nvme: move block_device_operations and ns/ctrl freeing to common code

This moves the block_device_operations over to common code mostly
as-is.  The only change is that the ns and ctrl refcounting got some
small refcounting to have wrappers around the kref_put operations.

A new free_ctrl operation is added to allow the PCI driver to free
it's ressources on the final drop.

Signed-off-by: Christoph Hellwig <hch@lst.de>
[Moved the integrity and pr changes due to merge conflict]
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

3 files changed, 439 insertions, 400 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index cc28150fc963..63ec86a93b83 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -15,12 +15,55 @@
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
 #include <linux/errno.h>
+#include <linux/hdreg.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/types.h>
+#include <linux/pr.h>
+#include <linux/ptrace.h>
+#include <linux/nvme_ioctl.h>
+#include <linux/t10-pi.h>
+#include <scsi/sg.h>
+#include <asm/unaligned.h>
 
 #include "nvme.h"
 
+DEFINE_SPINLOCK(dev_list_lock);
+
+static void nvme_free_ns(struct kref *kref)
+{
+	struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref);
+
+	if (ns->type == NVME_NS_LIGHTNVM)
+		nvme_nvm_unregister(ns->queue, ns->disk->disk_name);
+
+	spin_lock(&dev_list_lock);
+	ns->disk->private_data = NULL;
+	spin_unlock(&dev_list_lock);
+
+	nvme_put_ctrl(ns->ctrl);
+	put_disk(ns->disk);
+	kfree(ns);
+}
+
+void nvme_put_ns(struct nvme_ns *ns)
+{
+	kref_put(&ns->kref, nvme_free_ns);
+}
+
+static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk)
+{
+	struct nvme_ns *ns;
+
+	spin_lock(&dev_list_lock);
+	ns = disk->private_data;
+	if (ns && !kref_get_unless_zero(&ns->kref))
+		ns = NULL;
+	spin_unlock(&dev_list_lock);
+
+	return ns;
+}
+
 struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, unsigned int flags)
 {
@@ -269,3 +312,373 @@ int nvme_get_log_page(struct nvme_ctrl *dev, struct nvme_smart_log **log)
 		kfree(*log);
 	return error;
 }
+
+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;
+
+	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;
+	meta_len = (io.nblocks + 1) * ns->ms;
+	metadata = (void __user *)(uintptr_t)io.metadata;
+
+	if (ns->ext) {
+		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->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,
+			(void __user *)(uintptr_t)io.addr, length,
+			metadata, meta_len, io.slba, NULL, 0);
+}
+
+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;
+	int status;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
+		return -EFAULT;
+
+	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[0] = cpu_to_le32(cmd.cdw10);
+	c.common.cdw10[1] = cpu_to_le32(cmd.cdw11);
+	c.common.cdw10[2] = cpu_to_le32(cmd.cdw12);
+	c.common.cdw10[3] = cpu_to_le32(cmd.cdw13);
+	c.common.cdw10[4] = cpu_to_le32(cmd.cdw14);
+	c.common.cdw10[5] = 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,
+			(void __user *)cmd.addr, cmd.data_len,
+			&cmd.result, timeout);
+	if (status >= 0) {
+		if (put_user(cmd.result, &ucmd->result))
+			return -EFAULT;
+	}
+
+	return status;
+}
+
+static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
+		unsigned int cmd, unsigned long arg)
+{
+	struct nvme_ns *ns = bdev->bd_disk->private_data;
+
+	switch (cmd) {
+	case NVME_IOCTL_ID:
+		force_successful_syscall_return();
+		return ns->ns_id;
