//#define DEBUG
#include <linux/spinlock.h>
+#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/hdreg.h>
#include <linux/virtio.h>
#include <linux/virtio_blk.h>
#include <linux/scatterlist.h>
-#define VIRTIO_MAX_SG (3+MAX_PHYS_SEGMENTS)
+#define PART_BITS 4
+
+static int major, index;
-static unsigned char virtblk_index = 'a';
struct virtio_blk
{
spinlock_t lock;
mempool_t *pool;
+ /* What host tells us, plus 2 for header & tailer. */
+ unsigned int sg_elems;
+
/* Scatterlist: can be too big for stack. */
- struct scatterlist sg[VIRTIO_MAX_SG];
+ struct scatterlist sg[/*sg_elems*/];
};
struct virtblk_req
struct list_head list;
struct request *req;
struct virtio_blk_outhdr out_hdr;
- struct virtio_blk_inhdr in_hdr;
+ struct virtio_scsi_inhdr in_hdr;
+ u8 status;
};
-static bool blk_done(struct virtqueue *vq)
+static void blk_done(struct virtqueue *vq)
{
struct virtio_blk *vblk = vq->vdev->priv;
struct virtblk_req *vbr;
spin_lock_irqsave(&vblk->lock, flags);
while ((vbr = vblk->vq->vq_ops->get_buf(vblk->vq, &len)) != NULL) {
- int uptodate;
- switch (vbr->in_hdr.status) {
+ int error;
+
+ switch (vbr->status) {
case VIRTIO_BLK_S_OK:
- uptodate = 1;
+ error = 0;
break;
case VIRTIO_BLK_S_UNSUPP:
- uptodate = -ENOTTY;
+ error = -ENOTTY;
break;
default:
- uptodate = 0;
+ error = -EIO;
break;
}
- end_dequeued_request(vbr->req, uptodate);
+ if (blk_pc_request(vbr->req)) {
+ vbr->req->resid_len = vbr->in_hdr.residual;
+ vbr->req->sense_len = vbr->in_hdr.sense_len;
+ vbr->req->errors = vbr->in_hdr.errors;
+ }
+
+ __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);
- return true;
}
static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
struct request *req)
{
- unsigned long num, out, in;
+ unsigned long num, out = 0, in = 0;
struct virtblk_req *vbr;
vbr = mempool_alloc(vblk->pool, GFP_ATOMIC);
return false;
vbr->req = req;
- if (blk_fs_request(vbr->req)) {
+ switch (req->cmd_type) {
+ case REQ_TYPE_FS:
vbr->out_hdr.type = 0;
- vbr->out_hdr.sector = vbr->req->sector;
- vbr->out_hdr.ioprio = vbr->req->ioprio;
- } else if (blk_pc_request(vbr->req)) {
+ vbr->out_hdr.sector = blk_rq_pos(vbr->req);
+ vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+ break;
+ case REQ_TYPE_BLOCK_PC:
vbr->out_hdr.type = VIRTIO_BLK_T_SCSI_CMD;
vbr->out_hdr.sector = 0;
- vbr->out_hdr.ioprio = vbr->req->ioprio;
- } else {
+ vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+ break;
+ case REQ_TYPE_LINUX_BLOCK:
+ if (req->cmd[0] == REQ_LB_OP_FLUSH) {
+ vbr->out_hdr.type = VIRTIO_BLK_T_FLUSH;
+ vbr->out_hdr.sector = 0;
+ vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+ break;
+ }
+ /*FALLTHRU*/
+ default:
/* We don't put anything else in the queue. */
BUG();
}
if (blk_barrier_rq(vbr->req))
vbr->out_hdr.type |= VIRTIO_BLK_T_BARRIER;
- /* This init could be done at vblk creation time */
- sg_init_table(vblk->sg, VIRTIO_MAX_SG);
- sg_set_buf(&vblk->sg[0], &vbr->out_hdr, sizeof(vbr->out_hdr));
- num = blk_rq_map_sg(q, vbr->req, vblk->sg+1);
- sg_set_buf(&vblk->sg[num+1], &vbr->in_hdr, sizeof(vbr->in_hdr));
+ sg_set_buf(&vblk->sg[out++], &vbr->out_hdr, sizeof(vbr->out_hdr));
- if (rq_data_dir(vbr->req) == WRITE) {
- vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
- out = 1 + num;
- in = 1;
- } else {
- vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
- out = 1;
- in = 1 + num;
+ /*
+ * 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 (blk_pc_request(vbr->req))
+ 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 (blk_pc_request(vbr->req)) {
+ 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));
+
+ if (num) {
+ if (rq_data_dir(vbr->req) == WRITE) {
+ vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
