linux/drivers/block/virtio_blk.c
Linus Torvalds cdd5983063 virtio: fixes on top of 3.4-rc2
Here are some virtio fixes for 3.4:
 a test build fix, a patch by Ren fixing naming for systems with a massive
 number of virtio blk devices, and balloon fixes for powerpc
 by David Gibson.
 
 There was some discussion about Ren's patch for virtio disc naming: some people
 wanted to move the legacy name mangling function to the block core.  But
 there's no concensus on that yet, and we can always deduplicate later.
 Added comments in the hope that this will stop people from
 copying this legacy naming scheme into future drivers.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.11 (GNU/Linux)
 
 iQEcBAABAgAGBQJPio1GAAoJECgfDbjSjVRpGDAH/3C/bXm9mriuNauRHwktHgJe
 gmh2BfUgnxly6vheuz0Fv61lTe6V8kekHVolbUYwAUgXeWEKK1C59xehrMGRIPDG
 1XUiti50U3P+skhIfrbkS5nZ7L+5Hk0ToQ6dd9v0BM2GxDOvgwidlY1bZe+wJEZf
 Lvl6w/djBCr1e3k4qfRnpTcdJJ4FnOjGbikLQhSTGfUXeNo6uWS1hljYWnAhzFkd
 1xU8h5PP0TDR0nYb80CeB+9Lxw0w4qyNPJIBhNN6ucB/1U6R+55HpEpmrLUkn910
 sEFEFsc0cRVWr8FiOTlmzxLHnwTc8AY/Bsp9TMSmnTRu3ZQcoQMTQQCczRj04xI=
 =VmpJ
 -----END PGP SIGNATURE-----

Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio fixes from Michael S. Tsirkin:
 "Here are some virtio fixes for 3.4: a test build fix, a patch by Ren
  fixing naming for systems with a massive number of virtio blk devices,
  and balloon fixes for powerpc by David Gibson.

  There was some discussion about Ren's patch for virtio disc naming:
  some people wanted to move the legacy name mangling function to the
  block core.  But there's no concensus on that yet, and we can always
  deduplicate later.  Added comments in the hope that this will stop
  people from copying this legacy naming scheme into future drivers."

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio_balloon: fix handling of PAGE_SIZE != 4k
  virtio_balloon: Fix endian bug
  virtio_blk: helper function to format disk names
  tools/virtio: fix up vhost/test module build
2012-04-16 18:34:12 -07:00

