1 files changed, 503 insertions, 206 deletions

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 6ecf89cdf00..f63d358f3d9 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -3,103 +3,170 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/virtio.h>
 #include <linux/virtio_blk.h>
 #include <linux/scatterlist.h>
+#include <linux/string_helpers.h>
+#include <scsi/scsi_cmnd.h>
+#include <linux/idr.h>
+#include <linux/blk-mq.h>
+#include <linux/numa.h>
 
 #define PART_BITS 4
 
-static int major, index;
+static int major;
+static DEFINE_IDA(vd_index_ida);
+
+static struct workqueue_struct *virtblk_wq;
 
 struct virtio_blk
 {
-	spinlock_t lock;
-
 	struct virtio_device *vdev;
 	struct virtqueue *vq;
+	spinlock_t vq_lock;
 
 	/* The disk structure for the kernel. */
 	struct gendisk *disk;
 
-	/* Request tracking. */
-	struct list_head reqs;
+	/* Block layer tags. */
+	struct blk_mq_tag_set tag_set;
+
+	/* Process context for config space updates */
+	struct work_struct config_work;
+
+	/* Lock for config space updates */
+	struct mutex config_lock;
 
-	mempool_t *pool;
+	/* enable config space updates */
+	bool config_enable;
 
 	/* What host tells us, plus 2 for header & tailer. */
 	unsigned int sg_elems;
 
-	/* Scatterlist: can be too big for stack. */
-	struct scatterlist sg[/*sg_elems*/];
+	/* Ida index - used to track minor number allocations. */
+	int index;
 };
 
 struct virtblk_req
 {
-	struct list_head list;
 	struct request *req;
 	struct virtio_blk_outhdr out_hdr;
 	struct virtio_scsi_inhdr in_hdr;
 	u8 status;
+	struct scatterlist sg[];
 };
 
-static void blk_done(struct virtqueue *vq)
+static inline int virtblk_result(struct virtblk_req *vbr)
+{
+	switch (vbr->status) {
+	case VIRTIO_BLK_S_OK:
+		return 0;
+	case VIRTIO_BLK_S_UNSUPP:
+		return -ENOTTY;
+	default:
+		return -EIO;
+	}
+}
+
+static int __virtblk_add_req(struct virtqueue *vq,
+			     struct virtblk_req *vbr,
+			     struct scatterlist *data_sg,
+			     bool have_data)
+{
+	struct scatterlist hdr, status, cmd, sense, inhdr, *sgs[6];
+	unsigned int num_out = 0, num_in = 0;
+	int type = vbr->out_hdr.type & ~VIRTIO_BLK_T_OUT;
+
+	sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
+	sgs[num_out++] = &hdr;
+
+	/*
+	 * If this is a packet command we need a couple of additional headers.
+	 * Behind the normal outhdr we put a segment with the scsi command
+	 * block, and before the normal inhdr we put the sense data and the
+	 * inhdr with additional status information.
+	 */
+	if (type == VIRTIO_BLK_T_SCSI_CMD) {
+		sg_init_one(&cmd, vbr->req->cmd, vbr->req->cmd_len);
+		sgs[num_out++] = &cmd;
+	}
+
+	if (have_data) {
+		if (vbr->out_hdr.type & VIRTIO_BLK_T_OUT)
+			sgs[num_out++] = data_sg;
+		else
+			sgs[num_out + num_in++] = data_sg;
+	}
+
+	if (type == VIRTIO_BLK_T_SCSI_CMD) {
+		sg_init_one(&sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
+		sgs[num_out + num_in++] = &sense;
+		sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
+		sgs[num_out + num_in++] = &inhdr;
+	}
+
+	sg_init_one(&status, &vbr->status, sizeof(vbr->status));
+	sgs[num_out + num_in++] = &status;
+
+	return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
+}
+
+static inline void virtblk_request_done(struct request *req)
+{
+	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+	int error = virtblk_result(vbr);
+
+	if (req->cmd_type == REQ_TYPE_BLOCK_PC) {
+		req->resid_len = vbr->in_hdr.residual;
+		req->sense_len = vbr->in_hdr.sense_len;
+		req->errors = vbr->in_hdr.errors;
+	} else if (req->cmd_type == REQ_TYPE_SPECIAL) {
+		req->errors = (error != 0);
+	}
+
+	blk_mq_end_io(req, error);
+}
+
+static void virtblk_done(struct virtqueue *vq)
 {
 	struct virtio_blk *vblk = vq->vdev->priv;
+	bool req_done = false;
 	struct virtblk_req *vbr;
-	unsigned int len;
 	unsigned long flags;
+	unsigned int len;
 
