Merge branch 'for-4.5/nvme' of git://git.kernel.dk/linux-block

Pull NVMe updates from Jens Axboe:
 "Last branch for this series is the nvme changes.  It's in a separate
  branch to avoid splitting too much between core and NVMe changes,
  since NVMe is still helping drive some blk-mq changes.  That said, not
  a huge amount of core changes in here.  The grunt of the work is the
  continued split of the code"

* 'for-4.5/nvme' of git://git.kernel.dk/linux-block: (67 commits)
  uapi: update install list after nvme.h rename
  NVMe: Export NVMe attributes to sysfs group
  NVMe: Shutdown controller only for power-off
  NVMe: IO queue deletion re-write
  NVMe: Remove queue freezing on resets
  NVMe: Use a retryable error code on reset
  NVMe: Fix admin queue ring wrap
  nvme: make SG_IO support optional
  nvme: fixes for NVME_IOCTL_IO_CMD on the char device
  nvme: synchronize access to ctrl->namespaces
  nvme: Move nvme_freeze/unfreeze_queues to nvme core
  PCI/AER: include header file
  NVMe: Export namespace attributes to sysfs
  NVMe: Add pci error handlers
  block: remove REQ_NO_TIMEOUT flag
  nvme: merge iod and cmd_info
  nvme: meta_sg doesn't have to be an array
  nvme: properly free resources for cancelled command
  nvme: simplify completion handling
  nvme: special case AEN requests
  ...

19 files changed, 2596 insertions, 2197 deletions

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index f6325d573c10..711e4d8de6fa 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -66,7 +66,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 	}
 
 	if (unlikely(!bip))
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	memset(bip, 0, sizeof(*bip));
 
@@ -89,7 +89,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 	return bip;
 err:
 	mempool_free(bip, bs->bio_integrity_pool);
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(bio_integrity_alloc);
 
@@ -298,10 +298,10 @@ int bio_integrity_prep(struct bio *bio)
 
 	/* Allocate bio integrity payload and integrity vectors */
 	bip = bio_integrity_alloc(bio, GFP_NOIO, nr_pages);
-	if (unlikely(bip == NULL)) {
+	if (IS_ERR(bip)) {
 		printk(KERN_ERR "could not allocate data integrity bioset\n");
 		kfree(buf);
-		return -EIO;
+		return PTR_ERR(bip);
 	}
 
 	bip->bip_flags |= BIP_BLOCK_INTEGRITY;
@@ -465,9 +465,8 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 	BUG_ON(bip_src == NULL);
 
 	bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt);
-
-	if (bip == NULL)
-		return -EIO;
+	if (IS_ERR(bip))
+		return PTR_ERR(bip);
 
 	memcpy(bip->bip_vec, bip_src->bip_vec,
 	       bip_src->bip_vcnt * sizeof(struct bio_vec));
diff --git a/block/blk-core.c b/block/blk-core.c
index 476244d59309..ab51685988c2 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -680,6 +680,13 @@ static void blk_queue_usage_counter_release(struct percpu_ref *ref)
 	wake_up_all(&q->mq_freeze_wq);
 }
 
+static void blk_rq_timed_out_timer(unsigned long data)
+{
+	struct request_queue *q = (struct request_queue *)data;
+
+	kblockd_schedule_work(&q->timeout_work);
+}
+
 struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 {
 	struct request_queue *q;
@@ -841,6 +848,7 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
 		goto fail;
 
+	INIT_WORK(&q->timeout_work, blk_timeout_work);
 	q->request_fn		= rfn;
 	q->prep_rq_fn		= NULL;
 	q->unprep_rq_fn		= NULL;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 6889d7183a2a..4c0622fae413 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -603,8 +603,6 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 			blk_mq_complete_request(rq, -EIO);
 		return;
 	}
-	if (rq->cmd_flags & REQ_NO_TIMEOUT)
-		return;
 
 	if (time_after_eq(jiffies, rq->deadline)) {
 		if (!blk_mark_rq_complete(rq))
@@ -615,15 +613,19 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 	}
 }
 