+	case NVME_IOCTL_ADMIN_CMD:
+		return nvme_user_cmd(ns->ctrl, NULL, (void __user *)arg);
+	case NVME_IOCTL_IO_CMD:
+		return nvme_user_cmd(ns->ctrl, ns, (void __user *)arg);
+	case NVME_IOCTL_SUBMIT_IO:
+		return nvme_submit_io(ns, (void __user *)arg);
+	case SG_GET_VERSION_NUM:
+		return nvme_sg_get_version_num((void __user *)arg);
+	case SG_IO:
+		return nvme_sg_io(ns, (void __user *)arg);
+	default:
+		return -ENOTTY;
+	}
+}
+
+#ifdef CONFIG_COMPAT
+static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
+			unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case SG_IO:
+		return -ENOIOCTLCMD;
+	}
+	return nvme_ioctl(bdev, mode, cmd, arg);
+}
+#else
+#define nvme_compat_ioctl	NULL
+#endif
+
+static int nvme_open(struct block_device *bdev, fmode_t mode)
+{
+	return nvme_get_ns_from_disk(bdev->bd_disk) ? 0 : -ENXIO;
+}
+
+static void nvme_release(struct gendisk *disk, fmode_t mode)
+{
+	nvme_put_ns(disk->private_data);
+}
+
+static int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
+{
+	/* some standard values */
+	geo->heads = 1 << 6;
+	geo->sectors = 1 << 5;
+	geo->cylinders = get_capacity(bdev->bd_disk) >> 11;
+	return 0;
+}
+
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+static void nvme_init_integrity(struct nvme_ns *ns)
+{
+	struct blk_integrity integrity;
+
+	switch (ns->pi_type) {
+	case NVME_NS_DPS_PI_TYPE3:
+		integrity.profile = &t10_pi_type3_crc;
+		break;
+	case NVME_NS_DPS_PI_TYPE1:
+	case NVME_NS_DPS_PI_TYPE2:
+		integrity.profile = &t10_pi_type1_crc;
+		break;
+	default:
+		integrity.profile = NULL;
+		break;
+	}
+	integrity.tuple_size = ns->ms;
+	blk_integrity_register(ns->disk, &integrity);
+	blk_queue_max_integrity_segments(ns->queue, 1);
+}
+#else
+static void nvme_init_integrity(struct nvme_ns *ns)
+{
+}
+#endif /* CONFIG_BLK_DEV_INTEGRITY */
+
+static void nvme_config_discard(struct nvme_ns *ns)
+{
+	u32 logical_block_size = queue_logical_block_size(ns->queue);
+	ns->queue->limits.discard_zeroes_data = 0;
+	ns->queue->limits.discard_alignment = logical_block_size;
+	ns->queue->limits.discard_granularity = logical_block_size;
+	blk_queue_max_discard_sectors(ns->queue, 0xffffffff);
+	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
+}
+
+int nvme_revalidate_disk(struct gendisk *disk)
+{
+	struct nvme_ns *ns = disk->private_data;
+	struct nvme_id_ns *id;
+	u8 lbaf, pi_type;
+	u16 old_ms;
+	unsigned short bs;
+
+	if (nvme_identify_ns(ns->ctrl, ns->ns_id, &id)) {
+		dev_warn(ns->ctrl->dev, "%s: Identify failure nvme%dn%d\n",
+				__func__, ns->ctrl->instance, ns->ns_id);
+		return -ENODEV;
+	}
+	if (id->ncap == 0) {
+		kfree(id);
+		return -ENODEV;
+	}
+
+	if (nvme_nvm_ns_supported(ns, id) && ns->type != NVME_NS_LIGHTNVM) {
+		if (nvme_nvm_register(ns->queue, disk->disk_name)) {
+			dev_warn(ns->ctrl->dev,
+				"%s: LightNVM init failure\n", __func__);
+			kfree(id);
+			return -ENODEV;
+		}
+		ns->type = NVME_NS_LIGHTNVM;
+	}
+
+	old_ms = ns->ms;
+	lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
+	ns->lba_shift = id->lbaf[lbaf].ds;
+	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
+	ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
+
+	/*
+	 * If identify namespace failed, use default 512 byte block size so
+	 * block layer can use before failing read/write for 0 capacity.
+	 */
+	if (ns->lba_shift == 0)
+		ns->lba_shift = 9;
+	bs = 1 << ns->lba_shift;
+
