#include <linux/cdrom.h>
#include <linux/module.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
#include <linux/scatterlist.h>
+#include <linux/bitmap.h>
#include <xen/xen.h>
#include <xen/xenbus.h>
#include <xen/grant_table.h>
#include <xen/events.h>
#include <xen/page.h>
+#include <xen/platform_pci.h>
#include <xen/interface/grant_table.h>
#include <xen/interface/io/blkif.h>
struct blk_shadow {
struct blkif_request req;
- unsigned long request;
+ struct request *request;
unsigned long frame[BLKIF_MAX_SEGMENTS_PER_REQUEST];
};
+static DEFINE_MUTEX(blkfront_mutex);
static const struct block_device_operations xlvbd_block_fops;
-#define BLK_RING_SIZE __RING_SIZE((struct blkif_sring *)0, PAGE_SIZE)
+#define BLK_RING_SIZE __CONST_RING_SIZE(blkif, PAGE_SIZE)
/*
* We have one of these per vbd, whether ide, scsi or 'other'. They
*/
struct blkfront_info
{
+ spinlock_t io_lock;
struct mutex mutex;
struct xenbus_device *xbdev;
struct gendisk *gd;
struct gnttab_free_callback callback;
struct blk_shadow shadow[BLK_RING_SIZE];
unsigned long shadow_free;
- int feature_barrier;
+ unsigned int feature_flush;
+ unsigned int flush_op;
+ unsigned int feature_discard:1;
+ unsigned int feature_secdiscard:1;
+ unsigned int discard_granularity;
+ unsigned int discard_alignment;
int is_ready;
-
- /**
- * The number of people holding this device open. We won't allow a
- * hot-unplug unless this is 0.
- */
- int users;
};
-static DEFINE_SPINLOCK(blkif_io_lock);
-
static unsigned int nr_minors;
static unsigned long *minors;
static DEFINE_SPINLOCK(minor_lock);
#define EXTENDED (1<<EXT_SHIFT)
#define VDEV_IS_EXTENDED(dev) ((dev)&(EXTENDED))
#define BLKIF_MINOR_EXT(dev) ((dev)&(~EXTENDED))
+#define EMULATED_HD_DISK_MINOR_OFFSET (0)
+#define EMULATED_HD_DISK_NAME_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET / 256)
+#define EMULATED_SD_DISK_MINOR_OFFSET (0)
+#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_SD_DISK_MINOR_OFFSET / 256)
#define DEV_NAME "xvd" /* name in /dev */
{
unsigned long free = info->shadow_free;
BUG_ON(free >= BLK_RING_SIZE);
- info->shadow_free = info->shadow[free].req.id;
- info->shadow[free].req.id = 0x0fffffee; /* debug */
+ info->shadow_free = info->shadow[free].req.u.rw.id;
+ info->shadow[free].req.u.rw.id = 0x0fffffee; /* debug */
return free;
}
static void add_id_to_freelist(struct blkfront_info *info,
unsigned long id)
{
- info->shadow[id].req.id = info->shadow_free;
- info->shadow[id].request = 0;
+ info->shadow[id].req.u.rw.id = info->shadow_free;
+ info->shadow[id].request = NULL;
info->shadow_free = id;
}
if (end > nr_minors) {
unsigned long *bitmap, *old;
- bitmap = kzalloc(BITS_TO_LONGS(end) * sizeof(*bitmap),
+ bitmap = kcalloc(BITS_TO_LONGS(end), sizeof(*bitmap),
GFP_KERNEL);
if (bitmap == NULL)
return -ENOMEM;
spin_lock(&minor_lock);
if (find_next_bit(minors, end, minor) >= end) {
- for (; minor < end; ++minor)
- __set_bit(minor, minors);
+ bitmap_set(minors, minor, nr);
rc = 0;
} else
rc = -EBUSY;
BUG_ON(end > nr_minors);
spin_lock(&minor_lock);
- for (; minor < end; ++minor)
- __clear_bit(minor, minors);
+ bitmap_clear(minors, minor, nr);
spin_unlock(&minor_lock);
}
}
/*
- * blkif_queue_request
+ * Generate a Xen blkfront IO request from a blk layer request. Reads
+ * and writes are handled as expected.