-static void blk_mq_rq_timer(unsigned long priv)
+static void blk_mq_timeout_work(struct work_struct *work)
 {
-	struct request_queue *q = (struct request_queue *)priv;
+	struct request_queue *q =
+		container_of(work, struct request_queue, timeout_work);
 	struct blk_mq_timeout_data data = {
 		.next		= 0,
 		.next_set	= 0,
 	};
 	int i;
 
+	if (blk_queue_enter(q, true))
+		return;
+
 	blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data);
 
 	if (data.next_set) {
@@ -638,6 +640,7 @@ static void blk_mq_rq_timer(unsigned long priv)
 				blk_mq_tag_idle(hctx);
 		}
 	}
+	blk_queue_exit(q);
 }
 
 /*
@@ -2008,7 +2011,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		hctxs[i]->queue_num = i;
 	}
 
-	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
+	INIT_WORK(&q->timeout_work, blk_mq_timeout_work);
 	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);
 
 	q->nr_queues = nr_cpu_ids;
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 3610af561748..a30441a200c0 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -127,13 +127,16 @@ static void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout
 	}
 }
 
-void blk_rq_timed_out_timer(unsigned long data)
+void blk_timeout_work(struct work_struct *work)
 {
-	struct request_queue *q = (struct request_queue *) data;
+	struct request_queue *q =
+		container_of(work, struct request_queue, timeout_work);
 	unsigned long flags, next = 0;
 	struct request *rq, *tmp;
 	int next_set = 0;
 
+	if (blk_queue_enter(q, true))
+		return;
 	spin_lock_irqsave(q->queue_lock, flags);
 
 	list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list)
@@ -143,6 +146,7 @@ void blk_rq_timed_out_timer(unsigned long data)
 		mod_timer(&q->timeout, round_jiffies_up(next));
 
 	spin_unlock_irqrestore(q->queue_lock, flags);
+	blk_queue_exit(q);
 }
 
 /**
@@ -193,9 +197,6 @@ void blk_add_timer(struct request *req)
 	struct request_queue *q = req->q;
 	unsigned long expiry;
 
-	if (req->cmd_flags & REQ_NO_TIMEOUT)
-		return;
-
 	/* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */
 	if (!q->mq_ops && !q->rq_timed_out_fn)
 		return;
diff --git a/block/blk.h b/block/blk.h
index c43926d3d74d..70e4aee9cdcb 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -93,7 +93,7 @@ static inline void blk_flush_integrity(void)
 }
 #endif
 
-void blk_rq_timed_out_timer(unsigned long data);
+void blk_timeout_work(struct work_struct *work);
 unsigned long blk_rq_timeout(unsigned long timeout);
 void blk_add_timer(struct request *req);
 void blk_delete_timer(struct request *);
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index 002a94abdbc4..5d6237391dcd 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -8,3 +8,14 @@ config BLK_DEV_NVME
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called nvme.
+
+config BLK_DEV_NVME_SCSI
+	bool "SCSI emulation for NVMe device nodes"
+	depends on BLK_DEV_NVME
+	---help---
+	  This adds support for the SG_IO ioctl on the NVMe character
+	  and block devices nodes, as well a a translation for a small
+	  number of selected SCSI commands to NVMe commands to the NVMe
+	  driver.  If you don't know what this means you probably want
+	  to say N here, and if you know what it means you probably
+	  want to say N as well.
diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile
index a5fe23952586..51bf90871549 100644
--- a/drivers/nvme/host/Makefile
+++ b/drivers/nvme/host/Makefile
@@ -1,5 +1,6 @@
 
