Merge branch 'for-4.8/drivers' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "This branch also contains core changes.  I've come to the conclusion
  that from 4.9 and forward, I'll be doing just a single branch.  We
  often have dependencies between core and drivers, and it's hard to
  always split them up appropriately without pulling core into drivers
  when that happens.

  That said, this contains:

   - separate secure erase type for the core block layer, from
     Christoph.

   - set of discard fixes, from Christoph.

   - bio shrinking fixes from Christoph, as a followup up to the
     op/flags change in the core branch.

   - map and append request fixes from Christoph.

   - NVMeF (NVMe over Fabrics) code from Christoph.  This is pretty
     exciting!

   - nvme-loop fixes from Arnd.

   - removal of ->driverfs_dev from Dan, after providing a
     device_add_disk() helper.

   - bcache fixes from Bhaktipriya and Yijing.

   - cdrom subchannel read fix from Vchannaiah.

   - set of lightnvm updates from Wenwei, Matias, Johannes, and Javier.

   - set of drbd updates and fixes from Fabian, Lars, and Philipp.

   - mg_disk error path fix from Bart.

   - user notification for failed device add for loop, from Minfei.

   - NVMe in general:
        + NVMe delay quirk from Guilherme.
        + SR-IOV support and command retry limits from Keith.
        + fix for memory-less NUMA node from Masayoshi.
        + use UINT_MAX for discard sectors, from Minfei.
        + cancel IO fixes from Ming.
        + don't allocate unused major, from Neil.
        + error code fixup from Dan.
        + use constants for PSDT/FUSE from James.
        + variable init fix from Jay.
        + fabrics fixes from Ming, Sagi, and Wei.
        + various fixes"

* 'for-4.8/drivers' of git://git.kernel.dk/linux-block: (115 commits)
  nvme/pci: Provide SR-IOV support
  nvme: initialize variable before logical OR'ing it
  block: unexport various bio mapping helpers
  scsi/osd: open code blk_make_request
  target: stop using blk_make_request
  block: simplify and export blk_rq_append_bio
  block: ensure bios return from blk_get_request are properly initialized
  virtio_blk: use blk_rq_map_kern
  memstick: don't allow REQ_TYPE_BLOCK_PC requests
  block: shrink bio size again
  block: simplify and cleanup bvec pool handling
  block: get rid of bio_rw and READA
  block: don't ignore -EOPNOTSUPP blkdev_issue_write_same
  block: introduce BLKDEV_DISCARD_ZERO to fix zeroout
  NVMe: don't allocate unused nvme_major
  nvme: avoid crashes when node 0 is memoryless node.
  nvme: Limit command retries
  loop: Make user notify for adding loop device failed
  nvme-loop: fix nvme-loop Kconfig dependencies
  nvmet: fix return value check in nvmet_subsys_alloc()
  ...

9 files changed, 3479 insertions, 86 deletions

diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index d296fc3ae06e..db39d53cdfb9 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -24,3 +24,22 @@ config BLK_DEV_NVME_SCSI
 	  to say N here, unless you run a distro that abuses the SCSI
 	  emulation to provide stable device names for mount by id, like
 	  some OpenSuSE and SLES versions.
+
+config NVME_FABRICS
+	tristate
+
+config NVME_RDMA
+	tristate "NVM Express over Fabrics RDMA host driver"
+	depends on INFINIBAND
+	depends on BLK_DEV_NVME
+	select NVME_FABRICS
+	select SG_POOL
+	help
+	  This provides support for the NVMe over Fabrics protocol using
+	  the RDMA (Infiniband, RoCE, iWarp) transport.  This allows you
+	  to use remote block devices exported using the NVMe protocol set.
+
+	  To configure a NVMe over Fabrics controller use the nvme-cli tool
+	  from https://github.com/linux-nvme/nvme-cli.
+
+	  If unsure, say N.
diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile
index 9a3ca892b4a7..47abcec23514 100644
--- a/drivers/nvme/host/Makefile
+++ b/drivers/nvme/host/Makefile
@@ -1,8 +1,14 @@
 obj-$(CONFIG_NVME_CORE)			+= nvme-core.o
 obj-$(CONFIG_BLK_DEV_NVME)		+= nvme.o
+obj-$(CONFIG_NVME_FABRICS)		+= nvme-fabrics.o
+obj-$(CONFIG_NVME_RDMA)			+= nvme-rdma.o
 
 nvme-core-y				:= core.o
 nvme-core-$(CONFIG_BLK_DEV_NVME_SCSI)	+= scsi.o
 nvme-core-$(CONFIG_NVM)			+= lightnvm.o
 
 nvme-y					+= pci.o
+
+nvme-fabrics-y				+= fabrics.o
+
+nvme-rdma-y				+= rdma.o
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 1c5a032d490d..7ff2e820bbf4 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -30,6 +30,7 @@
 #include <asm/unaligned.h>
 
 #include "nvme.h"
+#include "fabrics.h"
 
 #define NVME_MINORS		(1U << MINORBITS)
 
@@ -47,8 +48,10 @@ unsigned char shutdown_timeout = 5;
 module_param(shutdown_timeout, byte, 0644);
 MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown");
 
-static int nvme_major;
-module_param(nvme_major, int, 0);
+unsigned int nvme_max_retries = 5;
+module_param_named(max_retries, nvme_max_retries, uint, 0644);
+MODULE_PARM_DESC(max_retries, "max number of retries a command may have");
+EXPORT_SYMBOL_GPL(nvme_max_retries);
 
 static int nvme_char_major;
 module_param(nvme_char_major, int, 0);
@@ -58,6 +61,23 @@ static DEFINE_SPINLOCK(dev_list_lock);
 
 static struct class *nvme_class;
 
+void nvme_cancel_request(struct request *req, void *data, bool reserved)
+{
+	int status;
+
+	if (!blk_mq_request_started(req))
+		return;
+
+	dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
+				"Cancelling I/O %d", req->tag);
+
+	status = NVME_SC_ABORT_REQ;
+	if (blk_queue_dying(req->q))
+		status |= NVME_SC_DNR;
+	blk_mq_complete_request(req, status);
+}
+EXPORT_SYMBOL_GPL(nvme_cancel_request);
+
 bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		enum nvme_ctrl_state new_state)
 {
@@ -68,7 +88,9 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	switch (new_state) {
 	case NVME_CTRL_LIVE:
 		switch (old_state) {
+		case NVME_CTRL_NEW:
 		case NVME_CTRL_RESETTING:
+		case NVME_CTRL_RECONNECTING:
 			changed = true;
 			/* FALLTHRU */
 		default:
@@ -79,6 +101,16 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		switch (old_state) {
 		case NVME_CTRL_NEW:
 		case NVME_CTRL_LIVE:
+		case NVME_CTRL_RECONNECTING:
+			changed = true;
+			/* FALLTHRU */
+		default:
+			break;
+		}
+		break;
+	case NVME_CTRL_RECONNECTING:
+		switch (old_state) {
+		case NVME_CTRL_LIVE:
 			changed = true;
 			/* FALLTHRU */
 		default:
@@ -89,6 +121,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		switch (old_state) {
 		case NVME_CTRL_LIVE:
 		case NVME_CTRL_RESETTING:
+		case NVME_CTRL_RECONNECTING:
 			changed = true;
 			/* FALLTHRU */
 		default:
@@ -174,21 +207,21 @@ void nvme_requeue_req(struct request *req)
 EXPORT_SYMBOL_GPL(nvme_requeue_req);
 
 struct request *nvme_alloc_request(struct request_queue *q,
-		struct nvme_command *cmd, unsigned int flags)
+		struct nvme_command *cmd, unsigned int flags, int qid)
 {
-	bool write = cmd->common.opcode & 1;
 	struct request *req;
 
-	req = blk_mq_alloc_request(q, write, flags);
+	if (qid == NVME_QID_ANY) {
+		req = blk_mq_alloc_request(q, nvme_is_write(cmd), flags);
+	} else {
+		req = blk_mq_alloc_request_hctx(q, nvme_is_write(cmd), flags,
+				qid ? qid - 1 : 0);
+	}
 	if (IS_ERR(req))
 		return req;
 
 	req->cmd_type = REQ_TYPE_DRV_PRIV;
 	req->cmd_flags |= REQ_FAILFAST_DRIVER;
-	req->__data_len = 0;
-	req->__sector = (sector_t) -1;
-	req->bio = req->biotail = NULL;
-
 	req->cmd = (unsigned char *)cmd;
 	req->cmd_len = sizeof(struct nvme_command);
 
@@ -307,12 +340,12 @@ EXPORT_SYMBOL_GPL(nvme_setup_cmd);
  */
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		struct nvme_completion *cqe, void *buffer, unsigned bufflen,
-		unsigned timeout)
+		unsigned timeout, int qid, int at_head, int flags)
 {
 	struct request *req;
 	int ret;
 
-	req = nvme_alloc_request(q, cmd, 0);
+	req = nvme_alloc_request(q, cmd, flags, qid);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -325,17 +358,19 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 			goto out;
 	}
 
-	blk_execute_rq(req->q, NULL, req, 0);
+	blk_execute_rq(req->q, NULL, req, at_head);
 	ret = req->errors;
  out:
 	blk_mq_free_request(req);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(__nvme_submit_sync_cmd);
 
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buffer, unsigned bufflen)
 {
-	return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen, 0);
+	return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen, 0,
+			NVME_QID_ANY, 0, 0);
 }
 EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd);
 
@@ -344,7 +379,7 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void __user *meta_buffer, unsigned meta_len, u32 meta_seed,
 		u32 *result, unsigned timeout)
 {
-	bool write = cmd->common.opcode & 1;
+	bool write = nvme_is_write(cmd);
 	struct nvme_completion cqe;
 	struct nvme_ns *ns = q->queuedata;
 	struct gendisk *disk = ns ? ns->disk : NULL;
@@ -353,7 +388,7 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
 	void *meta = NULL;
 	int ret;
 
-	req = nvme_alloc_request(q, cmd, 0);
+	req = nvme_alloc_request(q, cmd, 0, NVME_QID_ANY);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -439,6 +474,74 @@ int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
 			result, timeout);
 }
 
+static void nvme_keep_alive_end_io(struct request *rq, int error)
+{
+	struct nvme_ctrl *ctrl = rq->end_io_data;
+
+	blk_mq_free_request(rq);
+
+	if (error) {
+		dev_err(ctrl->device,
+			"failed nvme_keep_alive_end_io error=%d\n", error);
+		return;
+	}
+
+	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+}
+
+static int nvme_keep_alive(struct nvme_ctrl *ctrl)
+{
+	struct nvme_command c;
+	struct request *rq;
+
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = nvme_admin_keep_alive;
+
+	rq = nvme_alloc_request(ctrl->admin_q, &c, BLK_MQ_REQ_RESERVED,
+			NVME_QID_ANY);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	rq->timeout = ctrl->kato * HZ;
+	rq->end_io_data = ctrl;
+
+	blk_execute_rq_nowait(rq->q, NULL, rq, 0, nvme_keep_alive_end_io);
+
+	return 0;
+}
+
+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);
+
+	if (nvme_keep_alive(ctrl)) {
+		/* allocation failure, reset the controller */
+		dev_err(ctrl->device, "keep-alive failed\n");
+		ctrl->ops->reset_ctrl(ctrl);
+		return;
+	}
+}
+
+void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
+{
+	if (unlikely(ctrl->kato == 0))
+		return;
+
+	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
+	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+}
+EXPORT_SYMBOL_GPL(nvme_start_keep_alive);
+
+void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
+{
+	if (unlikely(ctrl->kato == 0))
+		return;
+
+	cancel_delayed_work_sync(&ctrl->ka_work);
+}
+EXPORT_SYMBOL_GPL(nvme_stop_keep_alive);
+
 int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
 {
 	struct nvme_command c = { };
@@ -500,10 +603,11 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid,
 	memset(&c, 0, sizeof(c));
 	c.features.opcode = nvme_admin_get_features;
 	c.features.nsid = cpu_to_le32(nsid);
-	c.features.prp1 = cpu_to_le64(dma_addr);
+	c.features.dptr.prp1 = cpu_to_le64(dma_addr);
 	c.features.fid = cpu_to_le32(fid);
 
-	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0);
+	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0,
+			NVME_QID_ANY, 0, 0);
 	if (ret >= 0)
 		*result = le32_to_cpu(cqe.result);
 	return ret;
@@ -518,11 +622,12 @@ int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
 
 	memset(&c, 0, sizeof(c));
 	c.features.opcode = nvme_admin_set_features;
-	c.features.prp1 = cpu_to_le64(dma_addr);
+	c.features.dptr.prp1 = cpu_to_le64(dma_addr);
 	c.features.fid = cpu_to_le32(fid);
 	c.features.dword11 = cpu_to_le32(dword11);
 
-	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0);
+	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0,
+			NVME_QID_ANY, 0, 0);
 	if (ret >= 0)
 		*result = le32_to_cpu(cqe.result);
 	return ret;
@@ -558,11 +663,22 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 
 	status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, 0,
 			&result);
-	if (status)
+	if (status < 0)
 		return status;
 
-	nr_io_queues = min(result & 0xffff, result >> 16) + 1;
-	*count = min(*count, nr_io_queues);
+	/*
+	 * Degraded controllers might return an error when setting the queue
+	 * count.  We still want to be able to bring them online and offer
+	 * access to the admin queue, as that might be only way to fix them up.
+	 */
+	if (status > 0) {
+		dev_err(ctrl->dev, "Could not set queue count (%d)\n", status);
+		*count = 0;
+	} else {
+		nr_io_queues = min(result & 0xffff, result >> 16) + 1;
+		*count = min(*count, nr_io_queues);
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nvme_set_queue_count);
@@ -726,6 +842,7 @@ static void nvme_init_integrity(struct nvme_ns *ns)
 {
 	struct blk_integrity integrity;
 
+	memset(&integrity, 0, sizeof(integrity));
 	switch (ns->pi_type) {
 	case NVME_NS_DPS_PI_TYPE3:
 		integrity.profile = &t10_pi_type3_crc;
@@ -764,7 +881,7 @@ static void nvme_config_discard(struct nvme_ns *ns)
 
 	ns->queue->limits.discard_alignment = logical_block_size;
 	ns->queue->limits.discard_granularity = logical_block_size;
-	blk_queue_max_discard_sectors(ns->queue, 0xffffffff);
+	blk_queue_max_discard_sectors(ns->queue, UINT_MAX);
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
 }
 
@@ -991,6 +1108,15 @@ int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap)
 	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
 	if (ret)
 		return ret;
+
+	/* Checking for ctrl->tagset is a trick to avoid sleeping on module
+	 * load, since we only need the quirk on reset_controller. Notice
+	 * that the HGST device needs this delay only in firmware activation
+	 * procedure; unfortunately we have no (easy) way to verify this.
+	 */
+	if ((ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY) && ctrl->tagset)
+		msleep(NVME_QUIRK_DELAY_AMOUNT);
+
 	return nvme_wait_ready(ctrl, cap, false);
 }
 EXPORT_SYMBOL_GPL(nvme_disable_ctrl);
@@ -1088,6 +1214,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	struct nvme_id_ctrl *id;
 	u64 cap;
 	int ret, page_shift;
+	u32 max_hw_sectors;
 
 	ret = ctrl->ops->reg_read32(ctrl, NVME_REG_VS, &ctrl->vs);
 	if (ret) {
@@ -1120,9 +1247,11 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	memcpy(ctrl->model, id->mn, sizeof(id->mn));
 	memcpy(ctrl->firmware_rev, id->fr, sizeof(id->fr));
 	if (id->mdts)
-		ctrl->max_hw_sectors = 1 << (id->mdts + page_shift - 9);
+		max_hw_sectors = 1 << (id->mdts + page_shift - 9);
 	else
-		ctrl->max_hw_sectors = UINT_MAX;
+		max_hw_sectors = UINT_MAX;
+	ctrl->max_hw_sectors =
+		min_not_zero(ctrl->max_hw_sectors, max_hw_sectors);
 
 	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) && id->vs[3]) {
 		unsigned int max_hw_sectors;
@@ -1138,9 +1267,33 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	}
 
 	nvme_set_queue_limits(ctrl, ctrl->admin_q);
+	ctrl->sgls = le32_to_cpu(id->sgls);
+	ctrl->kas = le16_to_cpu(id->kas);
+
+	if (ctrl->ops->is_fabrics) {
+		ctrl->icdoff = le16_to_cpu(id->icdoff);
+		ctrl->ioccsz = le32_to_cpu(id->ioccsz);
+		ctrl->iorcsz = le32_to_cpu(id->iorcsz);
+		ctrl->maxcmd = le16_to_cpu(id->maxcmd);
+
+		/*
+		 * In fabrics we need to verify the cntlid matches the
+		 * admin connect
+		 */
+		if (ctrl->cntlid != le16_to_cpu(id->cntlid))
+			ret = -EINVAL;
+
+		if (!ctrl->opts->discovery_nqn && !ctrl->kas) {
+			dev_err(ctrl->dev,
+				"keep-alive support is mandatory for fabrics\n");
+			ret = -EINVAL;
+		}
+	} else {
+		ctrl->cntlid = le16_to_cpu(id->cntlid);
+	}
 
 	kfree(id);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_init_identify);
 