-	spin_lock_irqsave(&vblk->lock, flags);
-	while ((vbr = virtqueue_get_buf(vblk->vq, &len)) != NULL) {
-		int error;
-
-		switch (vbr->status) {
-		case VIRTIO_BLK_S_OK:
-			error = 0;
-			break;
-		case VIRTIO_BLK_S_UNSUPP:
-			error = -ENOTTY;
-			break;
-		default:
-			error = -EIO;
-			break;
+	spin_lock_irqsave(&vblk->vq_lock, flags);
+	do {
+		virtqueue_disable_cb(vq);
+		while ((vbr = virtqueue_get_buf(vblk->vq, &len)) != NULL) {
+			blk_mq_complete_request(vbr->req);
+			req_done = true;
 		}
-
-		switch (vbr->req->cmd_type) {
-		case REQ_TYPE_BLOCK_PC:
-			vbr->req->resid_len = vbr->in_hdr.residual;
-			vbr->req->sense_len = vbr->in_hdr.sense_len;
-			vbr->req->errors = vbr->in_hdr.errors;
-			break;
-		case REQ_TYPE_SPECIAL:
-			vbr->req->errors = (error != 0);
+		if (unlikely(virtqueue_is_broken(vq)))
 			break;
-		default:
-			break;
-		}
+	} while (!virtqueue_enable_cb(vq));
 
-		__blk_end_request_all(vbr->req, error);
-		list_del(&vbr->list);
-		mempool_free(vbr, vblk->pool);
-	}
 	/* In case queue is stopped waiting for more buffers. */
-	blk_start_queue(vblk->disk->queue);
-	spin_unlock_irqrestore(&vblk->lock, flags);
+	if (req_done)
+		blk_mq_start_stopped_hw_queues(vblk->disk->queue, true);
+	spin_unlock_irqrestore(&vblk->vq_lock, flags);
 }
 
-static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
-		   struct request *req)
+static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
 {
-	unsigned long num, out = 0, in = 0;
-	struct virtblk_req *vbr;
+	struct virtio_blk *vblk = hctx->queue->queuedata;
+	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+	unsigned long flags;
+	unsigned int num;
+	const bool last = (req->cmd_flags & REQ_END) != 0;
+	int err;
+	bool notify = false;
 
-	vbr = mempool_alloc(vblk->pool, GFP_ATOMIC);
-	if (!vbr)
-		/* When another request finishes we'll try again. */
-		return false;
+	BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
 	vbr->req = req;
-
 	if (req->cmd_flags & REQ_FLUSH) {
 		vbr->out_hdr.type = VIRTIO_BLK_T_FLUSH;
 		vbr->out_hdr.sector = 0;
@@ -127,68 +194,34 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 		}
 	}
 
-	sg_set_buf(&vblk->sg[out++], &vbr->out_hdr, sizeof(vbr->out_hdr));
-
-	/*
-	 * If this is a packet command we need a couple of additional headers.
-	 * Behind the normal outhdr we put a segment with the scsi command
-	 * block, and before the normal inhdr we put the sense data and the
-	 * inhdr with additional status information before the normal inhdr.
-	 */
-	if (vbr->req->cmd_type == REQ_TYPE_BLOCK_PC)
-		sg_set_buf(&vblk->sg[out++], vbr->req->cmd, vbr->req->cmd_len);
-
-	num = blk_rq_map_sg(q, vbr->req, vblk->sg + out);
-
-	if (vbr->req->cmd_type == REQ_TYPE_BLOCK_PC) {
-		sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, 96);
-		sg_set_buf(&vblk->sg[num + out + in++], &vbr->in_hdr,
-			   sizeof(vbr->in_hdr));
-	}
-
-	sg_set_buf(&vblk->sg[num + out + in++], &vbr->status,
-		   sizeof(vbr->status));
-
+	num = blk_rq_map_sg(hctx->queue, vbr->req, vbr->sg);
 	if (num) {
-		if (rq_data_dir(vbr->req) == WRITE) {
+		if (rq_data_dir(vbr->req) == WRITE)
 			vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
-			out += num;
-		} else {
+		else
 			vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
-			in += num;
-		}
 	}
 
