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
  ...

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));

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;

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;

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;

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 *);

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.

drivers/nvme/host/Makefile

 
 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

drivers/nvme/host/lightnvm.c

@@ -294,7 +294,6 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
 static int nvme_nvm_identity(struct nvm_dev *nvmdev, struct nvm_id *nvm_id)
 {
 	struct nvme_ns *ns = nvmdev->q->queuedata;
-	struct nvme_dev *dev = ns->dev;
 	struct nvme_nvm_id *nvme_nvm_id;
 	struct nvme_nvm_command c = {};
 	int ret;
@@ -307,7 +306,7 @@ static int nvme_nvm_identity(struct nvm_dev *nvmdev, struct nvm_id *nvm_id)
 	if (!nvme_nvm_id)
 		return -ENOMEM;
 
-	ret = nvme_submit_sync_cmd(dev->admin_q, (struct nvme_command *)&c,
+	ret = nvme_submit_sync_cmd(ns->ctrl->admin_q, (struct nvme_command *)&c,
 				nvme_nvm_id, sizeof(struct nvme_nvm_id));
 	if (ret) {
 		ret = -EIO;
@@ -332,9 +331,8 @@ static int nvme_nvm_get_l2p_tbl(struct nvm_dev *nvmdev, u64 slba, u32 nlb,
 				nvm_l2p_update_fn *update_l2p, void *priv)
 {
 	struct nvme_ns *ns = nvmdev->q->queuedata;
-	struct nvme_dev *dev = ns->dev;
 	struct nvme_nvm_command c = {};
-	u32 len = queue_max_hw_sectors(dev->admin_q) << 9;
+	u32 len = queue_max_hw_sectors(ns->ctrl->admin_q) << 9;
 	u32 nlb_pr_rq = len / sizeof(u64);
 	u64 cmd_slba = slba;
 	void *entries;
@@ -352,10 +350,10 @@ static int nvme_nvm_get_l2p_tbl(struct nvm_dev *nvmdev, u64 slba, u32 nlb,
 		c.l2p.slba = cpu_to_le64(cmd_slba);
 		c.l2p.nlb = cpu_to_le32(cmd_nlb);
 
-		ret = nvme_submit_sync_cmd(dev->admin_q,
+		ret = nvme_submit_sync_cmd(ns->ctrl->admin_q,
 				(struct nvme_command *)&c, entries, len);
 		if (ret) {
-			dev_err(dev->dev, "L2P table transfer failed (%d)\n",
+			dev_err(ns->ctrl->dev, "L2P table transfer failed (%d)\n",
 									ret);
 			ret = -EIO;
 			goto out;
@@ -381,7 +379,7 @@ static int nvme_nvm_get_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr ppa,
 {
 	struct request_queue *q = nvmdev->q;
 	struct nvme_ns *ns = q->queuedata;
-	struct nvme_dev *dev = ns->dev;
+	struct nvme_ctrl *ctrl = ns->ctrl;
 	struct nvme_nvm_command c = {};
 	struct nvme_nvm_bb_tbl *bb_tbl;
 	int tblsz = sizeof(struct nvme_nvm_bb_tbl) + nr_blocks;
@@ -395,30 +393,30 @@ static int nvme_nvm_get_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr ppa,
 	if (!bb_tbl)
 		return -ENOMEM;
 
-	ret = nvme_submit_sync_cmd(dev->admin_q, (struct nvme_command *)&c,
+	ret = nvme_submit_sync_cmd(ctrl->admin_q, (struct nvme_command *)&c,
 								bb_tbl, tblsz);
 	if (ret) {
-		dev_err(dev->dev, "get bad block table failed (%d)\n", ret);
+		dev_err(ctrl->dev, "get bad block table failed (%d)\n", ret);
 		ret = -EIO;
 		goto out;
 	}
 
 	if (bb_tbl->tblid[0] != 'B' || bb_tbl->tblid[1] != 'B' ||
 		bb_tbl->tblid[2] != 'L' || bb_tbl->tblid[3] != 'T') {
-		dev_err(dev->dev, "bbt format mismatch\n");
+		dev_err(ctrl->dev, "bbt format mismatch\n");
 		ret = -EINVAL;
 		goto out;
 	}
 
 	if (le16_to_cpu(bb_tbl->verid) != 1) {
 		ret = -EINVAL;
-		dev_err(dev->dev, "bbt version not supported\n");
+		dev_err(ctrl->dev, "bbt version not supported\n");
 		goto out;
 	}
 
 	if (le32_to_cpu(bb_tbl->tblks) != nr_blocks) {
 		ret = -EINVAL;
-		dev_err(dev->dev, "bbt unsuspected blocks returned (%u!=%u)",
+		dev_err(ctrl->dev, "bbt unsuspected blocks returned (%u!=%u)",
 					le32_to_cpu(bb_tbl->tblks), nr_blocks);
 		goto out;
 	}
@@ -434,7 +432,6 @@ static int nvme_nvm_set_bb_tbl(struct nvm_dev *nvmdev, struct nvm_rq *rqd,
 								int type)
 {
 	struct nvme_ns *ns = nvmdev->q->queuedata;
-	struct nvme_dev *dev = ns->dev;
 	struct nvme_nvm_command c = {};
 	int ret = 0;
 