 obj-$(CONFIG_BLK_DEV_NVME)     += nvme.o
 
-lightnvm-$(CONFIG_NVM)	:= lightnvm.o
-nvme-y		+= pci.o scsi.o $(lightnvm-y)
+lightnvm-$(CONFIG_NVM)			:= lightnvm.o
+nvme-y					+= core.o pci.o $(lightnvm-y)
+nvme-$(CONFIG_BLK_DEV_NVME_SCSI)        += scsi.o
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
new file mode 100644
index 000000000000..c5bf001af559
--- /dev/null
+++ b/drivers/nvme/host/core.c
@@ -0,0 +1,1472 @@
+/*
+ * NVM Express device driver
+ * Copyright (c) 2011-2014, Intel Corporation.
+ *
+ * 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.
+ */
+
+#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/hdreg.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/list_sort.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/pr.h>
+#include <linux/ptrace.h>
+#include <linux/nvme_ioctl.h>
+#include <linux/t10-pi.h>
+#include <scsi/sg.h>
+#include <asm/unaligned.h>
+
+#include "nvme.h"
+
+#define NVME_MINORS		(1U << MINORBITS)
+
+static int nvme_major;
+module_param(nvme_major, int, 0);
+
+static int nvme_char_major;
+module_param(nvme_char_major, int, 0);
+
+static LIST_HEAD(nvme_ctrl_list);
+DEFINE_SPINLOCK(dev_list_lock);
+
+static struct class *nvme_class;
+
+static void nvme_free_ns(struct kref *kref)
+{
+	struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref);
+
+	if (ns->type == NVME_NS_LIGHTNVM)
+		nvme_nvm_unregister(ns->queue, ns->disk->disk_name);
+
+	spin_lock(&dev_list_lock);
+	ns->disk->private_data = NULL;
+	spin_unlock(&dev_list_lock);
+
+	nvme_put_ctrl(ns->ctrl);
+	put_disk(ns->disk);
+	kfree(ns);
+}
+
+static void nvme_put_ns(struct nvme_ns *ns)
+{
+	kref_put(&ns->kref, nvme_free_ns);
+}
+
+static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk)
+{
+	struct nvme_ns *ns;
+
+	spin_lock(&dev_list_lock);
+	ns = disk->private_data;
+	if (ns && !kref_get_unless_zero(&ns->kref))
+		ns = NULL;
+	spin_unlock(&dev_list_lock);
+
+	return ns;
+}
+
+void nvme_requeue_req(struct request *req)
+{
+	unsigned long flags;
+
+	blk_mq_requeue_request(req);
+	spin_lock_irqsave(req->q->queue_lock, flags);
+	if (!blk_queue_stopped(req->q))
+		blk_mq_kick_requeue_list(req->q);
+	spin_unlock_irqrestore(req->q->queue_lock, flags);
+}
+
+struct request *nvme_alloc_request(struct request_queue *q,
+		struct nvme_command *cmd, unsigned int flags)
+{
+	bool write = cmd->common.opcode & 1;
+	struct request *req;
+
+	req = blk_mq_alloc_request(q, write, flags);
+	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);
+	req->special = (void *)0;
+
+	return req;
+}
+
+/*
+ * Returns 0 on success.  If the result is negative, it's a Linux error code;
+ * if the result is positive, it's an NVM Express status code
+ */
+int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
+		void *buffer, unsigned bufflen, u32 *result, unsigned timeout)
+{
+	struct request *req;
+	int ret;
+
+	req = nvme_alloc_request(q, cmd, 0);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	req->timeout = timeout ? timeout : ADMIN_TIMEOUT;
+
+	if (buffer && bufflen) {
+		ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL);
+		if (ret)
+			goto out;
+	}
+
+	blk_execute_rq(req->q, NULL, req, 0);
+	if (result)
+		*result = (u32)(uintptr_t)req->special;
+	ret = req->errors;
+ out:
+	blk_mq_free_request(req);
+	return ret;
+}
+
+int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
+		void *buffer, unsigned bufflen)
+{
+	return __nvme_submit_sync_cmd(q, cmd, buffer, bufflen, NULL, 0);
+}
+
+int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
+		void __user *ubuffer, unsigned bufflen,
+		void __user *meta_buffer, unsigned meta_len, u32 meta_seed,
+		u32 *result, unsigned timeout)
+{
+	bool write = cmd->common.opcode & 1;
+	struct nvme_ns *ns = q->queuedata;
+	struct gendisk *disk = ns ? ns->disk : NULL;
+	struct request *req;
+	struct bio *bio = NULL;
+	void *meta = NULL;
+	int ret;
+
+	req = nvme_alloc_request(q, cmd, 0);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	req->timeout = timeout ? timeout : ADMIN_TIMEOUT;
+
+	if (ubuffer && bufflen) {
+		ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen,
+				GFP_KERNEL);
+		if (ret)
+			goto out;
+		bio = req->bio;
+
+		if (!disk)
+			goto submit;
+		bio->bi_bdev = bdget_disk(disk, 0);
+		if (!bio->bi_bdev) {
+			ret = -ENODEV;
+			goto out_unmap;
+		}
+
+		if (meta_buffer) {
+			struct bio_integrity_payload *bip;
+
+			meta = kmalloc(meta_len, GFP_KERNEL);
+			if (!meta) {
+				ret = -ENOMEM;
+				goto out_unmap;
+			}
+
+			if (write) {
+				if (copy_from_user(meta, meta_buffer,
+						meta_len)) {
+					ret = -EFAULT;
+					goto out_free_meta;
+				}
+			}
+
+			bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
+			if (IS_ERR(bip)) {
+				ret = PTR_ERR(bip);
+				goto out_free_meta;
+			}
+
+			bip->bip_iter.bi_size = meta_len;
+			bip->bip_iter.bi_sector = meta_seed;
+
+			ret = bio_integrity_add_page(bio, virt_to_page(meta),
+					meta_len, offset_in_page(meta));
+			if (ret != meta_len) {
+				ret = -ENOMEM;
+				goto out_free_meta;
+			}
+		}
+	}
+ submit:
+	blk_execute_rq(req->q, disk, req, 0);
+	ret = req->errors;
+	if (result)
+		*result = (u32)(uintptr_t)req->special;
+	if (meta && !ret && !write) {
+		if (copy_to_user(meta_buffer, meta, meta_len))
+			ret = -EFAULT;
+	}
+ out_free_meta:
+	kfree(meta);
+ out_unmap:
+	if (bio) {
+		if (disk && bio->bi_bdev)
+			bdput(bio->bi_bdev);
+		blk_rq_unmap_user(bio);
+	}
+ out:
+	blk_mq_free_request(req);
+	return ret;
+}
+
+int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
+		void __user *ubuffer, unsigned bufflen, u32 *result,
+		unsigned timeout)
+{
+	return __nvme_submit_user_cmd(q, cmd, ubuffer, bufflen, NULL, 0, 0,
+			result, timeout);
+}
+
+int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
+{
+	struct nvme_command c = { };
+	int error;
+
+	/* gcc-4.4.4 (at least) has issues with initializers and anon unions */
+	c.identify.opcode = nvme_admin_identify;
+	c.identify.cns = cpu_to_le32(1);
+
+	*id = kmalloc(sizeof(struct nvme_id_ctrl), GFP_KERNEL);
+	if (!*id)
+		return -ENOMEM;
+
+	error = nvme_submit_sync_cmd(dev->admin_q, &c, *id,
+			sizeof(struct nvme_id_ctrl));
+	if (error)
+		kfree(*id);
+	return error;
+}
+
+static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *ns_list)
+{