-	if (virtqueue_add_buf(vblk->vq, vblk->sg, out, in, vbr) < 0) {
-		mempool_free(vbr, vblk->pool);
-		return false;
+	spin_lock_irqsave(&vblk->vq_lock, flags);
+	err = __virtblk_add_req(vblk->vq, vbr, vbr->sg, num);
+	if (err) {
+		virtqueue_kick(vblk->vq);
+		blk_mq_stop_hw_queue(hctx);
+		spin_unlock_irqrestore(&vblk->vq_lock, flags);
+		/* Out of mem doesn't actually happen, since we fall back
+		 * to direct descriptors */
+		if (err == -ENOMEM || err == -ENOSPC)
+			return BLK_MQ_RQ_QUEUE_BUSY;
+		return BLK_MQ_RQ_QUEUE_ERROR;
 	}
 
-	list_add_tail(&vbr->list, &vblk->reqs);
-	return true;
-}
-
-static void do_virtblk_request(struct request_queue *q)
-{
-	struct virtio_blk *vblk = q->queuedata;
-	struct request *req;
-	unsigned int issued = 0;
-
-	while ((req = blk_peek_request(q)) != NULL) {
-		BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
-
-		/* If this request fails, stop queue and wait for something to
-		   finish to restart it. */
-		if (!do_req(q, vblk, req)) {
-			blk_stop_queue(q);
-			break;
-		}
-		blk_start_request(req);
-		issued++;
-	}
+	if (last && virtqueue_kick_prepare(vblk->vq))
+		notify = true;
+	spin_unlock_irqrestore(&vblk->vq_lock, flags);
 
-	if (issued)
-		virtqueue_kick(vblk->vq);
+	if (notify)
+		virtqueue_notify(vblk->vq);
+	return BLK_MQ_RQ_QUEUE_OK;
 }
 
 /* return id (s/n) string for *disk to *id_str
@@ -230,26 +263,23 @@ static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
 	if (!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_SCSI))
 		return -ENOTTY;
 
-	return scsi_cmd_ioctl(disk->queue, disk, mode, cmd,
-			      (void __user *)data);
+	return scsi_cmd_blk_ioctl(bdev, mode, cmd,
+				  (void __user *)data);
 }
 
 /* We provide getgeo only to please some old bootloader/partitioning tools */
 static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
 {
 	struct virtio_blk *vblk = bd->bd_disk->private_data;
-	struct virtio_blk_geometry vgeo;
-	int err;
 
 	/* see if the host passed in geometry config */
-	err = virtio_config_val(vblk->vdev, VIRTIO_BLK_F_GEOMETRY,
-				offsetof(struct virtio_blk_config, geometry),
-				&vgeo);
-
-	if (!err) {
-		geo->heads = vgeo.heads;
-		geo->sectors = vgeo.sectors;
-		geo->cylinders = vgeo.cylinders;
+	if (virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_GEOMETRY)) {
+		virtio_cread(vblk->vdev, struct virtio_blk_config,
+			     geometry.cylinders, &geo->cylinders);
+		virtio_cread(vblk->vdev, struct virtio_blk_config,
+			     geometry.heads, &geo->heads);
+		virtio_cread(vblk->vdev, struct virtio_blk_config,
+			     geometry.sectors, &geo->sectors);
 	} else {
 		/* some standard values, similar to sd */
 		geo->heads = 1 << 6;
@@ -270,6 +300,11 @@ static int index_to_minor(int index)
 	return index << PART_BITS;
 }
 