@@ -444,10 +441,10 @@ static int nvme_nvm_set_bb_tbl(struct nvm_dev *nvmdev, struct nvm_rq *rqd,
 	c.set_bb.nlb = cpu_to_le16(rqd->nr_pages - 1);
 	c.set_bb.value = type;
 
-	ret = nvme_submit_sync_cmd(dev->admin_q, (struct nvme_command *)&c,
+	ret = nvme_submit_sync_cmd(ns->ctrl->admin_q, (struct nvme_command *)&c,
 								NULL, 0);
 	if (ret)
-		dev_err(dev->dev, "set bad block table failed (%d)\n", ret);
+		dev_err(ns->ctrl->dev, "set bad block table failed (%d)\n", ret);
 	return ret;
 }
 
@@ -532,9 +529,8 @@ static int nvme_nvm_erase_block(struct nvm_dev *dev, struct nvm_rq *rqd)
 static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name)
 {
 	struct nvme_ns *ns = nvmdev->q->queuedata;
-	struct nvme_dev *dev = ns->dev;
 
-	return dma_pool_create(name, dev->dev, PAGE_SIZE, PAGE_SIZE, 0);
+	return dma_pool_create(name, ns->ctrl->dev, PAGE_SIZE, PAGE_SIZE, 0);
 }
 
 static void nvme_nvm_destroy_dma_pool(void *pool)
@@ -592,8 +588,9 @@ void nvme_nvm_unregister(struct request_queue *q, char *disk_name)
 
 int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id)
 {
-	struct nvme_dev *dev = ns->dev;
-	struct pci_dev *pdev = to_pci_dev(dev->dev);
+	struct nvme_ctrl *ctrl = ns->ctrl;
+	/* XXX: this is poking into PCI structures from generic code! */
+	struct pci_dev *pdev = to_pci_dev(ctrl->dev);
 
 	/* QEMU NVMe simulator - PCI ID + Vendor specific bit */
 	if (pdev->vendor == PCI_VENDOR_ID_CNEX &&

drivers/nvme/host/nvme.h

@@ -19,58 +19,77 @@
 #include <linux/kref.h>
 #include <linux/blk-mq.h>
 
+enum {
+	/*
+	 * Driver internal status code for commands that were cancelled due
+	 * to timeouts or controller shutdown.  The value is negative so
+	 * that it a) doesn't overlap with the unsigned hardware error codes,
+	 * and b) can easily be tested for.
+	 */
+	NVME_SC_CANCELLED		= -EINTR,
+};
+
 extern unsigned char nvme_io_timeout;
 #define NVME_IO_TIMEOUT	(nvme_io_timeout * HZ)
 
+extern unsigned char admin_timeout;
+#define ADMIN_TIMEOUT	(admin_timeout * HZ)
+
+extern unsigned char shutdown_timeout;
+#define SHUTDOWN_TIMEOUT	(shutdown_timeout * HZ)
+
 enum {
 	NVME_NS_LBA		= 0,
 	NVME_NS_LIGHTNVM	= 1,
 };
 
