//#define DEBUG
#include <linux/spinlock.h>
+#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/hdreg.h>
#include <linux/virtio.h>
struct list_head list;
struct request *req;
struct virtio_blk_outhdr out_hdr;
+ struct virtio_scsi_inhdr in_hdr;
u8 status;
};
spin_lock_irqsave(&vblk->lock, flags);
while ((vbr = vblk->vq->vq_ops->get_buf(vblk->vq, &len)) != NULL) {
int error;
+
switch (vbr->status) {
case VIRTIO_BLK_S_OK:
error = 0;
break;
}
+ 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);
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 = blk_rq_pos(vbr->req);
vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
- } else if (blk_pc_request(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 = req_get_ioprio(vbr->req);
- } else {
+ 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;
- 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->status, sizeof(vbr->status));
+ 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));
}
- if (vblk->vq->vq_ops->add_buf(vblk->vq, vblk->sg, out, in, vbr)) {
+ 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) < 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;
+ 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
blk_stop_queue(q);
break;
}
- blkdev_dequeue_request(req);
+ blk_start_request(req);
issued++;
}
vblk->vq->vq_ops->kick(vblk->vq);
}
+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(bdev->bd_disk->queue,
- bdev->bd_disk, mode, 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);
}
return 0;
}
-static struct block_device_operations virtblk_fops = {
+static const struct block_device_operations virtblk_fops = {
.locked_ioctl = virtblk_ioctl,
.owner = THIS_MODULE,
.getgeo = virtblk_getgeo,
return index << PART_BITS;
}
-static int virtblk_probe(struct virtio_device *vdev)
+static int __devinit virtblk_probe(struct virtio_device *vdev)
{
struct virtio_blk *vblk;
+ struct request_queue *q;
int err;
u64 cap;
- u32 v;
- u32 blk_size, sg_elems;
+ 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;
sg_init_table(vblk->sg, vblk->sg_elems);
/* We expect one virtqueue, for output. */
- vblk->vq = vdev->config->find_vq(vdev, 0, 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_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;
}
- queue_flag_set_unlocked(QUEUE_FLAG_VIRT, vblk->disk->queue);
+ q->queuedata = vblk;
if (index < 26) {
sprintf(vblk->disk->disk_name, "vd%c", 'a' + index % 26);
index++;
/* If barriers are supported, tell block layer that queue is ordered */
- if (virtio_has_feature(vdev, 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);
/* If disk is read-only in the host, the guest should obey */
if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
set_capacity(vblk->disk, cap);
/* We can handle whatever the host told us to handle. */
- blk_queue_max_phys_segments(vblk->disk->queue, vblk->sg_elems-2);
- blk_queue_max_hw_segments(vblk->disk->queue, vblk->sg_elems-2);
+ 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);
/* No real sector limit. */
- blk_queue_max_sectors(vblk->disk->queue, -1U);
+ blk_queue_max_sectors(q, -1U);
/* Host can optionally specify maximum segment size and number of
* segments. */
offsetof(struct virtio_blk_config, size_max),
&v);
if (!err)
- blk_queue_max_segment_size(vblk->disk->queue, v);
+ blk_queue_max_segment_size(q, v);
else
- blk_queue_max_segment_size(vblk->disk->queue, -1U);
+ 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_hardsect_size(vblk->disk->queue, blk_size);
+ 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_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;
blk_cleanup_queue(vblk->disk->queue);
put_disk(vblk->disk);
mempool_destroy(vblk->pool);
- vdev->config->del_vq(vblk->vq);
+ 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 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
};
-static struct virtio_driver virtio_blk = {
+/*
+ * 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,
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff