Merge git://git.infradead.org/users/willy/linux-nvme

Pull NVM Express driver update from Matthew Wilcox.

* git://git.infradead.org/users/willy/linux-nvme:
NVMe: Merge issue on character device bring-up
NVMe: Handle ioremap failure
NVMe: Add pci suspend/resume driver callbacks
NVMe: Use normal shutdown
NVMe: Separate controller init from disk discovery
NVMe: Separate queue alloc/free from create/delete
NVMe: Group pci related actions in functions
NVMe: Disk stats for read/write commands only
NVMe: Bring up cdev on set feature failure
NVMe: Fix checkpatch issues
NVMe: Namespace IDs are unsigned
NVMe: Update nvme_id_power_state with latest spec
NVMe: Split header file into user-visible and kernel-visible pieces
NVMe: Call nvme_process_cq from submission path
NVMe: Remove "process_cq did something" message
NVMe: Return correct value from interrupt handler
NVMe: Disk IO statistics
NVMe: Restructure MSI / MSI-X setup
NVMe: Use kzalloc instead of kmalloc+memset

drivers/block/nvme-core.c

···
 #include <linux/moduleparam.h>
 #include <linux/pci.h>
 #include <linux/poison.h>
+#include <linux/ptrace.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/types.h>
···
 	u16 sq_head;
 	u16 sq_tail;
 	u16 cq_head;
-	u16 cq_phase;
+	u8 cq_phase;
+	u8 cqe_seen;
+	u8 q_suspended;
 	unsigned long cmdid_data[];
 };
 
···
 static struct nvme_cmd_info *nvme_cmd_info(struct nvme_queue *nvmeq)
 {
 	return (void *)&nvmeq->cmdid_data[BITS_TO_LONGS(nvmeq->q_depth)];
+}
+
+static unsigned nvme_queue_extra(int depth)
+{
+	return DIV_ROUND_UP(depth, 8) + (depth * sizeof(struct nvme_cmd_info));
 }
 
 /**
···
 		iod->npages = -1;
 		iod->length = nbytes;
 		iod->nents = 0;
+		iod->start_time = jiffies;
 	}
 
 	return iod;
···
 	kfree(iod);
 }
 
+static void nvme_start_io_acct(struct bio *bio)
+{
+	struct gendisk *disk = bio->bi_bdev->bd_disk;
+	const int rw = bio_data_dir(bio);
+	int cpu = part_stat_lock();
+	part_round_stats(cpu, &disk->part0);
+	part_stat_inc(cpu, &disk->part0, ios[rw]);
+	part_stat_add(cpu, &disk->part0, sectors[rw], bio_sectors(bio));
+	part_inc_in_flight(&disk->part0, rw);
+	part_stat_unlock();
+}
+
+static void nvme_end_io_acct(struct bio *bio, unsigned long start_time)
+{
+	struct gendisk *disk = bio->bi_bdev->bd_disk;
+	const int rw = bio_data_dir(bio);
+	unsigned long duration = jiffies - start_time;
+	int cpu = part_stat_lock();
+	part_stat_add(cpu, &disk->part0, ticks[rw], duration);
+	part_round_stats(cpu, &disk->part0);
+	part_dec_in_flight(&disk->part0, rw);
+	part_stat_unlock();
+}
+
 static void bio_completion(struct nvme_dev *dev, void *ctx,
 						struct nvme_completion *cqe)
 {
···
 	struct bio *bio = iod->private;
 	u16 status = le16_to_cpup(&cqe->status) >> 1;
 
-	if (iod->nents)
+	if (iod->nents) {
 		dma_unmap_sg(&dev->pci_dev->dev, iod->sg, iod->nents,
 			bio_data_dir(bio) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+		nvme_end_io_acct(bio, iod->start_time);
+	}
 	nvme_free_iod(dev, iod);
 	if (status)
 		bio_endio(bio, -EIO);
···
 
 	if (atomic_dec_and_test(&bp->cnt)) {
 		bio_endio(bp->parent, bp->err);
-		if (bp->bv1)
-			kfree(bp->bv1);
-		if (bp->bv2)
-			kfree(bp->bv2);
+		kfree(bp->bv1);
+		kfree(bp->bv2);
 		kfree(bp);
 	}
 }
···
 	cmnd->rw.control = cpu_to_le16(control);
 	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
 
+	nvme_start_io_acct(bio);
 	if (++nvmeq->sq_tail == nvmeq->q_depth)
 		nvmeq->sq_tail = 0;
 	writel(nvmeq->sq_tail, nvmeq->q_db);
···
 	return result;
 }
 
-static void nvme_make_request(struct request_queue *q, struct bio *bio)
-{
-	struct nvme_ns *ns = q->queuedata;
-	struct nvme_queue *nvmeq = get_nvmeq(ns->dev);
-	int result = -EBUSY;
-
-	spin_lock_irq(&nvmeq->q_lock);
-	if (bio_list_empty(&nvmeq->sq_cong))
-		result = nvme_submit_bio_queue(nvmeq, ns, bio);
-	if (unlikely(result)) {
-		if (bio_list_empty(&nvmeq->sq_cong))
-			add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
-		bio_list_add(&nvmeq->sq_cong, bio);
-	}
-
-	spin_unlock_irq(&nvmeq->q_lock);
-	put_nvmeq(nvmeq);
-}
-
-static irqreturn_t nvme_process_cq(struct nvme_queue *nvmeq)
+static int nvme_process_cq(struct nvme_queue *nvmeq)
 {
 	u16 head, phase;
 
···
 	 * a big problem.
 	 */
 	if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
-		return IRQ_NONE;
+		return 0;
 
 	writel(head, nvmeq->q_db + (1 << nvmeq->dev->db_stride));
 	nvmeq->cq_head = head;
 	nvmeq->cq_phase = phase;
 
-	return IRQ_HANDLED;
+	nvmeq->cqe_seen = 1;
+	return 1;
+}
+
+static void nvme_make_request(struct request_queue *q, struct bio *bio)
+{
+	struct nvme_ns *ns = q->queuedata;
+	struct nvme_queue *nvmeq = get_nvmeq(ns->dev);
+	int result = -EBUSY;
+
+	if (!nvmeq) {
+		put_nvmeq(NULL);
+		bio_endio(bio, -EIO);
+		return;
+	}
+
+	spin_lock_irq(&nvmeq->q_lock);
+	if (!nvmeq->q_suspended && bio_list_empty(&nvmeq->sq_cong))
+		result = nvme_submit_bio_queue(nvmeq, ns, bio);
+	if (unlikely(result)) {
+		if (bio_list_empty(&nvmeq->sq_cong))
+			add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
+		bio_list_add(&nvmeq->sq_cong, bio);
+	}
+
+	nvme_process_cq(nvmeq);
+	spin_unlock_irq(&nvmeq->q_lock);
+	put_nvmeq(nvmeq);
 }
 
 static irqreturn_t nvme_irq(int irq, void *data)
···
 	irqreturn_t result;
 	struct nvme_queue *nvmeq = data;
 	spin_lock(&nvmeq->q_lock);
-	result = nvme_process_cq(nvmeq);
+	nvme_process_cq(nvmeq);
+	result = nvmeq->cqe_seen ? IRQ_HANDLED : IRQ_NONE;
+	nvmeq->cqe_seen = 0;
 	spin_unlock(&nvmeq->q_lock);
 	return result;
 }
···
 	}
 }
 
-static void nvme_free_queue_mem(struct nvme_queue *nvmeq)
+static void nvme_free_queue(struct nvme_queue *nvmeq)
 {
+	spin_lock_irq(&nvmeq->q_lock);
+	while (bio_list_peek(&nvmeq->sq_cong)) {
+		struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
+		bio_endio(bio, -EIO);
+	}
+	spin_unlock_irq(&nvmeq->q_lock);
+
 	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
 				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
 	dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
···
 	kfree(nvmeq);
 }
 