+	/* XXX: PI implementation requires metadata equal t10 pi tuple size */
+	pi_type = ns->ms == sizeof(struct t10_pi_tuple) ?
+					id->dps & NVME_NS_DPS_PI_MASK : 0;
+
+	blk_mq_freeze_queue(disk->queue);
+	if (blk_get_integrity(disk) && (ns->pi_type != pi_type ||
+				ns->ms != old_ms ||
+				bs != queue_logical_block_size(disk->queue) ||
+				(ns->ms && ns->ext)))
+		blk_integrity_unregister(disk);
+
+	ns->pi_type = pi_type;
+	blk_queue_logical_block_size(ns->queue, bs);
+
+	if (ns->ms && !ns->ext)
+		nvme_init_integrity(ns);
+
+	if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk))
+		set_capacity(disk, 0);
+	else
+		set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
+
+	if (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM)
+		nvme_config_discard(ns);
+	blk_mq_unfreeze_queue(disk->queue);
+
+	kfree(id);
+	return 0;
+}
+
+static char nvme_pr_type(enum pr_type type)
+{
+	switch (type) {
+	case PR_WRITE_EXCLUSIVE:
+		return 1;
+	case PR_EXCLUSIVE_ACCESS:
+		return 2;
+	case PR_WRITE_EXCLUSIVE_REG_ONLY:
+		return 3;
+	case PR_EXCLUSIVE_ACCESS_REG_ONLY:
+		return 4;
+	case PR_WRITE_EXCLUSIVE_ALL_REGS:
+		return 5;
+	case PR_EXCLUSIVE_ACCESS_ALL_REGS:
+		return 6;
+	default:
+		return 0;
+	}
+};
+
+static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
+				u64 key, u64 sa_key, u8 op)
+{
+	struct nvme_ns *ns = bdev->bd_disk->private_data;
+	struct nvme_command c;
+	u8 data[16] = { 0, };
+
+	put_unaligned_le64(key, &data[0]);
+	put_unaligned_le64(sa_key, &data[8]);
+
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = op;
+	c.common.nsid = cpu_to_le32(ns->ns_id);
+	c.common.cdw10[0] = cpu_to_le32(cdw10);
+
+	return nvme_submit_sync_cmd(ns->queue, &c, data, 16);
+}
+
+static int nvme_pr_register(struct block_device *bdev, u64 old,
+		u64 new, unsigned flags)
+{
+	u32 cdw10;
+
+	if (flags & ~PR_FL_IGNORE_KEY)
+		return -EOPNOTSUPP;
+
+	cdw10 = old ? 2 : 0;
+	cdw10 |= (flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0;
+	cdw10 |= (1 << 30) | (1 << 31); /* PTPL=1 */
+	return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_register);
+}
+
+static int nvme_pr_reserve(struct block_device *bdev, u64 key,
+		enum pr_type type, unsigned flags)
+{
+	u32 cdw10;
+
+	if (flags & ~PR_FL_IGNORE_KEY)
+		return -EOPNOTSUPP;
+
+	cdw10 = nvme_pr_type(type) << 8;
+	cdw10 |= ((flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0);
+	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_acquire);
+}
+
+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 = {
+	.pr_register	= nvme_pr_register,
+	.pr_reserve	= nvme_pr_reserve,
+	.pr_release	= nvme_pr_release,
+	.pr_preempt	= nvme_pr_preempt,
+	.pr_clear	= nvme_pr_clear,
+};
+
+const struct block_device_operations nvme_fops = {
+	.owner		= THIS_MODULE,
+	.ioctl		= nvme_ioctl,
+	.compat_ioctl	= nvme_compat_ioctl,
+	.open		= nvme_open,
+	.release	= nvme_release,
+	.getgeo		= nvme_getgeo,
+	.revalidate_disk= nvme_revalidate_disk,
+	.pr_ops		= &nvme_pr_ops,
+};
+
+static void nvme_free_ctrl(struct kref *kref)
+{
+	struct nvme_ctrl *ctrl = container_of(kref, struct nvme_ctrl, kref);
+
+	ctrl->ops->free_ctrl(ctrl);
+}
+
+void nvme_put_ctrl(struct nvme_ctrl *ctrl)
+{
+	kref_put(&ctrl->kref, nvme_free_ctrl);
+}
+
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 5ba9acbfddfa..3b3f855580ee 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -19,6 +19,8 @@
 #include <linux/kref.h>
 #include <linux/blk-mq.h>
 