@@ -1322,7 +1475,7 @@ static struct attribute *nvme_ns_attrs[] = {
 	NULL,
 };
 
-static umode_t nvme_attrs_are_visible(struct kobject *kobj,
+static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
 		struct attribute *a, int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
@@ -1341,7 +1494,7 @@ static umode_t nvme_attrs_are_visible(struct kobject *kobj,
 
 static const struct attribute_group nvme_ns_attr_group = {
 	.attrs		= nvme_ns_attrs,
-	.is_visible	= nvme_attrs_are_visible,
+	.is_visible	= nvme_ns_attrs_are_visible,
 };
 
 #define nvme_show_str_function(field)						\
@@ -1367,6 +1520,49 @@ nvme_show_str_function(serial);
 nvme_show_str_function(firmware_rev);
 nvme_show_int_function(cntlid);
 
+static ssize_t nvme_sysfs_delete(struct device *dev,
+				struct device_attribute *attr, const char *buf,
+				size_t count)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	if (device_remove_file_self(dev, attr))
+		ctrl->ops->delete_ctrl(ctrl);
+	return count;
+}
+static DEVICE_ATTR(delete_controller, S_IWUSR, NULL, nvme_sysfs_delete);
+
+static ssize_t nvme_sysfs_show_transport(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->ops->name);
+}
+static DEVICE_ATTR(transport, S_IRUGO, nvme_sysfs_show_transport, NULL);
+
+static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%s\n",
+			ctrl->ops->get_subsysnqn(ctrl));
+}
+static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL);
+
+static ssize_t nvme_sysfs_show_address(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	return ctrl->ops->get_address(ctrl, buf, PAGE_SIZE);
+}
+static DEVICE_ATTR(address, S_IRUGO, nvme_sysfs_show_address, NULL);
+
 static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_reset_controller.attr,
 	&dev_attr_rescan_controller.attr,
@@ -1374,11 +1570,38 @@ static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_serial.attr,
 	&dev_attr_firmware_rev.attr,
 	&dev_attr_cntlid.attr,
+	&dev_attr_delete_controller.attr,
+	&dev_attr_transport.attr,
+	&dev_attr_subsysnqn.attr,
+	&dev_attr_address.attr,
 	NULL
 };
 
+#define CHECK_ATTR(ctrl, a, name)		\
+	if ((a) == &dev_attr_##name.attr &&	\
+	    !(ctrl)->ops->get_##name)		\
+		return 0
+
+static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
+		struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	if (a == &dev_attr_delete_controller.attr) {
+		if (!ctrl->ops->delete_ctrl)
+			return 0;
+	}
+
+	CHECK_ATTR(ctrl, a, subsysnqn);
+	CHECK_ATTR(ctrl, a, address);
+
+	return a->mode;
+}
+
 static struct attribute_group nvme_dev_attrs_group = {
-	.attrs = nvme_dev_attrs,
+	.attrs		= nvme_dev_attrs,
+	.is_visible	= nvme_dev_attrs_are_visible,
 };
 
 static const struct attribute_group *nvme_dev_attr_groups[] = {
@@ -1446,12 +1669,9 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
 	nvme_set_queue_limits(ctrl, ns->queue);
 
-	disk->major = nvme_major;
-	disk->first_minor = 0;
 	disk->fops = &nvme_fops;
 	disk->private_data = ns;
 	disk->queue = ns->queue;
-	disk->driverfs_dev = ctrl->device;
 	disk->flags = GENHD_FL_EXT_DEVT;
 	sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, ns->instance);
 
@@ -1466,7 +1686,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	if (ns->type == NVME_NS_LIGHTNVM)
 		return;
 
-	add_disk(ns->disk);
+	device_add_disk(ctrl->device, ns->disk);
 	if (sysfs_create_group(&disk_to_dev(ns->disk)->kobj,
 					&nvme_ns_attr_group))
 		pr_warn("%s: failed to create sysfs group for identification\n",
@@ -1517,6 +1737,17 @@ static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		nvme_alloc_ns(ctrl, nsid);
 }
 
+static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
+					unsigned nsid)
+{
+	struct nvme_ns *ns, *next;
+
+	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
+		if (ns->ns_id > nsid)
+			nvme_ns_remove(ns);
+	}
+}
+
 static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn)
 {
 	struct nvme_ns *ns;
@@ -1531,7 +1762,7 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn)
 	for (i = 0; i < num_lists; i++) {
 		ret = nvme_identify_ns_list(ctrl, prev, ns_list);
 		if (ret)
-			goto out;
+			goto free;
 
 		for (j = 0; j < min(nn, 1024U); j++) {
 			nsid = le32_to_cpu(ns_list[j]);
@@ -1551,22 +1782,20 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn)
 		nn -= j;
 	}
  out:
+	nvme_remove_invalid_namespaces(ctrl, prev);
+ free:
 	kfree(ns_list);
 	return ret;
 }
 
 static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl, unsigned nn)
 {
-	struct nvme_ns *ns, *next;
 	unsigned i;
 
 	for (i = 1; i <= nn; i++)
 		nvme_validate_ns(ctrl, i);
 
-	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
-		if (ns->ns_id > nn)
-			nvme_ns_remove(ns);
-	}
+	nvme_remove_invalid_namespaces(ctrl, nn);
 }
 
 static void nvme_scan_work(struct work_struct *work)
@@ -1852,16 +2081,10 @@ int __init nvme_core_init(void)
 {
 	int result;
 
-	result = register_blkdev(nvme_major, "nvme");
-	if (result < 0)
-		return result;
-	else if (result > 0)
-		nvme_major = result;
-
 	result = __register_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme",
 							&nvme_dev_fops);
 	if (result < 0)
-		goto unregister_blkdev;
+		return result;
 	else if (result > 0)
 		nvme_char_major = result;
 
@@ -1875,8 +2098,6 @@ int __init nvme_core_init(void)
 
  unregister_chrdev:
 	__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
- unregister_blkdev:
-	unregister_blkdev(nvme_major, "nvme");
 	return result;
 }
 