*
- * request block io
- *
- * id: for guest use only.
- * operation: BLKIF_OP_{READ,WRITE,PROBE}
- * buffer: buffer to read/write into. this should be a
- * virtual address in the guest os.
+ * @req: a request struct
*/
static int blkif_queue_request(struct request *req)
{
/* Fill out a communications ring structure. */
ring_req = RING_GET_REQUEST(&info->ring, info->ring.req_prod_pvt);
id = get_id_from_freelist(info);
- info->shadow[id].request = (unsigned long)req;
+ info->shadow[id].request = req;
- ring_req->id = id;
- ring_req->sector_number = (blkif_sector_t)blk_rq_pos(req);
- ring_req->handle = info->handle;
+ ring_req->u.rw.id = id;
+ ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req);
+ ring_req->u.rw.handle = info->handle;
ring_req->operation = rq_data_dir(req) ?
BLKIF_OP_WRITE : BLKIF_OP_READ;
- if (req->cmd_flags & REQ_HARDBARRIER)
- ring_req->operation = BLKIF_OP_WRITE_BARRIER;
-
- ring_req->nr_segments = blk_rq_map_sg(req->q, req, info->sg);
- BUG_ON(ring_req->nr_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST);
-
- for_each_sg(info->sg, sg, ring_req->nr_segments, i) {
- buffer_mfn = pfn_to_mfn(page_to_pfn(sg_page(sg)));
- fsect = sg->offset >> 9;
- lsect = fsect + (sg->length >> 9) - 1;
- /* install a grant reference. */
- ref = gnttab_claim_grant_reference(&gref_head);
- BUG_ON(ref == -ENOSPC);
-
- gnttab_grant_foreign_access_ref(
- ref,
- info->xbdev->otherend_id,
- buffer_mfn,
- rq_data_dir(req) );
-
- info->shadow[id].frame[i] = mfn_to_pfn(buffer_mfn);
- ring_req->seg[i] =
- (struct blkif_request_segment) {
- .gref = ref,
- .first_sect = fsect,
- .last_sect = lsect };
+
+ if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
+ /*
+ * Ideally we can do an unordered flush-to-disk. In case the
+ * backend onlysupports barriers, use that. A barrier request
+ * a superset of FUA, so we can implement it the same
+ * way. (It's also a FLUSH+FUA, since it is
+ * guaranteed ordered WRT previous writes.)
+ */
+ ring_req->operation = info->flush_op;
+ }
+
+ if (unlikely(req->cmd_flags & (REQ_DISCARD | REQ_SECURE))) {
+ /* id, sector_number and handle are set above. */
+ ring_req->operation = BLKIF_OP_DISCARD;
+ ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
+ if ((req->cmd_flags & REQ_SECURE) && info->feature_secdiscard)
+ ring_req->u.discard.flag = BLKIF_DISCARD_SECURE;
+ else
+ ring_req->u.discard.flag = 0;
+ } else {
+ ring_req->u.rw.nr_segments = blk_rq_map_sg(req->q, req,
+ info->sg);
+ BUG_ON(ring_req->u.rw.nr_segments >
+ BLKIF_MAX_SEGMENTS_PER_REQUEST);
+
+ for_each_sg(info->sg, sg, ring_req->u.rw.nr_segments, i) {
+ buffer_mfn = pfn_to_mfn(page_to_pfn(sg_page(sg)));
+ fsect = sg->offset >> 9;
+ lsect = fsect + (sg->length >> 9) - 1;
+ /* install a grant reference. */
+ ref = gnttab_claim_grant_reference(&gref_head);
+ BUG_ON(ref == -ENOSPC);
+
+ gnttab_grant_foreign_access_ref(
+ ref,
+ info->xbdev->otherend_id,
+ buffer_mfn,
+ rq_data_dir(req));
+
+ info->shadow[id].frame[i] = mfn_to_pfn(buffer_mfn);
