *ctrl)
+void nvme_queue_scan(struct nvme_ctrl *ctrl)
 {
 	/*
 	 * Only new queue scan work when admin and IO queues are both alive
@@ -179,7 +183,7 @@ int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_reset_ctrl);
 
-static int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
+int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
 {
 	int ret;
 
@@ -549,7 +553,12 @@ static void nvme_free_ns_head(struct kref *ref)
 	kfree(head);
 }
 
-static void nvme_put_ns_head(struct nvme_ns_head *head)
+bool nvme_tryget_ns_head(struct nvme_ns_head *head)
+{
+	return kref_get_unless_zero(&head->ref);
+}
+
+void nvme_put_ns_head(struct nvme_ns_head *head)
 {
 	kref_put(&head->ref, nvme_free_ns_head);
 }
@@ -575,11 +584,12 @@ EXPORT_SYMBOL_NS_GPL(nvme_put_ns, NVME_TARGET_PASSTHRU);
 
 static inline void nvme_clear_nvme_request(struct request *req)
 {
-	if (!(req->rq_flags & RQF_DONTPREP)) {
-		nvme_req(req)->retries = 0;
-		nvme_req(req)->flags = 0;
-		req->rq_flags |= RQF_DONTPREP;
-	}
+	struct nvme_command *cmd = nvme_req(req)->cmd;
+
+	memset(cmd, 0, sizeof(*cmd));
+	nvme_req(req)->retries = 0;
+	nvme_req(req)->flags = 0;
+	req->rq_flags |= RQF_DONTPREP;
 }
 
 static inline unsigned int nvme_req_op(struct nvme_command *cmd)
@@ -595,9 +605,12 @@ static inline void nvme_init_request(struct request *req,
 	else /* no queuedata implies admin queue */
 		req->timeout = NVME_ADMIN_TIMEOUT;
 
+	/* passthru commands should let the driver set the SGL flags */
+	cmd->common.flags &= ~NVME_CMD_SGL_ALL;
+
 	req->cmd_flags |= REQ_FAILFAST_DRIVER;
 	nvme_clear_nvme_request(req);
-	nvme_req(req)->cmd = cmd;
+	memcpy(nvme_req(req)->cmd, cmd, sizeof(*cmd));
 }
 
 struct request *nvme_alloc_request(struct request_queue *q,
@@ -726,14 +739,6 @@ static void nvme_assign_write_stream(struct nvme_ctrl *ctrl,
 		req->q->write_hints[streamid] += blk_rq_bytes(req) >> 9;
 }
 
-static void nvme_setup_passthrough(struct request *req,
-		struct nvme_command *cmd)
-{
-	memcpy(cmd, nvme_req(req)->cmd, sizeof(*cmd));
-	/* passthru commands should let the driver set the SGL flags */
-	cmd->common.flags &= ~NVME_CMD_SGL_ALL;
-}
-
 static inline void nvme_setup_flush(struct nvme_ns *ns,
 		struct nvme_command *cmnd)
 {
@@ -888,18 +893,18 @@ void nvme_cleanup_cmd(struct request *req)
 }
 EXPORT_SYMBOL_GPL(nvme_cleanup_cmd);
 
-blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
-		struct nvme_command *cmd)
+blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req)
 {
+	struct nvme_command *cmd = nvme_req(req)->cmd;
 	blk_status_t ret = BLK_STS_OK;
 
-	nvme_clear_nvme_request(req);
+	if (!(req->rq_flags & RQF_DONTPREP))
+		nvme_clear_nvme_request(req);
 
-	memset(cmd, 0, sizeof(*cmd));
 	switch (req_op(req)) {
 	case REQ_OP_DRV_IN:
 	case REQ_OP_DRV_OUT:
-		nvme_setup_passthrough(req, cmd);
+		/* these are setup prior to execution in nvme_init_request() */
 		break;
 	case REQ_OP_FLUSH:
 		nvme_setup_flush(ns, cmd);
@@ -1020,40 +1025,6 @@ int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 }
 EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd);
 
-static void *nvme_add_user_metadata(struct bio *bio, void __user *ubuf,
-		unsigned len, u32 seed, bool write)
-{
-	struct bio_integrity_payload *bip;
-	int ret = -ENOMEM;
-	void *buf;
-
-	buf = kmalloc(len, GFP_KERNEL);
-	if (!buf)
-		goto out;
-
-	ret = -EFAULT;
-	if (write && copy_from_user(buf, ubuf, len))
-		goto out_free_meta;
-
-	bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
-	if (IS_ERR(bip)) {
-		ret = PTR_ERR(bip);
-		goto out_free_meta;
-	}
-
-	bip->bip_iter.bi_size = len;
-	bip->bip_iter.bi_sector = seed;
-	ret = bio_integrity_add_page(bio, virt_to_page(buf), len,
-			offset_in_page(buf));
-	if (ret == len)
-		return buf;
-	ret = -ENOMEM;
-out_free_meta:
-	kfree(buf);
-out:
-	return ERR_PTR(ret);
-}
-
 static u32 nvme_known_admin_effects(u8 opcode)
 {
 	switch (opcode) {
@@ -1076,9 +1047,9 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
 		if (ns->head->effects)
 			effects = le32_to_cpu(ns->head->effects->iocs[opcode]);
 		if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))
-			dev_warn(ctrl->device,
-				 "IO command:%02x has unhandled effects:%08x\n",
-				 opcode, effects);
+			dev_warn_once(ctrl->device,
+				"IO command:%02x has unhandled effects:%08x\n",
+				opcode, effects);
 		return 0;
 	}
 
@@ -1120,7 +1091,7 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
 		mutex_unlock(&ctrl->scan_lock);
 	}
 	if (effects & NVME_CMD_EFFECTS_CCC)
-		nvme_init_identify(ctrl);
+		nvme_init_ctrl_finish(ctrl);
 	if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC)) {
 		nvme_queue_scan(ctrl);
 		flush_work(&ctrl->scan_work);
@@ -1137,68 +1108,20 @@ void nvme_execute_passthru_rq(struct request *rq)
 
 	effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode);
 	blk_execute_rq(disk, rq, 0);
-	nvme_passthru_end(ctrl, effects);
+	if (effects) /* nothing to be done for zero cmd effects */
+		nvme_passthru_end(ctrl, effects);
 }
 EXPORT_SYMBOL_NS_GPL(nvme_execute_passthru_rq, NVME_TARGET_PASSTHRU);
 
-static int nvme_submit_user_cmd(struct request_queue *q,
-		struct nvme_command *cmd, void __user *ubuffer,
-		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
-		u32 meta_seed, u64 *result, unsigned timeout)
+/*
+ * Recommended frequency for KATO commands per NVMe 1.4 section 7.12.1:
+ * 
+ *   The host should send Keep Alive commands at half of the Keep Alive Timeout
+ *   accounting for transport roundtrip times [..].
+ */
+static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl)
 {
-	bool write = nvme_is_write(cmd);
-	struct nvme_ns *ns = q->queuedata;
-	struct block_device *bdev = ns ? ns->disk->part0 : NULL;
-	struct request *req;
-	struct bio *bio = NULL;
-	void *meta = NULL;
-	int ret;
-
-	req = nvme_alloc_request(q, cmd, 0);
-	if (IS_ERR(req))
-		return PTR_ERR(req);
-
-	if (timeout)
-		req->timeout = timeout;
-	nvme_req(req)->flags |= NVME_REQ_USERCMD;
-
-	if (ubuffer && bufflen) {
-		ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen,
-				GFP_KERNEL);
-		if (ret)
-			goto out;
-		bio = req->bio;
-		if (bdev)
-			bio_set_dev(bio, bdev);
-		if (bdev && meta_buffer && meta_len) {
-			meta = nvme_add_user_metadata(bio, meta_buffer, meta_len,
-					meta_seed, write);
-			if (IS_ERR(meta)) {
-				ret = PTR_ERR(meta);
-				goto out_unmap;
-			}
-			req->cmd_flags |= REQ_INTEGRITY;
-		}
-	}
-
-	nvme_execute_passthru_rq(req);
-	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
-		ret = -EINTR;
-	else
-		ret = nvme_req(req)->status;
-	if (result)
-		*result = le64_to_cpu(nvme_req(req)->result.u64);
-	if (meta && !ret && !write) {
-		if (copy_to_user(meta_buffer, meta, meta_len))
-			ret = -EFAULT;
-	}
-	kfree(meta);
- out_unmap:
-	if (bio)
-		blk_rq_unmap_user(bio);
- out:
-	blk_mq_free_request(req);
-	return ret;
+	queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ / 2);
 }
 
