xen/blkback: Use physical sector size for setup

Currently xen-blkback passes the logical sector size over xenbus and
xen-blkfront sets up the paravirt disk with that logical block size.
But newer drives usually have the logical sector size set to 512 for
compatibility reasons and would show the actual sector size only in
physical sector size.
This results in the device being partitioned and accessed in dom0 with
the correct sector size, but the guest thinks 512 bytes is the correct
block size. And that results in poor performance.

To fix this, blkback gets modified to pass also physical-sector-size
over xenbus and blkfront to use both values to set up the paravirt
disk. I did not just change the passed in sector-size because I am
not sure having a bigger logical sector size than the physical one
is valid (and that would happen if a newer dom0 kernel hits an older
domU kernel). Also this way a domU set up before should still be
accessible (just some tools might detect the unaligned setup).

[v2: Make xenbus write failure non-fatal]
[v3: Use xenbus_scanf instead of xenbus_gather]
[v4: Rebased against segment changes]

Signed-off-by: Stefan Bader <stefan.bader@canonical.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

2 files changed, 23 insertions, 3 deletions

diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 4a4749c78942..7b06f943371c 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -782,6 +782,11 @@ again:
 				 dev->nodename);
 		goto abort;
 	}
+	err = xenbus_printf(xbt, dev->nodename, "physical-sector-size", "%u",
+			    bdev_physical_block_size(be->blkif->vbd.bdev));
+	if (err)
+		xenbus_dev_error(dev, err, "writing %s/physical-sector-size",
+				 dev->nodename);
 
 	err = xenbus_transaction_end(xbt, 0);
 	if (err == -EAGAIN)
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 08bdfc3b2de2..1a0f67c10ec7 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -609,6 +609,7 @@ wait:
 }
 
 static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
+				unsigned int physical_sector_size,
 				unsigned int segments)
 {
 	struct request_queue *rq;
@@ -631,6 +632,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
 
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
 	blk_queue_logical_block_size(rq, sector_size);
+	blk_queue_physical_block_size(rq, physical_sector_size);
 	blk_queue_max_hw_sectors(rq, 512);
 
 	/* Each segment in a request is up to an aligned page in size. */
@@ -737,7 +739,8 @@ static char *encode_disk_name(char *ptr, unsigned int n)
 
 static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 			       struct blkfront_info *info,
-			       u16 vdisk_info, u16 sector_size)
+			       u16 vdisk_info, u16 sector_size,
+			       unsigned int physical_sector_size)
 {
 	struct gendisk *gd;
 	int nr_minors = 1;
@@ -804,7 +807,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	gd->driverfs_dev = &(info->xbdev->dev);
 	set_capacity(gd, capacity);
 
-	if (xlvbd_init_blk_queue(gd, sector_size,
+	if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size,
 				 info->max_indirect_segments ? :
 				 BLKIF_MAX_SEGMENTS_PER_REQUEST)) {
 		del_gendisk(gd);
@@ -1698,6 +1701,7 @@ static void blkfront_connect(struct blkfront_info *info)
 {
 	unsigned long long sectors;
 	unsigned long sector_size;
+	unsigned int physical_sector_size;
 	unsigned int binfo;
 	int err;
 	int barrier, flush, discard, persistent;
@@ -1747,6 +1751,16 @@ static void blkfront_connect(struct blkfront_info *info)
 		return;
 	}
 
+	/*
+	 * physcial-sector-size is a newer field, so old backends may not
+	 * provide this. Assume physical sector size to be the same as
+	 * sector_size in that case.
+	 */
+	err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+			   "physical-sector-size", "%u", &physical_sector_size);
+	if (err != 1)
+		physical_sector_size = sector_size;
+
 	info->feature_flush = 0;
 	info->flush_op = 0;
 
@@ -1800,7 +1814,8 @@ static void blkfront_connect(struct blkfront_info *info)
 		return;
 	}
 
-	err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size);
+	err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size,
+				  physical_sector_size);
 	if (err) {
 		xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
 				 info->xbdev->otherend);