+	struct nvme_command c = { };
+
+	c.identify.opcode = nvme_admin_identify;
+	c.identify.cns = cpu_to_le32(2);
+	c.identify.nsid = cpu_to_le32(nsid);
+	return nvme_submit_sync_cmd(dev->admin_q, &c, ns_list, 0x1000);
+}
+
+int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid,
+		struct nvme_id_ns **id)
+{
+	struct nvme_command c = { };
+	int error;
+
+	/* gcc-4.4.4 (at least) has issues with initializers and anon unions */
+	c.identify.opcode = nvme_admin_identify,
+	c.identify.nsid = cpu_to_le32(nsid),
+
+	*id = kmalloc(sizeof(struct nvme_id_ns), GFP_KERNEL);
+	if (!*id)
+		return -ENOMEM;
+
+	error = nvme_submit_sync_cmd(dev->admin_q, &c, *id,
+			sizeof(struct nvme_id_ns));
+	if (error)
+		kfree(*id);
+	return error;
+}
+
+int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid,
+					dma_addr_t dma_addr, u32 *result)
+{
+	struct nvme_command c;
+
+	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.fid = cpu_to_le32(fid);
+
+	return __nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0, result, 0);
+}
+
+int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
+					dma_addr_t dma_addr, u32 *result)
+{
+	struct nvme_command c;
+
+	memset(&c, 0, sizeof(c));
+	c.features.opcode = nvme_admin_set_features;
+	c.features.prp1 = cpu_to_le64(dma_addr);
+	c.features.fid = cpu_to_le32(fid);
+	c.features.dword11 = cpu_to_le32(dword11);
+
+	return __nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0, result, 0);
+}
+
+int nvme_get_log_page(struct nvme_ctrl *dev, struct nvme_smart_log **log)
+{
+	struct nvme_command c = { };
+	int error;
+
+	c.common.opcode = nvme_admin_get_log_page,
+	c.common.nsid = cpu_to_le32(0xFFFFFFFF),
+	c.common.cdw10[0] = cpu_to_le32(
+			(((sizeof(struct nvme_smart_log) / 4) - 1) << 16) |
+			 NVME_LOG_SMART),
+
+	*log = kmalloc(sizeof(struct nvme_smart_log), GFP_KERNEL);
+	if (!*log)
+		return -ENOMEM;
+
+	error = nvme_submit_sync_cmd(dev->admin_q, &c, *log,
+			sizeof(struct nvme_smart_log));
+	if (error)
+		kfree(*log);
+	return error;
+}
+
+int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
+{
+	u32 q_count = (*count - 1) | ((*count - 1) << 16);
+	u32 result;
+	int status, nr_io_queues;
+
+	status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, 0,
+			&result);
+	if (status)
+		return status;
+
+	nr_io_queues = min(result & 0xffff, result >> 16) + 1;
+	*count = min(*count, nr_io_queues);
+	return 0;
+}
+
+static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
+{
+	struct nvme_user_io io;
+	struct nvme_command c;
+	unsigned length, meta_len;
+	void __user *metadata;
+
+	if (copy_from_user(&io, uio, sizeof(io)))
+		return -EFAULT;
+
+	switch (io.opcode) {
+	case nvme_cmd_write:
+	case nvme_cmd_read:
+	case nvme_cmd_compare:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	length = (io.nblocks + 1) << ns->lba_shift;
+	meta_len = (io.nblocks + 1) * ns->ms;
+	metadata = (void __user *)(uintptr_t)io.metadata;
+
+	if (ns->ext) {
+		length += meta_len;
+		meta_len = 0;
+	} else if (meta_len) {
+		if ((io.metadata & 3) || !io.metadata)
+			return -EINVAL;
+	}
+
+	memset(&c, 0, sizeof(c));
+	c.rw.opcode = io.opcode;
+	c.rw.flags = io.flags;