 static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
@@ -1223,24 +1146,7 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
 		startka = true;
 	spin_unlock_irqrestore(&ctrl->lock, flags);
 	if (startka)
-		queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
-}
-
-static int nvme_keep_alive(struct nvme_ctrl *ctrl)
-{
-	struct request *rq;
-
-	rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd,
-			BLK_MQ_REQ_RESERVED);
-	if (IS_ERR(rq))
-		return PTR_ERR(rq);
-
-	rq->timeout = ctrl->kato * HZ;
-	rq->end_io_data = ctrl;
-
-	blk_execute_rq_nowait(NULL, rq, 0, nvme_keep_alive_end_io);
-
-	return 0;
+		nvme_queue_keep_alive_work(ctrl);
 }
 
 static void nvme_keep_alive_work(struct work_struct *work)
@@ -1248,21 +1154,28 @@ static void nvme_keep_alive_work(struct work_struct *work)
 	struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
 			struct nvme_ctrl, ka_work);
 	bool comp_seen = ctrl->comp_seen;
+	struct request *rq;
 
 	if ((ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) && comp_seen) {
 		dev_dbg(ctrl->device,
 			"reschedule traffic based keep-alive timer\n");
 		ctrl->comp_seen = false;
-		queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
+		nvme_queue_keep_alive_work(ctrl);
 		return;
 	}
 
-	if (nvme_keep_alive(ctrl)) {
+	rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd,
+				BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+	if (IS_ERR(rq)) {
 		/* allocation failure, reset the controller */
-		dev_err(ctrl->device, "keep-alive failed\n");
+		dev_err(ctrl->device, "keep-alive failed: %ld\n", PTR_ERR(rq));
 		nvme_reset_ctrl(ctrl);
 		return;
 	}
+
+	rq->timeout = ctrl->kato * HZ;
+	rq->end_io_data = ctrl;
+	blk_execute_rq_nowait(NULL, rq, 0, nvme_keep_alive_end_io);
 }
 
 static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
@@ -1270,7 +1183,7 @@ static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
 	if (unlikely(ctrl->kato == 0))
 		return;
 
-	queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
+	nvme_queue_keep_alive_work(ctrl);
 }
 
 void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
@@ -1546,170 +1459,6 @@ static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 }
 
 /*
- * Convert integer values from ioctl structures to user pointers, silently
- * ignoring the upper bits in the compat case to match behaviour of 32-bit
- * kernels.
- */
-static void __user *nvme_to_user_ptr(uintptr_t ptrval)
-{
-	if (in_compat_syscall())
-		ptrval = (compat_uptr_t)ptrval;
-	return (void __user *)ptrval;
-}
-
-static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
-{
-	struct nvme_user_io io;
-	struct nvme_command c;
-	unsigned length, meta_len;
-	void __user *metadata;
-
-	if (copy_from_user(&io, uio, sizeof(io)))
-		return -EFAULT;
-	if (io.flags)
-		return -EINVAL;
-
-	switch (io.opcode) {
-	case nvme_cmd_write:
-	case nvme_cmd_read:
-	case nvme_cmd_compare:
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	length = (io.nblocks + 1) << ns->lba_shift;
-
-	if ((io.control & NVME_RW_PRINFO_PRACT) &&
-	    ns->ms == sizeof(struct t10_pi_tuple)) {
-		/*
-		 * Protection information is stripped/inserted by the
-		 * controller.
-		 */
-		if (nvme_to_user_ptr(io.metadata))
-			return -EINVAL;
-		meta_len = 0;
-		metadata = NULL;
-	} else {
-		meta_len = (io.nblocks + 1) * ns->ms;
-		metadata = nvme_to_user_ptr(io.metadata);
-	}
-
-	if (ns->features & NVME_NS_EXT_LBAS) {
-		length += meta_len;
-		meta_len = 0;
-	} else if (meta_len) {
-		if ((io.metadata & 3) || !io.metadata)
-			return -EINVAL;
-	}
-
-	memset(&c, 0, sizeof(c));
-	c.rw.opcode = io.opcode;
-	c.rw.flags = io.flags;
-	c.rw.nsid = cpu_to_le32(ns->head->ns_id);
-	c.rw.slba = cpu_to_le64(io.slba);
-	c.rw.length = cpu_to_le16(io.nblocks);
-	c.rw.control = cpu_to_le16(io.control);
-	c.rw.dsmgmt = cpu_to_le32(io.dsmgmt);
-	c.rw.reftag = cpu_to_le32(io.reftag);
-	c.rw.apptag = cpu_to_le16(io.apptag);
-	c.rw.appmask = cpu_to_le16(io.appmask);
-
-	return nvme_submit_user_cmd(ns->queue, &c,
-			nvme_to_user_ptr(io.addr), length,
-			metadata, meta_len, lower_32_bits(io.slba), NULL, 0);
-}
-
-static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-			struct nvme_passthru_cmd __user *ucmd)
-{
-	struct nvme_passthru_cmd cmd;
-	struct nvme_command c;
-	unsigned timeout = 0;
-	u64 result;
-	int status;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EACCES;
-	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
-		return -EFAULT;
-	if (cmd.flags)
-		return -EINVAL;
-
-	memset(&c, 0, sizeof(c));
-	c.common.opcode = cmd.opcode;
-	c.common.flags = cmd.flags;
-	c.common.nsid = cpu_to_le32(cmd.nsid);
-	c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
-	c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
-	c.common.cdw10 = cpu_to_le32(cmd.cdw10);
-	c.common.cdw11 = cpu_to_le32(cmd.cdw11);
-	c.common.cdw12 = cpu_to_le32(cmd.cdw12);
-	c.common.cdw13 = cpu_to_le32(cmd.cdw13);
-	c.common.cdw14 = cpu_to_le32(cmd.cdw14);
-	c.common.cdw15 = cpu_to_le32(cmd.cdw15);
-
-	if (cmd.timeout_ms)
-		timeout = msecs_to_jiffies(cmd.timeout_ms);
-
-	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
-			nvme_to_user_ptr(cmd.addr), cmd.data_len,
-			nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
-			0, &result, timeout);
-
-	if (status >= 0) {
-		if (put_user(result, &ucmd->result))
-			return -EFAULT;
-	}
-
-	return status;
-}
-
-static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-			struct nvme_passthru_cmd64 __user *ucmd)
-{
-	struct nvme_passthru_cmd64 cmd;
-	struct nvme_command c;
-	unsigned timeout = 0;
-	int status;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EACCES;
-	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
-		return -EFAULT;
-	if (cmd.flags)
-		return -EINVAL;
-
-	memset(&c, 0, sizeof(c));
-	c.common.opcode = cmd.opcode;
-	c.common.flags = cmd.flags;
-	c.common.nsid = cpu_to_le32(cmd.nsid);
-	c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
-	c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
-	c.common.cdw10 = cpu_to_le32(cmd.cdw10);
-	c.common.cdw11 = cpu_to_le32(cmd.cdw11);
-	c.common.cdw12 = cpu_to_le32(cmd.cdw12);
-	c.common.cdw13 = cpu_to_le32(cmd.cdw13);
-	c.common.cdw14 = cpu_to_le32(cmd.cdw14);
-	c.common.cdw15 = cpu_to_le32(cmd.cdw15);
-
-	if (cmd.timeout_ms)
-		timeout = msecs_to_jiffies(cmd.timeout_ms);
-
-	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
-			nvme_to_user_ptr(cmd.addr), cmd.data_len,
-			nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
-			0, &cmd.result, timeout);
-
-	if (status >= 0) {
-		if (put_user(cmd.result, &ucmd->result))
-			return -EFAULT;
-	}
-
-	return status;
-}
-
-/*
  * Issue ioctl requests on the first available path.  Note that unlike normal
  * block layer requests we will not retry failed request on another controller.
  */
@@ -1739,136 +1488,12 @@ void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
 		srcu_read_unlock(&head->srcu, idx);
 }
 