+struct nvme_passthru_cmd;
+
 extern unsigned char nvme_io_timeout;
 #define NVME_IO_TIMEOUT	(nvme_io_timeout * HZ)
 
@@ -34,6 +36,7 @@ struct nvme_ctrl {
 	const struct nvme_ctrl_ops *ops;
 	struct request_queue *admin_q;
 	struct device *dev;
+	struct kref kref;
 	int instance;
 
 	char name[12];
@@ -69,6 +72,7 @@ struct nvme_ns {
 
 struct nvme_ctrl_ops {
 	int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val);
+	void (*free_ctrl)(struct nvme_ctrl *ctrl);
 };
 
 static inline bool nvme_ctrl_ready(struct nvme_ctrl *ctrl)
@@ -148,6 +152,9 @@ static inline int nvme_error_status(u16 status)
 	}
 }
 
+void nvme_put_ctrl(struct nvme_ctrl *ctrl);
+void nvme_put_ns(struct nvme_ns *ns);
+
 struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, unsigned int flags);
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
@@ -170,6 +177,13 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid,
 int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
 			dma_addr_t dma_addr, u32 *result);
 
+extern const struct block_device_operations nvme_fops;
+extern spinlock_t dev_list_lock;
+
+int nvme_revalidate_disk(struct gendisk *disk);
+int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
+			struct nvme_passthru_cmd __user *ucmd);
+
 struct sg_io_hdr;
 
 int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index aa033f047aaf..e0f40afbf01b 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -79,7 +79,6 @@ static bool use_cmb_sqes = true;
 module_param(use_cmb_sqes, bool, 0644);
 MODULE_PARM_DESC(use_cmb_sqes, "use controller's memory buffer for I/O SQes");
 
-static DEFINE_SPINLOCK(dev_list_lock);
 static LIST_HEAD(dev_list);
 static struct task_struct *nvme_thread;
 static struct workqueue_struct *nvme_workq;
@@ -127,7 +126,6 @@ struct nvme_dev {
 	struct msix_entry *entry;
 	void __iomem *bar;
 	struct list_head namespaces;
-	struct kref kref;
 	struct device *device;
 	struct work_struct reset_work;
 	struct work_struct probe_work;
@@ -601,27 +599,6 @@ static void nvme_dif_remap(struct request *req,
 	}
 	kunmap_atomic(pmap);
 }
-
-static void nvme_init_integrity(struct nvme_ns *ns)
-{
-	struct blk_integrity integrity;
-
-	switch (ns->pi_type) {
-	case NVME_NS_DPS_PI_TYPE3:
-		integrity.profile = &t10_pi_type3_crc;
-		break;
-	case NVME_NS_DPS_PI_TYPE1:
-	case NVME_NS_DPS_PI_TYPE2:
-		integrity.profile = &t10_pi_type1_crc;
-		break;
-	default:
-		integrity.profile = NULL;
-		break;
-	}
-	integrity.tuple_size = ns->ms;
-	blk_integrity_register(ns->disk, &integrity);
-	blk_queue_max_integrity_segments(ns->queue, 1);
-}
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 static void nvme_dif_remap(struct request *req,
 			void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))
@@ -633,9 +610,6 @@ static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
 static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
 {
 }
-static void nvme_init_integrity(struct nvme_ns *ns)
-{
-}
 #endif
 
 static void req_completion(struct nvme_queue *nvmeq, void *ctx,
@@ -1633,94 +1607,6 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	return result;
 }
 
-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;
-
-	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;
-	meta_len = (io.nblocks + 1) * ns->ms;
-	metadata = (void __user *)(uintptr_t)io.metadata;
-
-	if (ns->ext) {
-		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->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,
-			(void __user *)(uintptr_t)io.addr, length,
-			metadata, meta_len, 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;
-	int status;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EACCES;
-	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
-		return -EFAULT;
-
-	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[0] = cpu_to_le32(cmd.cdw10);
-	c.common.cdw10[1] = cpu_to_le32(cmd.cdw11);
-	c.common.cdw10[2] = cpu_to_le32(cmd.cdw12);
-	c.common.cdw10[3] = cpu_to_le32(cmd.cdw13);
-	c.common.cdw10[4] = cpu_to_le32(cmd.cdw14);
-	c.common.cdw10[5] = 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,
-			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
-			&cmd.result, timeout);
-	if (status >= 0) {
-		if (put_user(cmd.result, &ucmd->result))
-			return -EFAULT;
-	}
-
-	return status;
-}
-
 static int nvme_subsys_reset(struct nvme_dev *dev)
 {
 	if (!dev->subsystem)
@@ -1730,281 +1616,6 @@ static int nvme_subsys_reset(struct nvme_dev *dev)
 	return 0;
 }
 