-static void nvme_free_queue(struct nvme_dev *dev, int qid)
+static void nvme_free_queues(struct nvme_dev *dev)
+{
+	int i;
+
+	for (i = dev->queue_count - 1; i >= 0; i--) {
+		nvme_free_queue(dev->queues[i]);
+		dev->queue_count--;
+		dev->queues[i] = NULL;
+	}
+}
+
+static void nvme_disable_queue(struct nvme_dev *dev, int qid)
 {
 	struct nvme_queue *nvmeq = dev->queues[qid];
 	int vector = dev->entry[nvmeq->cq_vector].vector;
 
 	spin_lock_irq(&nvmeq->q_lock);
-	nvme_cancel_ios(nvmeq, false);
-	while (bio_list_peek(&nvmeq->sq_cong)) {
-		struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
-		bio_endio(bio, -EIO);
+	if (nvmeq->q_suspended) {
+		spin_unlock_irq(&nvmeq->q_lock);
+		return;
 	}
+	nvmeq->q_suspended = 1;
 	spin_unlock_irq(&nvmeq->q_lock);
 
 	irq_set_affinity_hint(vector, NULL);
···
 		adapter_delete_cq(dev, qid);
 	}
 
-	nvme_free_queue_mem(nvmeq);
+	spin_lock_irq(&nvmeq->q_lock);
+	nvme_process_cq(nvmeq);
+	nvme_cancel_ios(nvmeq, false);
+	spin_unlock_irq(&nvmeq->q_lock);
 }
 
 static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 							int depth, int vector)
 {
 	struct device *dmadev = &dev->pci_dev->dev;
-	unsigned extra = DIV_ROUND_UP(depth, 8) + (depth *
-						sizeof(struct nvme_cmd_info));
+	unsigned extra = nvme_queue_extra(depth);
 	struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq) + extra, GFP_KERNEL);
 	if (!nvmeq)
 		return NULL;
···
 	nvmeq->q_db = &dev->dbs[qid << (dev->db_stride + 1)];
 	nvmeq->q_depth = depth;
 	nvmeq->cq_vector = vector;
+	nvmeq->q_suspended = 1;
+	dev->queue_count++;
 
 	return nvmeq;
 
···
 				IRQF_DISABLED | IRQF_SHARED, name, nvmeq);
 }
 
-static struct nvme_queue *nvme_create_queue(struct nvme_dev *dev, int qid,
-					    int cq_size, int vector)
+static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
 {
-	int result;
-	struct nvme_queue *nvmeq = nvme_alloc_queue(dev, qid, cq_size, vector);
+	struct nvme_dev *dev = nvmeq->dev;
+	unsigned extra = nvme_queue_extra(nvmeq->q_depth);
 
-	if (!nvmeq)
-		return ERR_PTR(-ENOMEM);
+	nvmeq->sq_tail = 0;
+	nvmeq->cq_head = 0;
+	nvmeq->cq_phase = 1;
+	nvmeq->q_db = &dev->dbs[qid << (dev->db_stride + 1)];
+	memset(nvmeq->cmdid_data, 0, extra);
+	memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
+	nvme_cancel_ios(nvmeq, false);
+	nvmeq->q_suspended = 0;
+}
+
+static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
+{
+	struct nvme_dev *dev = nvmeq->dev;
+	int result;
 
 	result = adapter_alloc_cq(dev, qid, nvmeq);
 	if (result < 0)
-		goto free_nvmeq;
+		return result;
 
 	result = adapter_alloc_sq(dev, qid, nvmeq);
 	if (result < 0)
···
 	if (result < 0)
 		goto release_sq;
 
-	return nvmeq;
+	spin_lock(&nvmeq->q_lock);
+	nvme_init_queue(nvmeq, qid);
+	spin_unlock(&nvmeq->q_lock);
+
+	return result;
 
  release_sq:
 	adapter_delete_sq(dev, qid);
  release_cq:
 	adapter_delete_cq(dev, qid);
- free_nvmeq:
-	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
-				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
-	dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
-					nvmeq->sq_cmds, nvmeq->sq_dma_addr);
-	kfree(nvmeq);
-	return ERR_PTR(result);
+	return result;
 }
 
 static int nvme_wait_ready(struct nvme_dev *dev, u64 cap, bool enabled)
···
 	return nvme_wait_ready(dev, cap, true);
 }
 
+static int nvme_shutdown_ctrl(struct nvme_dev *dev)
+{
+	unsigned long timeout;
+	u32 cc;
+
+	cc = (readl(&dev->bar->cc) & ~NVME_CC_SHN_MASK) | NVME_CC_SHN_NORMAL;
+	writel(cc, &dev->bar->cc);
+
+	timeout = 2 * HZ + jiffies;
+	while ((readl(&dev->bar->csts) & NVME_CSTS_SHST_MASK) !=
+							NVME_CSTS_SHST_CMPLT) {
+		msleep(100);
+		if (fatal_signal_pending(current))
+			return -EINTR;
+		if (time_after(jiffies, timeout)) {
+			dev_err(&dev->pci_dev->dev,
+				"Device shutdown incomplete; abort shutdown\n");
+			return -ENODEV;
+		}
+	}
+
+	return 0;
+}
+
 static int nvme_configure_admin_queue(struct nvme_dev *dev)
 {
 	int result;
···
 	u64 cap = readq(&dev->bar->cap);
 	struct nvme_queue *nvmeq;
 
-	dev->dbs = ((void __iomem *)dev->bar) + 4096;
-	dev->db_stride = NVME_CAP_STRIDE(cap);
-
 	result = nvme_disable_ctrl(dev, cap);
 	if (result < 0)
 		return result;
 
-	nvmeq = nvme_alloc_queue(dev, 0, 64, 0);
-	if (!nvmeq)
-		return -ENOMEM;
+	nvmeq = dev->queues[0];
+	if (!nvmeq) {
+		nvmeq = nvme_alloc_queue(dev, 0, 64, 0);
+		if (!nvmeq)
+			return -ENOMEM;
+		dev->queues[0] = nvmeq;
+	}
 
 	aqa = nvmeq->q_depth - 1;
 	aqa |= aqa << 16;
···
 
 	result = nvme_enable_ctrl(dev, cap);
 	if (result)
-		goto free_q;
+		return result;
 
 	result = queue_request_irq(dev, nvmeq, "nvme admin");
 	if (result)
-		goto free_q;
+		return result;
 
-	dev->queues[0] = nvmeq;
-	return result;
-
- free_q:
-	nvme_free_queue_mem(nvmeq);
+	spin_lock(&nvmeq->q_lock);
+	nvme_init_queue(nvmeq, 0);
+	spin_unlock(&nvmeq->q_lock);
 	return result;
 }
 
···
 	c.rw.appmask = cpu_to_le16(io.appmask);
 
 	if (meta_len) {
-		meta_iod = nvme_map_user_pages(dev, io.opcode & 1, io.metadata, meta_len);
+		meta_iod = nvme_map_user_pages(dev, io.opcode & 1, io.metadata,
+								meta_len);
 		if (IS_ERR(meta_iod)) {
 			status = PTR_ERR(meta_iod);
 			meta_iod = NULL;
···
 	put_nvmeq(nvmeq);
 	if (length != (io.nblocks + 1) << ns->lba_shift)
 		status = -ENOMEM;
+	else if (!nvmeq || nvmeq->q_suspended)
+		status = -EBUSY;
 	else
 		status = nvme_submit_sync_cmd(nvmeq, &c, NULL, NVME_IO_TIMEOUT);
 
···
 
 	switch (cmd) {
 	case NVME_IOCTL_ID:
+		force_successful_syscall_return();
 		return ns->ns_id;
 	case NVME_IOCTL_ADMIN_CMD:
 		return nvme_user_admin_cmd(ns->dev, (void __user *)arg);
···
 				if (!nvmeq)
 					continue;
 				spin_lock_irq(&nvmeq->q_lock);
-				if (nvme_process_cq(nvmeq))
-					printk("process_cq did something\n");
+				if (nvmeq->q_suspended)
+					goto unlock;
+				nvme_process_cq(nvmeq);
 				nvme_cancel_ios(nvmeq, true);
 				nvme_resubmit_bios(nvmeq);
+ unlock:
 				spin_unlock_irq(&nvmeq->q_lock);
 			}
 		}
···
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
 }
 
-static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, int nsid,
+static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
 			struct nvme_id_ns *id, struct nvme_lba_range_type *rt)
 {
 	struct nvme_ns *ns;
···
 	status = nvme_set_features(dev, NVME_FEAT_NUM_QUEUES, q_count, 0,
 								&result);
 	if (status)
-		return -EIO;
+		return status < 0 ? -EIO : -EBUSY;
 	return min(result & 0xffff, result >> 16) + 1;
+}
+
+static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
+{
+	return 4096 + ((nr_io_queues + 1) << (dev->db_stride + 3));
 }
 
 static int nvme_setup_io_queues(struct nvme_dev *dev)
 {
 	struct pci_dev *pdev = dev->pci_dev;
-	int result, cpu, i, nr_io_queues, db_bar_size, q_depth, q_count;
+	int result, cpu, i, vecs, nr_io_queues, size, q_depth;
 
 	nr_io_queues = num_online_cpus();
 	result = set_queue_count(dev, nr_io_queues);
···
 	if (result < nr_io_queues)
 		nr_io_queues = result;
 