+static int minor_to_index(int minor)
+{
+	return minor >> PART_BITS;
+}
+
 static ssize_t virtblk_serial_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -291,23 +326,208 @@ static ssize_t virtblk_serial_show(struct device *dev,
 }
 DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);
 
-static int __devinit virtblk_probe(struct virtio_device *vdev)
+static void virtblk_config_changed_work(struct work_struct *work)
+{
+	struct virtio_blk *vblk =
+		container_of(work, struct virtio_blk, config_work);
+	struct virtio_device *vdev = vblk->vdev;
+	struct request_queue *q = vblk->disk->queue;
+	char cap_str_2[10], cap_str_10[10];
+	char *envp[] = { "RESIZE=1", NULL };
+	u64 capacity, size;
+
+	mutex_lock(&vblk->config_lock);
+	if (!vblk->config_enable)
+		goto done;
+
+	/* Host must always specify the capacity. */
+	virtio_cread(vdev, struct virtio_blk_config, capacity, &capacity);
+
+	/* If capacity is too big, truncate with warning. */
+	if ((sector_t)capacity != capacity) {
+		dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n",
+			 (unsigned long long)capacity);
+		capacity = (sector_t)-1;
+	}
+
+	size = capacity * queue_logical_block_size(q);
+	string_get_size(size, STRING_UNITS_2, cap_str_2, sizeof(cap_str_2));
+	string_get_size(size, STRING_UNITS_10, cap_str_10, sizeof(cap_str_10));
+
+	dev_notice(&vdev->dev,
+		  "new size: %llu %d-byte logical blocks (%s/%s)\n",
+		  (unsigned long long)capacity,
+		  queue_logical_block_size(q),
+		  cap_str_10, cap_str_2);
+
+	set_capacity(vblk->disk, capacity);
+	revalidate_disk(vblk->disk);
+	kobject_uevent_env(&disk_to_dev(vblk->disk)->kobj, KOBJ_CHANGE, envp);
+done:
+	mutex_unlock(&vblk->config_lock);
+}
+
+static void virtblk_config_changed(struct virtio_device *vdev)
+{
+	struct virtio_blk *vblk = vdev->priv;
+
+	queue_work(virtblk_wq, &vblk->config_work);
+}
+
+static int init_vq(struct virtio_blk *vblk)
+{
+	int err = 0;
+
+	/* We expect one virtqueue, for output. */
+	vblk->vq = virtio_find_single_vq(vblk->vdev, virtblk_done, "requests");
+	if (IS_ERR(vblk->vq))
+		err = PTR_ERR(vblk->vq);
+
+	return err;
+}
+
+/*
+ * Legacy naming scheme used for virtio devices.  We are stuck with it for
+ * virtio blk but don't ever use it for any new driver.
+ */
+static int virtblk_name_format(char *prefix, int index, char *buf, int buflen)
+{
+	const int base = 'z' - 'a' + 1;
+	char *begin = buf + strlen(prefix);
+	char *end = buf + buflen;
+	char *p;
+	int unit;
+
+	p = end - 1;
+	*p = '\0';
+	unit = base;
+	do {
+		if (p == begin)
+			return -EINVAL;
+		*--p = 'a' + (index % unit);
+		index = (index / unit) - 1;
+	} while (index >= 0);
+
+	memmove(begin, p, end - p);
+	memcpy(buf, prefix, strlen(prefix));
+
+	return 0;
+}
+
+static int virtblk_get_cache_mode(struct virtio_device *vdev)
+{
+	u8 writeback;
+	int err;
+
+	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_CONFIG_WCE,
+				   struct virtio_blk_config, wce,
+				   &writeback);
+	if (err)
+		writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE);
+
+	return writeback;
+}
+
+static void virtblk_update_cache_mode(struct virtio_device *vdev)
+{
+	u8 writeback = virtblk_get_cache_mode(vdev);
+	struct virtio_blk *vblk = vdev->priv;
+
+	if (writeback)
+		blk_queue_flush(vblk->disk->queue, REQ_FLUSH);
+	else
+		blk_queue_flush(vblk->disk->queue, 0);
+
+	revalidate_disk(vblk->disk);
+}
+
+static const char *const virtblk_cache_types[] = {
+	"write through", "write back"
+};
+
+static ssize_t
+virtblk_cache_type_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	struct virtio_blk *vblk = disk->private_data;
+	struct virtio_device *vdev = vblk->vdev;
+	int i;
+
+	BUG_ON(!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_CONFIG_WCE));
+	for (i = ARRAY_SIZE(virtblk_cache_types); --i >= 0; )
+		if (sysfs_streq(buf, virtblk_cache_types[i]))
+			break;
+
+	if (i < 0)
+		return -EINVAL;
+
+	virtio_cwrite8(vdev, offsetof(struct virtio_blk_config, wce), i);
+	virtblk_update_cache_mode(vdev);
+	return count;
+}
+
+static ssize_t
+virtblk_cache_type_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	struct virtio_blk *vblk = disk->private_data;
+	u8 writeback = virtblk_get_cache_mode(vblk->vdev);
+
+	BUG_ON(writeback >= ARRAY_SIZE(virtblk_cache_types));
+	return snprintf(buf, 40, "%s\n", virtblk_cache_types[writeback]);
+}
+
+static const struct device_attribute dev_attr_cache_type_ro =
+	__ATTR(cache_type, S_IRUGO,
+	       virtblk_cache_type_show, NULL);
+static const struct device_attribute dev_attr_cache_type_rw =
+	__ATTR(cache_type, S_IRUGO|S_IWUSR,
+	       virtblk_cache_type_show, virtblk_cache_type_store);
+
+static int virtblk_init_request(void *data, struct request *rq,
+		unsigned int hctx_idx, unsigned int request_idx,
+		unsigned int numa_node)
+{
+	struct virtio_blk *vblk = data;
+	struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq);
+
+	sg_init_table(vbr->sg, vblk->sg_elems);
+	return 0;
+}
+
+static struct blk_mq_ops virtio_mq_ops = {
+	.queue_rq	= virtio_queue_rq,
+	.map_queue	= blk_mq_map_queue,
+	.complete	= virtblk_request_done,
+	.init_request	= virtblk_init_request,
+};
+
+static unsigned int virtblk_queue_depth;
+module_param_named(queue_depth, virtblk_queue_depth, uint, 0444);
+
+static int virtblk_probe(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk;
 	struct request_queue *q;
-	int err;
+	int err, index;
+
 	u64 cap;
 	u32 v, blk_size, sg_elems, opt_io_size;
 	u16 min_io_size;
 	u8 physical_block_exp, alignment_offset;
 