-static bool is_ctrl_ioctl(unsigned int cmd)
-{
-	if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD)
-		return true;
-	if (is_sed_ioctl(cmd))
-		return true;
-	return false;
-}
-
-static int nvme_handle_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
-				  void __user *argp,
-				  struct nvme_ns_head *head,
-				  int srcu_idx)
-{
-	struct nvme_ctrl *ctrl = ns->ctrl;
-	int ret;
-
-	nvme_get_ctrl(ns->ctrl);
-	nvme_put_ns_from_disk(head, srcu_idx);
-
-	switch (cmd) {
-	case NVME_IOCTL_ADMIN_CMD:
-		ret = nvme_user_cmd(ctrl, NULL, argp);
-		break;
-	case NVME_IOCTL_ADMIN64_CMD:
-		ret = nvme_user_cmd64(ctrl, NULL, argp);
-		break;
-	default:
-		ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
-		break;
-	}
-	nvme_put_ctrl(ctrl);
-	return ret;
-}
-
-static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
-		unsigned int cmd, unsigned long arg)
-{
-	struct nvme_ns_head *head = NULL;
-	void __user *argp = (void __user *)arg;
-	struct nvme_ns *ns;
-	int srcu_idx, ret;
-
-	ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
-	if (unlikely(!ns))
-		return -EWOULDBLOCK;
-
-	/*
-	 * Handle ioctls that apply to the controller instead of the namespace
-	 * seperately and drop the ns SRCU reference early.  This avoids a
-	 * deadlock when deleting namespaces using the passthrough interface.
-	 */
-	if (is_ctrl_ioctl(cmd))
-		return nvme_handle_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
-
-	switch (cmd) {
-	case NVME_IOCTL_ID:
-		force_successful_syscall_return();
-		ret = ns->head->ns_id;
-		break;
-	case NVME_IOCTL_IO_CMD:
-		ret = nvme_user_cmd(ns->ctrl, ns, argp);
-		break;
-	case NVME_IOCTL_SUBMIT_IO:
-		ret = nvme_submit_io(ns, argp);
-		break;
-	case NVME_IOCTL_IO64_CMD:
-		ret = nvme_user_cmd64(ns->ctrl, ns, argp);
-		break;
-	default:
-		if (ns->ndev)
-			ret = nvme_nvm_ioctl(ns, cmd, arg);
-		else
-			ret = -ENOTTY;
-	}
-
-	nvme_put_ns_from_disk(head, srcu_idx);
-	return ret;
-}
-
-#ifdef CONFIG_COMPAT
-struct nvme_user_io32 {
-	__u8	opcode;
-	__u8	flags;
-	__u16	control;
-	__u16	nblocks;
-	__u16	rsvd;
-	__u64	metadata;
-	__u64	addr;
-	__u64	slba;
-	__u32	dsmgmt;
-	__u32	reftag;
-	__u16	apptag;
-	__u16	appmask;
-} __attribute__((__packed__));
-
-#define NVME_IOCTL_SUBMIT_IO32	_IOW('N', 0x42, struct nvme_user_io32)
-
-static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
-		unsigned int cmd, unsigned long arg)
+static int nvme_ns_open(struct nvme_ns *ns)
 {
-	/*
-	 * Corresponds to the difference of NVME_IOCTL_SUBMIT_IO
-	 * between 32 bit programs and 64 bit kernel.
-	 * The cause is that the results of sizeof(struct nvme_user_io),
-	 * which is used to define NVME_IOCTL_SUBMIT_IO,
-	 * are not same between 32 bit compiler and 64 bit compiler.
-	 * NVME_IOCTL_SUBMIT_IO32 is for 64 bit kernel handling
-	 * NVME_IOCTL_SUBMIT_IO issued from 32 bit programs.
-	 * Other IOCTL numbers are same between 32 bit and 64 bit.
-	 * So there is nothing to do regarding to other IOCTL numbers.
-	 */
-	if (cmd == NVME_IOCTL_SUBMIT_IO32)
-		return nvme_ioctl(bdev, mode, NVME_IOCTL_SUBMIT_IO, arg);
-
-	return nvme_ioctl(bdev, mode, cmd, arg);
-}
-#else
-#define nvme_compat_ioctl	NULL
-#endif /* CONFIG_COMPAT */
 
-static int nvme_open(struct block_device *bdev, fmode_t mode)
-{
-	struct nvme_ns *ns = bdev->bd_disk->private_data;
-
-#ifdef CONFIG_NVME_MULTIPATH
 	/* should never be called due to GENHD_FL_HIDDEN */
-	if (WARN_ON_ONCE(ns->head->disk))
+	if (WARN_ON_ONCE(nvme_ns_head_multipath(ns->head)))
 		goto fail;
-#endif
 	if (!kref_get_unless_zero(&ns->kref))
 		goto fail;
 	if (!try_module_get(ns->ctrl->ops->module))
@@ -1882,15 +1507,24 @@ fail:
 	return -ENXIO;
 }
 
-static void nvme_release(struct gendisk *disk, fmode_t mode)
+static void nvme_ns_release(struct nvme_ns *ns)
 {
-	struct nvme_ns *ns = disk->private_data;
 
 	module_put(ns->ctrl->ops->module);
 	nvme_put_ns(ns);
 }
 
-static int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
+static int nvme_open(struct block_device *bdev, fmode_t mode)
+{
+	return nvme_ns_open(bdev->bd_disk->private_data);
+}
+
+static void nvme_release(struct gendisk *disk, fmode_t mode)
+{
+	nvme_ns_release(disk->private_data);
+}
+
+int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 {
 	/* some standard values */
 	geo->heads = 1 << 6;
@@ -1939,7 +1573,7 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
 	struct request_queue *queue = disk->queue;
 	u32 size = queue_logical_block_size(queue);
 
-	if (!(ctrl->oncs & NVME_CTRL_ONCS_DSM)) {
+	if (ctrl->max_discard_sectors == 0) {
 		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, queue);
 		return;
 	}
@@ -1957,39 +1591,13 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
 	if (blk_queue_flag_test_and_set(QUEUE_FLAG_DISCARD, queue))
 		return;
 
-	blk_queue_max_discard_sectors(queue, UINT_MAX);
-	blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);
+	blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors);
+	blk_queue_max_discard_segments(queue, ctrl->max_discard_segments);
 
 	if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
 		blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
 }
 