-	q_count = nr_io_queues;
-	/* Deregister the admin queue's interrupt */
-	free_irq(dev->entry[0].vector, dev->queues[0]);
-
-	db_bar_size = 4096 + ((nr_io_queues + 1) << (dev->db_stride + 3));
-	if (db_bar_size > 8192) {
+	size = db_bar_size(dev, nr_io_queues);
+	if (size > 8192) {
 		iounmap(dev->bar);
-		dev->bar = ioremap(pci_resource_start(pdev, 0), db_bar_size);
+		do {
+			dev->bar = ioremap(pci_resource_start(pdev, 0), size);
+			if (dev->bar)
+				break;
+			if (!--nr_io_queues)
+				return -ENOMEM;
+			size = db_bar_size(dev, nr_io_queues);
+		} while (1);
 		dev->dbs = ((void __iomem *)dev->bar) + 4096;
 		dev->queues[0]->q_db = dev->dbs;
 	}
 
-	for (i = 0; i < nr_io_queues; i++)
+	/* Deregister the admin queue's interrupt */
+	free_irq(dev->entry[0].vector, dev->queues[0]);
+
+	vecs = nr_io_queues;
+	for (i = 0; i < vecs; i++)
 		dev->entry[i].entry = i;
 	for (;;) {
-		result = pci_enable_msix(pdev, dev->entry, nr_io_queues);
-		if (result == 0) {
+		result = pci_enable_msix(pdev, dev->entry, vecs);
+		if (result <= 0)
 			break;
-		} else if (result > 0) {
-			nr_io_queues = result;
-			continue;
-		} else {
-			nr_io_queues = 0;
-			break;
-		}
+		vecs = result;
 	}
 
-	if (nr_io_queues == 0) {
-		nr_io_queues = q_count;
+	if (result < 0) {
+		vecs = nr_io_queues;
+		if (vecs > 32)
+			vecs = 32;
 		for (;;) {
-			result = pci_enable_msi_block(pdev, nr_io_queues);
+			result = pci_enable_msi_block(pdev, vecs);
 			if (result == 0) {
-				for (i = 0; i < nr_io_queues; i++)
+				for (i = 0; i < vecs; i++)
 					dev->entry[i].vector = i + pdev->irq;
 				break;
-			} else if (result > 0) {
-				nr_io_queues = result;
-				continue;
-			} else {
-				nr_io_queues = 1;
+			} else if (result < 0) {
+				vecs = 1;
 				break;
 			}
+			vecs = result;
 		}
 	}
 
+	/*
+	 * Should investigate if there's a performance win from allocating
+	 * more queues than interrupt vectors; it might allow the submission
+	 * path to scale better, even if the receive path is limited by the
+	 * number of interrupts.
+	 */
+	nr_io_queues = vecs;
+
 	result = queue_request_irq(dev, dev->queues[0], "nvme admin");
-	/* XXX: handle failure here */
+	if (result) {
+		dev->queues[0]->q_suspended = 1;
+		goto free_queues;
+	}
+
+	/* Free previously allocated queues that are no longer usable */
+	spin_lock(&dev_list_lock);
+	for (i = dev->queue_count - 1; i > nr_io_queues; i--) {
+		struct nvme_queue *nvmeq = dev->queues[i];
+
+		spin_lock(&nvmeq->q_lock);
+		nvme_cancel_ios(nvmeq, false);
+		spin_unlock(&nvmeq->q_lock);
+
+		nvme_free_queue(nvmeq);
+		dev->queue_count--;
+		dev->queues[i] = NULL;
+	}
+	spin_unlock(&dev_list_lock);
 
 	cpu = cpumask_first(cpu_online_mask);
 	for (i = 0; i < nr_io_queues; i++) {
···
 
 	q_depth = min_t(int, NVME_CAP_MQES(readq(&dev->bar->cap)) + 1,
 								NVME_Q_DEPTH);
-	for (i = 0; i < nr_io_queues; i++) {
-		dev->queues[i + 1] = nvme_create_queue(dev, i + 1, q_depth, i);
-		if (IS_ERR(dev->queues[i + 1]))
-			return PTR_ERR(dev->queues[i + 1]);
-		dev->queue_count++;
+	for (i = dev->queue_count - 1; i < nr_io_queues; i++) {
+		dev->queues[i + 1] = nvme_alloc_queue(dev, i + 1, q_depth, i);
+		if (!dev->queues[i + 1]) {
+			result = -ENOMEM;
+			goto free_queues;
+		}
 	}
 
 	for (; i < num_possible_cpus(); i++) {
···
 		dev->queues[i + 1] = dev->queues[target + 1];
 	}
 
+	for (i = 1; i < dev->queue_count; i++) {
+		result = nvme_create_queue(dev->queues[i], i);
+		if (result) {
+			for (--i; i > 0; i--)
+				nvme_disable_queue(dev, i);
+			goto free_queues;
+		}
+	}
+
 	return 0;
-}
 
-static void nvme_free_queues(struct nvme_dev *dev)
-{
-	int i;
-
-	for (i = dev->queue_count - 1; i >= 0; i--)
-		nvme_free_queue(dev, i);
+ free_queues:
+	nvme_free_queues(dev);
+	return result;
 }
 
 /*
···
  */
 static int nvme_dev_add(struct nvme_dev *dev)
 {
-	int res, nn, i;
+	int res;
+	unsigned nn, i;
 	struct nvme_ns *ns;
 	struct nvme_id_ctrl *ctrl;
 	struct nvme_id_ns *id_ns;
 	void *mem;
 	dma_addr_t dma_addr;
 	int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12;
-
-	res = nvme_setup_io_queues(dev);
-	if (res)
-		return res;
 
 	mem = dma_alloc_coherent(&dev->pci_dev->dev, 8192, &dma_addr,
 								GFP_KERNEL);
···
 	return res;
 }
 
-static int nvme_dev_remove(struct nvme_dev *dev)
+static int nvme_dev_map(struct nvme_dev *dev)
 {
-	struct nvme_ns *ns, *next;
+	int bars, result = -ENOMEM;
+	struct pci_dev *pdev = dev->pci_dev;
+
+	if (pci_enable_device_mem(pdev))
+		return result;
+
+	dev->entry[0].vector = pdev->irq;
+	pci_set_master(pdev);
+	bars = pci_select_bars(pdev, IORESOURCE_MEM);
+	if (pci_request_selected_regions(pdev, bars, "nvme"))
+		goto disable_pci;
+
+	if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)))
+		dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
+	else if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)))
+		dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
+	else
+		goto disable_pci;
+
+	pci_set_drvdata(pdev, dev);
+	dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
+	if (!dev->bar)
+		goto disable;
+
+	dev->db_stride = NVME_CAP_STRIDE(readq(&dev->bar->cap));
+	dev->dbs = ((void __iomem *)dev->bar) + 4096;
+
+	return 0;
+
+ disable:
+	pci_release_regions(pdev);
+ disable_pci:
+	pci_disable_device(pdev);
+	return result;
+}
+
+static void nvme_dev_unmap(struct nvme_dev *dev)
+{
+	if (dev->pci_dev->msi_enabled)
+		pci_disable_msi(dev->pci_dev);
+	else if (dev->pci_dev->msix_enabled)
+		pci_disable_msix(dev->pci_dev);
+
+	if (dev->bar) {
+		iounmap(dev->bar);
+		dev->bar = NULL;
+	}
+
+	pci_release_regions(dev->pci_dev);
+	if (pci_is_enabled(dev->pci_dev))
+		pci_disable_device(dev->pci_dev);
+}
+
+static void nvme_dev_shutdown(struct nvme_dev *dev)
+{
+	int i;
+
+	for (i = dev->queue_count - 1; i >= 0; i--)
+		nvme_disable_queue(dev, i);
 
 	spin_lock(&dev_list_lock);
-	list_del(&dev->node);
+	list_del_init(&dev->node);
 	spin_unlock(&dev_list_lock);
+
+	if (dev->bar)
+		nvme_shutdown_ctrl(dev);
+	nvme_dev_unmap(dev);
+}
+
+static void nvme_dev_remove(struct nvme_dev *dev)
+{
+	struct nvme_ns *ns, *next;
 
 	list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
 		list_del(&ns->list);
 		del_gendisk(ns->disk);
 		nvme_ns_free(ns);
 	}
-
-	nvme_free_queues(dev);
-
-	return 0;
 }
 
 static int nvme_setup_prp_pools(struct nvme_dev *dev)
···
 {
 	struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref);
 	nvme_dev_remove(dev);
-	if (dev->pci_dev->msi_enabled)
-		pci_disable_msi(dev->pci_dev);
-	else if (dev->pci_dev->msix_enabled)
-		pci_disable_msix(dev->pci_dev);
-	iounmap(dev->bar);
+	nvme_dev_shutdown(dev);
+	nvme_free_queues(dev);
 	nvme_release_instance(dev);
 	nvme_release_prp_pools(dev);
-	pci_disable_device(dev->pci_dev);
-	pci_release_regions(dev->pci_dev);
 	kfree(dev->queues);
 	kfree(dev->entry);
 	kfree(dev);
···
 	.compat_ioctl	= nvme_dev_ioctl,
 };
 