+	c.rw.nsid = cpu_to_le32(ns->ns_id);
+	c.rw.slba = cpu_to_le64(io.slba);
+	c.rw.length = cpu_to_le16(io.nblocks);
+	c.rw.control = cpu_to_le16(io.control);
+	c.rw.dsmgmt = cpu_to_le32(io.dsmgmt);
+	c.rw.reftag = cpu_to_le32(io.reftag);
+	c.rw.apptag = cpu_to_le16(io.apptag);
+	c.rw.appmask = cpu_to_le16(io.appmask);
+
+	return __nvme_submit_user_cmd(ns->queue, &c,
+			(void __user *)(uintptr_t)io.addr, length,
+			metadata, meta_len, io.slba, NULL, 0);
+}
+
+static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
+			struct nvme_passthru_cmd __user *ucmd)
+{
+	struct nvme_passthru_cmd cmd;
+	struct nvme_command c;
+	unsigned timeout = 0;
+	int status;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
+		return -EFAULT;
+
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = cmd.opcode;
+	c.common.flags = cmd.flags;
+	c.common.nsid = cpu_to_le32(cmd.nsid);
+	c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
+	c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
+	c.common.cdw10[0] = cpu_to_le32(cmd.cdw10);
+	c.common.cdw10[1] = cpu_to_le32(cmd.cdw11);
+	c.common.cdw10[2] = cpu_to_le32(cmd.cdw12);
+	c.common.cdw10[3] = cpu_to_le32(cmd.cdw13);
+	c.common.cdw10[4] = cpu_to_le32(cmd.cdw14);
+	c.common.cdw10[5] = cpu_to_le32(cmd.cdw15);
+
+	if (cmd.timeout_ms)
+		timeout = msecs_to_jiffies(cmd.timeout_ms);
+
+	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
+			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
+			&cmd.result, timeout);
+	if (status >= 0) {
+		if (put_user(cmd.result, &ucmd->result))
+			return -EFAULT;
+	}
+
+	return status;
+}
+
+static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
+		unsigned int cmd, unsigned long arg)
+{
+	struct nvme_ns *ns = bdev->bd_disk->private_data;
+
+	switch (cmd) {
+	case NVME_IOCTL_ID:
+		force_successful_syscall_return();
+		return ns->ns_id;
+	case NVME_IOCTL_ADMIN_CMD:
+		return nvme_user_cmd(ns->ctrl, NULL, (void __user *)arg);
+	case NVME_IOCTL_IO_CMD:
+		return nvme_user_cmd(ns->ctrl, ns, (void __user *)arg);
+	case NVME_IOCTL_SUBMIT_IO:
+		return nvme_submit_io(ns, (void __user *)arg);
+#ifdef CONFIG_BLK_DEV_NVME_SCSI
+	case SG_GET_VERSION_NUM:
+		return nvme_sg_get_version_num((void __user *)arg);
+	case SG_IO:
+		return nvme_sg_io(ns, (void __user *)arg);
+#endif
+	default:
+		return -ENOTTY;
+	}
+}
+
+#ifdef CONFIG_COMPAT
+static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
+			unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case SG_IO:
+		return -ENOIOCTLCMD;
+	}
+	return nvme_ioctl(bdev, mode, cmd, arg);
+}
+#else
+#define nvme_compat_ioctl	NULL
+#endif
+
+static int nvme_open(struct block_device *bdev, fmode_t mode)
+{
+	return nvme_get_ns_from_disk(bdev->bd_disk) ? 0 : -ENXIO;
+}
+
+static void nvme_release(struct gendisk *disk, fmode_t mode)
+{
+	nvme_put_ns(disk->private_data);
+}
+
+static int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
+{
+	/* some standard values */
+	geo->heads = 1 << 6;
+	geo->sectors = 1 << 5;
+	geo->cylinders = get_capacity(bdev->bd_disk) >> 11;
+	return 0;
+}
+
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+static void nvme_init_integrity(struct nvme_ns *ns)