@@ -1884,7 +2105,6 @@ void nvme_core_exit(void)
 {
 	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/fabrics.c b/drivers/nvme/host/fabrics.c
new file mode 100644
index 000000000000..dc996761042f
--- /dev/null
+++ b/drivers/nvme/host/fabrics.c
@@ -0,0 +1,952 @@
+/*
+ * NVMe over Fabrics common host code.
+ * Copyright (c) 2015-2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/init.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/parser.h>
+#include <linux/seq_file.h>
+#include "nvme.h"
+#include "fabrics.h"
+
+static LIST_HEAD(nvmf_transports);
+static DEFINE_MUTEX(nvmf_transports_mutex);
+
+static LIST_HEAD(nvmf_hosts);
+static DEFINE_MUTEX(nvmf_hosts_mutex);
+
+static struct nvmf_host *nvmf_default_host;
+
+static struct nvmf_host *__nvmf_host_find(const char *hostnqn)
+{
+	struct nvmf_host *host;
+
+	list_for_each_entry(host, &nvmf_hosts, list) {
+		if (!strcmp(host->nqn, hostnqn))
+			return host;
+	}
+
+	return NULL;
+}
+
+static struct nvmf_host *nvmf_host_add(const char *hostnqn)
+{
+	struct nvmf_host *host;
+
+	mutex_lock(&nvmf_hosts_mutex);
+	host = __nvmf_host_find(hostnqn);
+	if (host)
+		goto out_unlock;
+
+	host = kmalloc(sizeof(*host), GFP_KERNEL);
+	if (!host)
+		goto out_unlock;
+
+	kref_init(&host->ref);
+	memcpy(host->nqn, hostnqn, NVMF_NQN_SIZE);
+	uuid_le_gen(&host->id);
+
+	list_add_tail(&host->list, &nvmf_hosts);
+out_unlock:
+	mutex_unlock(&nvmf_hosts_mutex);
+	return host;
+}
+
+static struct nvmf_host *nvmf_host_default(void)
+{
+	struct nvmf_host *host;
+
+	host = kmalloc(sizeof(*host), GFP_KERNEL);
+	if (!host)
+		return NULL;
+
+	kref_init(&host->ref);
+	uuid_le_gen(&host->id);
+	snprintf(host->nqn, NVMF_NQN_SIZE,
+		"nqn.2014-08.org.nvmexpress:NVMf:uuid:%pUl", &host->id);
+
+	mutex_lock(&nvmf_hosts_mutex);
+	list_add_tail(&host->list, &nvmf_hosts);
+	mutex_unlock(&nvmf_hosts_mutex);
+
+	return host;
+}
+
+static void nvmf_host_destroy(struct kref *ref)
+{
+	struct nvmf_host *host = container_of(ref, struct nvmf_host, ref);
+
+	mutex_lock(&nvmf_hosts_mutex);
+	list_del(&host->list);
+	mutex_unlock(&nvmf_hosts_mutex);
+
+	kfree(host);
+}
+
+static void nvmf_host_put(struct nvmf_host *host)
+{
+	if (host)
+		kref_put(&host->ref, nvmf_host_destroy);
+}
+
+/**
+ * nvmf_get_address() -  Get address/port
+ * @ctrl:	Host NVMe controller instance which we got the address
+ * @buf:	OUTPUT parameter that will contain the address/port
+ * @size:	buffer size
+ */
+int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
+{
+	return snprintf(buf, size, "traddr=%s,trsvcid=%s\n",
+			ctrl->opts->traddr, ctrl->opts->trsvcid);
+}
+EXPORT_SYMBOL_GPL(nvmf_get_address);
+
+/**
+ * nvmf_get_subsysnqn() - Get subsystem NQN
+ * @ctrl:	Host NVMe controller instance which we got the NQN
+ */
+const char *nvmf_get_subsysnqn(struct nvme_ctrl *ctrl)
+{
+	return ctrl->opts->subsysnqn;
+}
+EXPORT_SYMBOL_GPL(nvmf_get_subsysnqn);
+
+/**
+ * nvmf_reg_read32() -  NVMe Fabrics "Property Get" API function.
+ * @ctrl:	Host NVMe controller instance maintaining the admin
+ *		queue used to submit the property read command to
+ *		the allocated NVMe controller resource on the target system.
+ * @off:	Starting offset value of the targeted property
+ *		register (see the fabrics section of the NVMe standard).
+ * @val:	OUTPUT parameter that will contain the value of
+ *		the property after a successful read.
+ *
+ * Used by the host system to retrieve a 32-bit capsule property value
+ * from an NVMe controller on the target system.
+ *
+ * ("Capsule property" is an "PCIe register concept" applied to the
+ * NVMe fabrics space.)
+ *
+ * Return:
+ *	0: successful read
+ *	> 0: NVMe error status code
+ *	< 0: Linux errno error code
+ */
+int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
+{
+	struct nvme_command cmd;
+	struct nvme_completion cqe;
+	int ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.prop_get.opcode = nvme_fabrics_command;
+	cmd.prop_get.fctype = nvme_fabrics_type_property_get;
+	cmd.prop_get.offset = cpu_to_le32(off);
+
+	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &cqe, NULL, 0, 0,
+			NVME_QID_ANY, 0, 0);
+
+	if (ret >= 0)
+		*val = le64_to_cpu(cqe.result64);
+	if (unlikely(ret != 0))
+		dev_err(ctrl->device,
+			"Property Get error: %d, offset %#x\n",
+			ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvmf_reg_read32);
+
+/**
+ * nvmf_reg_read64() -  NVMe Fabrics "Property Get" API function.
+ * @ctrl:	Host NVMe controller instance maintaining the admin
+ *		queue used to submit the property read command to
+ *		the allocated controller resource on the target system.
+ * @off:	Starting offset value of the targeted property
+ *		register (see the fabrics section of the NVMe standard).
+ * @val:	OUTPUT parameter that will contain the value of
+ *		the property after a successful read.
+ *
+ * Used by the host system to retrieve a 64-bit capsule property value
+ * from an NVMe controller on the target system.
+ *
+ * ("Capsule property" is an "PCIe register concept" applied to the
+ * NVMe fabrics space.)
+ *
+ * Return:
+ *	0: successful read
+ *	> 0: NVMe error status code
+ *	< 0: Linux errno error code
+ */
+int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
+{
+	struct nvme_command cmd;
+	struct nvme_completion cqe;
+	int ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.prop_get.opcode = nvme_fabrics_command;
+	cmd.prop_get.fctype = nvme_fabrics_type_property_get;
+	cmd.prop_get.attrib = 1;
+	cmd.prop_get.offset = cpu_to_le32(off);
+
+	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &cqe, NULL, 0, 0,
+			NVME_QID_ANY, 0, 0);
+
+	if (ret >= 0)
+		*val = le64_to_cpu(cqe.result64);
+	if (unlikely(ret != 0))
+		dev_err(ctrl->device,
+			"Property Get error: %d, offset %#x\n",
+			ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvmf_reg_read64);
+
+/**
+ * nvmf_reg_write32() -  NVMe Fabrics "Property Write" API function.
+ * @ctrl:	Host NVMe controller instance maintaining the admin
+ *		queue used to submit the property read command to
+ *		the allocated NVMe controller resource on the target system.
+ * @off:	Starting offset value of the targeted property
+ *		register (see the fabrics section of the NVMe standard).
+ * @val:	Input parameter that contains the value to be
+ *		written to the property.
+ *
+ * Used by the NVMe host system to write a 32-bit capsule property value
+ * to an NVMe controller on the target system.
+ *
+ * ("Capsule property" is an "PCIe register concept" applied to the
+ * NVMe fabrics space.)
+ *
+ * Return:
+ *	0: successful write
+ *	> 0: NVMe error status code
+ *	< 0: Linux errno error code
+ */
+int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
+{
+	struct nvme_command cmd;
+	int ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.prop_set.opcode = nvme_fabrics_command;
+	cmd.prop_set.fctype = nvme_fabrics_type_property_set;
+	cmd.prop_set.attrib = 0;
+	cmd.prop_set.offset = cpu_to_le32(off);
+	cmd.prop_set.value = cpu_to_le64(val);
+
+	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, NULL, 0, 0,
+			NVME_QID_ANY, 0, 0);
+	if (unlikely(ret))
+		dev_err(ctrl->device,
+			"Property Set error: %d, offset %#x\n",
+			ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvmf_reg_write32);
+
+/**
+ * nvmf_log_connect_error() - Error-parsing-diagnostic print
+ * out function for connect() errors.
+ *
+ * @ctrl: the specific /dev/nvmeX device that had the error.
+ *
+ * @errval: Error code to be decoded in a more human-friendly
+ *	    printout.
+ *
+ * @offset: For use with the NVMe error code NVME_SC_CONNECT_INVALID_PARAM.
+ *
+ * @cmd: This is the SQE portion of a submission capsule.
+ *
+ * @data: This is the "Data" portion of a submission capsule.
+ */
+static void nvmf_log_connect_error(struct nvme_ctrl *ctrl,
+		int errval, int offset, struct nvme_command *cmd,
+		struct nvmf_connect_data *data)
+{
+	int err_sctype = errval & (~NVME_SC_DNR);
+
+	switch (err_sctype) {
+
+	case (NVME_SC_CONNECT_INVALID_PARAM):
+		if (offset >> 16) {
+			char *inv_data = "Connect Invalid Data Parameter";
+
+			switch (offset & 0xffff) {
+			case (offsetof(struct nvmf_connect_data, cntlid)):
+				dev_err(ctrl->device,
+					"%s, cntlid: %d\n",
+					inv_data, data->cntlid);
+				break;
+			case (offsetof(struct nvmf_connect_data, hostnqn)):
+				dev_err(ctrl->device,
+					"%s, hostnqn \"%s\"\n",
+					inv_data, data->hostnqn);
+				break;
+			case (offsetof(struct nvmf_connect_data, subsysnqn)):
+				dev_err(ctrl->device,
+					"%s, subsysnqn \"%s\"\n",
+					inv_data, data->subsysnqn);
+				break;
+			default:
+				dev_err(ctrl->device,
+					"%s, starting byte offset: %d\n",
+				       inv_data, offset & 0xffff);
+				break;
+			}
+		} else {
+			char *inv_sqe = "Connect Invalid SQE Parameter";
+
+			switch (offset) {
+			case (offsetof(struct nvmf_connect_command, qid)):
+				dev_err(ctrl->device,
+				       "%s, qid %d\n",
+					inv_sqe, cmd->connect.qid);
+				break;
+			default:
+				dev_err(ctrl->device,
+					"%s, starting byte offset: %d\n",
+					inv_sqe, offset);
+			}
+		}
+		break;
+	default:
+		dev_err(ctrl->device,
+			"Connect command failed, error wo/DNR bit: %d\n",
+			err_sctype);
+		break;
+	} /* switch (err_sctype) */
+}
+
+/**
+ * nvmf_connect_admin_queue() - NVMe Fabrics Admin Queue "Connect"
+ *				API function.
+ * @ctrl:	Host nvme controller instance used to request
+ *              a new NVMe controller allocation on the target
+ *              system and  establish an NVMe Admin connection to
+ *              that controller.
+ *
+ * This function enables an NVMe host device to request a new allocation of
+ * an NVMe controller resource on a target system as well establish a
+ * fabrics-protocol connection of the NVMe Admin queue between the
+ * host system device and the allocated NVMe controller on the
+ * target system via a NVMe Fabrics "Connect" command.
+ *
+ * Return:
+ *	0: success
+ *	> 0: NVMe error status code
+ *	< 0: Linux errno error code
+ *
+ */
+int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
+{
+	struct nvme_command cmd;
+	struct nvme_completion cqe;
+	struct nvmf_connect_data *data;
+	int ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.connect.opcode = nvme_fabrics_command;
+	cmd.connect.fctype = nvme_fabrics_type_connect;
+	cmd.connect.qid = 0;
+	cmd.connect.sqsize = cpu_to_le16(ctrl->sqsize);
+	/*
+	 * Set keep-alive timeout in seconds granularity (ms * 1000)
+	 * and add a grace period for controller kato enforcement
+	 */
+	cmd.connect.kato = ctrl->opts->discovery_nqn ? 0 :
+		cpu_to_le32((ctrl->kato + NVME_KATO_GRACE) * 1000);
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_le));
+	data->cntlid = cpu_to_le16(0xffff);
+	strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
+	strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);
+
+	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &cqe,
+			data, sizeof(*data), 0, NVME_QID_ANY, 1,
+			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+	if (ret) {
+		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(cqe.result),
+				       &cmd, data);
+		goto out_free_data;
+	}
+
+	ctrl->cntlid = le16_to_cpu(cqe.result16);
+
+out_free_data:
+	kfree(data);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvmf_connect_admin_queue);
+
+/**
+ * nvmf_connect_io_queue() - NVMe Fabrics I/O Queue "Connect"
+ *			     API function.
+ * @ctrl:	Host nvme controller instance used to establish an
+ *		NVMe I/O queue connection to the already allocated NVMe
+ *		controller on the target system.
+ * @qid:	NVMe I/O queue number for the new I/O connection between
+ *		host and target (note qid == 0 is illegal as this is
+ *		the Admin queue, per NVMe standard).
+ *
+ * This function issues a fabrics-protocol connection
+ * of a NVMe I/O queue (via NVMe Fabrics "Connect" command)
+ * between the host system device and the allocated NVMe controller
+ * on the target system.
+ *
+ * Return:
+ *	0: success
+ *	> 0: NVMe error status code
+ *	< 0: Linux errno error code
+ */
+int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
+{
+	struct nvme_command cmd;
+	struct nvmf_connect_data *data;
+	struct nvme_completion cqe;
+	int ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.connect.opcode = nvme_fabrics_command;
+	cmd.connect.fctype = nvme_fabrics_type_connect;
+	cmd.connect.qid = cpu_to_le16(qid);
+	cmd.connect.sqsize = cpu_to_le16(ctrl->sqsize);
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_le));
+	data->cntlid = cpu_to_le16(ctrl->cntlid);
+	strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
+	strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);
+
+	ret = __nvme_submit_sync_cmd(ctrl->connect_q, &cmd, &cqe,
+			data, sizeof(*data), 0, qid, 1,
+			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+	if (ret) {
+		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(cqe.result),
+				       &cmd, data);
+	}
+	kfree(data);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
+
+/**
+ * nvmf_register_transport() - NVMe Fabrics Library registration function.
+ * @ops:	Transport ops instance to be registered to the
+ *		common fabrics library.
+ *
+ * API function that registers the type of specific transport fabric
+ * being implemented to the common NVMe fabrics library. Part of
+ * the overall init sequence of starting up a fabrics driver.
+ */
+void nvmf_register_transport(struct nvmf_transport_ops *ops)
+{
+	mutex_lock(&nvmf_transports_mutex);
+	list_add_tail(&ops->entry, &nvmf_transports);
+	mutex_unlock(&nvmf_transports_mutex);
+}
+EXPORT_SYMBOL_GPL(nvmf_register_transport);
+
+/**
+ * nvmf_unregister_transport() - NVMe Fabrics Library unregistration function.
+ * @ops:	Transport ops instance to be unregistered from the
+ *		common fabrics library.
+ *
+ * Fabrics API function that unregisters the type of specific transport
+ * fabric being implemented from the common NVMe fabrics library.
+ * Part of the overall exit sequence of unloading the implemented driver.
+ */
+void nvmf_unregister_transport(struct nvmf_transport_ops *ops)
+{
+	mutex_lock(&nvmf_transports_mutex);
+	list_del(&ops->entry);
+	mutex_unlock(&nvmf_transports_mutex);
+}
+EXPORT_SYMBOL_GPL(nvmf_unregister_transport);
+
+static struct nvmf_transport_ops *nvmf_lookup_transport(
+		struct nvmf_ctrl_options *opts)
+{
+	struct nvmf_transport_ops *ops;
+
+	lockdep_assert_held(&nvmf_transports_mutex);
+
+	list_for_each_entry(ops, &nvmf_transports, entry) {
+		if (strcmp(ops->name, opts->transport) == 0)
+			return ops;
+	}
+
+	return NULL;
+}
+
+static const match_table_t opt_tokens = {
+	{ NVMF_OPT_TRANSPORT,		"transport=%s"		},
+	{ NVMF_OPT_TRADDR,		"traddr=%s"		},
+	{ NVMF_OPT_TRSVCID,		"trsvcid=%s"		},
+	{ NVMF_OPT_NQN,			"nqn=%s"		},
+	{ NVMF_OPT_QUEUE_SIZE,		"queue_size=%d"		},
+	{ NVMF_OPT_NR_IO_QUEUES,	"nr_io_queues=%d"	},
+	{ NVMF_OPT_RECONNECT_DELAY,	"reconnect_delay=%d"	},
+	{ NVMF_OPT_KATO,		"keep_alive_tmo=%d"	},
+	{ NVMF_OPT_HOSTNQN,		"hostnqn=%s"		},