+ ring_req->u.rw.seg[i] =
+ (struct blkif_request_segment) {
+ .gref = ref,
+ .first_sect = fsect,
+ .last_sect = lsect };
+ }
}
info->ring.req_prod_pvt++;
blk_start_request(req);
- if (req->cmd_type != REQ_TYPE_FS) {
+ if ((req->cmd_type != REQ_TYPE_FS) ||
+ ((req->cmd_flags & (REQ_FLUSH | REQ_FUA)) &&
+ !info->flush_op)) {
__blk_end_request_all(req, -EIO);
continue;
}
static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
{
struct request_queue *rq;
+ struct blkfront_info *info = gd->private_data;
- rq = blk_init_queue(do_blkif_request, &blkif_io_lock);
+ rq = blk_init_queue(do_blkif_request, &info->io_lock);
if (rq == NULL)
return -1;
queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
+ if (info->feature_discard) {
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq);
+ blk_queue_max_discard_sectors(rq, get_capacity(gd));
+ rq->limits.discard_granularity = info->discard_granularity;
+ rq->limits.discard_alignment = info->discard_alignment;
+ if (info->feature_secdiscard)
+ queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, rq);
+ }
+
/* Hard sector size and max sectors impersonate the equiv. hardware. */
blk_queue_logical_block_size(rq, sector_size);
blk_queue_max_hw_sectors(rq, 512);
}
-static int xlvbd_barrier(struct blkfront_info *info)
+static void xlvbd_flush(struct blkfront_info *info)
{
- int err;
-
- err = blk_queue_ordered(info->rq,
- info->feature_barrier ? QUEUE_ORDERED_DRAIN : QUEUE_ORDERED_NONE);
-
- if (err)
- return err;
-
- printk(KERN_INFO "blkfront: %s: barriers %s\n",
+ blk_queue_flush(info->rq, info->feature_flush);
+ printk(KERN_INFO "blkfront: %s: %s: %s\n",
info->gd->disk_name,
- info->feature_barrier ? "enabled" : "disabled");
- return 0;
+ info->flush_op == BLKIF_OP_WRITE_BARRIER ?
+ "barrier" : (info->flush_op == BLKIF_OP_FLUSH_DISKCACHE ?
+ "flush diskcache" : "barrier or flush"),
+ info->feature_flush ? "enabled" : "disabled");
}
+static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset)
+{
+ int major;
+ major = BLKIF_MAJOR(vdevice);
+ *minor = BLKIF_MINOR(vdevice);
+ switch (major) {
+ case XEN_IDE0_MAJOR:
+ *offset = (*minor / 64) + EMULATED_HD_DISK_NAME_OFFSET;
+ *minor = ((*minor / 64) * PARTS_PER_DISK) +
+ EMULATED_HD_DISK_MINOR_OFFSET;
+ break;
+ case XEN_IDE1_MAJOR:
+ *offset = (*minor / 64) + 2 + EMULATED_HD_DISK_NAME_OFFSET;
+ *minor = (((*minor / 64) + 2) * PARTS_PER_DISK) +
+ EMULATED_HD_DISK_MINOR_OFFSET;
+ break;
+ case XEN_SCSI_DISK0_MAJOR:
+ *offset = (*minor / PARTS_PER_DISK) + EMULATED_SD_DISK_NAME_OFFSET;
+ *minor = *minor + EMULATED_SD_DISK_MINOR_OFFSET;
+ break;
+ case XEN_SCSI_DISK1_MAJOR:
+ case XEN_SCSI_DISK2_MAJOR:
+ case XEN_SCSI_DISK3_MAJOR:
+ case XEN_SCSI_DISK4_MAJOR:
+ case XEN_SCSI_DISK5_MAJOR:
+ case XEN_SCSI_DISK6_MAJOR:
+ case XEN_SCSI_DISK7_MAJOR:
+ *offset = (*minor / PARTS_PER_DISK) +
+ ((major - XEN_SCSI_DISK1_MAJOR + 1) * 16) +
+ EMULATED_SD_DISK_NAME_OFFSET;
+ *minor = *minor +