+static int nvme_dev_start(struct nvme_dev *dev)
+{
+	int result;
+
+	result = nvme_dev_map(dev);
+	if (result)
+		return result;
+
+	result = nvme_configure_admin_queue(dev);
+	if (result)
+		goto unmap;
+
+	spin_lock(&dev_list_lock);
+	list_add(&dev->node, &dev_list);
+	spin_unlock(&dev_list_lock);
+
+	result = nvme_setup_io_queues(dev);
+	if (result && result != -EBUSY)
+		goto disable;
+
+	return result;
+
+ disable:
+	spin_lock(&dev_list_lock);
+	list_del_init(&dev->node);
+	spin_unlock(&dev_list_lock);
+ unmap:
+	nvme_dev_unmap(dev);
+	return result;
+}
+
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
-	int bars, result = -ENOMEM;
+	int result = -ENOMEM;
 	struct nvme_dev *dev;
 
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
···
 	if (!dev->queues)
 		goto free;
 
-	if (pci_enable_device_mem(pdev))
-		goto free;
-	pci_set_master(pdev);
-	bars = pci_select_bars(pdev, IORESOURCE_MEM);
-	if (pci_request_selected_regions(pdev, bars, "nvme"))
-		goto disable;
-
 	INIT_LIST_HEAD(&dev->namespaces);
 	dev->pci_dev = pdev;
-	pci_set_drvdata(pdev, dev);
-
-	if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)))
-		dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
-	else if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)))
-		dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
-	else
-		goto disable;
-
 	result = nvme_set_instance(dev);
 	if (result)
-		goto disable;
-
-	dev->entry[0].vector = pdev->irq;
+		goto free;
 
 	result = nvme_setup_prp_pools(dev);
 	if (result)
-		goto disable_msix;
+		goto release;
 
-	dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
-	if (!dev->bar) {
-		result = -ENOMEM;
-		goto disable_msix;
+	result = nvme_dev_start(dev);
+	if (result) {
+		if (result == -EBUSY)
+			goto create_cdev;
+		goto release_pools;
 	}
-
-	result = nvme_configure_admin_queue(dev);
-	if (result)
-		goto unmap;
-	dev->queue_count++;
-
-	spin_lock(&dev_list_lock);
-	list_add(&dev->node, &dev_list);
-	spin_unlock(&dev_list_lock);
 
 	result = nvme_dev_add(dev);
 	if (result)
-		goto delete;
+		goto shutdown;
 
+ create_cdev:
 	scnprintf(dev->name, sizeof(dev->name), "nvme%d", dev->instance);
 	dev->miscdev.minor = MISC_DYNAMIC_MINOR;
 	dev->miscdev.parent = &pdev->dev;
···
 
  remove:
 	nvme_dev_remove(dev);
- delete:
-	spin_lock(&dev_list_lock);
-	list_del(&dev->node);
-	spin_unlock(&dev_list_lock);
-
+ shutdown:
+	nvme_dev_shutdown(dev);
+ release_pools:
 	nvme_free_queues(dev);
- unmap:
-	iounmap(dev->bar);
- disable_msix:
-	if (dev->pci_dev->msi_enabled)
-		pci_disable_msi(dev->pci_dev);
-	else if (dev->pci_dev->msix_enabled)
-		pci_disable_msix(dev->pci_dev);
-	nvme_release_instance(dev);
 	nvme_release_prp_pools(dev);
- disable:
-	pci_disable_device(pdev);
-	pci_release_regions(pdev);
+ release:
+	nvme_release_instance(dev);
  free:
 	kfree(dev->queues);
 	kfree(dev->entry);
···
 #define nvme_link_reset NULL
 #define nvme_slot_reset NULL
 #define nvme_error_resume NULL
-#define nvme_suspend NULL
-#define nvme_resume NULL
+
+static int nvme_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct nvme_dev *ndev = pci_get_drvdata(pdev);
+
+	nvme_dev_shutdown(ndev);
+	return 0;
+}
+
+static int nvme_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct nvme_dev *ndev = pci_get_drvdata(pdev);
+	int ret;
+
+	ret = nvme_dev_start(ndev);
+	/* XXX: should remove gendisks if resume fails */
+	if (ret)
+		nvme_free_queues(ndev);
+	return ret;
+}
+
+static SIMPLE_DEV_PM_OPS(nvme_dev_pm_ops, nvme_suspend, nvme_resume);
 
 static const struct pci_error_handlers nvme_err_handler = {
 	.error_detected	= nvme_error_detected,
···
 	.id_table	= nvme_id_table,
 	.probe		= nvme_probe,
 	.remove		= nvme_remove,
-	.suspend	= nvme_suspend,
-	.resume		= nvme_resume,
+	.driver		= {
+		.pm	= &nvme_dev_pm_ops,
+	},
 	.err_handler	= &nvme_err_handler,
 };
 

drivers/block/nvme-scsi.c

···
 	int res = SNTI_TRANSLATION_SUCCESS;
 	int xfer_len;
 
-	inq_response = kmalloc(EXTENDED_INQUIRY_DATA_PAGE_LENGTH, GFP_KERNEL);
+	inq_response = kzalloc(EXTENDED_INQUIRY_DATA_PAGE_LENGTH, GFP_KERNEL);
 	if (inq_response == NULL) {
 		res = -ENOMEM;
 		goto out_mem;
 	}
 
-	memset(inq_response, 0, EXTENDED_INQUIRY_DATA_PAGE_LENGTH);
 	inq_response[1] = INQ_BDEV_CHARACTERISTICS_PAGE;    /* Page Code */
 	inq_response[2] = 0x00;    /* Page Length MSB */
 	inq_response[3] = 0x3C;    /* Page Length LSB */
···
 	int xfer_len;
 	u8 *log_response;
 
-	log_response = kmalloc(LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH, GFP_KERNEL);
+	log_response = kzalloc(LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH, GFP_KERNEL);
 	if (log_response == NULL) {
 		res = -ENOMEM;
 		goto out_mem;
 	}
-	memset(log_response, 0, LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH);
 
 	log_response[0] = LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE;
 	/* Subpage=0x00, Page Length MSB=0 */
···
 	u8 temp_c;
 	u16 temp_k;
 
-	log_response = kmalloc(LOG_INFO_EXCP_PAGE_LENGTH, GFP_KERNEL);
+	log_response = kzalloc(LOG_INFO_EXCP_PAGE_LENGTH, GFP_KERNEL);
 	if (log_response == NULL) {
 		res = -ENOMEM;
 		goto out_mem;
 	}
-	memset(log_response, 0, LOG_INFO_EXCP_PAGE_LENGTH);
 
 	mem = dma_alloc_coherent(&dev->pci_dev->dev,
 					sizeof(struct nvme_smart_log),
···
 	u8 temp_c_cur, temp_c_thresh;
 	u16 temp_k;
 
-	log_response = kmalloc(LOG_TEMP_PAGE_LENGTH, GFP_KERNEL);
+	log_response = kzalloc(LOG_TEMP_PAGE_LENGTH, GFP_KERNEL);
 	if (log_response == NULL) {
 		res = -ENOMEM;
 		goto out_mem;
 	}
-	memset(log_response, 0, LOG_TEMP_PAGE_LENGTH);
 
 	mem = dma_alloc_coherent(&dev->pci_dev->dev,
 					sizeof(struct nvme_smart_log),
···
 	blk_desc_offset = mph_size;
 	mode_pages_offset_1 = blk_desc_offset + blk_desc_len;
 
-	response = kmalloc(resp_size, GFP_KERNEL);
+	response = kzalloc(resp_size, GFP_KERNEL);
 	if (response == NULL) {
 		res = -ENOMEM;
 		goto out_mem;
 	}
-	memset(response, 0, resp_size);
 
 	res = nvme_trans_fill_mode_parm_hdr(&response[0], mph_size, cdb10,
 					llbaa, mode_data_length, blk_desc_len);
···
 	}
 	id_ns = mem;
 
-	response = kmalloc(resp_size, GFP_KERNEL);
+	response = kzalloc(resp_size, GFP_KERNEL);
 	if (response == NULL) {
 		res = -ENOMEM;
 		goto out_dma;
 	}
-	memset(response, 0, resp_size);
 	nvme_trans_fill_read_cap(response, id_ns, cdb16);
 
 	xfer_len = min(alloc_len, resp_size);
···
 			goto out_dma;
 		}
 
-		response = kmalloc(resp_size, GFP_KERNEL);
+		response = kzalloc(resp_size, GFP_KERNEL);
 		if (response == NULL) {
 			res = -ENOMEM;
 			goto out_dma;
 		}
-		memset(response, 0, resp_size);
 