-static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
-							unsigned long arg)
-{
-	struct nvme_ns *ns = bdev->bd_disk->private_data;
-
-	switch (cmd) {
-	case NVME_IOCTL_ID:
-		force_successful_syscall_return();
-		return ns->ns_id;
-	case NVME_IOCTL_ADMIN_CMD:
-		return nvme_user_cmd(ns->ctrl, NULL, (void __user *)arg);
-	case NVME_IOCTL_IO_CMD:
-		return nvme_user_cmd(ns->ctrl, ns, (void __user *)arg);
-	case NVME_IOCTL_SUBMIT_IO:
-		return nvme_submit_io(ns, (void __user *)arg);
-	case SG_GET_VERSION_NUM:
-		return nvme_sg_get_version_num((void __user *)arg);
-	case SG_IO:
-		return nvme_sg_io(ns, (void __user *)arg);
-	default:
-		return -ENOTTY;
-	}
-}
-
-#ifdef CONFIG_COMPAT
-static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
-					unsigned int cmd, unsigned long arg)
-{
-	switch (cmd) {
-	case SG_IO:
-		return -ENOIOCTLCMD;
-	}
-	return nvme_ioctl(bdev, mode, cmd, arg);
-}
-#else
-#define nvme_compat_ioctl	NULL
-#endif
-
-static void nvme_free_dev(struct kref *kref);
-static void nvme_free_ns(struct kref *kref)
-{
-	struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref);
-	struct nvme_dev *dev = to_nvme_dev(ns->ctrl);
-
-	if (ns->type == NVME_NS_LIGHTNVM)
-		nvme_nvm_unregister(ns->queue, ns->disk->disk_name);
-
-	spin_lock(&dev_list_lock);
-	ns->disk->private_data = NULL;
-	spin_unlock(&dev_list_lock);
-
-	kref_put(&dev->kref, nvme_free_dev);
-	put_disk(ns->disk);
-	kfree(ns);
-}
-
-static int nvme_open(struct block_device *bdev, fmode_t mode)
-{
-	int ret = 0;
-	struct nvme_ns *ns;
-
-	spin_lock(&dev_list_lock);
-	ns = bdev->bd_disk->private_data;
-	if (!ns)
-		ret = -ENXIO;
-	else if (!kref_get_unless_zero(&ns->kref))
-		ret = -ENXIO;
-	spin_unlock(&dev_list_lock);
-
-	return ret;
-}
-
-static void nvme_release(struct gendisk *disk, fmode_t mode)
-{
-	struct nvme_ns *ns = disk->private_data;
-	kref_put(&ns->kref, nvme_free_ns);
-}
-
-static int nvme_getgeo(struct block_device *bd, struct hd_geometry *geo)
-{
-	/* some standard values */
-	geo->heads = 1 << 6;
-	geo->sectors = 1 << 5;
-	geo->cylinders = get_capacity(bd->bd_disk) >> 11;
-	return 0;
-}
-
-static void nvme_config_discard(struct nvme_ns *ns)
-{
-	u32 logical_block_size = queue_logical_block_size(ns->queue);
-	ns->queue->limits.discard_zeroes_data = 0;
-	ns->queue->limits.discard_alignment = logical_block_size;
-	ns->queue->limits.discard_granularity = logical_block_size;
-	blk_queue_max_discard_sectors(ns->queue, 0xffffffff);
-	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
-}
-
-static int nvme_revalidate_disk(struct gendisk *disk)
-{
-	struct nvme_ns *ns = disk->private_data;
-	struct nvme_dev *dev = to_nvme_dev(ns->ctrl);
-	struct nvme_id_ns *id;
-	u8 lbaf, pi_type;
-	u16 old_ms;
-	unsigned short bs;
-
-	if (nvme_identify_ns(&dev->ctrl, ns->ns_id, &id)) {
-		dev_warn(dev->dev, "%s: Identify failure nvme%dn%d\n", __func__,
-						dev->ctrl.instance, ns->ns_id);
-		return -ENODEV;
-	}
-	if (id->ncap == 0) {
-		kfree(id);
-		return -ENODEV;
-	}
-
-	if (nvme_nvm_ns_supported(ns, id) && ns->type != NVME_NS_LIGHTNVM) {
-		if (nvme_nvm_register(ns->queue, disk->disk_name)) {
-			dev_warn(dev->dev,
-				"%s: LightNVM init failure\n", __func__);
-			kfree(id);
-			return -ENODEV;
-		}
-		ns->type = NVME_NS_LIGHTNVM;
-	}
-
-	old_ms = ns->ms;
-	lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
-	ns->lba_shift = id->lbaf[lbaf].ds;
-	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
-	ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