+ ((major - XEN_SCSI_DISK1_MAJOR + 1) * 16 * PARTS_PER_DISK) +
+ EMULATED_SD_DISK_MINOR_OFFSET;
+ break;
+ case XEN_SCSI_DISK8_MAJOR:
+ case XEN_SCSI_DISK9_MAJOR:
+ case XEN_SCSI_DISK10_MAJOR:
+ case XEN_SCSI_DISK11_MAJOR:
+ case XEN_SCSI_DISK12_MAJOR:
+ case XEN_SCSI_DISK13_MAJOR:
+ case XEN_SCSI_DISK14_MAJOR:
+ case XEN_SCSI_DISK15_MAJOR:
+ *offset = (*minor / PARTS_PER_DISK) +
+ ((major - XEN_SCSI_DISK8_MAJOR + 8) * 16) +
+ EMULATED_SD_DISK_NAME_OFFSET;
+ *minor = *minor +
+ ((major - XEN_SCSI_DISK8_MAJOR + 8) * 16 * PARTS_PER_DISK) +
+ EMULATED_SD_DISK_MINOR_OFFSET;
+ break;
+ case XENVBD_MAJOR:
+ *offset = *minor / PARTS_PER_DISK;
+ break;
+ default:
+ printk(KERN_WARNING "blkfront: your disk configuration is "
+ "incorrect, please use an xvd device instead\n");
+ return -ENODEV;
+ }
+ return 0;
+}
static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
struct blkfront_info *info,
{
struct gendisk *gd;
int nr_minors = 1;
- int err = -ENODEV;
+ int err;
unsigned int offset;
int minor;
int nr_parts;
}
if (!VDEV_IS_EXTENDED(info->vdevice)) {
- minor = BLKIF_MINOR(info->vdevice);
- nr_parts = PARTS_PER_DISK;
+ err = xen_translate_vdev(info->vdevice, &minor, &offset);
+ if (err)
+ return err;
+ nr_parts = PARTS_PER_DISK;
} else {
minor = BLKIF_MINOR_EXT(info->vdevice);
nr_parts = PARTS_PER_EXT_DISK;
+ offset = minor / nr_parts;
+ if (xen_hvm_domain() && offset < EMULATED_HD_DISK_NAME_OFFSET + 4)
+ printk(KERN_WARNING "blkfront: vdevice 0x%x might conflict with "
+ "emulated IDE disks,\n\t choose an xvd device name"
+ "from xvde on\n", info->vdevice);
}
+ err = -ENODEV;
if ((minor % nr_parts) == 0)
nr_minors = nr_parts;
if (gd == NULL)
goto release;
- offset = minor / nr_parts;
-
if (nr_minors > 1) {
if (offset < 26)
sprintf(gd->disk_name, "%s%c", DEV_NAME, 'a' + offset);
info->rq = gd->queue;
info->gd = gd;
- if (info->feature_barrier)
- xlvbd_barrier(info);
+ xlvbd_flush(info);
if (vdisk_info & VDISK_READONLY)
set_disk_ro(gd, 1);
if (info->rq == NULL)
return;
- spin_lock_irqsave(&blkif_io_lock, flags);
+ spin_lock_irqsave(&info->io_lock, flags);
/* No more blkif_request(). */
blk_stop_queue(info->rq);
/* No more gnttab callback work. */
gnttab_cancel_free_callback(&info->callback);
- spin_unlock_irqrestore(&blkif_io_lock, flags);
+ spin_unlock_irqrestore(&info->io_lock, flags);
/* Flush gnttab callback work. Must be done with no locks held. */
- flush_scheduled_work();
+ flush_work_sync(&info->work);
del_gendisk(info->gd);
{
struct blkfront_info *info = container_of(work, struct blkfront_info, work);
- spin_lock_irq(&blkif_io_lock);
+ spin_lock_irq(&info->io_lock);
if (info->connected == BLKIF_STATE_CONNECTED)
kick_pending_request_queues(info);
- spin_unlock_irq(&blkif_io_lock);
+ spin_unlock_irq(&info->io_lock);
}
static void blkif_free(struct blkfront_info *info, int suspend)
{
/* Prevent new requests being issued until we fix things up. */
- spin_lock_irq(&blkif_io_lock);
+ spin_lock_irq(&info->io_lock);
info->connected = suspend ?