 		/* The first LUN ID will always be 0 per the SAM spec */
 		for (lun_id = 0; lun_id < le32_to_cpu(id_ctrl->nn); lun_id++) {
···
 
 	resp_size = ((desc_format) ? (DESC_FMT_SENSE_DATA_SIZE) :
 					(FIXED_FMT_SENSE_DATA_SIZE));
-	response = kmalloc(resp_size, GFP_KERNEL);
+	response = kzalloc(resp_size, GFP_KERNEL);
 	if (response == NULL) {
 		res = -ENOMEM;
 		goto out;
 	}
-	memset(response, 0, resp_size);
 
 	if (desc_format == DESCRIPTOR_FORMAT_SENSE_DATA_TYPE) {
 		/* Descriptor Format Sense Data */

include/linux/nvme.h

···
 /*
  * Definitions for the NVM Express interface
- * Copyright (c) 2011, Intel Corporation.
+ * Copyright (c) 2011-2013, 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,
···
 #ifndef _LINUX_NVME_H
 #define _LINUX_NVME_H
 
-#include <linux/types.h>
+#include <uapi/linux/nvme.h>
+#include <linux/pci.h>
+#include <linux/miscdevice.h>
+#include <linux/kref.h>
 
 struct nvme_bar {
 	__u64			cap;	/* Controller Capabilities */
···
 	NVME_CC_SHN_NONE	= 0 << 14,
 	NVME_CC_SHN_NORMAL	= 1 << 14,
 	NVME_CC_SHN_ABRUPT	= 2 << 14,
+	NVME_CC_SHN_MASK	= 3 << 14,
 	NVME_CC_IOSQES		= 6 << 16,
 	NVME_CC_IOCQES		= 4 << 20,
 	NVME_CSTS_RDY		= 1 << 0,
···
 	NVME_CSTS_SHST_NORMAL	= 0 << 2,
 	NVME_CSTS_SHST_OCCUR	= 1 << 2,
 	NVME_CSTS_SHST_CMPLT	= 2 << 2,
-};
-
-struct nvme_id_power_state {
-	__le16			max_power;	/* centiwatts */
-	__u16			rsvd2;
-	__le32			entry_lat;	/* microseconds */
-	__le32			exit_lat;	/* microseconds */
-	__u8			read_tput;
-	__u8			read_lat;
-	__u8			write_tput;
-	__u8			write_lat;
-	__u8			rsvd16[16];
+	NVME_CSTS_SHST_MASK	= 3 << 2,
 };
 