+ out += num;
+ } else {
+ vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
+ in += num;
+ }
}
- if (vblk->vq->vq_ops->add_buf(vblk->vq, vblk->sg, out, in, vbr)) {
+ if (vblk->vq->vq_ops->add_buf(vblk->vq, vblk->sg, out, in, vbr) < 0) {
mempool_free(vbr, vblk->pool);
return false;
}
static void do_virtblk_request(struct request_queue *q)
{
- struct virtio_blk *vblk = NULL;
+ struct virtio_blk *vblk = q->queuedata;
struct request *req;
unsigned int issued = 0;
- while ((req = elv_next_request(q)) != NULL) {
- vblk = req->rq_disk->private_data;
- BUG_ON(req->nr_phys_segments > ARRAY_SIZE(vblk->sg));
+ 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. */
blk_stop_queue(q);
break;
}
- blkdev_dequeue_request(req);
+ blk_start_request(req);
issued++;
}
vblk->vq->vq_ops->kick(vblk->vq);
}
-static int virtblk_ioctl(struct inode *inode, struct file *filp,
+static void virtblk_prepare_flush(struct request_queue *q, struct request *req)
+{
+ req->cmd_type = REQ_TYPE_LINUX_BLOCK;
+ req->cmd[0] = REQ_LB_OP_FLUSH;
+}
+
+static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
unsigned cmd, unsigned long data)
{
- return scsi_cmd_ioctl(filp, inode->i_bdev->bd_disk->queue,
- inode->i_bdev->bd_disk, cmd,
+ struct gendisk *disk = bdev->bd_disk;
+ struct virtio_blk *vblk = disk->private_data;
+
+ /*
+ * Only allow the generic SCSI ioctls if the host can support it.
+ */
+ if (!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_SCSI))
+ return -ENOTTY;
+
+ return scsi_cmd_ioctl(disk->queue, disk, mode, cmd,
(void __user *)data);
}
-static struct block_device_operations virtblk_fops = {
- .ioctl = virtblk_ioctl,
- .owner = THIS_MODULE,
+/* 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;
+ } else {
+ /* some standard values, similar to sd */
+ geo->heads = 1 << 6;
+ geo->sectors = 1 << 5;
+ geo->cylinders = get_capacity(bd->bd_disk) >> 11;
+ }
+ return 0;
+}
+
+static const struct block_device_operations virtblk_fops = {
+ .locked_ioctl = virtblk_ioctl,
+ .owner = THIS_MODULE,
+ .getgeo = virtblk_getgeo,
};
-static int virtblk_probe(struct virtio_device *vdev)
+static int index_to_minor(int index)
+{
+ return index << PART_BITS;
+}
+
+static int __devinit virtblk_probe(struct virtio_device *vdev)
{
struct virtio_blk *vblk;
- int err, major;
- void *token;
- unsigned int len;
+ struct request_queue *q;
+ int err;
u64 cap;
- u32 v;
-
- vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
+ 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;
+
+ /* 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);
+ if (err)
+ sg_elems = 1;
+
+ /* 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);
if (!vblk) {
err = -ENOMEM;
goto out;
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);
/* We expect one virtqueue, for output. */
- vblk->vq = vdev->config->find_vq(vdev, blk_done);
+ vblk->vq = virtio_find_single_vq(vdev, blk_done, "requests");
if (IS_ERR(vblk->vq)) {
err = PTR_ERR(vblk->vq);
goto out_free_vblk;
goto out_free_vq;
}
- major = register_blkdev(0, "virtblk");
- if (major < 0) {
- err = major;
- goto out_mempool;
- }
-
/* FIXME: How many partitions? How long is a piece of string? */
- vblk->disk = alloc_disk(1 << 4);
+ vblk->disk = alloc_disk(1 << PART_BITS);
if (!vblk->disk) {
err = -ENOMEM;
- goto out_unregister_blkdev;
+ goto out_mempool;
}
- vblk->disk->queue = blk_init_queue(do_virtblk_request, &vblk->lock);
- if (!vblk->disk->queue) {
+ q = vblk->disk->queue = blk_init_queue(do_virtblk_request, &vblk->lock);
+ if (!q) {
err = -ENOMEM;
goto out_put_disk;
}
- sprintf(vblk->disk->disk_name, "vd%c", virtblk_index++);
+ 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);
+ }
+