+	{ NVMF_OPT_ERR,			NULL			}
+};
+
+static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
+		const char *buf)
+{
+	substring_t args[MAX_OPT_ARGS];
+	char *options, *o, *p;
+	int token, ret = 0;
+	size_t nqnlen  = 0;
+
+	/* Set defaults */
+	opts->queue_size = NVMF_DEF_QUEUE_SIZE;
+	opts->nr_io_queues = num_online_cpus();
+	opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY;
+
+	options = o = kstrdup(buf, GFP_KERNEL);
+	if (!options)
+		return -ENOMEM;
+
+	while ((p = strsep(&o, ",\n")) != NULL) {
+		if (!*p)
+			continue;
+
+		token = match_token(p, opt_tokens, args);
+		opts->mask |= token;
+		switch (token) {
+		case NVMF_OPT_TRANSPORT:
+			p = match_strdup(args);
+			if (!p) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			opts->transport = p;
+			break;
+		case NVMF_OPT_NQN:
+			p = match_strdup(args);
+			if (!p) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			opts->subsysnqn = p;
+			nqnlen = strlen(opts->subsysnqn);
+			if (nqnlen >= NVMF_NQN_SIZE) {
+				pr_err("%s needs to be < %d bytes\n",
+				opts->subsysnqn, NVMF_NQN_SIZE);
+				ret = -EINVAL;
+				goto out;
+			}
+			opts->discovery_nqn =
+				!(strcmp(opts->subsysnqn,
+					 NVME_DISC_SUBSYS_NAME));
+			if (opts->discovery_nqn)
+				opts->nr_io_queues = 0;
+			break;
+		case NVMF_OPT_TRADDR:
+			p = match_strdup(args);
+			if (!p) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			opts->traddr = p;
+			break;
+		case NVMF_OPT_TRSVCID:
+			p = match_strdup(args);
+			if (!p) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			opts->trsvcid = p;
+			break;
+		case NVMF_OPT_QUEUE_SIZE:
+			if (match_int(args, &token)) {
+				ret = -EINVAL;
+				goto out;
+			}
+			if (token < NVMF_MIN_QUEUE_SIZE ||
+			    token > NVMF_MAX_QUEUE_SIZE) {
+				pr_err("Invalid queue_size %d\n", token);
+				ret = -EINVAL;
+				goto out;
+			}
+			opts->queue_size = token;
+			break;
+		case NVMF_OPT_NR_IO_QUEUES:
+			if (match_int(args, &token)) {
+				ret = -EINVAL;
+				goto out;
+			}
+			if (token <= 0) {
+				pr_err("Invalid number of IOQs %d\n", token);
+				ret = -EINVAL;
+				goto out;
+			}
+			opts->nr_io_queues = min_t(unsigned int,
+					num_online_cpus(), token);
+			break;
+		case NVMF_OPT_KATO:
+			if (match_int(args, &token)) {
+				ret = -EINVAL;
+				goto out;
+			}
+
+			if (opts->discovery_nqn) {
+				pr_err("Discovery controllers cannot accept keep_alive_tmo != 0\n");
+				ret = -EINVAL;
+				goto out;
+			}
+
+			if (token < 0) {
+				pr_err("Invalid keep_alive_tmo %d\n", token);
+				ret = -EINVAL;
+				goto out;
+			} else if (token == 0) {
+				/* Allowed for debug */
+				pr_warn("keep_alive_tmo 0 won't execute keep alives!!!\n");
+			}
+			opts->kato = token;
+			break;
+		case NVMF_OPT_HOSTNQN:
+			if (opts->host) {
+				pr_err("hostnqn already user-assigned: %s\n",
+				       opts->host->nqn);
+				ret = -EADDRINUSE;
+				goto out;
+			}
+			p = match_strdup(args);
+			if (!p) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			nqnlen = strlen(p);
+			if (nqnlen >= NVMF_NQN_SIZE) {
+				pr_err("%s needs to be < %d bytes\n",
+					p, NVMF_NQN_SIZE);
+				ret = -EINVAL;
+				goto out;
+			}
+			opts->host = nvmf_host_add(p);
+			if (!opts->host) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			break;
+		case NVMF_OPT_RECONNECT_DELAY:
+			if (match_int(args, &token)) {
+				ret = -EINVAL;
+				goto out;
+			}
+			if (token <= 0) {
+				pr_err("Invalid reconnect_delay %d\n", token);
+				ret = -EINVAL;
+				goto out;
+			}
+			opts->reconnect_delay = token;
+			break;
+		default:
+			pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n",
+				p);
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	if (!opts->host) {
+		kref_get(&nvmf_default_host->ref);
+		opts->host = nvmf_default_host;
+	}
+
+out:
+	if (!opts->discovery_nqn && !opts->kato)
+		opts->kato = NVME_DEFAULT_KATO;
+	kfree(options);
+	return ret;
+}
+
+static int nvmf_check_required_opts(struct nvmf_ctrl_options *opts,
+		unsigned int required_opts)
+{
+	if ((opts->mask & required_opts) != required_opts) {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(opt_tokens); i++) {
+			if ((opt_tokens[i].token & required_opts) &&
+			    !(opt_tokens[i].token & opts->mask)) {
+				pr_warn("missing parameter '%s'\n",
+					opt_tokens[i].pattern);
+			}
+		}
+
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int nvmf_check_allowed_opts(struct nvmf_ctrl_options *opts,
+		unsigned int allowed_opts)
+{
+	if (opts->mask & ~allowed_opts) {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(opt_tokens); i++) {
+			if (opt_tokens[i].token & ~allowed_opts) {
+				pr_warn("invalid parameter '%s'\n",
+					opt_tokens[i].pattern);
+			}
+		}
+
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+void nvmf_free_options(struct nvmf_ctrl_options *opts)
+{
+	nvmf_host_put(opts->host);
+	kfree(opts->transport);
+	kfree(opts->traddr);
+	kfree(opts->trsvcid);
+	kfree(opts->subsysnqn);
+	kfree(opts);
+}
+EXPORT_SYMBOL_GPL(nvmf_free_options);
+
+#define NVMF_REQUIRED_OPTS	(NVMF_OPT_TRANSPORT | NVMF_OPT_NQN)
+#define NVMF_ALLOWED_OPTS	(NVMF_OPT_QUEUE_SIZE | NVMF_OPT_NR_IO_QUEUES | \
+				 NVMF_OPT_KATO | NVMF_OPT_HOSTNQN)
+
+static struct nvme_ctrl *
+nvmf_create_ctrl(struct device *dev, const char *buf, size_t count)
+{
+	struct nvmf_ctrl_options *opts;
+	struct nvmf_transport_ops *ops;
+	struct nvme_ctrl *ctrl;
+	int ret;
+
+	opts = kzalloc(sizeof(*opts), GFP_KERNEL);
+	if (!opts)
+		return ERR_PTR(-ENOMEM);
+
+	ret = nvmf_parse_options(opts, buf);
+	if (ret)
+		goto out_free_opts;
+
+	/*
+	 * Check the generic options first as we need a valid transport for
+	 * the lookup below.  Then clear the generic flags so that transport
+	 * drivers don't have to care about them.
+	 */
+	ret = nvmf_check_required_opts(opts, NVMF_REQUIRED_OPTS);
+	if (ret)
+		goto out_free_opts;
+	opts->mask &= ~NVMF_REQUIRED_OPTS;
+
+	mutex_lock(&nvmf_transports_mutex);
+	ops = nvmf_lookup_transport(opts);
+	if (!ops) {
+		pr_info("no handler found for transport %s.\n",
+			opts->transport);
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	ret = nvmf_check_required_opts(opts, ops->required_opts);
+	if (ret)
+		goto out_unlock;
+	ret = nvmf_check_allowed_opts(opts, NVMF_ALLOWED_OPTS |
+				ops->allowed_opts | ops->required_opts);
+	if (ret)
+		goto out_unlock;
+
+	ctrl = ops->create_ctrl(dev, opts);
+	if (IS_ERR(ctrl)) {
+		ret = PTR_ERR(ctrl);
+		goto out_unlock;
+	}
+
+	mutex_unlock(&nvmf_transports_mutex);
+	return ctrl;
+
+out_unlock:
+	mutex_unlock(&nvmf_transports_mutex);
+out_free_opts:
+	nvmf_host_put(opts->host);
+	kfree(opts);
+	return ERR_PTR(ret);
+}
+
+static struct class *nvmf_class;
+static struct device *nvmf_device;
+static DEFINE_MUTEX(nvmf_dev_mutex);
+
+static ssize_t nvmf_dev_write(struct file *file, const char __user *ubuf,
+		size_t count, loff_t *pos)
+{
+	struct seq_file *seq_file = file->private_data;
+	struct nvme_ctrl *ctrl;
+	const char *buf;
+	int ret = 0;
+
+	if (count > PAGE_SIZE)
+		return -ENOMEM;
+
+	buf = memdup_user_nul(ubuf, count);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
+	mutex_lock(&nvmf_dev_mutex);
+	if (seq_file->private) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	ctrl = nvmf_create_ctrl(nvmf_device, buf, count);
+	if (IS_ERR(ctrl)) {
+		ret = PTR_ERR(ctrl);
+		goto out_unlock;
+	}
+
+	seq_file->private = ctrl;
+
+out_unlock:
+	mutex_unlock(&nvmf_dev_mutex);
+	kfree(buf);
+	return ret ? ret : count;
+}
+
+static int nvmf_dev_show(struct seq_file *seq_file, void *private)
+{
+	struct nvme_ctrl *ctrl;
+	int ret = 0;
+
+	mutex_lock(&nvmf_dev_mutex);
+	ctrl = seq_file->private;
+	if (!ctrl) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	seq_printf(seq_file, "instance=%d,cntlid=%d\n",
+			ctrl->instance, ctrl->cntlid);
+
+out_unlock:
+	mutex_unlock(&nvmf_dev_mutex);
+	return ret;
+}
+
+static int nvmf_dev_open(struct inode *inode, struct file *file)
+{
+	/*
+	 * The miscdevice code initializes file->private_data, but doesn't
+	 * make use of it later.
+	 */
+	file->private_data = NULL;
+	return single_open(file, nvmf_dev_show, NULL);
+}
+
+static int nvmf_dev_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq_file = file->private_data;
+	struct nvme_ctrl *ctrl = seq_file->private;
+
+	if (ctrl)
+		nvme_put_ctrl(ctrl);
+	return single_release(inode, file);
+}
+
+static const struct file_operations nvmf_dev_fops = {
+	.owner		= THIS_MODULE,
+	.write		= nvmf_dev_write,
+	.read		= seq_read,
+	.open		= nvmf_dev_open,
+	.release	= nvmf_dev_release,
+};
+
+static struct miscdevice nvmf_misc = {
+	.minor		= MISC_DYNAMIC_MINOR,
+	.name           = "nvme-fabrics",
+	.fops		= &nvmf_dev_fops,
+};
+
+static int __init nvmf_init(void)
+{
+	int ret;
+
+	nvmf_default_host = nvmf_host_default();
+	if (!nvmf_default_host)
+		return -ENOMEM;
+
+	nvmf_class = class_create(THIS_MODULE, "nvme-fabrics");
+	if (IS_ERR(nvmf_class)) {
+		pr_err("couldn't register class nvme-fabrics\n");
+		ret = PTR_ERR(nvmf_class);
+		goto out_free_host;
+	}
+
+	nvmf_device =
+		device_create(nvmf_class, NULL, MKDEV(0, 0), NULL, "ctl");
+	if (IS_ERR(nvmf_device)) {
+		pr_err("couldn't create nvme-fabris device!\n");
+		ret = PTR_ERR(nvmf_device);
+		goto out_destroy_class;
+	}
+
+	ret = misc_register(&nvmf_misc);
+	if (ret) {
+		pr_err("couldn't register misc device: %d\n", ret);
+		goto out_destroy_device;
+	}
+
+	return 0;
+
+out_destroy_device:
+	device_destroy(nvmf_class, MKDEV(0, 0));
+out_destroy_class:
+	class_destroy(nvmf_class);
+out_free_host:
+	nvmf_host_put(nvmf_default_host);
+	return ret;
+}
+
+static void __exit nvmf_exit(void)
+{
+	misc_deregister(&nvmf_misc);
+	device_destroy(nvmf_class, MKDEV(0, 0));
+	class_destroy(nvmf_class);
+	nvmf_host_put(nvmf_default_host);
+
+	BUILD_BUG_ON(sizeof(struct nvmf_connect_command) != 64);
+	BUILD_BUG_ON(sizeof(struct nvmf_property_get_command) != 64);
+	BUILD_BUG_ON(sizeof(struct nvmf_property_set_command) != 64);
+	BUILD_BUG_ON(sizeof(struct nvmf_connect_data) != 1024);
+}
+
+MODULE_LICENSE("GPL v2");
+
+module_init(nvmf_init);
+module_exit(nvmf_exit);
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
new file mode 100644
index 000000000000..89df52c8be97
--- /dev/null
+++ b/drivers/nvme/host/fabrics.h
@@ -0,0 +1,132 @@
+/*
+ * NVMe over Fabrics common host code.
+ * Copyright (c) 2015-2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#ifndef _NVME_FABRICS_H
+#define _NVME_FABRICS_H 1
+
+#include <linux/in.h>
+#include <linux/inet.h>
+
+#define NVMF_MIN_QUEUE_SIZE	16
+#define NVMF_MAX_QUEUE_SIZE	1024
+#define NVMF_DEF_QUEUE_SIZE	128
+#define NVMF_DEF_RECONNECT_DELAY	10
+
+/*
+ * Define a host as seen by the target.  We allocate one at boot, but also
+ * allow the override it when creating controllers.  This is both to provide
+ * persistence of the Host NQN over multiple boots, and to allow using
+ * multiple ones, for example in a container scenario.  Because we must not
+ * use different Host NQNs with the same Host ID we generate a Host ID and
+ * use this structure to keep track of the relation between the two.
+ */
+struct nvmf_host {
+	struct kref		ref;
+	struct list_head	list;
+	char			nqn[NVMF_NQN_SIZE];
+	uuid_le			id;
+};
+
+/**
+ * enum nvmf_parsing_opts - used to define the sysfs parsing options used.
+ */
+enum {
+	NVMF_OPT_ERR		= 0,
+	NVMF_OPT_TRANSPORT	= 1 << 0,
+	NVMF_OPT_NQN		= 1 << 1,
+	NVMF_OPT_TRADDR		= 1 << 2,
+	NVMF_OPT_TRSVCID	= 1 << 3,
+	NVMF_OPT_QUEUE_SIZE	= 1 << 4,
+	NVMF_OPT_NR_IO_QUEUES	= 1 << 5,
+	NVMF_OPT_TL_RETRY_COUNT	= 1 << 6,
+	NVMF_OPT_KATO		= 1 << 7,
+	NVMF_OPT_HOSTNQN	= 1 << 8,
+	NVMF_OPT_RECONNECT_DELAY = 1 << 9,
+};
+
+/**
+ * struct nvmf_ctrl_options - Used to hold the options specified
+ *			      with the parsing opts enum.
+ * @mask:	Used by the fabrics library to parse through sysfs options
+ *		on adding a NVMe controller.
+ * @transport:	Holds the fabric transport "technology name" (for a lack of
+ *		better description) that will be used by an NVMe controller
+ *		being added.
+ * @subsysnqn:	Hold the fully qualified NQN subystem name (format defined
+ *		in the NVMe specification, "NVMe Qualified Names").
+ * @traddr:	network address that will be used by the host to communicate
+ *		to the added NVMe controller.
+ * @trsvcid:	network port used for host-controller communication.
+ * @queue_size: Number of IO queue elements.
+ * @nr_io_queues: Number of controller IO queues that will be established.
+ * @reconnect_delay: Time between two consecutive reconnect attempts.
+ * @discovery_nqn: indicates if the subsysnqn is the well-known discovery NQN.
+ * @kato:	Keep-alive timeout.
+ * @host:	Virtual NVMe host, contains the NQN and Host ID.
+ */
+struct nvmf_ctrl_options {
+	unsigned		mask;
+	char			*transport;
+	char			*subsysnqn;
+	char			*traddr;
+	char			*trsvcid;
+	size_t			queue_size;
+	unsigned int		nr_io_queues;
+	unsigned int		reconnect_delay;
+	bool			discovery_nqn;
+	unsigned int		kato;
+	struct nvmf_host	*host;
+};
+
+/*
+ * struct nvmf_transport_ops - used to register a specific
+ *			       fabric implementation of NVMe fabrics.
+ * @entry:		Used by the fabrics library to add the new
+ *			registration entry to its linked-list internal tree.
+ * @name:		Name of the NVMe fabric driver implementation.
+ * @required_opts:	sysfs command-line options that must be specified
+ *			when adding a new NVMe controller.
+ * @allowed_opts:	sysfs command-line options that can be specified
+ *			when adding a new NVMe controller.
+ * @create_ctrl():	function pointer that points to a non-NVMe
+ *			implementation-specific fabric technology
+ *			that would go into starting up that fabric
+ *			for the purpose of conneciton to an NVMe controller
+ *			using that fabric technology.
+ *
+ * Notes:
+ *	1. At minimum, 'required_opts' and 'allowed_opts' should
+ *	   be set to the same enum parsing options defined earlier.
+ *	2. create_ctrl() must be defined (even if it does nothing)
+ */
+struct nvmf_transport_ops {
+	struct list_head	entry;
+	const char		*name;
+	int			required_opts;
+	int			allowed_opts;
+	struct nvme_ctrl	*(*create_ctrl)(struct device *dev,
+					struct nvmf_ctrl_options *opts);
+};
+
+int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val);
+int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val);
+int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val);
+int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl);
+int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid);
+void nvmf_register_transport(struct nvmf_transport_ops *ops);
+void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
+void nvmf_free_options(struct nvmf_ctrl_options *opts);
+const char *nvmf_get_subsysnqn(struct nvme_ctrl *ctrl);
+int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
+
+#endif /* _NVME_FABRICS_H */
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index a0af0558354c..63f483daf930 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -156,7 +156,7 @@ struct nvme_nvm_completion {
 