 #define NVME_VS(major, minor)	(major << 16 | minor)
-
-struct nvme_id_ctrl {
-	__le16			vid;
-	__le16			ssvid;
-	char			sn[20];
-	char			mn[40];
-	char			fr[8];
-	__u8			rab;
-	__u8			ieee[3];
-	__u8			mic;
-	__u8			mdts;
-	__u8			rsvd78[178];
-	__le16			oacs;
-	__u8			acl;
-	__u8			aerl;
-	__u8			frmw;
-	__u8			lpa;
-	__u8			elpe;
-	__u8			npss;
-	__u8			rsvd264[248];
-	__u8			sqes;
-	__u8			cqes;
-	__u8			rsvd514[2];
-	__le32			nn;
-	__le16			oncs;
-	__le16			fuses;
-	__u8			fna;
-	__u8			vwc;
-	__le16			awun;
-	__le16			awupf;
-	__u8			rsvd530[1518];
-	struct nvme_id_power_state	psd[32];
-	__u8			vs[1024];
-};
-
-enum {
-	NVME_CTRL_ONCS_COMPARE			= 1 << 0,
-	NVME_CTRL_ONCS_WRITE_UNCORRECTABLE	= 1 << 1,
-	NVME_CTRL_ONCS_DSM			= 1 << 2,
-};
-
-struct nvme_lbaf {
-	__le16			ms;
-	__u8			ds;
-	__u8			rp;
-};
-
-struct nvme_id_ns {
-	__le64			nsze;
-	__le64			ncap;
-	__le64			nuse;
-	__u8			nsfeat;
-	__u8			nlbaf;
-	__u8			flbas;
-	__u8			mc;
-	__u8			dpc;
-	__u8			dps;
-	__u8			rsvd30[98];
-	struct nvme_lbaf	lbaf[16];
-	__u8			rsvd192[192];
-	__u8			vs[3712];
-};
-
-enum {
-	NVME_NS_FEAT_THIN	= 1 << 0,
-	NVME_LBAF_RP_BEST	= 0,
-	NVME_LBAF_RP_BETTER	= 1,
-	NVME_LBAF_RP_GOOD	= 2,
-	NVME_LBAF_RP_DEGRADED	= 3,
-};
-
-struct nvme_smart_log {
-	__u8			critical_warning;
-	__u8			temperature[2];
-	__u8			avail_spare;
-	__u8			spare_thresh;
-	__u8			percent_used;
-	__u8			rsvd6[26];
-	__u8			data_units_read[16];
-	__u8			data_units_written[16];
-	__u8			host_reads[16];
-	__u8			host_writes[16];
-	__u8			ctrl_busy_time[16];
-	__u8			power_cycles[16];
-	__u8			power_on_hours[16];
-	__u8			unsafe_shutdowns[16];
-	__u8			media_errors[16];
-	__u8			num_err_log_entries[16];
-	__u8			rsvd192[320];
-};
-
-enum {
-	NVME_SMART_CRIT_SPARE		= 1 << 0,
-	NVME_SMART_CRIT_TEMPERATURE	= 1 << 1,
-	NVME_SMART_CRIT_RELIABILITY	= 1 << 2,
-	NVME_SMART_CRIT_MEDIA		= 1 << 3,
-	NVME_SMART_CRIT_VOLATILE_MEMORY	= 1 << 4,
-};
-
-struct nvme_lba_range_type {
-	__u8			type;
-	__u8			attributes;
-	__u8			rsvd2[14];
-	__u64			slba;
-	__u64			nlb;
-	__u8			guid[16];
-	__u8			rsvd48[16];
-};
-
-enum {
-	NVME_LBART_TYPE_FS	= 0x01,
-	NVME_LBART_TYPE_RAID	= 0x02,
-	NVME_LBART_TYPE_CACHE	= 0x03,
-	NVME_LBART_TYPE_SWAP	= 0x04,
-
-	NVME_LBART_ATTRIB_TEMP	= 1 << 0,
-	NVME_LBART_ATTRIB_HIDE	= 1 << 1,
-};
-
-/* I/O commands */
-
-enum nvme_opcode {
-	nvme_cmd_flush		= 0x00,
-	nvme_cmd_write		= 0x01,
-	nvme_cmd_read		= 0x02,
-	nvme_cmd_write_uncor	= 0x04,
-	nvme_cmd_compare	= 0x05,
-	nvme_cmd_dsm		= 0x09,
-};
-
-struct nvme_common_command {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__le32			nsid;
-	__le32			cdw2[2];
-	__le64			metadata;
-	__le64			prp1;
-	__le64			prp2;
-	__le32			cdw10[6];
-};
-
-struct nvme_rw_command {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__le32			nsid;
-	__u64			rsvd2;
-	__le64			metadata;
-	__le64			prp1;
-	__le64			prp2;
-	__le64			slba;
-	__le16			length;
-	__le16			control;
-	__le32			dsmgmt;
-	__le32			reftag;
-	__le16			apptag;
-	__le16			appmask;
-};
-
-enum {
-	NVME_RW_LR			= 1 << 15,
-	NVME_RW_FUA			= 1 << 14,
-	NVME_RW_DSM_FREQ_UNSPEC		= 0,
-	NVME_RW_DSM_FREQ_TYPICAL	= 1,
-	NVME_RW_DSM_FREQ_RARE		= 2,
-	NVME_RW_DSM_FREQ_READS		= 3,
-	NVME_RW_DSM_FREQ_WRITES		= 4,
-	NVME_RW_DSM_FREQ_RW		= 5,
-	NVME_RW_DSM_FREQ_ONCE		= 6,
-	NVME_RW_DSM_FREQ_PREFETCH	= 7,
-	NVME_RW_DSM_FREQ_TEMP		= 8,
-	NVME_RW_DSM_LATENCY_NONE	= 0 << 4,
-	NVME_RW_DSM_LATENCY_IDLE	= 1 << 4,
-	NVME_RW_DSM_LATENCY_NORM	= 2 << 4,
-	NVME_RW_DSM_LATENCY_LOW		= 3 << 4,
-	NVME_RW_DSM_SEQ_REQ		= 1 << 6,
-	NVME_RW_DSM_COMPRESSED		= 1 << 7,
-};
-
-struct nvme_dsm_cmd {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__le32			nsid;
-	__u64			rsvd2[2];
-	__le64			prp1;
-	__le64			prp2;
-	__le32			nr;
-	__le32			attributes;
-	__u32			rsvd12[4];
-};
-
-enum {
-	NVME_DSMGMT_IDR		= 1 << 0,
-	NVME_DSMGMT_IDW		= 1 << 1,
-	NVME_DSMGMT_AD		= 1 << 2,
-};
-
-struct nvme_dsm_range {
-	__le32			cattr;
-	__le32			nlb;
-	__le64			slba;
-};
-
-/* Admin commands */
-
-enum nvme_admin_opcode {
-	nvme_admin_delete_sq		= 0x00,
-	nvme_admin_create_sq		= 0x01,
-	nvme_admin_get_log_page		= 0x02,
-	nvme_admin_delete_cq		= 0x04,
-	nvme_admin_create_cq		= 0x05,
-	nvme_admin_identify		= 0x06,
-	nvme_admin_abort_cmd		= 0x08,
-	nvme_admin_set_features		= 0x09,
-	nvme_admin_get_features		= 0x0a,
-	nvme_admin_async_event		= 0x0c,
-	nvme_admin_activate_fw		= 0x10,
-	nvme_admin_download_fw		= 0x11,
-	nvme_admin_format_nvm		= 0x80,
-	nvme_admin_security_send	= 0x81,
-	nvme_admin_security_recv	= 0x82,
-};
-
-enum {
-	NVME_QUEUE_PHYS_CONTIG	= (1 << 0),
-	NVME_CQ_IRQ_ENABLED	= (1 << 1),
-	NVME_SQ_PRIO_URGENT	= (0 << 1),
-	NVME_SQ_PRIO_HIGH	= (1 << 1),
-	NVME_SQ_PRIO_MEDIUM	= (2 << 1),
-	NVME_SQ_PRIO_LOW	= (3 << 1),
-	NVME_FEAT_ARBITRATION	= 0x01,
-	NVME_FEAT_POWER_MGMT	= 0x02,
-	NVME_FEAT_LBA_RANGE	= 0x03,
-	NVME_FEAT_TEMP_THRESH	= 0x04,
-	NVME_FEAT_ERR_RECOVERY	= 0x05,
-	NVME_FEAT_VOLATILE_WC	= 0x06,
-	NVME_FEAT_NUM_QUEUES	= 0x07,
-	NVME_FEAT_IRQ_COALESCE	= 0x08,
-	NVME_FEAT_IRQ_CONFIG	= 0x09,
-	NVME_FEAT_WRITE_ATOMIC	= 0x0a,
-	NVME_FEAT_ASYNC_EVENT	= 0x0b,
-	NVME_FEAT_SW_PROGRESS	= 0x0c,
-	NVME_FWACT_REPL		= (0 << 3),
-	NVME_FWACT_REPL_ACTV	= (1 << 3),
-	NVME_FWACT_ACTV		= (2 << 3),
-};
-
-struct nvme_identify {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__le32			nsid;
-	__u64			rsvd2[2];
-	__le64			prp1;
-	__le64			prp2;
-	__le32			cns;
-	__u32			rsvd11[5];
-};
-
-struct nvme_features {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__le32			nsid;
-	__u64			rsvd2[2];
-	__le64			prp1;
-	__le64			prp2;
-	__le32			fid;
-	__le32			dword11;
-	__u32			rsvd12[4];
-};
-
-struct nvme_create_cq {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__u32			rsvd1[5];
-	__le64			prp1;
-	__u64			rsvd8;
-	__le16			cqid;
-	__le16			qsize;
-	__le16			cq_flags;
-	__le16			irq_vector;
-	__u32			rsvd12[4];
-};
-
-struct nvme_create_sq {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__u32			rsvd1[5];
-	__le64			prp1;
-	__u64			rsvd8;
-	__le16			sqid;
-	__le16			qsize;
-	__le16			sq_flags;
-	__le16			cqid;
-	__u32			rsvd12[4];
-};
-
-struct nvme_delete_queue {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__u32			rsvd1[9];
-	__le16			qid;
-	__u16			rsvd10;
-	__u32			rsvd11[5];
-};
-
-struct nvme_download_firmware {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__u32			rsvd1[5];
-	__le64			prp1;
-	__le64			prp2;
-	__le32			numd;
-	__le32			offset;
-	__u32			rsvd12[4];
-};
-
-struct nvme_format_cmd {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__le32			nsid;
-	__u64			rsvd2[4];
-	__le32			cdw10;
-	__u32			rsvd11[5];
-};
-
-struct nvme_command {
-	union {
-		struct nvme_common_command common;
-		struct nvme_rw_command rw;
-		struct nvme_identify identify;
-		struct nvme_features features;
-		struct nvme_create_cq create_cq;
-		struct nvme_create_sq create_sq;
-		struct nvme_delete_queue delete_queue;
-		struct nvme_download_firmware dlfw;
-		struct nvme_format_cmd format;
-		struct nvme_dsm_cmd dsm;
-	};
-};
-
-enum {
-	NVME_SC_SUCCESS			= 0x0,
-	NVME_SC_INVALID_OPCODE		= 0x1,
-	NVME_SC_INVALID_FIELD		= 0x2,
-	NVME_SC_CMDID_CONFLICT		= 0x3,
-	NVME_SC_DATA_XFER_ERROR		= 0x4,
-	NVME_SC_POWER_LOSS		= 0x5,
-	NVME_SC_INTERNAL		= 0x6,
-	NVME_SC_ABORT_REQ		= 0x7,
-	NVME_SC_ABORT_QUEUE		= 0x8,
-	NVME_SC_FUSED_FAIL		= 0x9,
-	NVME_SC_FUSED_MISSING		= 0xa,
-	NVME_SC_INVALID_NS		= 0xb,
-	NVME_SC_CMD_SEQ_ERROR		= 0xc,
-	NVME_SC_LBA_RANGE		= 0x80,
-	NVME_SC_CAP_EXCEEDED		= 0x81,
-	NVME_SC_NS_NOT_READY		= 0x82,
-	NVME_SC_CQ_INVALID		= 0x100,
-	NVME_SC_QID_INVALID		= 0x101,
-	NVME_SC_QUEUE_SIZE		= 0x102,
-	NVME_SC_ABORT_LIMIT		= 0x103,
-	NVME_SC_ABORT_MISSING		= 0x104,
-	NVME_SC_ASYNC_LIMIT		= 0x105,
-	NVME_SC_FIRMWARE_SLOT		= 0x106,
-	NVME_SC_FIRMWARE_IMAGE		= 0x107,
-	NVME_SC_INVALID_VECTOR		= 0x108,
-	NVME_SC_INVALID_LOG_PAGE	= 0x109,
-	NVME_SC_INVALID_FORMAT		= 0x10a,
-	NVME_SC_BAD_ATTRIBUTES		= 0x180,
-	NVME_SC_WRITE_FAULT		= 0x280,
-	NVME_SC_READ_ERROR		= 0x281,
-	NVME_SC_GUARD_CHECK		= 0x282,
-	NVME_SC_APPTAG_CHECK		= 0x283,
-	NVME_SC_REFTAG_CHECK		= 0x284,
-	NVME_SC_COMPARE_FAILED		= 0x285,
-	NVME_SC_ACCESS_DENIED		= 0x286,
-};
-
-struct nvme_completion {
-	__le32	result;		/* Used by admin commands to return data */
-	__u32	rsvd;
-	__le16	sq_head;	/* how much of this queue may be reclaimed */
-	__le16	sq_id;		/* submission queue that generated this entry */
-	__u16	command_id;	/* of the command which completed */
-	__le16	status;		/* did the command fail, and if so, why? */
-};
-
-struct nvme_user_io {
-	__u8	opcode;
-	__u8	flags;
-	__u16	control;
-	__u16	nblocks;
-	__u16	rsvd;
-	__u64	metadata;
-	__u64	addr;
-	__u64	slba;
-	__u32	dsmgmt;
-	__u32	reftag;
-	__u16	apptag;
-	__u16	appmask;
-};
-
-struct nvme_admin_cmd {
-	__u8	opcode;
-	__u8	flags;
-	__u16	rsvd1;
-	__u32	nsid;
-	__u32	cdw2;
-	__u32	cdw3;
-	__u64	metadata;
-	__u64	addr;
-	__u32	metadata_len;
-	__u32	data_len;
-	__u32	cdw10;
-	__u32	cdw11;
-	__u32	cdw12;
-	__u32	cdw13;
-	__u32	cdw14;
-	__u32	cdw15;
-	__u32	timeout_ms;
-	__u32	result;
-};
-
-#define NVME_IOCTL_ID		_IO('N', 0x40)
-#define NVME_IOCTL_ADMIN_CMD	_IOWR('N', 0x41, struct nvme_admin_cmd)
-#define NVME_IOCTL_SUBMIT_IO	_IOW('N', 0x42, struct nvme_user_io)
-
-#ifdef __KERNEL__
-#include <linux/pci.h>
-#include <linux/miscdevice.h>
-#include <linux/kref.h>
 