BLKIF_STATE_SUSPENDED : BLKIF_STATE_DISCONNECTED;
/* No more blkif_request(). */
blk_stop_queue(info->rq);
/* No more gnttab callback work. */
gnttab_cancel_free_callback(&info->callback);
- spin_unlock_irq(&blkif_io_lock);
+ spin_unlock_irq(&info->io_lock);
/* Flush gnttab callback work. Must be done with no locks held. */
- flush_scheduled_work();
+ flush_work_sync(&info->work);
/* Free resources associated with old device channel. */
if (info->ring_ref != GRANT_INVALID_REF) {
static void blkif_completion(struct blk_shadow *s)
{
int i;
- for (i = 0; i < s->req.nr_segments; i++)
- gnttab_end_foreign_access(s->req.seg[i].gref, 0, 0UL);
+ /* Do not let BLKIF_OP_DISCARD as nr_segment is in the same place
+ * flag. */
+ for (i = 0; i < s->req.u.rw.nr_segments; i++)
+ gnttab_end_foreign_access(s->req.u.rw.seg[i].gref, 0, 0UL);
}
static irqreturn_t blkif_interrupt(int irq, void *dev_id)
struct blkfront_info *info = (struct blkfront_info *)dev_id;
int error;
- spin_lock_irqsave(&blkif_io_lock, flags);
+ spin_lock_irqsave(&info->io_lock, flags);
if (unlikely(info->connected != BLKIF_STATE_CONNECTED)) {
- spin_unlock_irqrestore(&blkif_io_lock, flags);
+ spin_unlock_irqrestore(&info->io_lock, flags);
return IRQ_HANDLED;
}
bret = RING_GET_RESPONSE(&info->ring, i);
id = bret->id;
- req = (struct request *)info->shadow[id].request;
+ req = info->shadow[id].request;
- blkif_completion(&info->shadow[id]);
+ if (bret->operation != BLKIF_OP_DISCARD)
+ blkif_completion(&info->shadow[id]);
add_id_to_freelist(info, id);
error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
switch (bret->operation) {
+ case BLKIF_OP_DISCARD:
+ if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
+ struct request_queue *rq = info->rq;
+ printk(KERN_WARNING "blkfront: %s: discard op failed\n",
+ info->gd->disk_name);
+ error = -EOPNOTSUPP;
+ info->feature_discard = 0;
+ info->feature_secdiscard = 0;
+ queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
+ queue_flag_clear(QUEUE_FLAG_SECDISCARD, rq);
+ }
+ __blk_end_request_all(req, error);
+ break;
+ case BLKIF_OP_FLUSH_DISKCACHE:
case BLKIF_OP_WRITE_BARRIER:
if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
- printk(KERN_WARNING "blkfront: %s: write barrier op failed\n",
+ printk(KERN_WARNING "blkfront: %s: write %s op failed\n",
+ info->flush_op == BLKIF_OP_WRITE_BARRIER ?
