xen/blkfront: cope with backend that fail empty BLKIF_OP_WRITE_BARRIER requests

Some(?) Xen block backends fail BLKIF_OP_WRITE_BARRIER requests, which
Linux uses as a cache flush operation.  In that case, disable use
of FLUSH.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Daniel Stodden <daniel.stodden@citrix.com>
This commit is contained in:
Jeremy Fitzhardinge 2010-11-02 11:55:58 -04:00
parent be2f8373c1
commit dcb8baecea
1 changed files with 10 additions and 0 deletions

View File

@ -656,6 +656,16 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
printk(KERN_WARNING "blkfront: %s: write barrier op failed\n",
info->gd->disk_name);
error = -EOPNOTSUPP;
}
if (unlikely(bret->status == BLKIF_RSP_ERROR &&
info->shadow[id].req.nr_segments == 0)) {
printk(KERN_WARNING "blkfront: %s: empty write barrier op failed\n",
info->gd->disk_name);
error = -EOPNOTSUPP;
}
if (unlikely(error)) {
if (error == -EOPNOTSUPP)
error = 0;
info->feature_flush = 0;
xlvbd_flush(info);
}