718 lines
17 KiB
C

//#define DEBUG
#include <linux/spinlock.h>
#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>
#define PART_BITS 4
static int major;
static DEFINE_IDA(vd_index_ida);
struct workqueue_struct *virtblk_wq;
struct virtio_blk
{
spinlock_t lock;
struct virtio_device *vdev;
struct virtqueue *vq;
/* The disk structure for the kernel. */
struct gendisk *disk;
/* Request tracking. */
struct list_head reqs;
mempool_t *pool;
/* Process context for config space updates */
struct work_struct config_work;
/* Lock for config space updates */
struct mutex config_lock;
/* enable config space updates */
bool config_enable;
/* What host tells us, plus 2 for header & tailer. */
unsigned int sg_elems;
/* Ida index - used to track minor number allocations. */
int index;
/* Scatterlist: can be too big for stack. */
struct scatterlist sg[/*sg_elems*/];
};
struct virtblk_req
{
struct list_head list;
struct request *req;
struct virtio_blk_outhdr out_hdr;
struct virtio_scsi_inhdr in_hdr;
u8 status;
};
static void blk_done(struct virtqueue *vq)
{
struct virtio_blk *vblk = vq->vdev->priv;
struct virtblk_req *vbr;
unsigned int len;
unsigned long flags;
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;
}
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);
break;
default:
break;
}
__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);
}
static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
struct request *req)
{
unsigned long num, out = 0, in = 0;
struct virtblk_req *vbr;
vbr = mempool_alloc(vblk->pool, GFP_ATOMIC);
if (!vbr)
/* When another request finishes we'll try again. */
return false;
vbr->req = req;
if (req->cmd_flags & REQ_FLUSH) {
vbr->out_hdr.type = VIRTIO_BLK_T_FLUSH;
vbr->out_hdr.sector = 0;
vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
} else {
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);
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);
break;
case REQ_TYPE_SPECIAL:
vbr->out_hdr.type = VIRTIO_BLK_T_GET_ID;
vbr->out_hdr.sector = 0;
vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
break;
default:
/* We don't put anything else in the queue. */
BUG();
}
}
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, SCSI_SENSE_BUFFERSIZE);
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 (virtqueue_add_buf(vblk->vq, vblk->sg, out, in, vbr, GFP_ATOMIC)<0) {
mempool_free(vbr, vblk->pool);
return false;
}
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 (issued)
virtqueue_kick(vblk->vq);
}
/* return id (s/n) string for *disk to *id_str
*/
static int virtblk_get_id(struct gendisk *disk, char *id_str)
{
struct virtio_blk *vblk = disk->private_data;
struct request *req;
struct bio *bio;
int err;
bio = bio_map_kern(vblk->disk->queue, id_str, VIRTIO_BLK_ID_BYTES,
GFP_KERNEL);
if (IS_ERR(bio))
return PTR_ERR(bio);
req = blk_make_request(vblk->disk->queue, bio, GFP_KERNEL);
if (IS_ERR(req)) {
bio_put(bio);
return PTR_ERR(req);
}
req->cmd_type = REQ_TYPE_SPECIAL;
err = blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
blk_put_request(req);
return err;
}
static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long data)
{
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_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;
} 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 = {
.ioctl = virtblk_ioctl,
.owner = THIS_MODULE,
.getgeo = virtblk_getgeo,
};
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)
{
struct gendisk *disk = dev_to_disk(dev);
int err;
/* sysfs gives us a PAGE_SIZE buffer */
BUILD_BUG_ON(PAGE_SIZE < VIRTIO_BLK_ID_BYTES);
buf[VIRTIO_BLK_ID_BYTES] = '\0';
err = virtblk_get_id(disk, buf);
if (!err)
return strlen(buf);
if (err == -EIO) /* Unsupported? Make it empty. */
return 0;
return err;
}
DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);
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];
u64 capacity, size;
mutex_lock(&vblk->config_lock);
if (!vblk->config_enable)
goto done;
/* Host must always specify the capacity. */
vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity),
&capacity, sizeof(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);
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, blk_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 __devinit virtblk_probe(struct virtio_device *vdev)
{
struct virtio_blk *vblk;
struct request_queue *q;
int err, index;
u64 cap;
u32 v, blk_size, sg_elems, opt_io_size;
u16 min_io_size;
u8 physical_block_exp, alignment_offset;
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);
/* We need at least one SG element, whatever they say. */
if (err || !sg_elems)
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_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);
INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
vblk->config_enable = true;
err = init_vq(vblk);
if (err)
goto out_free_vblk;
vblk->pool = mempool_create_kmalloc_pool(1,sizeof(struct virtblk_req));
if (!vblk->pool) {
err = -ENOMEM;
goto out_free_vq;
}
/* 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;
}
q = vblk->disk->queue = blk_init_queue(do_virtblk_request, &vblk->lock);
if (!q) {
err = -ENOMEM;
goto out_put_disk;
}
q->queuedata = vblk;
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;
vblk->index = index;
/* configure queue flush support */
if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH))
blk_queue_flush(q, REQ_FLUSH);
/* 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) {
dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n",
(unsigned long long)cap);
cap = (sector_t)-1;
}
set_capacity(vblk->disk, cap);
/* We can handle whatever the host told us to handle. */
blk_queue_max_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_hw_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_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);
err = device_create_file(disk_to_dev(vblk->disk), &dev_attr_serial);
if (err)
goto out_del_disk;
return 0;
out_del_disk:
del_gendisk(vblk->disk);
blk_cleanup_queue(vblk->disk->queue);
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)
{
struct virtio_blk *vblk = vdev->priv;
int index = vblk->index;
/* Prevent config work handler from accessing the device. */
mutex_lock(&vblk->config_lock);
vblk->config_enable = false;
mutex_unlock(&vblk->config_lock);
/* Nothing should be pending. */
BUG_ON(!list_empty(&vblk->reqs));
/* Stop all the virtqueues. */
vdev->config->reset(vdev);
flush_work(&vblk->config_work);
del_gendisk(vblk->disk);
blk_cleanup_queue(vblk->disk->queue);
put_disk(vblk->disk);
mempool_destroy(vblk->pool);
vdev->config->del_vqs(vdev);
kfree(vblk);
ida_simple_remove(&vd_index_ida, index);
}
#ifdef CONFIG_PM
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);
spin_lock_irq(vblk->disk->queue->queue_lock);
blk_stop_queue(vblk->disk->queue);
spin_unlock_irq(vblk->disk->queue->queue_lock);
blk_sync_queue(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) {
spin_lock_irq(vblk->disk->queue->queue_lock);
blk_start_queue(vblk->disk->queue);
spin_unlock_irq(vblk->disk->queue->queue_lock);
}
return ret;
}
#endif
static const struct virtio_device_id id_table[] = {
{ VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID },
{ 0 },
};
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 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),
.config_changed = virtblk_config_changed,
#ifdef CONFIG_PM
.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) {
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);
MODULE_DEVICE_TABLE(virtio, id_table);
MODULE_DESCRIPTION("Virtio block driver");
MODULE_LICENSE("GPL");