 #define NVME_NVM_LP_MLC_PAIRS 886
 struct nvme_nvm_lp_mlc {
-	__u16			num_pairs;
+	__le16			num_pairs;
 	__u8			pairs[NVME_NVM_LP_MLC_PAIRS];
 };
 
@@ -500,7 +500,7 @@ static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 	struct bio *bio = rqd->bio;
 	struct nvme_nvm_command *cmd;
 
-	rq = blk_mq_alloc_request(q, bio_rw(bio), 0);
+	rq = blk_mq_alloc_request(q, bio_data_dir(bio), 0);
 	if (IS_ERR(rq))
 		return -ENOMEM;
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 4d196d2d57da..ab18b78102bf 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -38,6 +38,11 @@ extern unsigned char admin_timeout;
 extern unsigned char shutdown_timeout;
 #define SHUTDOWN_TIMEOUT	(shutdown_timeout * HZ)
 
+#define NVME_DEFAULT_KATO	5
+#define NVME_KATO_GRACE		10
+
+extern unsigned int nvme_max_retries;
+
 enum {
 	NVME_NS_LBA		= 0,
 	NVME_NS_LIGHTNVM	= 1,
@@ -65,12 +70,26 @@ enum nvme_quirks {
 	 * logical blocks.
 	 */
 	NVME_QUIRK_DISCARD_ZEROES		= (1 << 2),
+
+	/*
+	 * The controller needs a delay before starts checking the device
+	 * readiness, which is done by reading the NVME_CSTS_RDY bit.
+	 */
+	NVME_QUIRK_DELAY_BEFORE_CHK_RDY		= (1 << 3),
 };
 
+/* The below value is the specific amount of delay needed before checking
+ * readiness in case of the PCI_DEVICE(0x1c58, 0x0003), which needs the
+ * NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was
+ * found empirically.
+ */
+#define NVME_QUIRK_DELAY_AMOUNT		2000
+
 enum nvme_ctrl_state {
 	NVME_CTRL_NEW,
 	NVME_CTRL_LIVE,
 	NVME_CTRL_RESETTING,
+	NVME_CTRL_RECONNECTING,
 	NVME_CTRL_DELETING,
 	NVME_CTRL_DEAD,
 };
@@ -80,6 +99,7 @@ struct nvme_ctrl {
 	spinlock_t lock;
 	const struct nvme_ctrl_ops *ops;
 	struct request_queue *admin_q;
+	struct request_queue *connect_q;
 	struct device *dev;
 	struct kref kref;
 	int instance;
@@ -107,10 +127,22 @@ struct nvme_ctrl {
 	u8 event_limit;
 	u8 vwc;
 	u32 vs;
+	u32 sgls;
+	u16 kas;
+	unsigned int kato;
 	bool subsystem;
 	unsigned long quirks;
 	struct work_struct scan_work;
 	struct work_struct async_event_work;
+	struct delayed_work ka_work;
+
+	/* Fabrics only */
+	u16 sqsize;
+	u32 ioccsz;
+	u32 iorcsz;
+	u16 icdoff;
+	u16 maxcmd;
+	struct nvmf_ctrl_options *opts;
 };
 
 /*
@@ -144,7 +176,9 @@ struct nvme_ns {
 };
 
 struct nvme_ctrl_ops {
+	const char *name;
 	struct module *module;
+	bool is_fabrics;
 	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);
@@ -152,6 +186,9 @@ struct nvme_ctrl_ops {
 	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);
+	int (*delete_ctrl)(struct nvme_ctrl *ctrl);
+	const char *(*get_subsysnqn)(struct nvme_ctrl *ctrl);
+	int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
 };
 
 static inline bool nvme_ctrl_ready(struct nvme_ctrl *ctrl)
@@ -204,9 +241,11 @@ static inline int nvme_error_status(u16 status)
 static inline bool nvme_req_needs_retry(struct request *req, u16 status)
 {
 	return !(status & NVME_SC_DNR || blk_noretry_request(req)) &&
-		(jiffies - req->start_time) < req->timeout;
+		(jiffies - req->start_time) < req->timeout &&
+		req->retries < nvme_max_retries;
 }
 
+void nvme_cancel_request(struct request *req, void *data, bool reserved);
 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);
@@ -230,8 +269,9 @@ void nvme_stop_queues(struct nvme_ctrl *ctrl);
 void nvme_start_queues(struct nvme_ctrl *ctrl);
 void nvme_kill_queues(struct nvme_ctrl *ctrl);
 
+#define NVME_QID_ANY -1
 struct request *nvme_alloc_request(struct request_queue *q,
-		struct nvme_command *cmd, unsigned int flags);
+		struct nvme_command *cmd, unsigned int flags, int qid);
 void nvme_requeue_req(struct request *req);
 int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmd);
@@ -239,7 +279,7 @@ 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,
 		struct nvme_completion *cqe, void *buffer, unsigned bufflen,
-		unsigned timeout);
+		unsigned timeout, int qid, int at_head, int flags);
 int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void __user *ubuffer, unsigned bufflen, u32 *result,
 		unsigned timeout);
@@ -256,6 +296,8 @@ 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);
 int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count);
+void nvme_start_keep_alive(struct nvme_ctrl *ctrl);
+void nvme_stop_keep_alive(struct nvme_ctrl *ctrl);
 
 struct sg_io_hdr;
 
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index befac5b19490..4cb9b156cab7 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -310,6 +310,11 @@ static int nvme_init_iod(struct request *rq, unsigned size,
 	iod->npages = -1;
 	iod->nents = 0;
 	iod->length = size;
+
+	if (!(rq->cmd_flags & REQ_DONTPREP)) {
+		rq->retries = 0;
+		rq->cmd_flags |= REQ_DONTPREP;
+	}
 	return 0;
 }
 
@@ -520,8 +525,8 @@ static int nvme_map_data(struct nvme_dev *dev, struct request *req,
 			goto out_unmap;
 	}
 
-	cmnd->rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
-	cmnd->rw.prp2 = cpu_to_le64(iod->first_dma);
+	cmnd->rw.dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+	cmnd->rw.dptr.prp2 = cpu_to_le64(iod->first_dma);
 	if (blk_integrity_rq(req))
 		cmnd->rw.metadata = cpu_to_le64(sg_dma_address(&iod->meta_sg));
 	return BLK_MQ_RQ_QUEUE_OK;
@@ -623,6 +628,7 @@ static void nvme_complete_rq(struct request *req)
 
 	if (unlikely(req->errors)) {
 		if (nvme_req_needs_retry(req, req->errors)) {
+			req->retries++;
 			nvme_requeue_req(req);
 			return;
 		}
@@ -901,7 +907,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		 req->tag, nvmeq->qid);
 
 	abort_req = nvme_alloc_request(dev->ctrl.admin_q, &cmd,
-			BLK_MQ_REQ_NOWAIT);
+			BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
 	if (IS_ERR(abort_req)) {
 		atomic_inc(&dev->ctrl.abort_limit);
 		return BLK_EH_RESET_TIMER;
@@ -919,22 +925,6 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	return BLK_EH_RESET_TIMER;
 }
 
-static void nvme_cancel_io(struct request *req, void *data, bool reserved)
-{
-	int status;
-
-	if (!blk_mq_request_started(req))
-		return;
-
-	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))
-		status |= NVME_SC_DNR;
-	blk_mq_complete_request(req, status);
-}
-
 static void nvme_free_queue(struct nvme_queue *nvmeq)
 {
 	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
@@ -1399,16 +1389,8 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	if (result < 0)
 		return result;
 
-	/*
-	 * Degraded controllers might return an error when setting the queue
-	 * count.  We still want to be able to bring them online and offer
-	 * access to the admin queue, as that might be only way to fix them up.
-	 */
-	if (result > 0) {
-		dev_err(dev->ctrl.device,
-			"Could not set queue count (%d)\n", result);
+	if (nr_io_queues == 0)
 		return 0;
-	}
 
 	if (dev->cmb && NVME_CMB_SQS(dev->cmbsz)) {
 		result = nvme_cmb_qdepth(dev, nr_io_queues,
@@ -1536,7 +1518,7 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
 	cmd.delete_queue.opcode = opcode;
 	cmd.delete_queue.qid = cpu_to_le16(nvmeq->qid);
 
-	req = nvme_alloc_request(q, &cmd, BLK_MQ_REQ_NOWAIT);
+	req = nvme_alloc_request(q, &cmd, BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -1727,8 +1709,8 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	}
 	nvme_pci_disable(dev);
 
-	blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_io, dev);
-	blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_io, dev);
+	blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl);
+	blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl);
 	mutex_unlock(&dev->shutdown_lock);
 }
 
@@ -1902,6 +1884,7 @@ static int nvme_pci_reset_ctrl(struct nvme_ctrl *ctrl)
 }
 
 static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
+	.name			= "pcie",
 	.module			= THIS_MODULE,
 	.reg_read32		= nvme_pci_reg_read32,
 	.reg_write32		= nvme_pci_reg_write32,
@@ -1940,7 +1923,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	node = dev_to_node(&pdev->dev);
 	if (node == NUMA_NO_NODE)
-		set_dev_node(&pdev->dev, 0);
+		set_dev_node(&pdev->dev, first_memory_node);
 
 	dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
 	if (!dev)
@@ -2037,6 +2020,24 @@ static void nvme_remove(struct pci_dev *pdev)
 	nvme_put_ctrl(&dev->ctrl);
 }
 
+static int nvme_pci_sriov_configure(struct pci_dev *pdev, int numvfs)
+{
+	int ret = 0;
+
+	if (numvfs == 0) {
+		if (pci_vfs_assigned(pdev)) {
+			dev_warn(&pdev->dev,
+				"Cannot disable SR-IOV VFs while assigned\n");
+			return -EPERM;
+		}
+		pci_disable_sriov(pdev);
+		return 0;
+	}
+
+	ret = pci_enable_sriov(pdev, numvfs);
+	return ret ? ret : numvfs;
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int nvme_suspend(struct device *dev)
 {
@@ -2122,6 +2123,8 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_DISCARD_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
 		.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
+	{ PCI_DEVICE(0x1c58, 0x0003),	/* HGST adapter */
+		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
 	{ 0, }
@@ -2137,6 +2140,7 @@ static struct pci_driver nvme_driver = {
 	.driver		= {
 		.pm	= &nvme_dev_pm_ops,
 	},
+	.sriov_configure = nvme_pci_sriov_configure,
 	.err_handler	= &nvme_err_handler,
 };
 
