OpenCloudOS-Kernel/drivers/block/virtio_blk.c

790 lines
19 KiB
C
Raw Normal View History

//#define DEBUG
#include <linux/spinlock.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#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
{
struct virtio_device *vdev;
struct virtqueue *vq;
/* The disk structure for the kernel. */
struct gendisk *disk;
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 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;
virtio-blk: Use block layer provided spinlock Block layer will allocate a spinlock for the queue if the driver does not provide one in blk_init_queue(). The reason to use the internal spinlock is that blk_cleanup_queue() will switch to use the internal spinlock in the cleanup code path. if (q->queue_lock != &q->__queue_lock) q->queue_lock = &q->__queue_lock; However, processes which are in D state might have taken the driver provided spinlock, when the processes wake up, they would release the block provided spinlock. ===================================== [ BUG: bad unlock balance detected! ] 3.4.0-rc7+ #238 Not tainted ------------------------------------- fio/3587 is trying to release lock (&(&q->__queue_lock)->rlock) at: [<ffffffff813274d2>] blk_queue_bio+0x2a2/0x380 but there are no more locks to release! other info that might help us debug this: 1 lock held by fio/3587: #0: (&(&vblk->lock)->rlock){......}, at: [<ffffffff8132661a>] get_request_wait+0x19a/0x250 Other drivers use block layer provided spinlock as well, e.g. SCSI. Switching to the block layer provided spinlock saves a bit of memory and does not increase lock contention. Performance test shows no real difference is observed before and after this patch. Changes in v2: Improve commit log as Michael suggested. Cc: virtualization@lists.linux-foundation.org Cc: kvm@vger.kernel.org Cc: stable@kernel.org Signed-off-by: Asias He <asias@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2012-05-25 16:03:27 +08:00
spin_lock_irqsave(vblk->disk->queue->queue_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);
mempool_free(vbr, vblk->pool);
}
/* In case queue is stopped waiting for more buffers. */
blk_start_queue(vblk->disk->queue);
virtio-blk: Use block layer provided spinlock Block layer will allocate a spinlock for the queue if the driver does not provide one in blk_init_queue(). The reason to use the internal spinlock is that blk_cleanup_queue() will switch to use the internal spinlock in the cleanup code path. if (q->queue_lock != &q->__queue_lock) q->queue_lock = &q->__queue_lock; However, processes which are in D state might have taken the driver provided spinlock, when the processes wake up, they would release the block provided spinlock. ===================================== [ BUG: bad unlock balance detected! ] 3.4.0-rc7+ #238 Not tainted ------------------------------------- fio/3587 is trying to release lock (&(&q->__queue_lock)->rlock) at: [<ffffffff813274d2>] blk_queue_bio+0x2a2/0x380 but there are no more locks to release! other info that might help us debug this: 1 lock held by fio/3587: #0: (&(&vblk->lock)->rlock){......}, at: [<ffffffff8132661a>] get_request_wait+0x19a/0x250 Other drivers use block layer provided spinlock as well, e.g. SCSI. Switching to the block layer provided spinlock saves a bit of memory and does not increase lock contention. Performance test shows no real difference is observed before and after this patch. Changes in v2: Improve commit log as Michael suggested. Cc: virtualization@lists.linux-foundation.org Cc: kvm@vger.kernel.org Cc: stable@kernel.org Signed-off-by: Asias He <asias@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2012-05-25 16:03:27 +08:00
spin_unlock_irqrestore(vblk->disk->queue->queue_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;
}
return true;
}
static void do_virtblk_request(struct request_queue *q)
{
struct virtio_blk *vblk = q->queuedata;
struct request *req;
unsigned int issued = 0;
block: implement and enforce request peek/start/fetch Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Miller <mike.miller@hp.com> Cc: unsik Kim <donari75@gmail.com> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Cc: David S. Miller <davem@davemloft.net> Cc: Laurent Vivier <Laurent@lvivier.info> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: Pierre Ossman <drzeus@drzeus.cx> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com> Cc: Stefan Weinhuber <wein@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-08 10:54:16 +08:00
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;
}
block: implement and enforce request peek/start/fetch Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Miller <mike.miller@hp.com> Cc: unsik Kim <donari75@gmail.com> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Cc: David S. Miller <davem@davemloft.net> Cc: Laurent Vivier <Laurent@lvivier.info> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: Pierre Ossman <drzeus@drzeus.cx> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com> Cc: Stefan Weinhuber <wein@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-08 10:54:16 +08:00
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 virtblk_get_cache_mode(struct virtio_device *vdev)
{
u8 writeback;
int err;
err = virtio_config_val(vdev, VIRTIO_BLK_F_CONFIG_WCE,
offsetof(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;
u8 writeback;
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;
writeback = i;
vdev->config->set(vdev,
offsetof(struct virtio_blk_config, wce),
&writeback, sizeof(writeback));
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 __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;
}
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;
}
virtio-blk: Use block layer provided spinlock Block layer will allocate a spinlock for the queue if the driver does not provide one in blk_init_queue(). The reason to use the internal spinlock is that blk_cleanup_queue() will switch to use the internal spinlock in the cleanup code path. if (q->queue_lock != &q->__queue_lock) q->queue_lock = &q->__queue_lock; However, processes which are in D state might have taken the driver provided spinlock, when the processes wake up, they would release the block provided spinlock. ===================================== [ BUG: bad unlock balance detected! ] 3.4.0-rc7+ #238 Not tainted ------------------------------------- fio/3587 is trying to release lock (&(&q->__queue_lock)->rlock) at: [<ffffffff813274d2>] blk_queue_bio+0x2a2/0x380 but there are no more locks to release! other info that might help us debug this: 1 lock held by fio/3587: #0: (&(&vblk->lock)->rlock){......}, at: [<ffffffff8132661a>] get_request_wait+0x19a/0x250 Other drivers use block layer provided spinlock as well, e.g. SCSI. Switching to the block layer provided spinlock saves a bit of memory and does not increase lock contention. Performance test shows no real difference is observed before and after this patch. Changes in v2: Improve commit log as Michael suggested. Cc: virtualization@lists.linux-foundation.org Cc: kvm@vger.kernel.org Cc: stable@kernel.org Signed-off-by: Asias He <asias@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2012-05-25 16:03:27 +08:00
q = vblk->disk->queue = blk_init_queue(do_virtblk_request, NULL);
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 */
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));
/* 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;
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_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);
del_gendisk(vblk->disk);
blk_cleanup_queue(vblk->disk->queue);
/* Stop all the virtqueues. */
vdev->config->reset(vdev);
flush_work(&vblk->config_work);
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_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),
.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");