-static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns)
-{
-	u64 max_blocks;
-
-	if (!(ns->ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) ||
-	    (ns->ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES))
-		return;
-	/*
-	 * Even though NVMe spec explicitly states that MDTS is not
-	 * applicable to the write-zeroes:- "The restriction does not apply to
-	 * commands that do not transfer data between the host and the
-	 * controller (e.g., Write Uncorrectable ro Write Zeroes command).".
-	 * In order to be more cautious use controller's max_hw_sectors value
-	 * to configure the maximum sectors for the write-zeroes which is
-	 * configured based on the controller's MDTS field in the
-	 * nvme_init_identify() if available.
-	 */
-	if (ns->ctrl->max_hw_sectors == UINT_MAX)
-		max_blocks = (u64)USHRT_MAX + 1;
-	else
-		max_blocks = ns->ctrl->max_hw_sectors + 1;
-
-	blk_queue_max_write_zeroes_sectors(disk->queue,
-					   nvme_lba_to_sect(ns, max_blocks));
-}
-
 static bool nvme_ns_ids_valid(struct nvme_ns_ids *ids)
 {
 	return !uuid_is_null(&ids->uuid) ||
@@ -2159,7 +1767,8 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	set_capacity_and_notify(disk, capacity);
 
 	nvme_config_discard(disk, ns);
-	nvme_config_write_zeroes(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));
@@ -2228,11 +1837,10 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 	if (blk_queue_is_zoned(ns->queue)) {
 		ret = nvme_revalidate_zones(ns);
 		if (ret && !nvme_first_scan(ns->disk))
-			return ret;
+			goto out;
 	}
 
-#ifdef CONFIG_NVME_MULTIPATH
-	if (ns->head->disk) {
+	if (nvme_ns_head_multipath(ns->head)) {
 		blk_mq_freeze_queue(ns->head->disk->queue);
 		nvme_update_disk_info(ns->head->disk, ns, id);
 		blk_stack_limits(&ns->head->disk->queue->limits,
@@ -2240,11 +1848,19 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 		blk_queue_update_readahead(ns->head->disk->queue);
 		blk_mq_unfreeze_queue(ns->head->disk->queue);
 	}
-#endif
 	return 0;
 
 out_unfreeze:
 	blk_mq_unfreeze_queue(ns->disk->queue);
+out:
+	/*
+	 * If probing fails due an unsupported feature, hide the block device,
+	 * but still allow other access.
+	 */
+	if (ret == -ENODEV) {
+		ns->disk->flags |= GENHD_FL_HIDDEN;
+		ret = 0;
+	}
 	return ret;
 }
 
@@ -2325,22 +1941,25 @@ static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new,
 		enum pr_type type, bool abort)
 {
 	u32 cdw10 = nvme_pr_type(type) << 8 | (abort ? 2 : 1);
+
 	return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire);
 }
 
 static int nvme_pr_clear(struct block_device *bdev, u64 key)
 {
 	u32 cdw10 = 1 | (key ? 1 << 3 : 0);
+
 	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_register);
 }
 
 static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
 {
 	u32 cdw10 = nvme_pr_type(type) << 8 | (key ? 1 << 3 : 0);
+
 	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
 }
 
-static const struct pr_ops nvme_pr_ops = {
+const struct pr_ops nvme_pr_ops = {
 	.pr_register	= nvme_pr_register,
 	.pr_reserve	= nvme_pr_reserve,
 	.pr_release	= nvme_pr_release,
@@ -2373,7 +1992,6 @@ EXPORT_SYMBOL_GPL(nvme_sec_submit);
 static const struct block_device_operations nvme_bdev_ops = {
 	.owner		= THIS_MODULE,
 	.ioctl		= nvme_ioctl,
-	.compat_ioctl	= nvme_compat_ioctl,
 	.open		= nvme_open,
 	.release	= nvme_release,
 	.getgeo		= nvme_getgeo,
@@ -2382,31 +2000,25 @@ static const struct block_device_operations nvme_bdev_ops = {
 };
 
 #ifdef CONFIG_NVME_MULTIPATH
-static int nvme_ns_head_open(struct block_device *bdev, fmode_t mode)
+struct nvme_ctrl *nvme_find_get_live_ctrl(struct nvme_subsystem *subsys)
 {
-	struct nvme_ns_head *head = bdev->bd_disk->private_data;
-
-	if (!kref_get_unless_zero(&head->ref))
-		return -ENXIO;
-	return 0;
-}
+	struct nvme_ctrl *ctrl;
+	int ret;
 
-static void nvme_ns_head_release(struct gendisk *disk, fmode_t mode)
-{
-	nvme_put_ns_head(disk->private_data);
+	ret = mutex_lock_killable(&nvme_subsystems_lock);
+	if (ret)
+		return ERR_PTR(ret);
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+		if (ctrl->state == NVME_CTRL_LIVE)
+			goto found;
+	}
+	mutex_unlock(&nvme_subsystems_lock);
+	return ERR_PTR(-EWOULDBLOCK);
+found:
+	nvme_get_ctrl(ctrl);
+	mutex_unlock(&nvme_subsystems_lock);
+	return ctrl;
 }
-
-const struct block_device_operations nvme_ns_head_ops = {
-	.owner		= THIS_MODULE,
-	.submit_bio	= nvme_ns_head_submit_bio,
-	.open		= nvme_ns_head_open,
-	.release	= nvme_ns_head_release,
-	.ioctl		= nvme_ioctl,
-	.compat_ioctl	= nvme_compat_ioctl,
-	.getgeo		= nvme_getgeo,
-	.report_zones	= nvme_report_zones,
-	.pr_ops		= &nvme_pr_ops,
-};
 #endif /* CONFIG_NVME_MULTIPATH */
 
 static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
@@ -2563,28 +2175,28 @@ static int nvme_configure_acre(struct nvme_ctrl *ctrl)
 	return ret;
 }
 
+/*
+ * APST (Autonomous Power State Transition) lets us program a table of power
+ * state transitions that the controller will perform automatically.
+ * We configure it with a simple heuristic: we are willing to spend at most 2%
+ * of the time transitioning between power states.  Therefore, when running in
+ * any given state, we will enter the next lower-power non-operational state
+ * after waiting 50 * (enlat + exlat) microseconds, as long as that state's exit
+ * latency is under the requested maximum latency.
+ *
+ * We will not autonomously enter any non-operational state for which the total
+ * latency exceeds ps_max_latency_us.
+ *
+ * Users can set ps_max_latency_us to zero to turn off APST.
+ */
 static int nvme_configure_apst(struct nvme_ctrl *ctrl)
 {
-	/*
-	 * APST (Autonomous Power State Transition) lets us program a
-	 * table of power state transitions that the controller will
-	 * perform automatically.  We configure it with a simple
-	 * heuristic: we are willing to spend at most 2% of the time
-	 * transitioning between power states.  Therefore, when running
-	 * in any given state, we will enter the next lower-power
-	 * non-operational state after waiting 50 * (enlat + exlat)
-	 * microseconds, as long as that state's exit latency is under
-	 * the requested maximum latency.
-	 *
-	 * We will not autonomously enter any non-operational state for
-	 * which the total latency exceeds ps_max_latency_us.  Users
-	 * can set ps_max_latency_us to zero to turn off APST.
-	 */
-
-	unsigned apste;
 	struct nvme_feat_auto_pst *table;
+	unsigned apste = 0;
 	u64 max_lat_us = 0;
+	__le64 target = 0;
 	int max_ps = -1;
+	int state;
 	int ret;
 