 /*
- * Represents an NVM Express device.  Each nvme_dev is a PCI function.
+ * List of workarounds for devices that required behavior not specified in
+ * the standard.
  */
-struct nvme_dev {
-	struct list_head node;
-	struct nvme_queue **queues;
+enum nvme_quirks {
+	/*
+	 * Prefers I/O aligned to a stripe size specified in a vendor
+	 * specific Identify field.
+	 */
+	NVME_QUIRK_STRIPE_SIZE			= (1 << 0),
+
+	/*
+	 * The controller doesn't handle Identify value others than 0 or 1
+	 * correctly.
+	 */
+	NVME_QUIRK_IDENTIFY_CNS			= (1 << 1),
+};
+
+struct nvme_ctrl {
+	const struct nvme_ctrl_ops *ops;
 	struct request_queue *admin_q;
-	struct blk_mq_tag_set tagset;
-	struct blk_mq_tag_set admin_tagset;
-	u32 __iomem *dbs;
 	struct device *dev;
-	struct dma_pool *prp_page_pool;
-	struct dma_pool *prp_small_pool;
+	struct kref kref;
 	int instance;
-	unsigned queue_count;
-	unsigned online_queues;
-	unsigned max_qid;
-	int q_depth;
-	u32 db_stride;
-	u32 ctrl_config;
-	struct msix_entry *entry;
-	struct nvme_bar __iomem *bar;
+	struct blk_mq_tag_set *tagset;
 	struct list_head namespaces;
-	struct kref kref;
-	struct device *device;
-	struct work_struct reset_work;
-	struct work_struct probe_work;
-	struct work_struct scan_work;
+	struct mutex namespaces_mutex;
+	struct device *device;	/* char device */
+	struct list_head node;
+
 	char name[12];
 	char serial[20];
 	char model[40];
 	char firmware_rev[8];
-	bool subsystem;
+
+	u32 ctrl_config;
+
+	u32 page_size;
 	u32 max_hw_sectors;
 	u32 stripe_size;
-	u32 page_size;
-	void __iomem *cmb;
-	dma_addr_t cmb_dma_addr;
-	u64 cmb_size;
-	u32 cmbsz;
 	u16 oncs;
-	u16 abort_limit;
+	atomic_t abort_limit;
 	u8 event_limit;
 	u8 vwc;
+	u32 vs;
+	bool subsystem;
+	unsigned long quirks;
 };
 
 /*
@@ -79,11 +98,14 @@ struct nvme_dev {
 struct nvme_ns {
 	struct list_head list;
 
-	struct nvme_dev *dev;
+	struct nvme_ctrl *ctrl;
 	struct request_queue *queue;
 	struct gendisk *disk;
 	struct kref kref;
 
+	u8 eui[8];
+	u8 uuid[16];
+
 	unsigned ns_id;
 	int lba_shift;
 	u16 ms;
@@ -94,41 +116,156 @@ struct nvme_ns {
 	u32 mode_select_block_len;
 };
 
-/*
- * The nvme_iod describes the data in an I/O, including the list of PRP
- * entries.  You can't see it in this data structure because C doesn't let
- * me express that.  Use nvme_alloc_iod to ensure there's enough space
- * allocated to store the PRP list.
- */
-struct nvme_iod {
-	unsigned long private;	/* For the use of the submitter of the I/O */
-	int npages;		/* In the PRP list. 0 means small pool in use */
-	int offset;		/* Of PRP list */
-	int nents;		/* Used in scatterlist */
-	int length;		/* Of data, in bytes */
-	dma_addr_t first_dma;
-	struct scatterlist meta_sg[1]; /* metadata requires single contiguous buffer */
-	struct scatterlist sg[0];
+struct nvme_ctrl_ops {
+	int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val);
+	int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val);
+	int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
+	bool (*io_incapable)(struct nvme_ctrl *ctrl);
+	int (*reset_ctrl)(struct nvme_ctrl *ctrl);
+	void (*free_ctrl)(struct nvme_ctrl *ctrl);
 };
 
+static inline bool nvme_ctrl_ready(struct nvme_ctrl *ctrl)
+{
+	u32 val = 0;
+
+	if (ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &val))
+		return false;
+	return val & NVME_CSTS_RDY;
+}
+
+static inline bool nvme_io_incapable(struct nvme_ctrl *ctrl)
+{
+	u32 val = 0;
+
+	if (ctrl->ops->io_incapable(ctrl))
+		return false;
+	if (ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &val))
+		return false;
+	return val & NVME_CSTS_CFS;
+}
+
+static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl)
+{
+	if (!ctrl->subsystem)
+		return -ENOTTY;
+	return ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, 0x4E564D65);
+}
+
 static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector)
 {
 	return (sector >> (ns->lba_shift - 9));
 }
 