vblk->disk->major = major;
- vblk->disk->first_minor = 0;
+ 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++;
/* If barriers are supported, tell block layer that queue is ordered */
- token = vdev->config->find(vdev, VIRTIO_CONFIG_BLK_F, &len);
- if (virtio_use_bit(vdev, token, len, VIRTIO_BLK_F_BARRIER))
- blk_queue_ordered(vblk->disk->queue, QUEUE_ORDERED_TAG, NULL);
+ if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH))
+ blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH,
+ virtblk_prepare_flush);
+ else if (virtio_has_feature(vdev, VIRTIO_BLK_F_BARRIER))
+ blk_queue_ordered(q, QUEUE_ORDERED_TAG, NULL);
- err = virtio_config_val(vdev, VIRTIO_CONFIG_BLK_F_CAPACITY, &cap);
- if (err) {
- dev_err(&vdev->dev, "Bad/missing capacity in config\n");
- goto out_put_disk;
- }
+ /* 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));
/* If capacity is too big, truncate with warning. */
if ((sector_t)cap != cap) {
}
set_capacity(vblk->disk, cap);
- err = virtio_config_val(vdev, VIRTIO_CONFIG_BLK_F_SIZE_MAX, &v);
- if (!err)
- blk_queue_max_segment_size(vblk->disk->queue, v);
- else if (err != -ENOENT) {
- dev_err(&vdev->dev, "Bad SIZE_MAX in config\n");
- goto out_put_disk;
- }
+ /* We can handle whatever the host told us to handle. */
+ blk_queue_max_phys_segments(q, vblk->sg_elems-2);
+ blk_queue_max_hw_segments(q, vblk->sg_elems-2);
+
+ /* No need to bounce any requests */
+ blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
- err = virtio_config_val(vdev, VIRTIO_CONFIG_BLK_F_SEG_MAX, &v);
+ /* No real sector limit. */
+ blk_queue_max_sectors(q, -1U);
+
+ /* 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);
if (!err)
- blk_queue_max_hw_segments(vblk->disk->queue, v);
- else if (err != -ENOENT) {
- dev_err(&vdev->dev, "Bad SEG_MAX in config\n");
- goto out_put_disk;
- }
+ 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);
+ 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);
+ 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);
+ 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);
+ 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);
+ if (!err && opt_io_size)
+ blk_queue_io_opt(q, blk_size * opt_io_size);
+
add_disk(vblk->disk);
return 0;
out_put_disk:
put_disk(vblk->disk);
-out_unregister_blkdev:
- unregister_blkdev(major, "virtblk");
out_mempool:
mempool_destroy(vblk->pool);
out_free_vq:
- vdev->config->del_vq(vblk->vq);
+ vdev->config->del_vqs(vdev);
out_free_vblk:
kfree(vblk);
out:
return err;
}
-static void virtblk_remove(struct virtio_device *vdev)
+static void __devexit virtblk_remove(struct virtio_device *vdev)
{
struct virtio_blk *vblk = vdev->priv;
- int major = vblk->disk->major;
+ /* Nothing should be pending. */
BUG_ON(!list_empty(&vblk->reqs));
+
+ /* Stop all the virtqueues. */
+ vdev->config->reset(vdev);
+
+ del_gendisk(vblk->disk);
blk_cleanup_queue(vblk->disk->queue);
put_disk(vblk->disk);
- unregister_blkdev(major, "virtblk");
mempool_destroy(vblk->pool);
+ vdev->config->del_vqs(vdev);
kfree(vblk);
}
-static struct virtio_device_id id_table[] = {
+static const struct virtio_device_id id_table[] = {
{ VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID },
{ 0 },
};
-static struct virtio_driver virtio_blk = {
+static unsigned int features[] = {
+ VIRTIO_BLK_F_BARRIER, 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 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,
static int __init init(void)
{
+ major = register_blkdev(0, "virtblk");
+ if (major < 0)
+ return major;
return register_virtio_driver(&virtio_blk);
}
static void __exit fini(void)
{
+ unregister_blkdev(major, "virtblk");
unregister_virtio_driver(&virtio_blk);
}
module_init(init);