+ "barrier" : "flush disk cache",
+ info->gd->disk_name);
+ error = -EOPNOTSUPP;
+ }
+ if (unlikely(bret->status == BLKIF_RSP_ERROR &&
+ info->shadow[id].req.u.rw.nr_segments == 0)) {
+ printk(KERN_WARNING "blkfront: %s: empty write %s op failed\n",
+ info->flush_op == BLKIF_OP_WRITE_BARRIER ?
+ "barrier" : "flush disk cache",
info->gd->disk_name);
error = -EOPNOTSUPP;
- info->feature_barrier = 0;
- xlvbd_barrier(info);
+ }
+ if (unlikely(error)) {
+ if (error == -EOPNOTSUPP)
+ error = 0;
+ info->feature_flush = 0;
+ info->flush_op = 0;
+ xlvbd_flush(info);
}
/* fall through */
case BLKIF_OP_READ:
kick_pending_request_queues(info);
- spin_unlock_irqrestore(&blkif_io_lock, flags);
+ spin_unlock_irqrestore(&info->io_lock, flags);
return IRQ_HANDLED;
}
}
}
+ if (xen_hvm_domain()) {
+ char *type;
+ int len;
+ /* no unplug has been done: do not hook devices != xen vbds */
+ if (xen_platform_pci_unplug & XEN_UNPLUG_UNNECESSARY) {
+ int major;
+
+ if (!VDEV_IS_EXTENDED(vdevice))
+ major = BLKIF_MAJOR(vdevice);
+ else
+ major = XENVBD_MAJOR;
+
+ if (major != XENVBD_MAJOR) {
+ printk(KERN_INFO
+ "%s: HVM does not support vbd %d as xen block device\n",
+ __FUNCTION__, vdevice);
+ return -ENODEV;
+ }
+ }
+ /* do not create a PV cdrom device if we are an HVM guest */
+ type = xenbus_read(XBT_NIL, dev->nodename, "device-type", &len);
+ if (IS_ERR(type))
+ return -ENODEV;
+ if (strncmp(type, "cdrom", 5) == 0) {
+ kfree(type);
+ return -ENODEV;
+ }
+ kfree(type);
+ }
info = kzalloc(sizeof(*info), GFP_KERNEL);
if (!info) {
xenbus_dev_fatal(dev, -ENOMEM, "allocating info structure");
}
mutex_init(&info->mutex);
+ spin_lock_init(&info->io_lock);
info->xbdev = dev;
info->vdevice = vdevice;
info->connected = BLKIF_STATE_DISCONNECTED;
INIT_WORK(&info->work, blkif_restart_queue);
for (i = 0; i < BLK_RING_SIZE; i++)
- info->shadow[i].req.id = i+1;
- info->shadow[BLK_RING_SIZE-1].req.id = 0x0fffffff;
+ info->shadow[i].req.u.rw.id = i+1;
+ info->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff;
/* Front end dir is a number, which is used as the id. */
info->handle = simple_strtoul(strrchr(dev->nodename, '/')+1, NULL, 0);
/* Stage 2: Set up free list. */
memset(&info->shadow, 0, sizeof(info->shadow));
for (i = 0; i < BLK_RING_SIZE; i++)
- info->shadow[i].req.id = i+1;
+ info->shadow[i].req.u.rw.id = i+1;
info->shadow_free = info->ring.req_prod_pvt;
- info->shadow[BLK_RING_SIZE-1].req.id = 0x0fffffff;
+ info->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff;
/* Stage 3: Find pending requests and requeue them. */
for (i = 0; i < BLK_RING_SIZE; i++) {
/* Not in use? */
- if (copy[i].request == 0)
+ if (!copy[i].request)
continue;
/* Grab a request slot and copy shadow state into it. */
*req = copy[i].req;
/* We get a new request id, and must reset the shadow state. */
- req->id = get_id_from_freelist(info);
- memcpy(&info->shadow[req->id], ©[i], sizeof(copy[i]));
+ req->u.rw.id = get_id_from_freelist(info);
+ memcpy(&info->shadow[req->u.rw.id], ©[i], sizeof(copy[i]));
+ if (req->operation != BLKIF_OP_DISCARD) {