+static inline void nvme_setup_flush(struct nvme_ns *ns,
+		struct nvme_command *cmnd)
+{
+	memset(cmnd, 0, sizeof(*cmnd));
+	cmnd->common.opcode = nvme_cmd_flush;
+	cmnd->common.nsid = cpu_to_le32(ns->ns_id);
+}
+
+static inline void nvme_setup_rw(struct nvme_ns *ns, struct request *req,
+		struct nvme_command *cmnd)
+{
+	u16 control = 0;
+	u32 dsmgmt = 0;
+
+	if (req->cmd_flags & REQ_FUA)
+		control |= NVME_RW_FUA;
+	if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD))
+		control |= NVME_RW_LR;
+
+	if (req->cmd_flags & REQ_RAHEAD)
+		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
+
+	memset(cmnd, 0, sizeof(*cmnd));
+	cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
+	cmnd->rw.command_id = req->tag;
+	cmnd->rw.nsid = cpu_to_le32(ns->ns_id);
+	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
+	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
+
+	if (ns->ms) {
+		switch (ns->pi_type) {
+		case NVME_NS_DPS_PI_TYPE3:
+			control |= NVME_RW_PRINFO_PRCHK_GUARD;
+			break;
+		case NVME_NS_DPS_PI_TYPE1:
+		case NVME_NS_DPS_PI_TYPE2:
+			control |= NVME_RW_PRINFO_PRCHK_GUARD |
+					NVME_RW_PRINFO_PRCHK_REF;
+			cmnd->rw.reftag = cpu_to_le32(
+					nvme_block_nr(ns, blk_rq_pos(req)));
+			break;
+		}
+		if (!blk_integrity_rq(req))
+			control |= NVME_RW_PRINFO_PRACT;
+	}
+
+	cmnd->rw.control = cpu_to_le16(control);
+	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
+}
+
+
+static inline int nvme_error_status(u16 status)
+{
+	switch (status & 0x7ff) {
+	case NVME_SC_SUCCESS:
+		return 0;
+	case NVME_SC_CAP_EXCEEDED:
+		return -ENOSPC;
+	default:
+		return -EIO;
+	}
+}
+
+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;
+}
+
+int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap);
+int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap);
+int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl);
+int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
+		const struct nvme_ctrl_ops *ops, unsigned long quirks);
+void nvme_uninit_ctrl(struct nvme_ctrl *ctrl);
+void nvme_put_ctrl(struct nvme_ctrl *ctrl);
+int nvme_init_identify(struct nvme_ctrl *ctrl);
+
+void nvme_scan_namespaces(struct nvme_ctrl *ctrl);
+void nvme_remove_namespaces(struct nvme_ctrl *ctrl);
+
+void nvme_stop_queues(struct nvme_ctrl *ctrl);
+void nvme_start_queues(struct nvme_ctrl *ctrl);
+
+struct request *nvme_alloc_request(struct request_queue *q,
+		struct nvme_command *cmd, unsigned int flags);
+void nvme_requeue_req(struct request *req);
 int nvme_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,
-		void *buffer, void __user *ubuffer, unsigned bufflen,
+		void *buffer, unsigned bufflen,  u32 *result, unsigned timeout);
+int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
+		void __user *ubuffer, unsigned bufflen, u32 *result,
+		unsigned timeout);
+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);
-int nvme_identify_ctrl(struct nvme_dev *dev, struct nvme_id_ctrl **id);
-int nvme_identify_ns(struct nvme_dev *dev, unsigned nsid,
+int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id);
+int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid,
 		struct nvme_id_ns **id);
-int nvme_get_log_page(struct nvme_dev *dev, struct nvme_smart_log **log);
-int nvme_get_features(struct nvme_dev *dev, unsigned fid, unsigned nsid,
+int nvme_get_log_page(struct nvme_ctrl *dev, struct nvme_smart_log **log);
+int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid,
 			dma_addr_t dma_addr, u32 *result);
-int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11,
+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);
+
+extern spinlock_t dev_list_lock;
 
 struct sg_io_hdr;
 
@@ -154,4 +291,7 @@ static inline int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *i
 }
 #endif /* CONFIG_NVM */
 
+int __init nvme_core_init(void);
+void nvme_core_exit(void);
+
 #endif /* _NVME_H */

drivers/target/target_core_iblock.c

@@ -615,9 +615,9 @@ iblock_alloc_bip(struct se_cmd *cmd, struct bio *bio)
 	}
 
 	bip = bio_integrity_alloc(bio, GFP_NOIO, cmd->t_prot_nents);
-	if (!bip) {
+	if (IS_ERR(bip)) {
 		pr_err("Unable to allocate bio_integrity_payload\n");
-		return -ENOMEM;
+		return PTR_ERR(bip);
 	}
 
 	bip->bip_iter.bi_size = (cmd->data_length / dev->dev_attrib.block_size) *

include/linux/aer.h

@@ -7,6 +7,7 @@
 #ifndef _AER_H_
 #define _AER_H_
 
+#include <linux/errno.h>
 #include <linux/types.h>
 
 #define AER_NONFATAL			0

include/linux/bio.h

@@ -318,16 +318,6 @@ enum bip_flags {
 	BIP_IP_CHECKSUM		= 1 << 4, /* IP checksum */
 };
 