-	if (index_to_minor(index) >= 1 << MINORBITS)
-		return -ENOSPC;
+	err = ida_simple_get(&vd_index_ida, 0, minor_to_index(1 << MINORBITS),
+			     GFP_KERNEL);
+	if (err < 0)
+		goto out;
+	index = err;
 
 	/* We need to know how many segments before we allocate. */
-	err = virtio_config_val(vdev, VIRTIO_BLK_F_SEG_MAX,
-				offsetof(struct virtio_blk_config, seg_max),
-				&sg_elems);
+	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_SEG_MAX,
+				   struct virtio_blk_config, seg_max,
+				   &sg_elems);
 
 	/* We need at least one SG element, whatever they say. */
 	if (err || !sg_elems)
@@ -315,78 +535,80 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 
 	/* We need an extra sg elements at head and tail. */
 	sg_elems += 2;
-	vdev->priv = vblk = kmalloc(sizeof(*vblk) +
-				    sizeof(vblk->sg[0]) * sg_elems, GFP_KERNEL);
+	vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
 	if (!vblk) {
 		err = -ENOMEM;
-		goto out;
+		goto out_free_index;
 	}
 
-	INIT_LIST_HEAD(&vblk->reqs);
-	spin_lock_init(&vblk->lock);
 	vblk->vdev = vdev;
 	vblk->sg_elems = sg_elems;
-	sg_init_table(vblk->sg, vblk->sg_elems);
+	mutex_init(&vblk->config_lock);
 