 	/*
@@ -2605,83 +2217,72 @@ static int nvme_configure_apst(struct nvme_ctrl *ctrl)
 
 	if (!ctrl->apst_enabled || ctrl->ps_max_latency_us == 0) {
 		/* Turn off APST. */
-		apste = 0;
 		dev_dbg(ctrl->device, "APST disabled\n");
-	} else {
-		__le64 target = cpu_to_le64(0);
-		int state;
-
-		/*
-		 * Walk through all states from lowest- to highest-power.
-		 * According to the spec, lower-numbered states use more
-		 * power.  NPSS, despite the name, is the index of the
-		 * lowest-power state, not the number of states.
-		 */
-		for (state = (int)ctrl->npss; state >= 0; state--) {
-			u64 total_latency_us, exit_latency_us, transition_ms;
-
-			if (target)
-				table->entries[state] = target;
-
-			/*
-			 * Don't allow transitions to the deepest state
-			 * if it's quirked off.
-			 */
-			if (state == ctrl->npss &&
-			    (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS))
-				continue;
-
-			/*
-			 * Is this state a useful non-operational state for
-			 * higher-power states to autonomously transition to?
-			 */
-			if (!(ctrl->psd[state].flags &
-			      NVME_PS_FLAGS_NON_OP_STATE))
-				continue;
-
-			exit_latency_us =
-				(u64)le32_to_cpu(ctrl->psd[state].exit_lat);
-			if (exit_latency_us > ctrl->ps_max_latency_us)
-				continue;
+		goto done;
+	}
 
-			total_latency_us =
-				exit_latency_us +
-				le32_to_cpu(ctrl->psd[state].entry_lat);
+	/*
+	 * Walk through all states from lowest- to highest-power.
+	 * According to the spec, lower-numbered states use more power.  NPSS,
+	 * despite the name, is the index of the lowest-power state, not the
+	 * number of states.
+	 */
+	for (state = (int)ctrl->npss; state >= 0; state--) {
+		u64 total_latency_us, exit_latency_us, transition_ms;
 
-			/*
-			 * This state is good.  Use it as the APST idle
-			 * target for higher power states.
-			 */
-			transition_ms = total_latency_us + 19;
-			do_div(transition_ms, 20);
-			if (transition_ms > (1 << 24) - 1)
-				transition_ms = (1 << 24) - 1;
+		if (target)
+			table->entries[state] = target;
 
-			target = cpu_to_le64((state << 3) |
-					     (transition_ms << 8));
+		/*
+		 * Don't allow transitions to the deepest state if it's quirked
+		 * off.
+		 */
+		if (state == ctrl->npss &&
+		    (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS))
+			continue;
 
-			if (max_ps == -1)
-				max_ps = state;
+		/*
+		 * Is this state a useful non-operational state for higher-power
+		 * states to autonomously transition to?
+		 */
+		if (!(ctrl->psd[state].flags & NVME_PS_FLAGS_NON_OP_STATE))
+			continue;
 
-			if (total_latency_us > max_lat_us)
-				max_lat_us = total_latency_us;
-		}
+		exit_latency_us = (u64)le32_to_cpu(ctrl->psd[state].exit_lat);
+		if (exit_latency_us > ctrl->ps_max_latency_us)
+			continue;
 
-		apste = 1;
+		total_latency_us = exit_latency_us +
+			le32_to_cpu(ctrl->psd[state].entry_lat);
 
-		if (max_ps == -1) {
-			dev_dbg(ctrl->device, "APST enabled but no non-operational states are available\n");
-		} else {
-			dev_dbg(ctrl->device, "APST enabled: max PS = %d, max round-trip latency = %lluus, table = %*phN\n",
-				max_ps, max_lat_us, (int)sizeof(*table), table);
-		}
+		/*
+		 * This state is good.  Use it as the APST idle target for
+		 * higher power states.
+		 */
+		transition_ms = total_latency_us + 19;
+		do_div(transition_ms, 20);
+		if (transition_ms > (1 << 24) - 1)
+			transition_ms = (1 << 24) - 1;
+
+		target = cpu_to_le64((state << 3) | (transition_ms << 8));
+		if (max_ps == -1)
+			max_ps = state;
+		if (total_latency_us > max_lat_us)
+			max_lat_us = total_latency_us;
 	}
 
+	if (max_ps == -1)
+		dev_dbg(ctrl->device, "APST enabled but no non-operational states are available\n");
+	else
+		dev_dbg(ctrl->device, "APST enabled: max PS = %d, max round-trip latency = %lluus, table = %*phN\n",
+			max_ps, max_lat_us, (int)sizeof(*table), table);
+	apste = 1;
+
+done:
 	ret = nvme_set_features(ctrl, NVME_FEAT_AUTO_PST, apste,
 				table, sizeof(*table), NULL);
 	if (ret)
 		dev_err(ctrl->device, "failed to set APST feature (%d)\n", ret);
-
 	kfree(table);
 	return ret;
 }
@@ -2703,7 +2304,8 @@ static void nvme_set_latency_tolerance(struct device *dev, s32 val)
 
 	if (ctrl->ps_max_latency_us != latency) {
 		ctrl->ps_max_latency_us = latency;
-		nvme_configure_apst(ctrl);
+		if (ctrl->state == NVME_CTRL_LIVE)
+			nvme_configure_apst(ctrl);
 	}
 }
 
@@ -2876,8 +2478,8 @@ static ssize_t subsys_##field##_show(struct device *dev,		\
 {									\
 	struct nvme_subsystem *subsys =					\
 		container_of(dev, struct nvme_subsystem, dev);		\
-	return sprintf(buf, "%.*s\n",					\
-		       (int)sizeof(subsys->field), subsys->field);	\
+	return sysfs_emit(buf, "%.*s\n",				\
+			   (int)sizeof(subsys->field), subsys->field);	\
 }									\
 static SUBSYS_ATTR_RO(field, S_IRUGO, subsys_##field##_show);
 
@@ -3060,28 +2662,74 @@ out:
 	return 0;
 }
 
-/*
- * Initialize the cached copies of the Identify data and various controller
- * register in our nvme_ctrl structure.  This should be called as soon as
- * the admin queue is fully up and running.
- */
-int nvme_init_identify(struct nvme_ctrl *ctrl)
+static inline u32 nvme_mps_to_sectors(struct nvme_ctrl *ctrl, u32 units)
 {
-	struct nvme_id_ctrl *id;
-	int ret, page_shift;
-	u32 max_hw_sectors;
-	bool prev_apst_enabled;
+	u32 page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12, val;
 
-	ret = ctrl->ops->reg_read32(ctrl, NVME_REG_VS, &ctrl->vs);
-	if (ret) {
-		dev_err(ctrl->device, "Reading VS failed (%d)\n", ret);
-		return ret;
+	if (check_shl_overflow(1U, units + page_shift - 9, &val))
+		return UINT_MAX;
+	return val;
+}
+
+static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl)
+{
+	struct nvme_command c = { };
+	struct nvme_id_ctrl_nvm *id;
+	int ret;
+
+	if (ctrl->oncs & NVME_CTRL_ONCS_DSM) {
+		ctrl->max_discard_sectors = UINT_MAX;
+		ctrl->max_discard_segments = NVME_DSM_MAX_RANGES;
+	} else {
+		ctrl->max_discard_sectors = 0;
+		ctrl->max_discard_segments = 0;
 	}
-	page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;
-	ctrl->sqsize = min_t(u16, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize);
 