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-
-static inline struct bio_integrity_payload *bio_integrity(struct bio *bio)
-{
-	if (bio->bi_rw & REQ_INTEGRITY)
-		return bio->bi_integrity;
-
-	return NULL;
-}
-
 /*
  * bio integrity payload
  */
@@ -349,6 +339,16 @@ struct bio_integrity_payload {
 	struct bio_vec		bip_inline_vecs[0];/* embedded bvec array */
 };
 
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+
+static inline struct bio_integrity_payload *bio_integrity(struct bio *bio)
+{
+	if (bio->bi_rw & REQ_INTEGRITY)
+		return bio->bi_integrity;
+
+	return NULL;
+}
+
 static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
 {
 	struct bio_integrity_payload *bip = bio_integrity(bio);
@@ -795,6 +795,18 @@ static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
 	return false;
 }
 
+static inline void *bio_integrity_alloc(struct bio * bio, gfp_t gfp,
+								unsigned int nr)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
+					unsigned int len, unsigned int offset)
+{
+	return 0;
+}
+
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 #endif /* CONFIG_BLOCK */

include/linux/blk_types.h

@@ -188,7 +188,6 @@ enum rq_flag_bits {
 	__REQ_PM,		/* runtime pm request */
 	__REQ_HASHED,		/* on IO scheduler merge hash */
 	__REQ_MQ_INFLIGHT,	/* track inflight for MQ */
-	__REQ_NO_TIMEOUT,	/* requests may never expire */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -242,7 +241,6 @@ enum rq_flag_bits {
 #define REQ_PM			(1ULL << __REQ_PM)
 #define REQ_HASHED		(1ULL << __REQ_HASHED)
 #define REQ_MQ_INFLIGHT		(1ULL << __REQ_MQ_INFLIGHT)
-#define REQ_NO_TIMEOUT		(1ULL << __REQ_NO_TIMEOUT)
 
 typedef unsigned int blk_qc_t;
 #define BLK_QC_T_NONE	-1U

include/linux/blkdev.h

@@ -409,6 +409,7 @@ struct request_queue {
 
 	unsigned int		rq_timeout;
 	struct timer_list	timeout;
+	struct work_struct	timeout_work;
 	struct list_head	timeout_list;
 
 	struct list_head	icq_list;

include/linux/nvme.h

@@ -17,20 +17,19 @@
 
 #include <linux/types.h>
 
-struct nvme_bar {
-	__u64			cap;	/* Controller Capabilities */
-	__u32			vs;	/* Version */
-	__u32			intms;	/* Interrupt Mask Set */
-	__u32			intmc;	/* Interrupt Mask Clear */
-	__u32			cc;	/* Controller Configuration */
-	__u32			rsvd1;	/* Reserved */
-	__u32			csts;	/* Controller Status */
-	__u32			nssr;	/* Subsystem Reset */
-	__u32			aqa;	/* Admin Queue Attributes */
-	__u64			asq;	/* Admin SQ Base Address */
-	__u64			acq;	/* Admin CQ Base Address */
-	__u32			cmbloc; /* Controller Memory Buffer Location */
-	__u32			cmbsz;  /* Controller Memory Buffer Size */
+enum {
+	NVME_REG_CAP	= 0x0000,	/* Controller Capabilities */
+	NVME_REG_VS	= 0x0008,	/* Version */
+	NVME_REG_INTMS	= 0x000c,	/* Interrupt Mask Set */
+	NVME_REG_INTMC	= 0x0010,	/* Interrupt Mask Set */
+	NVME_REG_CC	= 0x0014,	/* Controller Configuration */
+	NVME_REG_CSTS	= 0x001c,	/* Controller Status */
+	NVME_REG_NSSR	= 0x0020,	/* NVM Subsystem Reset */
+	NVME_REG_AQA	= 0x0024,	/* Admin Queue Attributes */
+	NVME_REG_ASQ	= 0x0028,	/* Admin SQ Base Address */
+	NVME_REG_ACQ	= 0x0030,	/* Admin SQ Base Address */
+	NVME_REG_CMBLOC = 0x0038,	/* Controller Memory Buffer Location */
+	NVME_REG_CMBSZ	= 0x003c,	/* Controller Memory Buffer Size */
 };
 
 #define NVME_CAP_MQES(cap)	((cap) & 0xffff)

include/uapi/linux/Kbuild

@@ -307,7 +307,7 @@ header-y += nfs_mount.h
 header-y += nl80211.h
 header-y += n_r3964.h
 header-y += nubus.h
-header-y += nvme.h
+header-y += nvme_ioctl.h
 header-y += nvram.h
 header-y += omap3isp.h
 header-y += omapfb.h