-	/* We expect one virtqueue, for output. */
-	vblk->vq = virtio_find_single_vq(vdev, blk_done, "requests");
-	if (IS_ERR(vblk->vq)) {
-		err = PTR_ERR(vblk->vq);
-		goto out_free_vblk;
-	}
+	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
+	vblk->config_enable = true;
 
-	vblk->pool = mempool_create_kmalloc_pool(1,sizeof(struct virtblk_req));
-	if (!vblk->pool) {
-		err = -ENOMEM;
-		goto out_free_vq;
-	}
+	err = init_vq(vblk);
+	if (err)
+		goto out_free_vblk;
+	spin_lock_init(&vblk->vq_lock);
 
 	/* FIXME: How many partitions?  How long is a piece of string? */
 	vblk->disk = alloc_disk(1 << PART_BITS);
 	if (!vblk->disk) {
 		err = -ENOMEM;
-		goto out_mempool;
+		goto out_free_vq;
+	}
+
+	/* Default queue sizing is to fill the ring. */
+	if (!virtblk_queue_depth) {
+		virtblk_queue_depth = vblk->vq->num_free;
+		/* ... but without indirect descs, we use 2 descs per req */
+		if (!virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC))
+			virtblk_queue_depth /= 2;
 	}
 
-	q = vblk->disk->queue = blk_init_queue(do_virtblk_request, &vblk->lock);
+	memset(&vblk->tag_set, 0, sizeof(vblk->tag_set));
+	vblk->tag_set.ops = &virtio_mq_ops;
+	vblk->tag_set.nr_hw_queues = 1;
+	vblk->tag_set.queue_depth = virtblk_queue_depth;
+	vblk->tag_set.numa_node = NUMA_NO_NODE;
+	vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	vblk->tag_set.cmd_size =
+		sizeof(struct virtblk_req) +
+		sizeof(struct scatterlist) * sg_elems;
+	vblk->tag_set.driver_data = vblk;
+
+	err = blk_mq_alloc_tag_set(&vblk->tag_set);
+	if (err)
+		goto out_put_disk;
+
+	q = vblk->disk->queue = blk_mq_init_queue(&vblk->tag_set);
 	if (!q) {
 		err = -ENOMEM;
-		goto out_put_disk;
+		goto out_free_tags;
 	}
 
 	q->queuedata = vblk;
 
-	if (index < 26) {
-		sprintf(vblk->disk->disk_name, "vd%c", 'a' + index % 26);
-	} else if (index < (26 + 1) * 26) {
-		sprintf(vblk->disk->disk_name, "vd%c%c",
-			'a' + index / 26 - 1, 'a' + index % 26);
-	} else {
-		const unsigned int m1 = (index / 26 - 1) / 26 - 1;
-		const unsigned int m2 = (index / 26 - 1) % 26;
-		const unsigned int m3 =  index % 26;
-		sprintf(vblk->disk->disk_name, "vd%c%c%c",
-			'a' + m1, 'a' + m2, 'a' + m3);
-	}
+	virtblk_name_format("vd", index, vblk->disk->disk_name, DISK_NAME_LEN);
 
 	vblk->disk->major = major;
 	vblk->disk->first_minor = index_to_minor(index);
 	vblk->disk->private_data = vblk;
 	vblk->disk->fops = &virtblk_fops;
 	vblk->disk->driverfs_dev = &vdev->dev;
-	index++;
+	vblk->index = index;
 
 	/* configure queue flush support */
-	if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH))
-		blk_queue_flush(q, REQ_FLUSH);
+	virtblk_update_cache_mode(vdev);
 
 	/* If disk is read-only in the host, the guest should obey */
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
 		set_disk_ro(vblk->disk, 1);
 
 	/* Host must always specify the capacity. */
-	vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity),
-			  &cap, sizeof(cap));
+	virtio_cread(vdev, struct virtio_blk_config, capacity, &cap);
 