+{
+	struct blk_integrity integrity;
+
+	switch (ns->pi_type) {
+	case NVME_NS_DPS_PI_TYPE3:
+		integrity.profile = &t10_pi_type3_crc;
+		break;
+	case NVME_NS_DPS_PI_TYPE1:
+	case NVME_NS_DPS_PI_TYPE2:
+		integrity.profile = &t10_pi_type1_crc;
+		break;
+	default:
+		integrity.profile = NULL;
+		break;
+	}
+	integrity.tuple_size = ns->ms;
+	blk_integrity_register(ns->disk, &integrity);
+	blk_queue_max_integrity_segments(ns->queue, 1);
+}
+#else
+static void nvme_init_integrity(struct nvme_ns *ns)
+{
+}
+#endif /* CONFIG_BLK_DEV_INTEGRITY */
+
+static void nvme_config_discard(struct nvme_ns *ns)
+{
+	u32 logical_block_size = queue_logical_block_size(ns->queue);
+	ns->queue->limits.discard_zeroes_data = 0;
+	ns->queue->limits.discard_alignment = logical_block_size;
+	ns->queue->limits.discard_granularity = logical_block_size;
+	blk_queue_max_discard_sectors(ns->queue, 0xffffffff);
+	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
+}
+
+static int nvme_revalidate_disk(struct gendisk *disk)
+{
+	struct nvme_ns *ns = disk->private_data;
+	struct nvme_id_ns *id;
+	u8 lbaf, pi_type;
+	u16 old_ms;
+	unsigned short bs;
+
+	if (nvme_identify_ns(ns->ctrl, ns->ns_id, &id)) {
+		dev_warn(ns->ctrl->dev, "%s: Identify failure nvme%dn%d\n",
+				__func__, ns->ctrl->instance, ns->ns_id);
+		return -ENODEV;
+	}
+	if (id->ncap == 0) {
+		kfree(id);
+		return -ENODEV;
+	}
+
+	if (nvme_nvm_ns_supported(ns, id) && ns->type != NVME_NS_LIGHTNVM) {
+		if (nvme_nvm_register(ns->queue, disk->disk_name)) {
+			dev_warn(ns->ctrl->dev,
+				"%s: LightNVM init failure\n", __func__);
+			kfree(id);
+			return -ENODEV;
+		}
+		ns->type = NVME_NS_LIGHTNVM;
+	}
+
+	if (ns->ctrl->vs >= NVME_VS(1, 1))
+		memcpy(ns->eui, id->eui64, sizeof(ns->eui));
+	if (ns->ctrl->vs >= NVME_VS(1, 2))
+		memcpy(ns->uuid, id->nguid, sizeof(ns->uuid));
+
+	old_ms = ns->ms;
+	lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
+	ns->lba_shift = id->lbaf[lbaf].ds;
+	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
+	ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
+
+	/*
+	 * If identify namespace failed, use default 512 byte block size so
+	 * block layer can use before failing read/write for 0 capacity.
+	 */
+	if (ns->lba_shift == 0)
+		ns->lba_shift = 9;
+	bs = 1 << ns->lba_shift;
+	/* XXX: PI implementation requires metadata equal t10 pi tuple size */
+	pi_type = ns->ms == sizeof(struct t10_pi_tuple) ?
+					id->dps & NVME_NS_DPS_PI_MASK : 0;
+
+	blk_mq_freeze_queue(disk->queue);
+	if (blk_get_integrity(disk) && (ns->pi_type != pi_type ||
+				ns->ms != old_ms ||
+				bs != queue_logical_block_size(disk->queue) ||
+				(ns->ms && ns->ext)))
+		blk_integrity_unregister(disk);
+
+	ns->pi_type = pi_type;
+	blk_queue_logical_block_size(ns->queue, bs);
+
+	if (ns->ms && !blk_get_integrity(disk) && !ns->ext)
+		nvme_init_integrity(ns);
+	if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk))
+		set_capacity(disk, 0);
+	else
+		set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
+
+	if (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM)