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
new file mode 100644
index 000000000000..3e3ce2b0424e
--- /dev/null
+++ b/drivers/nvme/host/rdma.c
@@ -0,0 +1,2018 @@
+/*
+ * NVMe over Fabrics RDMA host code.
+ * Copyright (c) 2015-2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <linux/jiffies.h>
+#include <linux/atomic.h>
+#include <linux/blk-mq.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/scatterlist.h>
+#include <linux/nvme.h>
+#include <linux/t10-pi.h>
+#include <asm/unaligned.h>
+
+#include <rdma/ib_verbs.h>
+#include <rdma/rdma_cm.h>
+#include <rdma/ib_cm.h>
+#include <linux/nvme-rdma.h>
+
+#include "nvme.h"
+#include "fabrics.h"
+
+
+#define NVME_RDMA_CONNECT_TIMEOUT_MS	1000		/* 1 second */
+
+#define NVME_RDMA_MAX_SEGMENT_SIZE	0xffffff	/* 24-bit SGL field */
+
+#define NVME_RDMA_MAX_SEGMENTS		256
+
+#define NVME_RDMA_MAX_INLINE_SEGMENTS	1
+
+#define NVME_RDMA_MAX_PAGES_PER_MR	512
+
+#define NVME_RDMA_DEF_RECONNECT_DELAY	20
+
+/*
+ * We handle AEN commands ourselves and don't even let the
+ * block layer know about them.
+ */
+#define NVME_RDMA_NR_AEN_COMMANDS      1
+#define NVME_RDMA_AQ_BLKMQ_DEPTH       \
+	(NVMF_AQ_DEPTH - NVME_RDMA_NR_AEN_COMMANDS)
+
+struct nvme_rdma_device {
+	struct ib_device       *dev;
+	struct ib_pd	       *pd;
+	struct ib_mr	       *mr;
+	struct kref		ref;
+	struct list_head	entry;
+};
+
+struct nvme_rdma_qe {
+	struct ib_cqe		cqe;
+	void			*data;
+	u64			dma;
+};
+
+struct nvme_rdma_queue;
+struct nvme_rdma_request {
+	struct ib_mr		*mr;
+	struct nvme_rdma_qe	sqe;
+	struct ib_sge		sge[1 + NVME_RDMA_MAX_INLINE_SEGMENTS];
+	u32			num_sge;
+	int			nents;
+	bool			inline_data;
+	bool			need_inval;
+	struct ib_reg_wr	reg_wr;
+	struct ib_cqe		reg_cqe;
+	struct nvme_rdma_queue  *queue;
+	struct sg_table		sg_table;
+	struct scatterlist	first_sgl[];
+};
+
+enum nvme_rdma_queue_flags {
+	NVME_RDMA_Q_CONNECTED = (1 << 0),
+};
+
+struct nvme_rdma_queue {
+	struct nvme_rdma_qe	*rsp_ring;
+	u8			sig_count;
+	int			queue_size;
+	size_t			cmnd_capsule_len;
+	struct nvme_rdma_ctrl	*ctrl;
+	struct nvme_rdma_device	*device;
+	struct ib_cq		*ib_cq;
+	struct ib_qp		*qp;
+
+	unsigned long		flags;
+	struct rdma_cm_id	*cm_id;
+	int			cm_error;
+	struct completion	cm_done;
+};
+
+struct nvme_rdma_ctrl {
+	/* read and written in the hot path */
+	spinlock_t		lock;
+
+	/* read only in the hot path */
+	struct nvme_rdma_queue	*queues;
+	u32			queue_count;
+
+	/* other member variables */
+	struct blk_mq_tag_set	tag_set;
+	struct work_struct	delete_work;
+	struct work_struct	reset_work;
+	struct work_struct	err_work;
+
+	struct nvme_rdma_qe	async_event_sqe;
+
+	int			reconnect_delay;
+	struct delayed_work	reconnect_work;
+
+	struct list_head	list;
+
+	struct blk_mq_tag_set	admin_tag_set;
+	struct nvme_rdma_device	*device;
+
+	u64			cap;
+	u32			max_fr_pages;
+
+	union {
+		struct sockaddr addr;
+		struct sockaddr_in addr_in;
+	};
+
+	struct nvme_ctrl	ctrl;
+};
+
+static inline struct nvme_rdma_ctrl *to_rdma_ctrl(struct nvme_ctrl *ctrl)
+{
+	return container_of(ctrl, struct nvme_rdma_ctrl, ctrl);
+}
+
+static LIST_HEAD(device_list);
+static DEFINE_MUTEX(device_list_mutex);
+
+static LIST_HEAD(nvme_rdma_ctrl_list);
+static DEFINE_MUTEX(nvme_rdma_ctrl_mutex);
+
+static struct workqueue_struct *nvme_rdma_wq;
+
+/*
+ * Disabling this option makes small I/O goes faster, but is fundamentally
+ * unsafe.  With it turned off we will have to register a global rkey that
+ * allows read and write access to all physical memory.
+ */
+static bool register_always = true;
+module_param(register_always, bool, 0444);
+MODULE_PARM_DESC(register_always,
+	 "Use memory registration even for contiguous memory regions");
+
+static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
+		struct rdma_cm_event *event);
+static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc);
+static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl);
+
+/* XXX: really should move to a generic header sooner or later.. */
+static inline void put_unaligned_le24(u32 val, u8 *p)
+{
+	*p++ = val;
+	*p++ = val >> 8;
+	*p++ = val >> 16;
+}
+
+static inline int nvme_rdma_queue_idx(struct nvme_rdma_queue *queue)
+{
+	return queue - queue->ctrl->queues;
+}
+
+static inline size_t nvme_rdma_inline_data_size(struct nvme_rdma_queue *queue)
+{
+	return queue->cmnd_capsule_len - sizeof(struct nvme_command);
+}
+
+static void nvme_rdma_free_qe(struct ib_device *ibdev, struct nvme_rdma_qe *qe,
+		size_t capsule_size, enum dma_data_direction dir)
+{
+	ib_dma_unmap_single(ibdev, qe->dma, capsule_size, dir);
+	kfree(qe->data);
+}
+
+static int nvme_rdma_alloc_qe(struct ib_device *ibdev, struct nvme_rdma_qe *qe,
+		size_t capsule_size, enum dma_data_direction dir)
+{
+	qe->data = kzalloc(capsule_size, GFP_KERNEL);
+	if (!qe->data)
+		return -ENOMEM;
+
+	qe->dma = ib_dma_map_single(ibdev, qe->data, capsule_size, dir);
+	if (ib_dma_mapping_error(ibdev, qe->dma)) {
+		kfree(qe->data);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void nvme_rdma_free_ring(struct ib_device *ibdev,
+		struct nvme_rdma_qe *ring, size_t ib_queue_size,
+		size_t capsule_size, enum dma_data_direction dir)
+{
+	int i;
+
+	for (i = 0; i < ib_queue_size; i++)
+		nvme_rdma_free_qe(ibdev, &ring[i], capsule_size, dir);
+	kfree(ring);
+}
+
+static struct nvme_rdma_qe *nvme_rdma_alloc_ring(struct ib_device *ibdev,
+		size_t ib_queue_size, size_t capsule_size,
+		enum dma_data_direction dir)
+{
+	struct nvme_rdma_qe *ring;
+	int i;
+
+	ring = kcalloc(ib_queue_size, sizeof(struct nvme_rdma_qe), GFP_KERNEL);
+	if (!ring)
+		return NULL;
+
+	for (i = 0; i < ib_queue_size; i++) {
+		if (nvme_rdma_alloc_qe(ibdev, &ring[i], capsule_size, dir))
+			goto out_free_ring;
+	}
+
+	return ring;
+
+out_free_ring:
+	nvme_rdma_free_ring(ibdev, ring, i, capsule_size, dir);
+	return NULL;
+}
+
+static void nvme_rdma_qp_event(struct ib_event *event, void *context)
+{
+	pr_debug("QP event %d\n", event->event);
+}
+
+static int nvme_rdma_wait_for_cm(struct nvme_rdma_queue *queue)
+{
+	wait_for_completion_interruptible_timeout(&queue->cm_done,
+			msecs_to_jiffies(NVME_RDMA_CONNECT_TIMEOUT_MS) + 1);
+	return queue->cm_error;
+}
+
+static int nvme_rdma_create_qp(struct nvme_rdma_queue *queue, const int factor)
+{
+	struct nvme_rdma_device *dev = queue->device;
+	struct ib_qp_init_attr init_attr;
+	int ret;
+
+	memset(&init_attr, 0, sizeof(init_attr));
+	init_attr.event_handler = nvme_rdma_qp_event;
+	/* +1 for drain */
+	init_attr.cap.max_send_wr = factor * queue->queue_size + 1;
+	/* +1 for drain */
+	init_attr.cap.max_recv_wr = queue->queue_size + 1;
+	init_attr.cap.max_recv_sge = 1;
+	init_attr.cap.max_send_sge = 1 + NVME_RDMA_MAX_INLINE_SEGMENTS;
+	init_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
+	init_attr.qp_type = IB_QPT_RC;
+	init_attr.send_cq = queue->ib_cq;
+	init_attr.recv_cq = queue->ib_cq;
+
+	ret = rdma_create_qp(queue->cm_id, dev->pd, &init_attr);
+
+	queue->qp = queue->cm_id->qp;
+	return ret;
+}
+
+static int nvme_rdma_reinit_request(void *data, struct request *rq)
+{
+	struct nvme_rdma_ctrl *ctrl = data;
+	struct nvme_rdma_device *dev = ctrl->device;
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	int ret = 0;
+
+	if (!req->need_inval)
+		goto out;
+
+	ib_dereg_mr(req->mr);
+
+	req->mr = ib_alloc_mr(dev->pd, IB_MR_TYPE_MEM_REG,
+			ctrl->max_fr_pages);
+	if (IS_ERR(req->mr)) {
+		ret = PTR_ERR(req->mr);
+		req->mr = NULL;
+	}
+
+	req->need_inval = false;
+
+out:
+	return ret;
+}
+
+static void __nvme_rdma_exit_request(struct nvme_rdma_ctrl *ctrl,
+		struct request *rq, unsigned int queue_idx)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx];
+	struct nvme_rdma_device *dev = queue->device;
+
+	if (req->mr)
+		ib_dereg_mr(req->mr);
+
+	nvme_rdma_free_qe(dev->dev, &req->sqe, sizeof(struct nvme_command),
+			DMA_TO_DEVICE);
+}
+
+static void nvme_rdma_exit_request(void *data, struct request *rq,
+				unsigned int hctx_idx, unsigned int rq_idx)
+{
+	return __nvme_rdma_exit_request(data, rq, hctx_idx + 1);
+}
+
+static void nvme_rdma_exit_admin_request(void *data, struct request *rq,
+				unsigned int hctx_idx, unsigned int rq_idx)
+{
+	return __nvme_rdma_exit_request(data, rq, 0);
+}
+
+static int __nvme_rdma_init_request(struct nvme_rdma_ctrl *ctrl,
+		struct request *rq, unsigned int queue_idx)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx];
+	struct nvme_rdma_device *dev = queue->device;
+	struct ib_device *ibdev = dev->dev;
+	int ret;
+
+	BUG_ON(queue_idx >= ctrl->queue_count);
+
+	ret = nvme_rdma_alloc_qe(ibdev, &req->sqe, sizeof(struct nvme_command),
+			DMA_TO_DEVICE);
+	if (ret)
+		return ret;
+
+	req->mr = ib_alloc_mr(dev->pd, IB_MR_TYPE_MEM_REG,
+			ctrl->max_fr_pages);
+	if (IS_ERR(req->mr)) {
+		ret = PTR_ERR(req->mr);
+		goto out_free_qe;
+	}
+
+	req->queue = queue;
+
+	return 0;
+
+out_free_qe:
+	nvme_rdma_free_qe(dev->dev, &req->sqe, sizeof(struct nvme_command),
+			DMA_TO_DEVICE);
+	return -ENOMEM;
+}
+
+static int nvme_rdma_init_request(void *data, struct request *rq,
+				unsigned int hctx_idx, unsigned int rq_idx,
+				unsigned int numa_node)
+{
+	return __nvme_rdma_init_request(data, rq, hctx_idx + 1);
+}
+
+static int nvme_rdma_init_admin_request(void *data, struct request *rq,
+				unsigned int hctx_idx, unsigned int rq_idx,
+				unsigned int numa_node)
+{
+	return __nvme_rdma_init_request(data, rq, 0);
+}
+
+static int nvme_rdma_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+		unsigned int hctx_idx)
+{
+	struct nvme_rdma_ctrl *ctrl = data;
+	struct nvme_rdma_queue *queue = &ctrl->queues[hctx_idx + 1];
+
+	BUG_ON(hctx_idx >= ctrl->queue_count);
+
+	hctx->driver_data = queue;
+	return 0;
+}
+
+static int nvme_rdma_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+		unsigned int hctx_idx)
+{
+	struct nvme_rdma_ctrl *ctrl = data;
+	struct nvme_rdma_queue *queue = &ctrl->queues[0];
+
+	BUG_ON(hctx_idx != 0);
+
+	hctx->driver_data = queue;
+	return 0;
+}
+
+static void nvme_rdma_free_dev(struct kref *ref)
+{
+	struct nvme_rdma_device *ndev =
+		container_of(ref, struct nvme_rdma_device, ref);
+
+	mutex_lock(&device_list_mutex);
+	list_del(&ndev->entry);
+	mutex_unlock(&device_list_mutex);
+
+	if (!register_always)
+		ib_dereg_mr(ndev->mr);
+	ib_dealloc_pd(ndev->pd);
+
+	kfree(ndev);
+}
+
+static void nvme_rdma_dev_put(struct nvme_rdma_device *dev)
+{
+	kref_put(&dev->ref, nvme_rdma_free_dev);
+}
+
+static int nvme_rdma_dev_get(struct nvme_rdma_device *dev)
+{
+	return kref_get_unless_zero(&dev->ref);
+}
+
+static struct nvme_rdma_device *
+nvme_rdma_find_get_device(struct rdma_cm_id *cm_id)
+{
+	struct nvme_rdma_device *ndev;
+
+	mutex_lock(&device_list_mutex);
+	list_for_each_entry(ndev, &device_list, entry) {
+		if (ndev->dev->node_guid == cm_id->device->node_guid &&
+		    nvme_rdma_dev_get(ndev))
+			goto out_unlock;
+	}
+
+	ndev = kzalloc(sizeof(*ndev), GFP_KERNEL);
+	if (!ndev)
+		goto out_err;
+
+	ndev->dev = cm_id->device;
+	kref_init(&ndev->ref);
+
+	ndev->pd = ib_alloc_pd(ndev->dev);
+	if (IS_ERR(ndev->pd))
+		goto out_free_dev;
+
+	if (!register_always) {
+		ndev->mr = ib_get_dma_mr(ndev->pd,
+					    IB_ACCESS_LOCAL_WRITE |
+					    IB_ACCESS_REMOTE_READ |
+					    IB_ACCESS_REMOTE_WRITE);
+		if (IS_ERR(ndev->mr))
+			goto out_free_pd;
+	}
+
+	if (!(ndev->dev->attrs.device_cap_flags &
+	      IB_DEVICE_MEM_MGT_EXTENSIONS)) {
+		dev_err(&ndev->dev->dev,
+			"Memory registrations not supported.\n");
+		goto out_free_mr;
+	}
+
+	list_add(&ndev->entry, &device_list);
+out_unlock:
+	mutex_unlock(&device_list_mutex);
+	return ndev;
+
+out_free_mr:
+	if (!register_always)
+		ib_dereg_mr(ndev->mr);
+out_free_pd:
+	ib_dealloc_pd(ndev->pd);
+out_free_dev:
+	kfree(ndev);
+out_err:
+	mutex_unlock(&device_list_mutex);
+	return NULL;
+}
+
+static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
+{
+	struct nvme_rdma_device *dev = queue->device;
+	struct ib_device *ibdev = dev->dev;
+
+	rdma_destroy_qp(queue->cm_id);
+	ib_free_cq(queue->ib_cq);
+
+	nvme_rdma_free_ring(ibdev, queue->rsp_ring, queue->queue_size,
+			sizeof(struct nvme_completion), DMA_FROM_DEVICE);
+
+	nvme_rdma_dev_put(dev);
+}
+
+static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue,
+		struct nvme_rdma_device *dev)
+{
+	struct ib_device *ibdev = dev->dev;
+	const int send_wr_factor = 3;			/* MR, SEND, INV */
+	const int cq_factor = send_wr_factor + 1;	/* + RECV */
+	int comp_vector, idx = nvme_rdma_queue_idx(queue);
+
+	int ret;
+
+	queue->device = dev;
+
+	/*
+	 * The admin queue is barely used once the controller is live, so don't
+	 * bother to spread it out.
+	 */
+	if (idx == 0)
+		comp_vector = 0;
+	else
+		comp_vector = idx % ibdev->num_comp_vectors;
+
+
+	/* +1 for ib_stop_cq */
+	queue->ib_cq = ib_alloc_cq(dev->dev, queue,
+				cq_factor * queue->queue_size + 1, comp_vector,
+				IB_POLL_SOFTIRQ);
+	if (IS_ERR(queue->ib_cq)) {
+		ret = PTR_ERR(queue->ib_cq);
+		goto out;
+	}
+
+	ret = nvme_rdma_create_qp(queue, send_wr_factor);
+	if (ret)
+		goto out_destroy_ib_cq;
+
+	queue->rsp_ring = nvme_rdma_alloc_ring(ibdev, queue->queue_size,
+			sizeof(struct nvme_completion), DMA_FROM_DEVICE);
+	if (!queue->rsp_ring) {
+		ret = -ENOMEM;
+		goto out_destroy_qp;
+	}
+
+	return 0;
+
+out_destroy_qp:
+	ib_destroy_qp(queue->qp);
+out_destroy_ib_cq:
+	ib_free_cq(queue->ib_cq);
+out:
+	return ret;
+}
+
+static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl,
+		int idx, size_t queue_size)
+{
+	struct nvme_rdma_queue *queue;
+	int ret;
+
+	queue = &ctrl->queues[idx];
+	queue->ctrl = ctrl;
+	init_completion(&queue->cm_done);
+
+	if (idx > 0)
+		queue->cmnd_capsule_len = ctrl->ctrl.ioccsz * 16;
+	else
+		queue->cmnd_capsule_len = sizeof(struct nvme_command);
+
+	queue->queue_size = queue_size;
+
+	queue->cm_id = rdma_create_id(&init_net, nvme_rdma_cm_handler, queue,
+			RDMA_PS_TCP, IB_QPT_RC);
+	if (IS_ERR(queue->cm_id)) {
+		dev_info(ctrl->ctrl.device,
+			"failed to create CM ID: %ld\n", PTR_ERR(queue->cm_id));
+		return PTR_ERR(queue->cm_id);
+	}
+
+	queue->cm_error = -ETIMEDOUT;
+	ret = rdma_resolve_addr(queue->cm_id, NULL, &ctrl->addr,
+			NVME_RDMA_CONNECT_TIMEOUT_MS);
+	if (ret) {
+		dev_info(ctrl->ctrl.device,
+			"rdma_resolve_addr failed (%d).\n", ret);
+		goto out_destroy_cm_id;
+	}
+
+	ret = nvme_rdma_wait_for_cm(queue);
+	if (ret) {
+		dev_info(ctrl->ctrl.device,
+			"rdma_resolve_addr wait failed (%d).\n", ret);
+		goto out_destroy_cm_id;
+	}
+
+	set_bit(NVME_RDMA_Q_CONNECTED, &queue->flags);
+
+	return 0;
+
+out_destroy_cm_id:
+	rdma_destroy_id(queue->cm_id);
+	return ret;
+}
+
+static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue)
+{
+	rdma_disconnect(queue->cm_id);
+	ib_drain_qp(queue->qp);
+}
+
+static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue)
+{
+	nvme_rdma_destroy_queue_ib(queue);
+	rdma_destroy_id(queue->cm_id);
+}
+
+static void nvme_rdma_stop_and_free_queue(struct nvme_rdma_queue *queue)
+{
+	if (!test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags))
+		return;
+	nvme_rdma_stop_queue(queue);
+	nvme_rdma_free_queue(queue);
+}
+
+static void nvme_rdma_free_io_queues(struct nvme_rdma_ctrl *ctrl)
+{
+	int i;
+
+	for (i = 1; i < ctrl->queue_count; i++)
+		nvme_rdma_stop_and_free_queue(&ctrl->queues[i]);
+}
+
+static int nvme_rdma_connect_io_queues(struct nvme_rdma_ctrl *ctrl)
+{
+	int i, ret = 0;
+
+	for (i = 1; i < ctrl->queue_count; i++) {
+		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl)
+{
+	int i, ret;
+
+	for (i = 1; i < ctrl->queue_count; i++) {
+		ret = nvme_rdma_init_queue(ctrl, i, ctrl->ctrl.sqsize);
+		if (ret) {
+			dev_info(ctrl->ctrl.device,
+				"failed to initialize i/o queue: %d\n", ret);
+			goto out_free_queues;
+		}
+	}
+
+	return 0;
+
+out_free_queues:
+	for (; i >= 1; i--)
+		nvme_rdma_stop_and_free_queue(&ctrl->queues[i]);
+
+	return ret;
+}
+
+static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl)
+{
+	nvme_rdma_free_qe(ctrl->queues[0].device->dev, &ctrl->async_event_sqe,
+			sizeof(struct nvme_command), DMA_TO_DEVICE);
+	nvme_rdma_stop_and_free_queue(&ctrl->queues[0]);
+	blk_cleanup_queue(ctrl->ctrl.admin_q);
+	blk_mq_free_tag_set(&ctrl->admin_tag_set);
+	nvme_rdma_dev_put(ctrl->device);
+}
+
+static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
+{
+	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
+
+	if (list_empty(&ctrl->list))
+		goto free_ctrl;
+
+	mutex_lock(&nvme_rdma_ctrl_mutex);
+	list_del(&ctrl->list);
+	mutex_unlock(&nvme_rdma_ctrl_mutex);
+
+	if (ctrl->ctrl.tagset) {
+		blk_cleanup_queue(ctrl->ctrl.connect_q);
+		blk_mq_free_tag_set(&ctrl->tag_set);
+		nvme_rdma_dev_put(ctrl->device);
+	}
+	kfree(ctrl->queues);
+	nvmf_free_options(nctrl->opts);
+free_ctrl:
+	kfree(ctrl);
+}
+
+static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
+			struct nvme_rdma_ctrl, reconnect_work);
+	bool changed;
+	int ret;
+
+	if (ctrl->queue_count > 1) {
+		nvme_rdma_free_io_queues(ctrl);
+
+		ret = blk_mq_reinit_tagset(&ctrl->tag_set);
+		if (ret)
+			goto requeue;
+	}
+
+	nvme_rdma_stop_and_free_queue(&ctrl->queues[0]);
+
+	ret = blk_mq_reinit_tagset(&ctrl->admin_tag_set);
+	if (ret)
+		goto requeue;
+
+	ret = nvme_rdma_init_queue(ctrl, 0, NVMF_AQ_DEPTH);
+	if (ret)
+		goto requeue;
+
+	blk_mq_start_stopped_hw_queues(ctrl->ctrl.admin_q, true);
+
+	ret = nvmf_connect_admin_queue(&ctrl->ctrl);
+	if (ret)
+		goto stop_admin_q;
+
+	ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
+	if (ret)
+		goto stop_admin_q;
+
+	nvme_start_keep_alive(&ctrl->ctrl);
+
+	if (ctrl->queue_count > 1) {
+		ret = nvme_rdma_init_io_queues(ctrl);
+		if (ret)