 	/* If capacity is too big, truncate with warning. */
 	if ((sector_t)cap != cap) {
@@ -407,89 +629,145 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 
 	/* Host can optionally specify maximum segment size and number of
 	 * segments. */
-	err = virtio_config_val(vdev, VIRTIO_BLK_F_SIZE_MAX,
-				offsetof(struct virtio_blk_config, size_max),
-				&v);
+	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_SIZE_MAX,
+				   struct virtio_blk_config, size_max, &v);
 	if (!err)
 		blk_queue_max_segment_size(q, v);
 	else
 		blk_queue_max_segment_size(q, -1U);
 
 	/* Host can optionally specify the block size of the device */
-	err = virtio_config_val(vdev, VIRTIO_BLK_F_BLK_SIZE,
-				offsetof(struct virtio_blk_config, blk_size),
-				&blk_size);
+	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_BLK_SIZE,
+				   struct virtio_blk_config, blk_size,
+				   &blk_size);
 	if (!err)
 		blk_queue_logical_block_size(q, blk_size);
 	else
 		blk_size = queue_logical_block_size(q);
 
 	/* Use topology information if available */
-	err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY,
-			offsetof(struct virtio_blk_config, physical_block_exp),
-			&physical_block_exp);
+	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
+				   struct virtio_blk_config, physical_block_exp,
+				   &physical_block_exp);
 	if (!err && physical_block_exp)
 		blk_queue_physical_block_size(q,
 				blk_size * (1 << physical_block_exp));
 
-	err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY,
-			offsetof(struct virtio_blk_config, alignment_offset),
-			&alignment_offset);
+	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
+				   struct virtio_blk_config, alignment_offset,
+				   &alignment_offset);
 	if (!err && alignment_offset)
 		blk_queue_alignment_offset(q, blk_size * alignment_offset);
 
-	err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY,
-			offsetof(struct virtio_blk_config, min_io_size),
-			&min_io_size);
+	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
+				   struct virtio_blk_config, min_io_size,
+				   &min_io_size);
 	if (!err && min_io_size)
 		blk_queue_io_min(q, blk_size * min_io_size);
 
-	err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY,
-			offsetof(struct virtio_blk_config, opt_io_size),
-			&opt_io_size);
+	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
+				   struct virtio_blk_config, opt_io_size,
+				   &opt_io_size);
 	if (!err && opt_io_size)
 		blk_queue_io_opt(q, blk_size * opt_io_size);
 
-
 	add_disk(vblk->disk);
 	err = device_create_file(disk_to_dev(vblk->disk), &dev_attr_serial);
 	if (err)
 		goto out_del_disk;
 
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_CONFIG_WCE))
+		err = device_create_file(disk_to_dev(vblk->disk),
+					 &dev_attr_cache_type_rw);
+	else
+		err = device_create_file(disk_to_dev(vblk->disk),
+					 &dev_attr_cache_type_ro);
+	if (err)
+		goto out_del_disk;
 	return 0;
 
 out_del_disk:
 	del_gendisk(vblk->disk);
 	blk_cleanup_queue(vblk->disk->queue);
+out_free_tags:
+	blk_mq_free_tag_set(&vblk->tag_set);
 out_put_disk:
 	put_disk(vblk->disk);
-out_mempool:
-	mempool_destroy(vblk->pool);
 out_free_vq:
 	vdev->config->del_vqs(vdev);
 out_free_vblk:
 	kfree(vblk);
+out_free_index:
+	ida_simple_remove(&vd_index_ida, index);
 out:
 	return err;
 }
 
-static void __devexit virtblk_remove(struct virtio_device *vdev)
+static void virtblk_remove(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
+	int index = vblk->index;
+	int refc;
 
-	/* Nothing should be pending. */
-	BUG_ON(!list_empty(&vblk->reqs));
+	/* Prevent config work handler from accessing the device. */
+	mutex_lock(&vblk->config_lock);
+	vblk->config_enable = false;
+	mutex_unlock(&vblk->config_lock);
+
+	del_gendisk(vblk->disk);
+	blk_cleanup_queue(vblk->disk->queue);
+
+	blk_mq_free_tag_set(&vblk->tag_set);
 