 #define NVME_IO_TIMEOUT	(5 * HZ)
 
···
 	struct request_queue *queue;
 	struct gendisk *disk;
 
-	int ns_id;
+	unsigned ns_id;
 	int lba_shift;
 	int ms;
 	u64 mode_select_num_blocks;
···
 	int offset;		/* Of PRP list */
 	int nents;		/* Used in scatterlist */
 	int length;		/* Of data, in bytes */
+	unsigned long start_time;
 	dma_addr_t first_dma;
 	struct scatterlist sg[0];
 };
···
 
 int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr);
 int nvme_sg_get_version_num(int __user *ip);
-
-#endif
 
 #endif /* _LINUX_NVME_H */

include/uapi/linux/Kbuild

···
 header-y += nfsacl.h
 header-y += nl80211.h
 header-y += nubus.h
+header-y += nvme.h
 header-y += nvram.h
 header-y += omap3isp.h
 header-y += omapfb.h

include/uapi/linux/nvme.h

···
+/*
+ * Definitions for the NVM Express interface
+ * Copyright (c) 2011-2013, 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#ifndef _UAPI_LINUX_NVME_H
+#define _UAPI_LINUX_NVME_H
+
+#include <linux/types.h>
+
+struct nvme_id_power_state {
+	__le16			max_power;	/* centiwatts */
+	__u8			rsvd2;
+	__u8			flags;
+	__le32			entry_lat;	/* microseconds */
+	__le32			exit_lat;	/* microseconds */
+	__u8			read_tput;
+	__u8			read_lat;
+	__u8			write_tput;
+	__u8			write_lat;
+	__u8			rsvd16[16];
+};
+
+enum {
+	NVME_PS_FLAGS_MAX_POWER_SCALE	= 1 << 0,
+	NVME_PS_FLAGS_NON_OP_STATE	= 1 << 1,
+};
+
+struct nvme_id_ctrl {
+	__le16			vid;
+	__le16			ssvid;
+	char			sn[20];
+	char			mn[40];
+	char			fr[8];
+	__u8			rab;
+	__u8			ieee[3];
+	__u8			mic;
+	__u8			mdts;
+	__u8			rsvd78[178];
+	__le16			oacs;
+	__u8			acl;
+	__u8			aerl;
+	__u8			frmw;
+	__u8			lpa;
+	__u8			elpe;
+	__u8			npss;
+	__u8			rsvd264[248];
+	__u8			sqes;
+	__u8			cqes;
+	__u8			rsvd514[2];
+	__le32			nn;
+	__le16			oncs;
+	__le16			fuses;
+	__u8			fna;
+	__u8			vwc;
+	__le16			awun;
+	__le16			awupf;
+	__u8			rsvd530[1518];
+	struct nvme_id_power_state	psd[32];
+	__u8			vs[1024];
+};
+
+enum {
+	NVME_CTRL_ONCS_COMPARE			= 1 << 0,
+	NVME_CTRL_ONCS_WRITE_UNCORRECTABLE	= 1 << 1,
+	NVME_CTRL_ONCS_DSM			= 1 << 2,
+};
+
+struct nvme_lbaf {
+	__le16			ms;
+	__u8			ds;
+	__u8			rp;
+};
+
+struct nvme_id_ns {
+	__le64			nsze;
+	__le64			ncap;
+	__le64			nuse;
+	__u8			nsfeat;
+	__u8			nlbaf;
+	__u8			flbas;
+	__u8			mc;
+	__u8			dpc;
+	__u8			dps;
+	__u8			rsvd30[98];
+	struct nvme_lbaf	lbaf[16];
+	__u8			rsvd192[192];
+	__u8			vs[3712];
+};
+
+enum {
+	NVME_NS_FEAT_THIN	= 1 << 0,
+	NVME_LBAF_RP_BEST	= 0,
+	NVME_LBAF_RP_BETTER	= 1,
+	NVME_LBAF_RP_GOOD	= 2,
+	NVME_LBAF_RP_DEGRADED	= 3,
+};
+
+struct nvme_smart_log {
+	__u8			critical_warning;
+	__u8			temperature[2];
+	__u8			avail_spare;
+	__u8			spare_thresh;
+	__u8			percent_used;
+	__u8			rsvd6[26];
+	__u8			data_units_read[16];
+	__u8			data_units_written[16];
+	__u8			host_reads[16];
+	__u8			host_writes[16];
+	__u8			ctrl_busy_time[16];
+	__u8			power_cycles[16];
+	__u8			power_on_hours[16];
+	__u8			unsafe_shutdowns[16];
+	__u8			media_errors[16];
+	__u8			num_err_log_entries[16];
+	__u8			rsvd192[320];
+};
+
+enum {
+	NVME_SMART_CRIT_SPARE		= 1 << 0,
+	NVME_SMART_CRIT_TEMPERATURE	= 1 << 1,
+	NVME_SMART_CRIT_RELIABILITY	= 1 << 2,
+	NVME_SMART_CRIT_MEDIA		= 1 << 3,
+	NVME_SMART_CRIT_VOLATILE_MEMORY	= 1 << 4,
+};
+
+struct nvme_lba_range_type {
+	__u8			type;
+	__u8			attributes;
+	__u8			rsvd2[14];
+	__u64			slba;
+	__u64			nlb;
+	__u8			guid[16];
+	__u8			rsvd48[16];
+};
+
+enum {
+	NVME_LBART_TYPE_FS	= 0x01,
+	NVME_LBART_TYPE_RAID	= 0x02,
+	NVME_LBART_TYPE_CACHE	= 0x03,
+	NVME_LBART_TYPE_SWAP	= 0x04,
+
+	NVME_LBART_ATTRIB_TEMP	= 1 << 0,
+	NVME_LBART_ATTRIB_HIDE	= 1 << 1,
+};
+
+/* I/O commands */
+
+enum nvme_opcode {
+	nvme_cmd_flush		= 0x00,
+	nvme_cmd_write		= 0x01,
+	nvme_cmd_read		= 0x02,
+	nvme_cmd_write_uncor	= 0x04,
+	nvme_cmd_compare	= 0x05,
+	nvme_cmd_dsm		= 0x09,
+};
+
+struct nvme_common_command {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__le32			cdw2[2];
+	__le64			metadata;
+	__le64			prp1;
+	__le64			prp2;
+	__le32			cdw10[6];
+};
+
+struct nvme_rw_command {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__u64			rsvd2;
+	__le64			metadata;
+	__le64			prp1;
+	__le64			prp2;
+	__le64			slba;
+	__le16			length;
+	__le16			control;
+	__le32			dsmgmt;
+	__le32			reftag;
+	__le16			apptag;
+	__le16			appmask;
+};
+
+enum {
+	NVME_RW_LR			= 1 << 15,
+	NVME_RW_FUA			= 1 << 14,
+	NVME_RW_DSM_FREQ_UNSPEC		= 0,
+	NVME_RW_DSM_FREQ_TYPICAL	= 1,
+	NVME_RW_DSM_FREQ_RARE		= 2,
+	NVME_RW_DSM_FREQ_READS		= 3,
+	NVME_RW_DSM_FREQ_WRITES		= 4,
+	NVME_RW_DSM_FREQ_RW		= 5,
+	NVME_RW_DSM_FREQ_ONCE		= 6,
+	NVME_RW_DSM_FREQ_PREFETCH	= 7,
+	NVME_RW_DSM_FREQ_TEMP		= 8,
+	NVME_RW_DSM_LATENCY_NONE	= 0 << 4,
+	NVME_RW_DSM_LATENCY_IDLE	= 1 << 4,
+	NVME_RW_DSM_LATENCY_NORM	= 2 << 4,
+	NVME_RW_DSM_LATENCY_LOW		= 3 << 4,
+	NVME_RW_DSM_SEQ_REQ		= 1 << 6,
+	NVME_RW_DSM_COMPRESSED		= 1 << 7,
+};
+
+struct nvme_dsm_cmd {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__u64			rsvd2[2];
+	__le64			prp1;
+	__le64			prp2;
+	__le32			nr;
+	__le32			attributes;
+	__u32			rsvd12[4];
+};
+
+enum {
+	NVME_DSMGMT_IDR		= 1 << 0,
+	NVME_DSMGMT_IDW		= 1 << 1,
+	NVME_DSMGMT_AD		= 1 << 2,
+};
+
+struct nvme_dsm_range {
+	__le32			cattr;
+	__le32			nlb;
+	__le64			slba;
+};