/* Rewrite any grant references invalidated by susp/resume. */
- for (j = 0; j < req->nr_segments; j++)
- gnttab_grant_foreign_access_ref(
- req->seg[j].gref,
- info->xbdev->otherend_id,
- pfn_to_mfn(info->shadow[req->id].frame[j]),
- rq_data_dir(
- (struct request *)
- info->shadow[req->id].request));
- info->shadow[req->id].req = *req;
+ for (j = 0; j < req->u.rw.nr_segments; j++)
+ gnttab_grant_foreign_access_ref(
+ req->u.rw.seg[j].gref,
+ info->xbdev->otherend_id,
+ pfn_to_mfn(info->shadow[req->u.rw.id].frame[j]),
+ rq_data_dir(info->shadow[req->u.rw.id].request));
+ }
+ info->shadow[req->u.rw.id].req = *req;
info->ring.req_prod_pvt++;
}
xenbus_switch_state(info->xbdev, XenbusStateConnected);
- spin_lock_irq(&blkif_io_lock);
+ spin_lock_irq(&info->io_lock);
/* Now safe for us to use the shared ring */
info->connected = BLKIF_STATE_CONNECTED;
/* Kick any other new requests queued since we resumed */
kick_pending_request_queues(info);
- spin_unlock_irq(&blkif_io_lock);
+ spin_unlock_irq(&info->io_lock);
return 0;
}
mutex_lock(&bdev->bd_mutex);
- if (info->users) {
+ if (bdev->bd_openers) {
xenbus_dev_error(xbdev, -EBUSY,
"Device in use; refusing to close");
xenbus_switch_state(xbdev, XenbusStateClosing);
bdput(bdev);
}
+static void blkfront_setup_discard(struct blkfront_info *info)
+{
+ int err;
+ char *type;
+ unsigned int discard_granularity;
+ unsigned int discard_alignment;
+ unsigned int discard_secure;
+
+ type = xenbus_read(XBT_NIL, info->xbdev->otherend, "type", NULL);
+ if (IS_ERR(type))
+ return;
+
+ info->feature_secdiscard = 0;
+ if (strncmp(type, "phy", 3) == 0) {
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "discard-granularity", "%u", &discard_granularity,
+ "discard-alignment", "%u", &discard_alignment,
+ NULL);
+ if (!err) {
+ info->feature_discard = 1;
+ info->discard_granularity = discard_granularity;
+ info->discard_alignment = discard_alignment;
+ }
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "discard-secure", "%d", &discard_secure,
+ NULL);
+ if (!err)
+ info->feature_secdiscard = discard_secure;
+
+ } else if (strncmp(type, "file", 4) == 0)
+ info->feature_discard = 1;
+
+ kfree(type);
+}
+
/*
* Invoked when the backend is finally 'ready' (and has told produced
* the details about the physical device - #sectors, size, etc).
unsigned long sector_size;
unsigned int binfo;
int err;
+ int barrier, flush, discard;
switch (info->connected) {
case BLKIF_STATE_CONNECTED:
return;
}
+ info->feature_flush = 0;
+ info->flush_op = 0;
+
err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
- "feature-barrier", "%lu", &info->feature_barrier,
+ "feature-barrier", "%d", &barrier,
+ NULL);
+
+ /*
+ * If there's no "feature-barrier" defined, then it means
+ * we're dealing with a very old backend which writes
+ * synchronously; nothing to do.
+ *
+ * If there are barriers, then we use flush.
+ */
+ if (!err && barrier) {
+ info->feature_flush = REQ_FLUSH | REQ_FUA;
+ info->flush_op = BLKIF_OP_WRITE_BARRIER;
+ }
+ /*
+ * And if there is "feature-flush-cache" use that above
+ * barriers.