+		nvme_config_discard(ns);
+	blk_mq_unfreeze_queue(disk->queue);
+
+	kfree(id);
+	return 0;
+}
+
+static char nvme_pr_type(enum pr_type type)
+{
+	switch (type) {
+	case PR_WRITE_EXCLUSIVE:
+		return 1;
+	case PR_EXCLUSIVE_ACCESS:
+		return 2;
+	case PR_WRITE_EXCLUSIVE_REG_ONLY:
+		return 3;
+	case PR_EXCLUSIVE_ACCESS_REG_ONLY:
+		return 4;
+	case PR_WRITE_EXCLUSIVE_ALL_REGS:
+		return 5;
+	case PR_EXCLUSIVE_ACCESS_ALL_REGS:
+		return 6;
+	default:
+		return 0;
+	}
+};
+
+static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
+				u64 key, u64 sa_key, u8 op)
+{
+	struct nvme_ns *ns = bdev->bd_disk->private_data;
+	struct nvme_command c;
+	u8 data[16] = { 0, };
+
+	put_unaligned_le64(key, &data[0]);
+	put_unaligned_le64(sa_key, &data[8]);
+
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = op;
+	c.common.nsid = cpu_to_le32(ns->ns_id);
+	c.common.cdw10[0] = cpu_to_le32(cdw10);
+
+	return nvme_submit_sync_cmd(ns->queue, &c, data, 16);
+}
+
+static int nvme_pr_register(struct block_device *bdev, u64 old,
+		u64 new, unsigned flags)
+{
+	u32 cdw10;
+
+	if (flags & ~PR_FL_IGNORE_KEY)
+		return -EOPNOTSUPP;
+
+	cdw10 = old ? 2 : 0;
+	cdw10 |= (flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0;
+	cdw10 |= (1 << 30) | (1 << 31); /* PTPL=1 */
+	return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_register);
+}
+
+static int nvme_pr_reserve(struct block_device *bdev, u64 key,
+		enum pr_type type, unsigned flags)
+{
+	u32 cdw10;
+
+	if (flags & ~PR_FL_IGNORE_KEY)
+		return -EOPNOTSUPP;
+
+	cdw10 = nvme_pr_type(type) << 8;
+	cdw10 |= ((flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0);
+	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_acquire);
+}
+
+static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new,
+		enum pr_type type, bool abort)
+{
+	u32 cdw10 = nvme_pr_type(type) << 8 | abort ? 2 : 1;
+	return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire);
+}
+
+static int nvme_pr_clear(struct block_device *bdev, u64 key)
+{
+	u32 cdw10 = 1 | (key ? 1 << 3 : 0);
+	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_register);
+}
+
+static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
+{
+	u32 cdw10 = nvme_pr_type(type) << 8 | key ? 1 << 3 : 0;
+	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
+}
+
+static const struct pr_ops nvme_pr_ops = {
+	.pr_register	= nvme_pr_register,
+	.pr_reserve	= nvme_pr_reserve,
+	.pr_release	= nvme_pr_release,
+	.pr_preempt	= nvme_pr_preempt,
+	.pr_clear	= nvme_pr_clear,
+};
+
+static const struct block_device_operations nvme_fops = {
+	.owner		= THIS_MODULE,
+	.ioctl		= nvme_ioctl,
+	.compat_ioctl	= nvme_compat_ioctl,
+	.open		= nvme_open,
+	.release	= nvme_release,
+	.getgeo		= nvme_getgeo,
+	.revalidate_disk= nvme_revalidate_disk,
+	.pr_ops		= &nvme_pr_ops,
+};
+
+static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
+{
+	unsigned long timeout =
+		((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies;
+	u32 csts, bit = enabled ? NVME_CSTS_RDY : 0;
+	int ret;
+
+	while ((ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts)) == 0) {
+		if ((csts & NVME_CSTS_RDY) == bit)
+			break;
+