+			goto stop_admin_q;
+
+		ret = nvme_rdma_connect_io_queues(ctrl);
+		if (ret)
+			goto stop_admin_q;
+	}
+
+	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+	WARN_ON_ONCE(!changed);
+
+	if (ctrl->queue_count > 1)
+		nvme_start_queues(&ctrl->ctrl);
+
+	dev_info(ctrl->ctrl.device, "Successfully reconnected\n");
+
+	return;
+
+stop_admin_q:
+	blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
+requeue:
+	/* Make sure we are not resetting/deleting */
+	if (ctrl->ctrl.state == NVME_CTRL_RECONNECTING) {
+		dev_info(ctrl->ctrl.device,
+			"Failed reconnect attempt, requeueing...\n");
+		queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
+					ctrl->reconnect_delay * HZ);
+	}
+}
+
+static void nvme_rdma_error_recovery_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *ctrl = container_of(work,
+			struct nvme_rdma_ctrl, err_work);
+
+	nvme_stop_keep_alive(&ctrl->ctrl);
+	if (ctrl->queue_count > 1)
+		nvme_stop_queues(&ctrl->ctrl);
+	blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
+
+	/* We must take care of fastfail/requeue all our inflight requests */
+	if (ctrl->queue_count > 1)
+		blk_mq_tagset_busy_iter(&ctrl->tag_set,
+					nvme_cancel_request, &ctrl->ctrl);
+	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
+				nvme_cancel_request, &ctrl->ctrl);
+
+	dev_info(ctrl->ctrl.device, "reconnecting in %d seconds\n",
+		ctrl->reconnect_delay);
+
+	queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
+				ctrl->reconnect_delay * HZ);
+}
+
+static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
+{
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING))
+		return;
+
+	queue_work(nvme_rdma_wq, &ctrl->err_work);
+}
+
+static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc,
+		const char *op)
+{
+	struct nvme_rdma_queue *queue = cq->cq_context;
+	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
+
+	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
+		dev_info(ctrl->ctrl.device,
+			     "%s for CQE 0x%p failed with status %s (%d)\n",
+			     op, wc->wr_cqe,
+			     ib_wc_status_msg(wc->status), wc->status);
+	nvme_rdma_error_recovery(ctrl);
+}
+
+static void nvme_rdma_memreg_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	if (unlikely(wc->status != IB_WC_SUCCESS))
+		nvme_rdma_wr_error(cq, wc, "MEMREG");
+}
+
+static void nvme_rdma_inv_rkey_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	if (unlikely(wc->status != IB_WC_SUCCESS))
+		nvme_rdma_wr_error(cq, wc, "LOCAL_INV");
+}
+
+static int nvme_rdma_inv_rkey(struct nvme_rdma_queue *queue,
+		struct nvme_rdma_request *req)
+{
+	struct ib_send_wr *bad_wr;
+	struct ib_send_wr wr = {
+		.opcode		    = IB_WR_LOCAL_INV,
+		.next		    = NULL,
+		.num_sge	    = 0,
+		.send_flags	    = 0,
+		.ex.invalidate_rkey = req->mr->rkey,
+	};
+
+	req->reg_cqe.done = nvme_rdma_inv_rkey_done;
+	wr.wr_cqe = &req->reg_cqe;
+
+	return ib_post_send(queue->qp, &wr, &bad_wr);
+}
+
+static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue,
+		struct request *rq)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
+	struct nvme_rdma_device *dev = queue->device;
+	struct ib_device *ibdev = dev->dev;
+	int res;
+
+	if (!blk_rq_bytes(rq))
+		return;
+
+	if (req->need_inval) {
+		res = nvme_rdma_inv_rkey(queue, req);
+		if (res < 0) {
+			dev_err(ctrl->ctrl.device,
+				"Queueing INV WR for rkey %#x failed (%d)\n",
+				req->mr->rkey, res);
+			nvme_rdma_error_recovery(queue->ctrl);
+		}
+	}
+
+	ib_dma_unmap_sg(ibdev, req->sg_table.sgl,
+			req->nents, rq_data_dir(rq) ==
+				    WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+
+	nvme_cleanup_cmd(rq);
+	sg_free_table_chained(&req->sg_table, true);
+}
+
+static int nvme_rdma_set_sg_null(struct nvme_command *c)
+{
+	struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;
+
+	sg->addr = 0;
+	put_unaligned_le24(0, sg->length);
+	put_unaligned_le32(0, sg->key);
+	sg->type = NVME_KEY_SGL_FMT_DATA_DESC << 4;
+	return 0;
+}
+
+static int nvme_rdma_map_sg_inline(struct nvme_rdma_queue *queue,
+		struct nvme_rdma_request *req, struct nvme_command *c)
+{
+	struct nvme_sgl_desc *sg = &c->common.dptr.sgl;
+
+	req->sge[1].addr = sg_dma_address(req->sg_table.sgl);
+	req->sge[1].length = sg_dma_len(req->sg_table.sgl);
+	req->sge[1].lkey = queue->device->pd->local_dma_lkey;
+
+	sg->addr = cpu_to_le64(queue->ctrl->ctrl.icdoff);
+	sg->length = cpu_to_le32(sg_dma_len(req->sg_table.sgl));
+	sg->type = (NVME_SGL_FMT_DATA_DESC << 4) | NVME_SGL_FMT_OFFSET;
+
+	req->inline_data = true;
+	req->num_sge++;
+	return 0;
+}
+
+static int nvme_rdma_map_sg_single(struct nvme_rdma_queue *queue,
+		struct nvme_rdma_request *req, struct nvme_command *c)
+{
+	struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;
+
+	sg->addr = cpu_to_le64(sg_dma_address(req->sg_table.sgl));
+	put_unaligned_le24(sg_dma_len(req->sg_table.sgl), sg->length);
+	put_unaligned_le32(queue->device->mr->rkey, sg->key);
+	sg->type = NVME_KEY_SGL_FMT_DATA_DESC << 4;
+	return 0;
+}
+
+static int nvme_rdma_map_sg_fr(struct nvme_rdma_queue *queue,
+		struct nvme_rdma_request *req, struct nvme_command *c,
+		int count)
+{
+	struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;
+	int nr;
+
+	nr = ib_map_mr_sg(req->mr, req->sg_table.sgl, count, NULL, PAGE_SIZE);
+	if (nr < count) {
+		if (nr < 0)
+			return nr;
+		return -EINVAL;
+	}
+
+	ib_update_fast_reg_key(req->mr, ib_inc_rkey(req->mr->rkey));
+
+	req->reg_cqe.done = nvme_rdma_memreg_done;
+	memset(&req->reg_wr, 0, sizeof(req->reg_wr));
+	req->reg_wr.wr.opcode = IB_WR_REG_MR;
+	req->reg_wr.wr.wr_cqe = &req->reg_cqe;
+	req->reg_wr.wr.num_sge = 0;
+	req->reg_wr.mr = req->mr;
+	req->reg_wr.key = req->mr->rkey;
+	req->reg_wr.access = IB_ACCESS_LOCAL_WRITE |
+			     IB_ACCESS_REMOTE_READ |
+			     IB_ACCESS_REMOTE_WRITE;
+
+	req->need_inval = true;
+
+	sg->addr = cpu_to_le64(req->mr->iova);
+	put_unaligned_le24(req->mr->length, sg->length);
+	put_unaligned_le32(req->mr->rkey, sg->key);
+	sg->type = (NVME_KEY_SGL_FMT_DATA_DESC << 4) |
+			NVME_SGL_FMT_INVALIDATE;
+
+	return 0;
+}
+
+static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
+		struct request *rq, unsigned int map_len,
+		struct nvme_command *c)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_device *dev = queue->device;
+	struct ib_device *ibdev = dev->dev;
+	int nents, count;
+	int ret;
+
+	req->num_sge = 1;
+	req->inline_data = false;
+	req->need_inval = false;
+
+	c->common.flags |= NVME_CMD_SGL_METABUF;
+
+	if (!blk_rq_bytes(rq))
+		return nvme_rdma_set_sg_null(c);
+
+	req->sg_table.sgl = req->first_sgl;
+	ret = sg_alloc_table_chained(&req->sg_table, rq->nr_phys_segments,
+				req->sg_table.sgl);
+	if (ret)
+		return -ENOMEM;
+
+	nents = blk_rq_map_sg(rq->q, rq, req->sg_table.sgl);
+	BUG_ON(nents > rq->nr_phys_segments);
+	req->nents = nents;
+
+	count = ib_dma_map_sg(ibdev, req->sg_table.sgl, nents,
+		    rq_data_dir(rq) == WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+	if (unlikely(count <= 0)) {
+		sg_free_table_chained(&req->sg_table, true);
+		return -EIO;
+	}
+
+	if (count == 1) {
+		if (rq_data_dir(rq) == WRITE &&
+		    map_len <= nvme_rdma_inline_data_size(queue) &&
+		    nvme_rdma_queue_idx(queue))
+			return nvme_rdma_map_sg_inline(queue, req, c);
+
+		if (!register_always)
+			return nvme_rdma_map_sg_single(queue, req, c);
+	}
+
+	return nvme_rdma_map_sg_fr(queue, req, c, count);
+}
+
+static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	if (unlikely(wc->status != IB_WC_SUCCESS))
+		nvme_rdma_wr_error(cq, wc, "SEND");
+}
+
+static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
+		struct nvme_rdma_qe *qe, struct ib_sge *sge, u32 num_sge,
+		struct ib_send_wr *first, bool flush)
+{
+	struct ib_send_wr wr, *bad_wr;
+	int ret;
+
+	sge->addr   = qe->dma;
+	sge->length = sizeof(struct nvme_command),
+	sge->lkey   = queue->device->pd->local_dma_lkey;
+
+	qe->cqe.done = nvme_rdma_send_done;
+
+	wr.next       = NULL;
+	wr.wr_cqe     = &qe->cqe;
+	wr.sg_list    = sge;
+	wr.num_sge    = num_sge;
+	wr.opcode     = IB_WR_SEND;
+	wr.send_flags = 0;
+
+	/*
+	 * Unsignalled send completions are another giant desaster in the
+	 * IB Verbs spec:  If we don't regularly post signalled sends
+	 * the send queue will fill up and only a QP reset will rescue us.
+	 * Would have been way to obvious to handle this in hardware or
+	 * at least the RDMA stack..
+	 *
+	 * This messy and racy code sniplet is copy and pasted from the iSER
+	 * initiator, and the magic '32' comes from there as well.
+	 *
+	 * Always signal the flushes. The magic request used for the flush
+	 * sequencer is not allocated in our driver's tagset and it's
+	 * triggered to be freed by blk_cleanup_queue(). So we need to
+	 * always mark it as signaled to ensure that the "wr_cqe", which is
+	 * embeded in request's payload, is not freed when __ib_process_cq()
+	 * calls wr_cqe->done().
+	 */
+	if ((++queue->sig_count % 32) == 0 || flush)
+		wr.send_flags |= IB_SEND_SIGNALED;
+
+	if (first)
+		first->next = &wr;
+	else
+		first = &wr;
+
+	ret = ib_post_send(queue->qp, first, &bad_wr);
+	if (ret) {
+		dev_err(queue->ctrl->ctrl.device,
+			     "%s failed with error code %d\n", __func__, ret);
+	}
+	return ret;
+}
+
+static int nvme_rdma_post_recv(struct nvme_rdma_queue *queue,
+		struct nvme_rdma_qe *qe)
+{
+	struct ib_recv_wr wr, *bad_wr;
+	struct ib_sge list;
+	int ret;
+
+	list.addr   = qe->dma;
+	list.length = sizeof(struct nvme_completion);
+	list.lkey   = queue->device->pd->local_dma_lkey;
+
+	qe->cqe.done = nvme_rdma_recv_done;
+
+	wr.next     = NULL;
+	wr.wr_cqe   = &qe->cqe;
+	wr.sg_list  = &list;
+	wr.num_sge  = 1;
+
+	ret = ib_post_recv(queue->qp, &wr, &bad_wr);
+	if (ret) {
+		dev_err(queue->ctrl->ctrl.device,
+			"%s failed with error code %d\n", __func__, ret);
+	}
+	return ret;
+}
+
+static struct blk_mq_tags *nvme_rdma_tagset(struct nvme_rdma_queue *queue)
+{
+	u32 queue_idx = nvme_rdma_queue_idx(queue);
+
+	if (queue_idx == 0)
+		return queue->ctrl->admin_tag_set.tags[queue_idx];
+	return queue->ctrl->tag_set.tags[queue_idx - 1];
+}
+
+static void nvme_rdma_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
+{
+	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(arg);
+	struct nvme_rdma_queue *queue = &ctrl->queues[0];
+	struct ib_device *dev = queue->device->dev;
+	struct nvme_rdma_qe *sqe = &ctrl->async_event_sqe;
+	struct nvme_command *cmd = sqe->data;
+	struct ib_sge sge;
+	int ret;
+
+	if (WARN_ON_ONCE(aer_idx != 0))
+		return;
+
+	ib_dma_sync_single_for_cpu(dev, sqe->dma, sizeof(*cmd), DMA_TO_DEVICE);
+
+	memset(cmd, 0, sizeof(*cmd));
+	cmd->common.opcode = nvme_admin_async_event;
+	cmd->common.command_id = NVME_RDMA_AQ_BLKMQ_DEPTH;
+	cmd->common.flags |= NVME_CMD_SGL_METABUF;
+	nvme_rdma_set_sg_null(cmd);
+
+	ib_dma_sync_single_for_device(dev, sqe->dma, sizeof(*cmd),
+			DMA_TO_DEVICE);
+
+	ret = nvme_rdma_post_send(queue, sqe, &sge, 1, NULL, false);
+	WARN_ON_ONCE(ret);
+}
+
+static int nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue,
+		struct nvme_completion *cqe, struct ib_wc *wc, int tag)
+{
+	u16 status = le16_to_cpu(cqe->status);
+	struct request *rq;
+	struct nvme_rdma_request *req;
+	int ret = 0;
+
+	status >>= 1;
+
+	rq = blk_mq_tag_to_rq(nvme_rdma_tagset(queue), cqe->command_id);
+	if (!rq) {
+		dev_err(queue->ctrl->ctrl.device,
+			"tag 0x%x on QP %#x not found\n",
+			cqe->command_id, queue->qp->qp_num);
+		nvme_rdma_error_recovery(queue->ctrl);
+		return ret;
+	}
+	req = blk_mq_rq_to_pdu(rq);
+
+	if (rq->cmd_type == REQ_TYPE_DRV_PRIV && rq->special)
+		memcpy(rq->special, cqe, sizeof(*cqe));
+
+	if (rq->tag == tag)
+		ret = 1;
+
+	if ((wc->wc_flags & IB_WC_WITH_INVALIDATE) &&
+	    wc->ex.invalidate_rkey == req->mr->rkey)
+		req->need_inval = false;
+
+	blk_mq_complete_request(rq, status);
+
+	return ret;
+}
+
+static int __nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc, int tag)
+{
+	struct nvme_rdma_qe *qe =
+		container_of(wc->wr_cqe, struct nvme_rdma_qe, cqe);
+	struct nvme_rdma_queue *queue = cq->cq_context;
+	struct ib_device *ibdev = queue->device->dev;
+	struct nvme_completion *cqe = qe->data;
+	const size_t len = sizeof(struct nvme_completion);
+	int ret = 0;
+
+	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+		nvme_rdma_wr_error(cq, wc, "RECV");
+		return 0;
+	}
+
+	ib_dma_sync_single_for_cpu(ibdev, qe->dma, len, DMA_FROM_DEVICE);
+	/*
+	 * AEN requests are special as they don't time out and can
+	 * survive any kind of queue freeze and often don't respond to
+	 * aborts.  We don't even bother to allocate a struct request
+	 * for them but rather special case them here.
+	 */
+	if (unlikely(nvme_rdma_queue_idx(queue) == 0 &&
+			cqe->command_id >= NVME_RDMA_AQ_BLKMQ_DEPTH))
+		nvme_complete_async_event(&queue->ctrl->ctrl, cqe);
+	else
+		ret = nvme_rdma_process_nvme_rsp(queue, cqe, wc, tag);
+	ib_dma_sync_single_for_device(ibdev, qe->dma, len, DMA_FROM_DEVICE);
+
+	nvme_rdma_post_recv(queue, qe);
+	return ret;
+}
+
+static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	__nvme_rdma_recv_done(cq, wc, -1);
+}
+
+static int nvme_rdma_conn_established(struct nvme_rdma_queue *queue)
+{
+	int ret, i;
+
+	for (i = 0; i < queue->queue_size; i++) {
+		ret = nvme_rdma_post_recv(queue, &queue->rsp_ring[i]);
+		if (ret)
+			goto out_destroy_queue_ib;
+	}
+
+	return 0;
+
+out_destroy_queue_ib:
+	nvme_rdma_destroy_queue_ib(queue);
+	return ret;
+}
+
+static int nvme_rdma_conn_rejected(struct nvme_rdma_queue *queue,
+		struct rdma_cm_event *ev)
+{
+	if (ev->param.conn.private_data_len) {
+		struct nvme_rdma_cm_rej *rej =
+			(struct nvme_rdma_cm_rej *)ev->param.conn.private_data;
+
+		dev_err(queue->ctrl->ctrl.device,
+			"Connect rejected, status %d.", le16_to_cpu(rej->sts));
+		/* XXX: Think of something clever to do here... */
+	} else {
+		dev_err(queue->ctrl->ctrl.device,
+			"Connect rejected, no private data.\n");
+	}
+
+	return -ECONNRESET;
+}
+
+static int nvme_rdma_addr_resolved(struct nvme_rdma_queue *queue)
+{
+	struct nvme_rdma_device *dev;
+	int ret;
+
+	dev = nvme_rdma_find_get_device(queue->cm_id);
+	if (!dev) {
+		dev_err(queue->cm_id->device->dma_device,
+			"no client data found!\n");
+		return -ECONNREFUSED;
+	}
+
+	ret = nvme_rdma_create_queue_ib(queue, dev);
+	if (ret) {
+		nvme_rdma_dev_put(dev);
+		goto out;
+	}
+
+	ret = rdma_resolve_route(queue->cm_id, NVME_RDMA_CONNECT_TIMEOUT_MS);
+	if (ret) {
+		dev_err(queue->ctrl->ctrl.device,
+			"rdma_resolve_route failed (%d).\n",
+			queue->cm_error);
+		goto out_destroy_queue;
+	}
+
+	return 0;
+
+out_destroy_queue:
+	nvme_rdma_destroy_queue_ib(queue);
+out:
+	return ret;
+}
+
+static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue)
+{
+	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
+	struct rdma_conn_param param = { };
+	struct nvme_rdma_cm_req priv;
+	int ret;
+
+	param.qp_num = queue->qp->qp_num;
+	param.flow_control = 1;
+
+	param.responder_resources = queue->device->dev->attrs.max_qp_rd_atom;
+	/* maximum retry count */
+	param.retry_count = 7;
+	param.rnr_retry_count = 7;
+	param.private_data = &priv;
+	param.private_data_len = sizeof(priv);
+
+	priv.recfmt = cpu_to_le16(NVME_RDMA_CM_FMT_1_0);
+	priv.qid = cpu_to_le16(nvme_rdma_queue_idx(queue));
+	priv.hrqsize = cpu_to_le16(queue->queue_size);
+	priv.hsqsize = cpu_to_le16(queue->queue_size);
+
+	ret = rdma_connect(queue->cm_id, &param);
+	if (ret) {
+		dev_err(ctrl->ctrl.device,
+			"rdma_connect failed (%d).\n", ret);
+		goto out_destroy_queue_ib;
+	}
+
+	return 0;
+
+out_destroy_queue_ib:
+	nvme_rdma_destroy_queue_ib(queue);
+	return ret;
+}
+
+/**
+ * nvme_rdma_device_unplug() - Handle RDMA device unplug
+ * @queue:      Queue that owns the cm_id that caught the event
+ *
+ * DEVICE_REMOVAL event notifies us that the RDMA device is about
+ * to unplug so we should take care of destroying our RDMA resources.
+ * This event will be generated for each allocated cm_id.
+ *
+ * In our case, the RDMA resources are managed per controller and not
+ * only per queue. So the way we handle this is we trigger an implicit
+ * controller deletion upon the first DEVICE_REMOVAL event we see, and
+ * hold the event inflight until the controller deletion is completed.
+ *
+ * One exception that we need to handle is the destruction of the cm_id
+ * that caught the event. Since we hold the callout until the controller
+ * deletion is completed, we'll deadlock if the controller deletion will
+ * call rdma_destroy_id on this queue's cm_id. Thus, we claim ownership
+ * of destroying this queue before-hand, destroy the queue resources
+ * after the controller deletion completed with the exception of destroying
+ * the cm_id implicitely by returning a non-zero rc to the callout.
+ */
+static int nvme_rdma_device_unplug(struct nvme_rdma_queue *queue)
+{
+	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
+	int ret, ctrl_deleted = 0;
+
+	/* First disable the queue so ctrl delete won't free it */
+	if (!test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags))
+		goto out;
+
+	/* delete the controller */
+	ret = __nvme_rdma_del_ctrl(ctrl);
+	if (!ret) {
+		dev_warn(ctrl->ctrl.device,
+			"Got rdma device removal event, deleting ctrl\n");
+		flush_work(&ctrl->delete_work);
+
+		/* Return non-zero so the cm_id will destroy implicitly */
+		ctrl_deleted = 1;
+
+		/* Free this queue ourselves */
+		rdma_disconnect(queue->cm_id);
+		ib_drain_qp(queue->qp);
+		nvme_rdma_destroy_queue_ib(queue);
+	}
+
+out:
+	return ctrl_deleted;
+}
+
+static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
+		struct rdma_cm_event *ev)