+
+/* Admin commands */
+
+enum nvme_admin_opcode {
+	nvme_admin_delete_sq		= 0x00,
+	nvme_admin_create_sq		= 0x01,
+	nvme_admin_get_log_page		= 0x02,
+	nvme_admin_delete_cq		= 0x04,
+	nvme_admin_create_cq		= 0x05,
+	nvme_admin_identify		= 0x06,
+	nvme_admin_abort_cmd		= 0x08,
+	nvme_admin_set_features		= 0x09,
+	nvme_admin_get_features		= 0x0a,
+	nvme_admin_async_event		= 0x0c,
+	nvme_admin_activate_fw		= 0x10,
+	nvme_admin_download_fw		= 0x11,
+	nvme_admin_format_nvm		= 0x80,
+	nvme_admin_security_send	= 0x81,
+	nvme_admin_security_recv	= 0x82,
+};
+
+enum {
+	NVME_QUEUE_PHYS_CONTIG	= (1 << 0),
+	NVME_CQ_IRQ_ENABLED	= (1 << 1),
+	NVME_SQ_PRIO_URGENT	= (0 << 1),
+	NVME_SQ_PRIO_HIGH	= (1 << 1),
+	NVME_SQ_PRIO_MEDIUM	= (2 << 1),
+	NVME_SQ_PRIO_LOW	= (3 << 1),
+	NVME_FEAT_ARBITRATION	= 0x01,
+	NVME_FEAT_POWER_MGMT	= 0x02,
+	NVME_FEAT_LBA_RANGE	= 0x03,
+	NVME_FEAT_TEMP_THRESH	= 0x04,
+	NVME_FEAT_ERR_RECOVERY	= 0x05,
+	NVME_FEAT_VOLATILE_WC	= 0x06,
+	NVME_FEAT_NUM_QUEUES	= 0x07,
+	NVME_FEAT_IRQ_COALESCE	= 0x08,
+	NVME_FEAT_IRQ_CONFIG	= 0x09,
+	NVME_FEAT_WRITE_ATOMIC	= 0x0a,
+	NVME_FEAT_ASYNC_EVENT	= 0x0b,
+	NVME_FEAT_SW_PROGRESS	= 0x0c,
+	NVME_FWACT_REPL		= (0 << 3),
+	NVME_FWACT_REPL_ACTV	= (1 << 3),
+	NVME_FWACT_ACTV		= (2 << 3),
+};
+
+struct nvme_identify {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__u64			rsvd2[2];
+	__le64			prp1;
+	__le64			prp2;
+	__le32			cns;
+	__u32			rsvd11[5];
+};
+
+struct nvme_features {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__u64			rsvd2[2];
+	__le64			prp1;
+	__le64			prp2;
+	__le32			fid;
+	__le32			dword11;
+	__u32			rsvd12[4];
+};
+
+struct nvme_create_cq {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__u32			rsvd1[5];
+	__le64			prp1;
+	__u64			rsvd8;
+	__le16			cqid;
+	__le16			qsize;
+	__le16			cq_flags;
+	__le16			irq_vector;
+	__u32			rsvd12[4];
+};
+
+struct nvme_create_sq {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__u32			rsvd1[5];
+	__le64			prp1;
+	__u64			rsvd8;
+	__le16			sqid;
+	__le16			qsize;
+	__le16			sq_flags;
+	__le16			cqid;
+	__u32			rsvd12[4];
+};
+
+struct nvme_delete_queue {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__u32			rsvd1[9];
+	__le16			qid;
+	__u16			rsvd10;
+	__u32			rsvd11[5];
+};
+
+struct nvme_download_firmware {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__u32			rsvd1[5];
+	__le64			prp1;
+	__le64			prp2;
+	__le32			numd;
+	__le32			offset;
+	__u32			rsvd12[4];
+};
+
+struct nvme_format_cmd {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__u64			rsvd2[4];
+	__le32			cdw10;
+	__u32			rsvd11[5];
+};
+
+struct nvme_command {
+	union {
+		struct nvme_common_command common;
+		struct nvme_rw_command rw;
+		struct nvme_identify identify;
+		struct nvme_features features;
+		struct nvme_create_cq create_cq;
+		struct nvme_create_sq create_sq;
+		struct nvme_delete_queue delete_queue;
+		struct nvme_download_firmware dlfw;
+		struct nvme_format_cmd format;
+		struct nvme_dsm_cmd dsm;
+	};
+};
+
+enum {
+	NVME_SC_SUCCESS			= 0x0,
+	NVME_SC_INVALID_OPCODE		= 0x1,
+	NVME_SC_INVALID_FIELD		= 0x2,
+	NVME_SC_CMDID_CONFLICT		= 0x3,
+	NVME_SC_DATA_XFER_ERROR		= 0x4,
+	NVME_SC_POWER_LOSS		= 0x5,
+	NVME_SC_INTERNAL		= 0x6,
+	NVME_SC_ABORT_REQ		= 0x7,
+	NVME_SC_ABORT_QUEUE		= 0x8,
+	NVME_SC_FUSED_FAIL		= 0x9,
+	NVME_SC_FUSED_MISSING		= 0xa,
+	NVME_SC_INVALID_NS		= 0xb,
+	NVME_SC_CMD_SEQ_ERROR		= 0xc,
+	NVME_SC_LBA_RANGE		= 0x80,
+	NVME_SC_CAP_EXCEEDED		= 0x81,
+	NVME_SC_NS_NOT_READY		= 0x82,
+	NVME_SC_CQ_INVALID		= 0x100,
+	NVME_SC_QID_INVALID		= 0x101,
+	NVME_SC_QUEUE_SIZE		= 0x102,
+	NVME_SC_ABORT_LIMIT		= 0x103,
+	NVME_SC_ABORT_MISSING		= 0x104,
+	NVME_SC_ASYNC_LIMIT		= 0x105,
+	NVME_SC_FIRMWARE_SLOT		= 0x106,
+	NVME_SC_FIRMWARE_IMAGE		= 0x107,
+	NVME_SC_INVALID_VECTOR		= 0x108,
+	NVME_SC_INVALID_LOG_PAGE	= 0x109,
+	NVME_SC_INVALID_FORMAT		= 0x10a,
+	NVME_SC_BAD_ATTRIBUTES		= 0x180,
+	NVME_SC_WRITE_FAULT		= 0x280,
+	NVME_SC_READ_ERROR		= 0x281,
+	NVME_SC_GUARD_CHECK		= 0x282,
+	NVME_SC_APPTAG_CHECK		= 0x283,
+	NVME_SC_REFTAG_CHECK		= 0x284,
+	NVME_SC_COMPARE_FAILED		= 0x285,
+	NVME_SC_ACCESS_DENIED		= 0x286,
+};
+
+struct nvme_completion {
+	__le32	result;		/* Used by admin commands to return data */
+	__u32	rsvd;
+	__le16	sq_head;	/* how much of this queue may be reclaimed */
+	__le16	sq_id;		/* submission queue that generated this entry */
+	__u16	command_id;	/* of the command which completed */
+	__le16	status;		/* did the command fail, and if so, why? */
+};
+
+struct nvme_user_io {
+	__u8	opcode;
+	__u8	flags;
+	__u16	control;
+	__u16	nblocks;
+	__u16	rsvd;
+	__u64	metadata;
+	__u64	addr;
+	__u64	slba;
+	__u32	dsmgmt;
+	__u32	reftag;
+	__u16	apptag;
+	__u16	appmask;
+};
+
+struct nvme_admin_cmd {
+	__u8	opcode;
+	__u8	flags;
+	__u16	rsvd1;
+	__u32	nsid;
+	__u32	cdw2;
+	__u32	cdw3;
+	__u64	metadata;
+	__u64	addr;
+	__u32	metadata_len;
+	__u32	data_len;
+	__u32	cdw10;
+	__u32	cdw11;
+	__u32	cdw12;
+	__u32	cdw13;
+	__u32	cdw14;
+	__u32	cdw15;
+	__u32	timeout_ms;
+	__u32	result;
+};
+
+#define NVME_IOCTL_ID		_IO('N', 0x40)
+#define NVME_IOCTL_ADMIN_CMD	_IOWR('N', 0x41, struct nvme_admin_cmd)
+#define NVME_IOCTL_SUBMIT_IO	_IOW('N', 0x42, struct nvme_user_io)
+
+#endif /* _UAPI_LINUX_NVME_H */