-	if (ctrl->vs >= NVME_VS(1, 1, 0))
-		ctrl->subsystem = NVME_CAP_NSSRC(ctrl->cap);
+	/*
+	 * Even though NVMe spec explicitly states that MDTS is not applicable
+	 * to the write-zeroes, we are cautious and limit the size to the
+	 * controllers max_hw_sectors value, which is based on the MDTS field
+	 * and possibly other limiting factors.
+	 */
+	if ((ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) &&
+	    !(ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES))
+		ctrl->max_zeroes_sectors = ctrl->max_hw_sectors;
+	else
+		ctrl->max_zeroes_sectors = 0;
+
+	if (nvme_ctrl_limited_cns(ctrl))
+		return 0;
+
+	id = kzalloc(sizeof(*id), GFP_KERNEL);
+	if (!id)
+		return 0;
+
+	c.identify.opcode = nvme_admin_identify;
+	c.identify.cns = NVME_ID_CNS_CS_CTRL;
+	c.identify.csi = NVME_CSI_NVM;
+
+	ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id));
+	if (ret)
+		goto free_data;
+
+	if (id->dmrl)
+		ctrl->max_discard_segments = id->dmrl;
+	if (id->dmrsl)
+		ctrl->max_discard_sectors = le32_to_cpu(id->dmrsl);
+	if (id->wzsl)
+		ctrl->max_zeroes_sectors = nvme_mps_to_sectors(ctrl, id->wzsl);
+
+free_data:
+	kfree(id);
+	return ret;
+}
+
+static int nvme_init_identify(struct nvme_ctrl *ctrl)
+{
+	struct nvme_id_ctrl *id;
+	u32 max_hw_sectors;
+	bool prev_apst_enabled;
+	int ret;
 
 	ret = nvme_identify_ctrl(ctrl, &id);
 	if (ret) {
@@ -3099,7 +2747,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		ctrl->cntlid = le16_to_cpu(id->cntlid);
 
 	if (!ctrl->identified) {
-		int i;
+		unsigned int i;
 
 		ret = nvme_init_subsystem(ctrl, id);
 		if (ret)
@@ -3138,7 +2786,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	atomic_set(&ctrl->abort_limit, id->acl + 1);
 	ctrl->vwc = id->vwc;
 	if (id->mdts)
-		max_hw_sectors = 1 << (id->mdts + page_shift - 9);
+		max_hw_sectors = nvme_mps_to_sectors(ctrl, id->mdts);
 	else
 		max_hw_sectors = UINT_MAX;
 	ctrl->max_hw_sectors =
@@ -3212,20 +2860,51 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	}
 
 	ret = nvme_mpath_init(ctrl, id);
-	kfree(id);
-
 	if (ret < 0)
-		return ret;
+		goto out_free;
 
 	if (ctrl->apst_enabled && !prev_apst_enabled)
 		dev_pm_qos_expose_latency_tolerance(ctrl->device);
 	else if (!ctrl->apst_enabled && prev_apst_enabled)
 		dev_pm_qos_hide_latency_tolerance(ctrl->device);
 
+out_free:
+	kfree(id);
+	return ret;
+}
+
+/*
+ * Initialize the cached copies of the Identify data and various controller
+ * register in our nvme_ctrl structure.  This should be called as soon as
+ * the admin queue is fully up and running.
+ */
+int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl)
+{
+	int ret;
+
+	ret = ctrl->ops->reg_read32(ctrl, NVME_REG_VS, &ctrl->vs);
+	if (ret) {
+		dev_err(ctrl->device, "Reading VS failed (%d)\n", ret);
+		return ret;
+	}
+
+	ctrl->sqsize = min_t(u16, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize);
+
+	if (ctrl->vs >= NVME_VS(1, 1, 0))
+		ctrl->subsystem = NVME_CAP_NSSRC(ctrl->cap);
+
+	ret = nvme_init_identify(ctrl);
+	if (ret)
+		return ret;
+
+	ret = nvme_init_non_mdts_limits(ctrl);
+	if (ret < 0)
+		return ret;
+
 	ret = nvme_configure_apst(ctrl);
 	if (ret < 0)
 		return ret;
-	
+
 	ret = nvme_configure_timestamp(ctrl);
 	if (ret < 0)
 		return ret;
@@ -3247,12 +2926,8 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	ctrl->identified = true;
 
 	return 0;
-
-out_free:
-	kfree(id);
-	return ret;
 }
-EXPORT_SYMBOL_GPL(nvme_init_identify);
+EXPORT_SYMBOL_GPL(nvme_init_ctrl_finish);
 
 static int nvme_dev_open(struct inode *inode, struct file *file)
 {
@@ -3286,65 +2961,6 @@ static int nvme_dev_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp)
-{
-	struct nvme_ns *ns;
-	int ret;
-
-	down_read(&ctrl->namespaces_rwsem);
-	if (list_empty(&ctrl->namespaces)) {
-		ret = -ENOTTY;
-		goto out_unlock;
-	}
-
-	ns = list_first_entry(&ctrl->namespaces, struct nvme_ns, list);
-	if (ns != list_last_entry(&ctrl->namespaces, struct nvme_ns, list)) {
-		dev_warn(ctrl->device,
-			"NVME_IOCTL_IO_CMD not supported when multiple namespaces present!\n");
-		ret = -EINVAL;
-		goto out_unlock;
-	}
-
-	dev_warn(ctrl->device,
-		"using deprecated NVME_IOCTL_IO_CMD ioctl on the char device!\n");
-	kref_get(&ns->kref);
-	up_read(&ctrl->namespaces_rwsem);
-
-	ret = nvme_user_cmd(ctrl, ns, argp);
-	nvme_put_ns(ns);
-	return ret;
-
-out_unlock:
-	up_read(&ctrl->namespaces_rwsem);
-	return ret;
-}
-
-static long nvme_dev_ioctl(struct file *file, unsigned int cmd,
-		unsigned long arg)
-{
-	struct nvme_ctrl *ctrl = file->private_data;
-	void __user *argp = (void __user *)arg;
-
-	switch (cmd) {
-	case NVME_IOCTL_ADMIN_CMD:
-		return nvme_user_cmd(ctrl, NULL, argp);
-	case NVME_IOCTL_ADMIN64_CMD:
-		return nvme_user_cmd64(ctrl, NULL, argp);
-	case NVME_IOCTL_IO_CMD:
-		return nvme_dev_user_cmd(ctrl, argp);
-	case NVME_IOCTL_RESET:
-		dev_warn(ctrl->device, "resetting controller\n");
-		return nvme_reset_ctrl_sync(ctrl);
-	case NVME_IOCTL_SUBSYS_RESET:
-		return nvme_reset_subsystem(ctrl);
-	case NVME_IOCTL_RESCAN:
-		nvme_queue_scan(ctrl);
-		return 0;
-	default:
-		return -ENOTTY;
-	}
-}
-
 static const struct file_operations nvme_dev_fops = {
 	.owner		= THIS_MODULE,
 	.open		= nvme_dev_open,
@@ -3398,13 +3014,13 @@ static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
 	int model_len = sizeof(subsys->model);
 
 	if (!uuid_is_null(&ids->uuid))
-		return sprintf(buf, "uuid.%pU\n", &ids->uuid);
+		return sysfs_emit(buf, "uuid.%pU\n", &ids->uuid);
 
 	if (memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
-		return sprintf(buf, "eui.%16phN\n", ids->nguid);
+		return sysfs_emit(buf, "eui.%16phN\n", ids->nguid);
 
 	if (memchr_inv(ids->eui64, 0, sizeof(ids->eui64)))
-		return sprintf(buf, "eui.%8phN\n", ids->eui64);
+		return sysfs_emit(buf, "eui.%8phN\n", ids->eui64);
 
 	while (serial_len > 0 && (subsys->serial[serial_len - 1] == ' ' ||
 				  subsys->serial[serial_len - 1] == '\0'))
@@ -3413,7 +3029,7 @@ static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
 				 subsys->model[model_len - 1] == '\0'))
 		model_len--;
 