-
-	/*
-	 * If identify namespace failed, use default 512 byte block size so
-	 * block layer can use before failing read/write for 0 capacity.
-	 */
-	if (ns->lba_shift == 0)
-		ns->lba_shift = 9;
-	bs = 1 << ns->lba_shift;
-
-	/* XXX: PI implementation requires metadata equal t10 pi tuple size */
-	pi_type = ns->ms == sizeof(struct t10_pi_tuple) ?
-					id->dps & NVME_NS_DPS_PI_MASK : 0;
-
-	blk_mq_freeze_queue(disk->queue);
-	if (blk_get_integrity(disk) && (ns->pi_type != pi_type ||
-				ns->ms != old_ms ||
-				bs != queue_logical_block_size(disk->queue) ||
-				(ns->ms && ns->ext)))
-		blk_integrity_unregister(disk);
-
-	ns->pi_type = pi_type;
-	blk_queue_logical_block_size(ns->queue, bs);
-
-	if (ns->ms && !ns->ext)
-		nvme_init_integrity(ns);
-
-	if ((ns->ms && !(ns->ms == 8 && ns->pi_type) &&
-						!blk_get_integrity(disk)) ||
-						ns->type == NVME_NS_LIGHTNVM)
-		set_capacity(disk, 0);
-	else
-		set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
-
-	if (dev->ctrl.oncs & NVME_CTRL_ONCS_DSM)
-		nvme_config_discard(ns);
-	blk_mq_unfreeze_queue(disk->queue);
-
-	kfree(id);
-	return 0;
-}
-
-static char nvme_pr_type(enum pr_type type)
-{
-	switch (type) {
-	case PR_WRITE_EXCLUSIVE:
-		return 1;
-	case PR_EXCLUSIVE_ACCESS:
-		return 2;
-	case PR_WRITE_EXCLUSIVE_REG_ONLY:
-		return 3;
-	case PR_EXCLUSIVE_ACCESS_REG_ONLY:
-		return 4;
-	case PR_WRITE_EXCLUSIVE_ALL_REGS:
-		return 5;
-	case PR_EXCLUSIVE_ACCESS_ALL_REGS:
-		return 6;
-	default:
-		return 0;
-	}
-};
-
-static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
-				u64 key, u64 sa_key, u8 op)
-{
-	struct nvme_ns *ns = bdev->bd_disk->private_data;
-	struct nvme_command c;
-	u8 data[16] = { 0, };
-
-	put_unaligned_le64(key, &data[0]);
-	put_unaligned_le64(sa_key, &data[8]);
-
-	memset(&c, 0, sizeof(c));
-	c.common.opcode = op;
-	c.common.nsid = cpu_to_le32(ns->ns_id);
-	c.common.cdw10[0] = cpu_to_le32(cdw10);
-
-	return nvme_submit_sync_cmd(ns->queue, &c, data, 16);
-}
-
-static int nvme_pr_register(struct block_device *bdev, u64 old,
-		u64 new, unsigned flags)
-{
-	u32 cdw10;
-
-	if (flags & ~PR_FL_IGNORE_KEY)
-		return -EOPNOTSUPP;
-
-	cdw10 = old ? 2 : 0;
-	cdw10 |= (flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0;
-	cdw10 |= (1 << 30) | (1 << 31); /* PTPL=1 */
-	return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_register);
-}
-
-static int nvme_pr_reserve(struct block_device *bdev, u64 key,
-		enum pr_type type, unsigned flags)
-{
-	u32 cdw10;
-
-	if (flags & ~PR_FL_IGNORE_KEY)
-		return -EOPNOTSUPP;
-
-	cdw10 = nvme_pr_type(type) << 8;
-	cdw10 |= ((flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0);
-	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_acquire);
-}
-
-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 = {
-	.pr_register	= nvme_pr_register,
-	.pr_reserve	= nvme_pr_reserve,
-	.pr_release	= nvme_pr_release,
-	.pr_preempt	= nvme_pr_preempt,
-	.pr_clear	= nvme_pr_clear,
-};
-
-static const struct block_device_operations nvme_fops = {
-	.owner		= THIS_MODULE,
-	.ioctl		= nvme_ioctl,
-	.compat_ioctl	= nvme_compat_ioctl,
-	.open		= nvme_open,
-	.release	= nvme_release,
-	.getgeo		= nvme_getgeo,
-	.revalidate_disk= nvme_revalidate_disk,
-	.pr_ops		= &nvme_pr_ops,
-};
-
 static int nvme_kthread(void *data)
 {
 	struct nvme_dev *dev, *next;
@@ -2105,7 +1716,7 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 	if (nvme_revalidate_disk(ns->disk))
 		goto out_free_disk;
 