+{
+	struct nvme_rdma_queue *queue = cm_id->context;
+	int cm_error = 0;
+
+	dev_dbg(queue->ctrl->ctrl.device, "%s (%d): status %d id %p\n",
+		rdma_event_msg(ev->event), ev->event,
+		ev->status, cm_id);
+
+	switch (ev->event) {
+	case RDMA_CM_EVENT_ADDR_RESOLVED:
+		cm_error = nvme_rdma_addr_resolved(queue);
+		break;
+	case RDMA_CM_EVENT_ROUTE_RESOLVED:
+		cm_error = nvme_rdma_route_resolved(queue);
+		break;
+	case RDMA_CM_EVENT_ESTABLISHED:
+		queue->cm_error = nvme_rdma_conn_established(queue);
+		/* complete cm_done regardless of success/failure */
+		complete(&queue->cm_done);
+		return 0;
+	case RDMA_CM_EVENT_REJECTED:
+		cm_error = nvme_rdma_conn_rejected(queue, ev);
+		break;
+	case RDMA_CM_EVENT_ADDR_ERROR:
+	case RDMA_CM_EVENT_ROUTE_ERROR:
+	case RDMA_CM_EVENT_CONNECT_ERROR:
+	case RDMA_CM_EVENT_UNREACHABLE:
+		dev_dbg(queue->ctrl->ctrl.device,
+			"CM error event %d\n", ev->event);
+		cm_error = -ECONNRESET;
+		break;
+	case RDMA_CM_EVENT_DISCONNECTED:
+	case RDMA_CM_EVENT_ADDR_CHANGE:
+	case RDMA_CM_EVENT_TIMEWAIT_EXIT:
+		dev_dbg(queue->ctrl->ctrl.device,
+			"disconnect received - connection closed\n");
+		nvme_rdma_error_recovery(queue->ctrl);
+		break;
+	case RDMA_CM_EVENT_DEVICE_REMOVAL:
+		/* return 1 means impliciy CM ID destroy */
+		return nvme_rdma_device_unplug(queue);
+	default:
+		dev_err(queue->ctrl->ctrl.device,
+			"Unexpected RDMA CM event (%d)\n", ev->event);
+		nvme_rdma_error_recovery(queue->ctrl);
+		break;
+	}
+
+	if (cm_error) {
+		queue->cm_error = cm_error;
+		complete(&queue->cm_done);
+	}
+
+	return 0;
+}
+
+static enum blk_eh_timer_return
+nvme_rdma_timeout(struct request *rq, bool reserved)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+
+	/* queue error recovery */
+	nvme_rdma_error_recovery(req->queue->ctrl);
+
+	/* fail with DNR on cmd timeout */
+	rq->errors = NVME_SC_ABORT_REQ | NVME_SC_DNR;
+
+	return BLK_EH_HANDLED;
+}
+
+static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
+		const struct blk_mq_queue_data *bd)
+{
+	struct nvme_ns *ns = hctx->queue->queuedata;
+	struct nvme_rdma_queue *queue = hctx->driver_data;
+	struct request *rq = bd->rq;
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_qe *sqe = &req->sqe;
+	struct nvme_command *c = sqe->data;
+	bool flush = false;
+	struct ib_device *dev;
+	unsigned int map_len;
+	int ret;
+
+	WARN_ON_ONCE(rq->tag < 0);
+
+	dev = queue->device->dev;
+	ib_dma_sync_single_for_cpu(dev, sqe->dma,
+			sizeof(struct nvme_command), DMA_TO_DEVICE);
+
+	ret = nvme_setup_cmd(ns, rq, c);
+	if (ret)
+		return ret;
+
+	c->common.command_id = rq->tag;
+	blk_mq_start_request(rq);
+
+	map_len = nvme_map_len(rq);
+	ret = nvme_rdma_map_data(queue, rq, map_len, c);
+	if (ret < 0) {
+		dev_err(queue->ctrl->ctrl.device,
+			     "Failed to map data (%d)\n", ret);
+		nvme_cleanup_cmd(rq);
+		goto err;
+	}
+
+	ib_dma_sync_single_for_device(dev, sqe->dma,
+			sizeof(struct nvme_command), DMA_TO_DEVICE);
+
+	if (rq->cmd_type == REQ_TYPE_FS && req_op(rq) == REQ_OP_FLUSH)
+		flush = true;
+	ret = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
+			req->need_inval ? &req->reg_wr.wr : NULL, flush);
+	if (ret) {
+		nvme_rdma_unmap_data(queue, rq);
+		goto err;
+	}
+
+	return BLK_MQ_RQ_QUEUE_OK;
+err:
+	return (ret == -ENOMEM || ret == -EAGAIN) ?
+		BLK_MQ_RQ_QUEUE_BUSY : BLK_MQ_RQ_QUEUE_ERROR;
+}
+
+static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
+{
+	struct nvme_rdma_queue *queue = hctx->driver_data;
+	struct ib_cq *cq = queue->ib_cq;
+	struct ib_wc wc;
+	int found = 0;
+
+	ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
+	while (ib_poll_cq(cq, 1, &wc) > 0) {
+		struct ib_cqe *cqe = wc.wr_cqe;
+
+		if (cqe) {
+			if (cqe->done == nvme_rdma_recv_done)
+				found |= __nvme_rdma_recv_done(cq, &wc, tag);
+			else
+				cqe->done(cq, &wc);
+		}
+	}
+
+	return found;
+}
+
+static void nvme_rdma_complete_rq(struct request *rq)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_queue *queue = req->queue;
+	int error = 0;
+
+	nvme_rdma_unmap_data(queue, rq);
+
+	if (unlikely(rq->errors)) {
+		if (nvme_req_needs_retry(rq, rq->errors)) {
+			nvme_requeue_req(rq);
+			return;
+		}
+
+		if (rq->cmd_type == REQ_TYPE_DRV_PRIV)
+			error = rq->errors;
+		else
+			error = nvme_error_status(rq->errors);
+	}
+
+	blk_mq_end_request(rq, error);
+}
+
+static struct blk_mq_ops nvme_rdma_mq_ops = {
+	.queue_rq	= nvme_rdma_queue_rq,
+	.complete	= nvme_rdma_complete_rq,
+	.map_queue	= blk_mq_map_queue,
+	.init_request	= nvme_rdma_init_request,
+	.exit_request	= nvme_rdma_exit_request,
+	.reinit_request	= nvme_rdma_reinit_request,
+	.init_hctx	= nvme_rdma_init_hctx,
+	.poll		= nvme_rdma_poll,
+	.timeout	= nvme_rdma_timeout,
+};
+
+static struct blk_mq_ops nvme_rdma_admin_mq_ops = {
+	.queue_rq	= nvme_rdma_queue_rq,
+	.complete	= nvme_rdma_complete_rq,
+	.map_queue	= blk_mq_map_queue,
+	.init_request	= nvme_rdma_init_admin_request,
+	.exit_request	= nvme_rdma_exit_admin_request,
+	.reinit_request	= nvme_rdma_reinit_request,
+	.init_hctx	= nvme_rdma_init_admin_hctx,
+	.timeout	= nvme_rdma_timeout,
+};
+
+static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl)
+{
+	int error;
+
+	error = nvme_rdma_init_queue(ctrl, 0, NVMF_AQ_DEPTH);
+	if (error)
+		return error;
+
+	ctrl->device = ctrl->queues[0].device;
+
+	/*
+	 * We need a reference on the device as long as the tag_set is alive,
+	 * as the MRs in the request structures need a valid ib_device.
+	 */
+	error = -EINVAL;
+	if (!nvme_rdma_dev_get(ctrl->device))
+		goto out_free_queue;
+
+	ctrl->max_fr_pages = min_t(u32, NVME_RDMA_MAX_SEGMENTS,
+		ctrl->device->dev->attrs.max_fast_reg_page_list_len);
+
+	memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
+	ctrl->admin_tag_set.ops = &nvme_rdma_admin_mq_ops;
+	ctrl->admin_tag_set.queue_depth = NVME_RDMA_AQ_BLKMQ_DEPTH;
+	ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */
+	ctrl->admin_tag_set.numa_node = NUMA_NO_NODE;
+	ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_rdma_request) +
+		SG_CHUNK_SIZE * sizeof(struct scatterlist);
+	ctrl->admin_tag_set.driver_data = ctrl;
+	ctrl->admin_tag_set.nr_hw_queues = 1;
+	ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;
+
+	error = blk_mq_alloc_tag_set(&ctrl->admin_tag_set);
+	if (error)
+		goto out_put_dev;
+
+	ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
+	if (IS_ERR(ctrl->ctrl.admin_q)) {
+		error = PTR_ERR(ctrl->ctrl.admin_q);
+		goto out_free_tagset;
+	}
+
+	error = nvmf_connect_admin_queue(&ctrl->ctrl);
+	if (error)
+		goto out_cleanup_queue;
+
+	error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->cap);
+	if (error) {
+		dev_err(ctrl->ctrl.device,
+			"prop_get NVME_REG_CAP failed\n");
+		goto out_cleanup_queue;
+	}
+
+	ctrl->ctrl.sqsize =
+		min_t(int, NVME_CAP_MQES(ctrl->cap) + 1, ctrl->ctrl.sqsize);
+
+	error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
+	if (error)
+		goto out_cleanup_queue;
+
+	ctrl->ctrl.max_hw_sectors =
+		(ctrl->max_fr_pages - 1) << (PAGE_SHIFT - 9);
+
+	error = nvme_init_identify(&ctrl->ctrl);
+	if (error)
+		goto out_cleanup_queue;
+
+	error = nvme_rdma_alloc_qe(ctrl->queues[0].device->dev,
+			&ctrl->async_event_sqe, sizeof(struct nvme_command),
+			DMA_TO_DEVICE);
+	if (error)
+		goto out_cleanup_queue;
+
+	nvme_start_keep_alive(&ctrl->ctrl);
+
+	return 0;
+
+out_cleanup_queue:
+	blk_cleanup_queue(ctrl->ctrl.admin_q);
+out_free_tagset:
+	/* disconnect and drain the queue before freeing the tagset */
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
+	blk_mq_free_tag_set(&ctrl->admin_tag_set);
+out_put_dev:
+	nvme_rdma_dev_put(ctrl->device);
+out_free_queue:
+	nvme_rdma_free_queue(&ctrl->queues[0]);
+	return error;
+}
+
+static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl)
+{
+	nvme_stop_keep_alive(&ctrl->ctrl);
+	cancel_work_sync(&ctrl->err_work);
+	cancel_delayed_work_sync(&ctrl->reconnect_work);
+
+	if (ctrl->queue_count > 1) {
+		nvme_stop_queues(&ctrl->ctrl);
+		blk_mq_tagset_busy_iter(&ctrl->tag_set,
+					nvme_cancel_request, &ctrl->ctrl);
+		nvme_rdma_free_io_queues(ctrl);
+	}
+
+	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
+		nvme_shutdown_ctrl(&ctrl->ctrl);
+
+	blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
+	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
+				nvme_cancel_request, &ctrl->ctrl);
+	nvme_rdma_destroy_admin_queue(ctrl);
+}
+
+static void nvme_rdma_del_ctrl_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *ctrl = container_of(work,
+				struct nvme_rdma_ctrl, delete_work);
+
+	nvme_remove_namespaces(&ctrl->ctrl);
+	nvme_rdma_shutdown_ctrl(ctrl);
+	nvme_uninit_ctrl(&ctrl->ctrl);
+	nvme_put_ctrl(&ctrl->ctrl);
+}
+
+static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl)
+{
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING))
+		return -EBUSY;
+
+	if (!queue_work(nvme_rdma_wq, &ctrl->delete_work))
+		return -EBUSY;
+
+	return 0;
+}
+
+static int nvme_rdma_del_ctrl(struct nvme_ctrl *nctrl)
+{
+	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
+	int ret;
+
+	ret = __nvme_rdma_del_ctrl(ctrl);
+	if (ret)
+		return ret;
+
+	flush_work(&ctrl->delete_work);
+
+	return 0;
+}
+
+static void nvme_rdma_remove_ctrl_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *ctrl = container_of(work,
+				struct nvme_rdma_ctrl, delete_work);
+
+	nvme_remove_namespaces(&ctrl->ctrl);
+	nvme_uninit_ctrl(&ctrl->ctrl);
+	nvme_put_ctrl(&ctrl->ctrl);
+}
+
+static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *ctrl = container_of(work,
+					struct nvme_rdma_ctrl, reset_work);
+	int ret;
+	bool changed;
+
+	nvme_rdma_shutdown_ctrl(ctrl);
+
+	ret = nvme_rdma_configure_admin_queue(ctrl);
+	if (ret) {
+		/* ctrl is already shutdown, just remove the ctrl */
+		INIT_WORK(&ctrl->delete_work, nvme_rdma_remove_ctrl_work);
+		goto del_dead_ctrl;
+	}
+
+	if (ctrl->queue_count > 1) {
+		ret = blk_mq_reinit_tagset(&ctrl->tag_set);
+		if (ret)
+			goto del_dead_ctrl;
+
+		ret = nvme_rdma_init_io_queues(ctrl);
+		if (ret)
+			goto del_dead_ctrl;
+
+		ret = nvme_rdma_connect_io_queues(ctrl);
+		if (ret)
+			goto del_dead_ctrl;
+	}
+
+	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+	WARN_ON_ONCE(!changed);
+
+	if (ctrl->queue_count > 1) {
+		nvme_start_queues(&ctrl->ctrl);
+		nvme_queue_scan(&ctrl->ctrl);
+	}
+
+	return;
+
+del_dead_ctrl:
+	/* Deleting this dead controller... */
+	dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
+	WARN_ON(!queue_work(nvme_rdma_wq, &ctrl->delete_work));
+}
+
+static int nvme_rdma_reset_ctrl(struct nvme_ctrl *nctrl)
+{
+	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
+
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
+		return -EBUSY;
+
+	if (!queue_work(nvme_rdma_wq, &ctrl->reset_work))
+		return -EBUSY;
+
+	flush_work(&ctrl->reset_work);
+
+	return 0;
+}
+
+static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
+	.name			= "rdma",
+	.module			= THIS_MODULE,
+	.is_fabrics		= true,
+	.reg_read32		= nvmf_reg_read32,
+	.reg_read64		= nvmf_reg_read64,
+	.reg_write32		= nvmf_reg_write32,
+	.reset_ctrl		= nvme_rdma_reset_ctrl,
+	.free_ctrl		= nvme_rdma_free_ctrl,
+	.submit_async_event	= nvme_rdma_submit_async_event,
+	.delete_ctrl		= nvme_rdma_del_ctrl,
+	.get_subsysnqn		= nvmf_get_subsysnqn,
+	.get_address		= nvmf_get_address,
+};
+
+static int nvme_rdma_create_io_queues(struct nvme_rdma_ctrl *ctrl)
+{
+	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+	int ret;
+
+	ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
+	if (ret)
+		return ret;
+
+	ctrl->queue_count = opts->nr_io_queues + 1;
+	if (ctrl->queue_count < 2)
+		return 0;
+
+	dev_info(ctrl->ctrl.device,
+		"creating %d I/O queues.\n", opts->nr_io_queues);
+
+	ret = nvme_rdma_init_io_queues(ctrl);
+	if (ret)
+		return ret;
+
+	/*
+	 * We need a reference on the device as long as the tag_set is alive,
+	 * as the MRs in the request structures need a valid ib_device.
+	 */
+	ret = -EINVAL;
+	if (!nvme_rdma_dev_get(ctrl->device))
+		goto out_free_io_queues;
+
+	memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
+	ctrl->tag_set.ops = &nvme_rdma_mq_ops;
+	ctrl->tag_set.queue_depth = ctrl->ctrl.sqsize;
+	ctrl->tag_set.reserved_tags = 1; /* fabric connect */
+	ctrl->tag_set.numa_node = NUMA_NO_NODE;
+	ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	ctrl->tag_set.cmd_size = sizeof(struct nvme_rdma_request) +
+		SG_CHUNK_SIZE * sizeof(struct scatterlist);
+	ctrl->tag_set.driver_data = ctrl;
+	ctrl->tag_set.nr_hw_queues = ctrl->queue_count - 1;
+	ctrl->tag_set.timeout = NVME_IO_TIMEOUT;
+
+	ret = blk_mq_alloc_tag_set(&ctrl->tag_set);
+	if (ret)
+		goto out_put_dev;
+	ctrl->ctrl.tagset = &ctrl->tag_set;
+
+	ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
+	if (IS_ERR(ctrl->ctrl.connect_q)) {
+		ret = PTR_ERR(ctrl->ctrl.connect_q);
+		goto out_free_tag_set;
+	}
+
+	ret = nvme_rdma_connect_io_queues(ctrl);
+	if (ret)
+		goto out_cleanup_connect_q;
+
+	return 0;
+
+out_cleanup_connect_q:
+	blk_cleanup_queue(ctrl->ctrl.connect_q);
+out_free_tag_set:
+	blk_mq_free_tag_set(&ctrl->tag_set);
+out_put_dev:
+	nvme_rdma_dev_put(ctrl->device);
+out_free_io_queues:
+	nvme_rdma_free_io_queues(ctrl);
+	return ret;
+}
+
+static int nvme_rdma_parse_ipaddr(struct sockaddr_in *in_addr, char *p)
+{
+	u8 *addr = (u8 *)&in_addr->sin_addr.s_addr;
+	size_t buflen = strlen(p);
+
+	/* XXX: handle IPv6 addresses */
+
+	if (buflen > INET_ADDRSTRLEN)
+		return -EINVAL;
+	if (in4_pton(p, buflen, addr, '\0', NULL) == 0)
+		return -EINVAL;
+	in_addr->sin_family = AF_INET;
+	return 0;
+}
+
+static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
+		struct nvmf_ctrl_options *opts)
+{
+	struct nvme_rdma_ctrl *ctrl;
+	int ret;
+	bool changed;
+
+	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
+	if (!ctrl)
+		return ERR_PTR(-ENOMEM);
+	ctrl->ctrl.opts = opts;
+	INIT_LIST_HEAD(&ctrl->list);
+
+	ret = nvme_rdma_parse_ipaddr(&ctrl->addr_in, opts->traddr);
+	if (ret) {
+		pr_err("malformed IP address passed: %s\n", opts->traddr);
+		goto out_free_ctrl;
+	}
+
+	if (opts->mask & NVMF_OPT_TRSVCID) {
+		u16 port;
+
+		ret = kstrtou16(opts->trsvcid, 0, &port);
+		if (ret)
+			goto out_free_ctrl;
+
+		ctrl->addr_in.sin_port = cpu_to_be16(port);
+	} else {
+		ctrl->addr_in.sin_port = cpu_to_be16(NVME_RDMA_IP_PORT);
+	}
+
+	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
+				0 /* no quirks, we're perfect! */);
+	if (ret)
+		goto out_free_ctrl;
+
+	ctrl->reconnect_delay = opts->reconnect_delay;
+	INIT_DELAYED_WORK(&ctrl->reconnect_work,
+			nvme_rdma_reconnect_ctrl_work);
+	INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work);
+	INIT_WORK(&ctrl->delete_work, nvme_rdma_del_ctrl_work);
+	INIT_WORK(&ctrl->reset_work, nvme_rdma_reset_ctrl_work);
+	spin_lock_init(&ctrl->lock);
+
+	ctrl->queue_count = opts->nr_io_queues + 1; /* +1 for admin queue */
+	ctrl->ctrl.sqsize = opts->queue_size;
+	ctrl->ctrl.kato = opts->kato;
+
+	ret = -ENOMEM;
+	ctrl->queues = kcalloc(ctrl->queue_count, sizeof(*ctrl->queues),
+				GFP_KERNEL);
+	if (!ctrl->queues)
+		goto out_uninit_ctrl;
+
+	ret = nvme_rdma_configure_admin_queue(ctrl);
+	if (ret)
+		goto out_kfree_queues;
+
+	/* sanity check icdoff */
+	if (ctrl->ctrl.icdoff) {
+		dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");
+		goto out_remove_admin_queue;
+	}
+
+	/* sanity check keyed sgls */
+	if (!(ctrl->ctrl.sgls & (1 << 20))) {
+		dev_err(ctrl->ctrl.device, "Mandatory keyed sgls are not support\n");
+		goto out_remove_admin_queue;
+	}
+
+	if (opts->queue_size > ctrl->ctrl.maxcmd) {
+		/* warn if maxcmd is lower than queue_size */
+		dev_warn(ctrl->ctrl.device,
+			"queue_size %zu > ctrl maxcmd %u, clamping down\n",
+			opts->queue_size, ctrl->ctrl.maxcmd);
+		opts->queue_size = ctrl->ctrl.maxcmd;
+	}
+
+	if (opts->nr_io_queues) {
+		ret = nvme_rdma_create_io_queues(ctrl);
+		if (ret)
+			goto out_remove_admin_queue;
+	}
+
+	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+	WARN_ON_ONCE(!changed);
+
+	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
+		ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
+
+	kref_get(&ctrl->ctrl.kref);
+
+	mutex_lock(&nvme_rdma_ctrl_mutex);
+	list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
+	mutex_unlock(&nvme_rdma_ctrl_mutex);
+
+	if (opts->nr_io_queues) {
+		nvme_queue_scan(&ctrl->ctrl);
+		nvme_queue_async_events(&ctrl->ctrl);
+	}
+
+	return &ctrl->ctrl;
+
+out_remove_admin_queue:
+	nvme_stop_keep_alive(&ctrl->ctrl);
+	nvme_rdma_destroy_admin_queue(ctrl);
+out_kfree_queues:
+	kfree(ctrl->queues);
+out_uninit_ctrl:
+	nvme_uninit_ctrl(&ctrl->ctrl);
+	nvme_put_ctrl(&ctrl->ctrl);
+	if (ret > 0)
+		ret = -EIO;
+	return ERR_PTR(ret);
+out_free_ctrl:
+	kfree(ctrl);
+	return ERR_PTR(ret);
+}
+
+static struct nvmf_transport_ops nvme_rdma_transport = {
+	.name		= "rdma",
+	.required_opts	= NVMF_OPT_TRADDR,
+	.allowed_opts	= NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY,
+	.create_ctrl	= nvme_rdma_create_ctrl,
+};
+
+static int __init nvme_rdma_init_module(void)
+{
+	nvme_rdma_wq = create_workqueue("nvme_rdma_wq");
+	if (!nvme_rdma_wq)
+		return -ENOMEM;
+
+	nvmf_register_transport(&nvme_rdma_transport);
+	return 0;
+}
+
+static void __exit nvme_rdma_cleanup_module(void)
+{
+	struct nvme_rdma_ctrl *ctrl;
+
+	nvmf_unregister_transport(&nvme_rdma_transport);
+
+	mutex_lock(&nvme_rdma_ctrl_mutex);
+	list_for_each_entry(ctrl, &nvme_rdma_ctrl_list, list)
+		__nvme_rdma_del_ctrl(ctrl);
+	mutex_unlock(&nvme_rdma_ctrl_mutex);
+
+	destroy_workqueue(nvme_rdma_wq);
+}
+
+module_init(nvme_rdma_init_module);
+module_exit(nvme_rdma_cleanup_module);
+
+MODULE_LICENSE("GPL v2");