-	return sprintf(buf, "nvme.%04x-%*phN-%*phN-%08x\n", subsys->vendor_id,
+	return sysfs_emit(buf, "nvme.%04x-%*phN-%*phN-%08x\n", subsys->vendor_id,
 		serial_len, subsys->serial, model_len, subsys->model,
 		head->ns_id);
 }
@@ -3422,7 +3038,7 @@ static DEVICE_ATTR_RO(wwid);
 static ssize_t nguid_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
-	return sprintf(buf, "%pU\n", dev_to_ns_head(dev)->ids.nguid);
+	return sysfs_emit(buf, "%pU\n", dev_to_ns_head(dev)->ids.nguid);
 }
 static DEVICE_ATTR_RO(nguid);
 
@@ -3437,23 +3053,23 @@ static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
 	if (uuid_is_null(&ids->uuid)) {
 		printk_ratelimited(KERN_WARNING
 				   "No UUID available providing old NGUID\n");
-		return sprintf(buf, "%pU\n", ids->nguid);
+		return sysfs_emit(buf, "%pU\n", ids->nguid);
 	}
-	return sprintf(buf, "%pU\n", &ids->uuid);
+	return sysfs_emit(buf, "%pU\n", &ids->uuid);
 }
 static DEVICE_ATTR_RO(uuid);
 
 static ssize_t eui_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
-	return sprintf(buf, "%8ph\n", dev_to_ns_head(dev)->ids.eui64);
+	return sysfs_emit(buf, "%8ph\n", dev_to_ns_head(dev)->ids.eui64);
 }
 static DEVICE_ATTR_RO(eui);
 
 static ssize_t nsid_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
-	return sprintf(buf, "%d\n", dev_to_ns_head(dev)->ns_id);
+	return sysfs_emit(buf, "%d\n", dev_to_ns_head(dev)->ns_id);
 }
 static DEVICE_ATTR_RO(nsid);
 
@@ -3518,7 +3134,7 @@ static ssize_t  field##_show(struct device *dev,				\
 			    struct device_attribute *attr, char *buf)		\
 {										\
         struct nvme_ctrl *ctrl = dev_get_drvdata(dev);				\
-        return sprintf(buf, "%.*s\n",						\
+        return sysfs_emit(buf, "%.*s\n",					\
 		(int)sizeof(ctrl->subsys->field), ctrl->subsys->field);		\
 }										\
 static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL);
@@ -3532,7 +3148,7 @@ static ssize_t  field##_show(struct device *dev,				\
 			    struct device_attribute *attr, char *buf)		\
 {										\
         struct nvme_ctrl *ctrl = dev_get_drvdata(dev);				\
-        return sprintf(buf, "%d\n", ctrl->field);	\
+        return sysfs_emit(buf, "%d\n", ctrl->field);				\
 }										\
 static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL);
 
@@ -3540,6 +3156,7 @@ nvme_show_int_function(cntlid);
 nvme_show_int_function(numa_node);
 nvme_show_int_function(queue_count);
 nvme_show_int_function(sqsize);
+nvme_show_int_function(kato);
 
 static ssize_t nvme_sysfs_delete(struct device *dev,
 				struct device_attribute *attr, const char *buf,
@@ -3580,9 +3197,9 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 
 	if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) &&
 	    state_name[ctrl->state])
-		return sprintf(buf, "%s\n", state_name[ctrl->state]);
+		return sysfs_emit(buf, "%s\n", state_name[ctrl->state]);
 
-	return sprintf(buf, "unknown state\n");
+	return sysfs_emit(buf, "unknown state\n");
 }
 
 static DEVICE_ATTR(state, S_IRUGO, nvme_sysfs_show_state, NULL);
@@ -3634,9 +3251,9 @@ static ssize_t nvme_ctrl_loss_tmo_show(struct device *dev,
 	struct nvmf_ctrl_options *opts = ctrl->opts;
 
 	if (ctrl->opts->max_reconnects == -1)
-		return sprintf(buf, "off\n");
-	return sprintf(buf, "%d\n",
-			opts->max_reconnects * opts->reconnect_delay);
+		return sysfs_emit(buf, "off\n");
+	return sysfs_emit(buf, "%d\n",
+			  opts->max_reconnects * opts->reconnect_delay);
 }
 
 static ssize_t nvme_ctrl_loss_tmo_store(struct device *dev,
@@ -3650,7 +3267,7 @@ static ssize_t nvme_ctrl_loss_tmo_store(struct device *dev,
 	if (err)
 		return -EINVAL;
 
-	else if (ctrl_loss_tmo < 0)
+	if (ctrl_loss_tmo < 0)
 		opts->max_reconnects = -1;
 	else
 		opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo,
@@ -3666,8 +3283,8 @@ static ssize_t nvme_ctrl_reconnect_delay_show(struct device *dev,
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
 
 	if (ctrl->opts->reconnect_delay == -1)
-		return sprintf(buf, "off\n");
-	return sprintf(buf, "%d\n", ctrl->opts->reconnect_delay);
+		return sysfs_emit(buf, "off\n");
+	return sysfs_emit(buf, "%d\n", ctrl->opts->reconnect_delay);
 }
 
 static ssize_t nvme_ctrl_reconnect_delay_store(struct device *dev,
@@ -3687,6 +3304,36 @@ static ssize_t nvme_ctrl_reconnect_delay_store(struct device *dev,
 static DEVICE_ATTR(reconnect_delay, S_IRUGO | S_IWUSR,
 	nvme_ctrl_reconnect_delay_show, nvme_ctrl_reconnect_delay_store);
 
+static ssize_t nvme_ctrl_fast_io_fail_tmo_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	if (ctrl->opts->fast_io_fail_tmo == -1)
+		return sysfs_emit(buf, "off\n");
+	return sysfs_emit(buf, "%d\n", ctrl->opts->fast_io_fail_tmo);
+}
+
+static ssize_t nvme_ctrl_fast_io_fail_tmo_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	struct nvmf_ctrl_options *opts = ctrl->opts;
+	int fast_io_fail_tmo, err;
+
+	err = kstrtoint(buf, 10, &fast_io_fail_tmo);
+	if (err)
+		return -EINVAL;
+
+	if (fast_io_fail_tmo < 0)
+		opts->fast_io_fail_tmo = -1;
+	else
+		opts->fast_io_fail_tmo = fast_io_fail_tmo;
+	return count;
+}
+static DEVICE_ATTR(fast_io_fail_tmo, S_IRUGO | S_IWUSR,
+	nvme_ctrl_fast_io_fail_tmo_show, nvme_ctrl_fast_io_fail_tmo_store);
+
 static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_reset_controller.attr,
 	&dev_attr_rescan_controller.attr,
@@ -3706,6 +3353,8 @@ static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_hostid.attr,
 	&dev_attr_ctrl_loss_tmo.attr,
 	&dev_attr_reconnect_delay.attr,
+	&dev_attr_fast_io_fail_tmo.attr,
+	&dev_attr_kato.attr,
 	NULL
 };
 
@@ -3727,6 +3376,8 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
 		return 0;
 	if (a == &dev_attr_reconnect_delay.attr && !ctrl->opts)
 		return 0;
+	if (a == &dev_attr_fast_io_fail_tmo.attr && !ctrl->opts)
+		return 0;
 
 	return a->mode;
 }
@@ -3749,7 +3400,7 @@ static struct nvme_ns_head *nvme_find_ns_head(struct nvme_subsystem *subsys,
 	lockdep_assert_held(&subsys->lock);
 
 	list_for_each_entry(h, &subsys->nsheads, entry) {
-		if (h->ns_id == nsid && kref_get_unless_zero(&h->ref))
+		if (h->ns_id == nsid && nvme_tryget_ns_head(h))
 			return h;
 	}
 