+ */
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "feature-flush-cache", "%d", &flush,
+ NULL);
+
+ if (!err && flush) {
+ info->feature_flush = REQ_FLUSH;
+ info->flush_op = BLKIF_OP_FLUSH_DISKCACHE;
+ }
+
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "feature-discard", "%d", &discard,
NULL);
- if (err)
- info->feature_barrier = 0;
+
+ if (!err && discard)
+ blkfront_setup_discard(info);
err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size);
if (err) {
xenbus_switch_state(info->xbdev, XenbusStateConnected);
/* Kick pending requests. */
- spin_lock_irq(&blkif_io_lock);
+ spin_lock_irq(&info->io_lock);
info->connected = BLKIF_STATE_CONNECTED;
kick_pending_request_queues(info);
- spin_unlock_irq(&blkif_io_lock);
+ spin_unlock_irq(&info->io_lock);
add_disk(info->gd);
case XenbusStateInitialising:
case XenbusStateInitWait:
case XenbusStateInitialised:
+ case XenbusStateReconfiguring:
+ case XenbusStateReconfigured:
case XenbusStateUnknown:
case XenbusStateClosed:
break;
mutex_lock(&bdev->bd_mutex);
info = disk->private_data;
- if (info && !info->users) {
+ dev_warn(disk_to_dev(disk),
+ "%s was hot-unplugged, %d stale handles\n",
+ xbdev->nodename, bdev->bd_openers);
+
+ if (info && !bdev->bd_openers) {
xlvbd_release_gendisk(info);
disk->private_data = NULL;
kfree(info);
struct blkfront_info *info;
int err = 0;
- lock_kernel();
+ mutex_lock(&blkfront_mutex);
info = disk->private_data;
if (!info) {
mutex_unlock(&info->mutex);
out:
- unlock_kernel();
+ mutex_unlock(&blkfront_mutex);
return err;
}
struct block_device *bdev;
struct xenbus_device *xbdev;
- lock_kernel();
+ mutex_lock(&blkfront_mutex);
bdev = bdget_disk(disk, 0);
- bdput(bdev);
if (bdev->bd_openers)
goto out;
if (xbdev && xbdev->state == XenbusStateClosing) {
/* pending switch to state closed */
+ dev_info(disk_to_dev(bdev->bd_disk), "releasing disk\n");
xlvbd_release_gendisk(info);
xenbus_frontend_closed(info->xbdev);
}
if (!xbdev) {
/* sudden device removal */
+ dev_info(disk_to_dev(bdev->bd_disk), "releasing disk\n");
xlvbd_release_gendisk(info);
disk->private_data = NULL;
kfree(info);
}
- unlock_kernel();
+out:
+ bdput(bdev);
+ mutex_unlock(&blkfront_mutex);
return 0;
}
{ "" }
};
-static struct xenbus_driver blkfront = {
- .name = "vbd",
- .owner = THIS_MODULE,
- .ids = blkfront_ids,
+static DEFINE_XENBUS_DRIVER(blkfront, ,
.probe = blkfront_probe,
.remove = blkfront_remove,
.resume = blkfront_resume,
.otherend_changed = blkback_changed,
.is_ready = blkfront_is_ready,
-};
+);
static int __init xlblk_init(void)
{
+ int ret;
+
if (!xen_domain())
return -ENODEV;
return -ENODEV;
}
- return xenbus_register_frontend(&blkfront);
+ ret = xenbus_register_frontend(&blkfront_driver);
+ if (ret) {
+ unregister_blkdev(XENVBD_MAJOR, DEV_NAME);
+ return ret;
+ }
+
+ return 0;
}
module_init(xlblk_init);
static void __exit xlblk_exit(void)
{
- return xenbus_unregister_driver(&blkfront);
+ return xenbus_unregister_driver(&blkfront_driver);
}
module_exit(xlblk_exit);
Code Review / linux-2.6.git / blobdiff