 	/* Stop all the virtqueues. */
 	vdev->config->reset(vdev);
 
-	del_gendisk(vblk->disk);
-	blk_cleanup_queue(vblk->disk->queue);
+	flush_work(&vblk->config_work);
+
+	refc = atomic_read(&disk_to_dev(vblk->disk)->kobj.kref.refcount);
 	put_disk(vblk->disk);
-	mempool_destroy(vblk->pool);
 	vdev->config->del_vqs(vdev);
 	kfree(vblk);
+
+	/* Only free device id if we don't have any users */
+	if (refc == 1)
+		ida_simple_remove(&vd_index_ida, index);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int virtblk_freeze(struct virtio_device *vdev)
+{
+	struct virtio_blk *vblk = vdev->priv;
+
+	/* Ensure we don't receive any more interrupts */
+	vdev->config->reset(vdev);
+
+	/* Prevent config work handler from accessing the device. */
+	mutex_lock(&vblk->config_lock);
+	vblk->config_enable = false;
+	mutex_unlock(&vblk->config_lock);
+
+	flush_work(&vblk->config_work);
+
+	blk_mq_stop_hw_queues(vblk->disk->queue);
+
+	vdev->config->del_vqs(vdev);
+	return 0;
+}
+
+static int virtblk_restore(struct virtio_device *vdev)
+{
+	struct virtio_blk *vblk = vdev->priv;
+	int ret;
+
+	vblk->config_enable = true;
+	ret = init_vq(vdev->priv);
+	if (!ret)
+		blk_mq_start_stopped_hw_queues(vblk->disk->queue, true);
+
+	return ret;
 }
+#endif
 
 static const struct virtio_device_id id_table[] = {
 	{ VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID },
@@ -499,36 +777,55 @@ static const struct virtio_device_id id_table[] = {
 static unsigned int features[] = {
 	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
 	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
-	VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY
+	VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE
 };
 
-/*
- * virtio_blk causes spurious section mismatch warning by
- * simultaneously referring to a __devinit and a __devexit function.
- * Use __refdata to avoid this warning.
- */
-static struct virtio_driver __refdata virtio_blk = {
-	.feature_table = features,
-	.feature_table_size = ARRAY_SIZE(features),
-	.driver.name =	KBUILD_MODNAME,
-	.driver.owner =	THIS_MODULE,
-	.id_table =	id_table,
-	.probe =	virtblk_probe,
-	.remove =	__devexit_p(virtblk_remove),
+static struct virtio_driver virtio_blk = {
+	.feature_table		= features,
+	.feature_table_size	= ARRAY_SIZE(features),
+	.driver.name		= KBUILD_MODNAME,
+	.driver.owner		= THIS_MODULE,
+	.id_table		= id_table,
+	.probe			= virtblk_probe,
+	.remove			= virtblk_remove,
+	.config_changed		= virtblk_config_changed,
+#ifdef CONFIG_PM_SLEEP
+	.freeze			= virtblk_freeze,
+	.restore		= virtblk_restore,
+#endif
 };
 
 static int __init init(void)
 {
+	int error;
+
+	virtblk_wq = alloc_workqueue("virtio-blk", 0, 0);
+	if (!virtblk_wq)
+		return -ENOMEM;
+
 	major = register_blkdev(0, "virtblk");
-	if (major < 0)
-		return major;
-	return register_virtio_driver(&virtio_blk);
+	if (major < 0) {
+		error = major;
+		goto out_destroy_workqueue;
+	}
+
+	error = register_virtio_driver(&virtio_blk);
+	if (error)
+		goto out_unregister_blkdev;
+	return 0;
+
+out_unregister_blkdev:
+	unregister_blkdev(major, "virtblk");
+out_destroy_workqueue:
+	destroy_workqueue(virtblk_wq);
+	return error;
 }
 
 static void __exit fini(void)
 {
 	unregister_blkdev(major, "virtblk");
 	unregister_virtio_driver(&virtio_blk);
+	destroy_workqueue(virtblk_wq);
 }
 module_init(init);
 module_exit(fini);