@@ -3772,6 +3423,66 @@ static int __nvme_check_ids(struct nvme_subsystem *subsys,
 	return 0;
 }
 
+void nvme_cdev_del(struct cdev *cdev, struct device *cdev_device)
+{
+	cdev_device_del(cdev, cdev_device);
+	ida_simple_remove(&nvme_ns_chr_minor_ida, MINOR(cdev_device->devt));
+}
+
+int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device,
+		const struct file_operations *fops, struct module *owner)
+{
+	int minor, ret;
+
+	minor = ida_simple_get(&nvme_ns_chr_minor_ida, 0, 0, GFP_KERNEL);
+	if (minor < 0)
+		return minor;
+	cdev_device->devt = MKDEV(MAJOR(nvme_ns_chr_devt), minor);
+	cdev_device->class = nvme_ns_chr_class;
+	device_initialize(cdev_device);
+	cdev_init(cdev, fops);
+	cdev->owner = owner;
+	ret = cdev_device_add(cdev, cdev_device);
+	if (ret)
+		ida_simple_remove(&nvme_ns_chr_minor_ida, minor);
+	return ret;
+}
+
+static int nvme_ns_chr_open(struct inode *inode, struct file *file)
+{
+	return nvme_ns_open(container_of(inode->i_cdev, struct nvme_ns, cdev));
+}
+
+static int nvme_ns_chr_release(struct inode *inode, struct file *file)
+{
+	nvme_ns_release(container_of(inode->i_cdev, struct nvme_ns, cdev));
+	return 0;
+}
+
+static const struct file_operations nvme_ns_chr_fops = {
+	.owner		= THIS_MODULE,
+	.open		= nvme_ns_chr_open,
+	.release	= nvme_ns_chr_release,
+	.unlocked_ioctl	= nvme_ns_chr_ioctl,
+	.compat_ioctl	= compat_ptr_ioctl,
+};
+
+static int nvme_add_ns_cdev(struct nvme_ns *ns)
+{
+	int ret;
+
+	ns->cdev_device.parent = ns->ctrl->device;
+	ret = dev_set_name(&ns->cdev_device, "ng%dn%d",
+			   ns->ctrl->instance, ns->head->instance);
+	if (ret)
+		return ret;
+	ret = nvme_cdev_add(&ns->cdev, &ns->cdev_device, &nvme_ns_chr_fops,
+			    ns->ctrl->ops->module);
+	if (ret)
+		kfree_const(ns->cdev_device.kobj.name);
+	return ret;
+}
+
 static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 		unsigned nsid, struct nvme_ns_ids *ids)
 {
@@ -3877,7 +3588,8 @@ out_unlock:
 	return ret;
 }
 
-static int ns_cmp(void *priv, struct list_head *a, struct list_head *b)
+static int ns_cmp(void *priv, const struct list_head *a,
+		const struct list_head *b)
 {
 	struct nvme_ns *nsa = container_of(a, struct nvme_ns, list);
 	struct nvme_ns *nsb = container_of(b, struct nvme_ns, list);
@@ -3911,8 +3623,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 	struct nvme_ns *ns;
 	struct gendisk *disk;
 	struct nvme_id_ns *id;
-	char disk_name[DISK_NAME_LEN];
-	int node = ctrl->numa_node, flags = GENHD_FL_EXT_DEVT;
+	int node = ctrl->numa_node;
 
 	if (nvme_identify_ns(ctrl, nsid, ids, &id))
 		return;
@@ -3938,7 +3649,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 
 	if (nvme_init_ns_head(ns, nsid, ids, id->nmic & NVME_NS_NMIC_SHARED))
 		goto out_free_queue;
-	nvme_set_disk_name(disk_name, ns, ctrl, &flags);
 
 	disk = alloc_disk_node(0, node);
 	if (!disk)
@@ -3947,15 +3657,22 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 	disk->fops = &nvme_bdev_ops;
 	disk->private_data = ns;
 	disk->queue = ns->queue;
-	disk->flags = flags;
-	memcpy(disk->disk_name, disk_name, DISK_NAME_LEN);
+	disk->flags = GENHD_FL_EXT_DEVT;
+	/*
+	 * Without the multipath code enabled, multiple controller per
+	 * subsystems are visible as devices and thus we cannot use the
+	 * subsystem instance.
+	 */
+	if (!nvme_mpath_set_disk_name(ns, disk->disk_name, &disk->flags))
+		sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance,
+			ns->head->instance);
 	ns->disk = disk;
 
 	if (nvme_update_ns_info(ns, id))
 		goto out_put_disk;
 
 	if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
-		if (nvme_nvm_register(ns, disk_name, node)) {
+		if (nvme_nvm_register(ns, disk->disk_name, node)) {
 			dev_warn(ctrl->device, "LightNVM init failure\n");
 			goto out_put_disk;
 		}
@@ -3968,6 +3685,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 	nvme_get_ctrl(ctrl);
 
 	device_add_disk(ctrl->device, ns->disk, nvme_ns_id_attr_groups);
+	if (!nvme_ns_head_multipath(ns->head))
+		nvme_add_ns_cdev(ns);
 
 	nvme_mpath_add_disk(ns, id);
 	nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name);
@@ -4012,6 +3731,8 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	synchronize_srcu(&ns->head->srcu); /* wait for concurrent submissions */
 
 	if (ns->disk->flags & GENHD_FL_UP) {
+		if (!nvme_ns_head_multipath(ns->head))
+			nvme_cdev_del(&ns->cdev, &ns->cdev_device);
 		del_gendisk(ns->disk);
 		blk_cleanup_queue(ns->queue);
 		if (blk_get_integrity(ns->disk))
@@ -4756,6 +4477,7 @@ static inline void _nvme_check_size(void)
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns_zns) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_zns) != NVME_IDENTIFY_DATA_SIZE);
+	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_nvm) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
 	BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);
@@ -4801,8 +4523,24 @@ static int __init nvme_core_init(void)
 		result = PTR_ERR(nvme_subsys_class);
 		goto destroy_class;
 	}
+
+	result = alloc_chrdev_region(&nvme_ns_chr_devt, 0, NVME_MINORS,
+				     "nvme-generic");
+	if (result < 0)
+		goto destroy_subsys_class;
+
+	nvme_ns_chr_class = class_create(THIS_MODULE, "nvme-generic");
+	if (IS_ERR(nvme_ns_chr_class)) {
+		result = PTR_ERR(nvme_ns_chr_class);
+		goto unregister_generic_ns;
+	}
+
 	return 0;
 
+unregister_generic_ns:
+	unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS);
+destroy_subsys_class:
+	class_destroy(nvme_subsys_class);
 destroy_class:
 	class_destroy(nvme_class);
 unregister_chrdev:
@@ -4819,12 +4557,15 @@ out:
 
 static void __exit nvme_core_exit(void)
 {
+	class_destroy(nvme_ns_chr_class);
 	class_destroy(nvme_subsys_class);
 	class_destroy(nvme_class);
+	unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS);
 	unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS);
 	destroy_workqueue(nvme_delete_wq);
 	destroy_workqueue(nvme_reset_wq);
 	destroy_workqueue(nvme_wq);
+	ida_destroy(&nvme_ns_chr_minor_ida);
 	ida_destroy(&nvme_instance_ida);
 }