-	kref_get(&dev->kref);
+	kref_get(&dev->ctrl.kref);
 	if (ns->type != NVME_NS_LIGHTNVM) {
 		add_disk(ns->disk);
 		if (ns->ms) {
@@ -2354,7 +1965,7 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 		blk_cleanup_queue(ns->queue);
 	}
 	list_del_init(&ns->list);
-	kref_put(&ns->kref, nvme_free_ns);
+	nvme_put_ns(ns);
 }
 
 static void nvme_scan_namespaces(struct nvme_dev *dev, unsigned nn)
@@ -2828,9 +2439,9 @@ static void nvme_release_instance(struct nvme_dev *dev)
 	spin_unlock(&dev_list_lock);
 }
 
-static void nvme_free_dev(struct kref *kref)
+static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 {
-	struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref);
+	struct nvme_dev *dev = to_nvme_dev(ctrl);
 
 	put_device(dev->dev);
 	put_device(dev->device);
@@ -2857,7 +2468,7 @@ static int nvme_dev_open(struct inode *inode, struct file *f)
 				ret = -EWOULDBLOCK;
 				break;
 			}
-			if (!kref_get_unless_zero(&dev->kref))
+			if (!kref_get_unless_zero(&dev->ctrl.kref))
 				break;
 			f->private_data = dev;
 			ret = 0;
@@ -2872,7 +2483,7 @@ static int nvme_dev_open(struct inode *inode, struct file *f)
 static int nvme_dev_release(struct inode *inode, struct file *f)
 {
 	struct nvme_dev *dev = f->private_data;
-	kref_put(&dev->kref, nvme_free_dev);
+	nvme_put_ctrl(&dev->ctrl);
 	return 0;
 }
 
@@ -2987,19 +2598,19 @@ static int nvme_remove_dead_ctrl(void *arg)
 
 	if (pci_get_drvdata(pdev))
 		pci_stop_and_remove_bus_device_locked(pdev);
-	kref_put(&dev->kref, nvme_free_dev);
+	nvme_put_ctrl(&dev->ctrl);
 	return 0;
 }
 
 static void nvme_dead_ctrl(struct nvme_dev *dev)
 {
 	dev_warn(dev->dev, "Device failed to resume\n");
-	kref_get(&dev->kref);
+	kref_get(&dev->ctrl.kref);
 	if (IS_ERR(kthread_run(nvme_remove_dead_ctrl, dev, "nvme%d",
 						dev->ctrl.instance))) {
 		dev_err(dev->dev,
 			"Failed to start controller remove task\n");
-		kref_put(&dev->kref, nvme_free_dev);
+		nvme_put_ctrl(&dev->ctrl);
 	}
 }
 
@@ -3077,6 +2688,7 @@ static int nvme_pci_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
 
 static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.reg_read32		= nvme_pci_reg_read32,
+	.free_ctrl		= nvme_pci_free_ctrl,
 };
 
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
@@ -3116,7 +2728,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (result)
 		goto release;
 
-	kref_init(&dev->kref);
+	kref_init(&dev->ctrl.kref);
 	dev->device = device_create(nvme_class, &pdev->dev,
 				MKDEV(nvme_char_major, dev->ctrl.instance),
 				dev, "nvme%d", dev->ctrl.instance);
@@ -3189,7 +2801,7 @@ static void nvme_remove(struct pci_dev *pdev)
 	nvme_free_queues(dev, 0);
 	nvme_release_cmb(dev);
 	nvme_release_prp_pools(dev);
-	kref_put(&dev->kref, nvme_free_dev);
+	nvme_put_ctrl(&dev->ctrl);
 }
 
 /* These functions are yet to be implemented */