block: add logical_block_size property

Add a logical block size attribute as various guest side tools only
increase the filesystem sector size based on it, not the advisory
physical block size.

For scsi we already have support for a different logical block size
in place for CDROMs that we can built upon.  Only my recent block
device characteristics VPD page needs some fixups.  Note that we
leave the logial block size for CDROMs hardcoded as the 2k value
is expected for it in general.

For virtio-blk we already have a feature flag claiming to support
a variable logical block size that was added for the s390 kuli
hypervisor.  Interestingly it does not actually change the units
in which the protocol works, which is still fixed at 512 bytes,
but only communicates a different minimum I/O granularity.  So
all we need to do in virtio is to add a trap for unaligned I/O
and round down the device size to the next multiple of the logical
block size.

IDE does not support any other logical block size than 512 bytes.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

3 files changed, 26 insertions, 9 deletions

diff --git a/hw/scsi-disk.c b/hw/scsi-disk.c
index da56d2bc1c..e64fbf11dd 100644
--- a/hw/scsi-disk.c
+++ b/hw/scsi-disk.c
@@ -396,8 +396,10 @@ static int scsi_disk_emulate_inquiry(SCSIRequest *req, uint8_t *outbuf)
         }
         case 0xb0: /* block device characteristics */
         {
-            unsigned int min_io_size = s->qdev.conf.min_io_size >> 9;
-            unsigned int opt_io_size = s->qdev.conf.opt_io_size >> 9;
+            unsigned int min_io_size =
+                    s->qdev.conf.min_io_size / s->qdev.blocksize;
+            unsigned int opt_io_size =
+                    s->qdev.conf.opt_io_size / s->qdev.blocksize;
 
             /* required VPD size with unmap support */
             outbuf[3] = buflen = 0x3c;
@@ -1036,11 +1038,12 @@ static int scsi_disk_initfn(SCSIDevice *dev)
     }
 
     if (bdrv_get_type_hint(s->bs) == BDRV_TYPE_CDROM) {
-        s->cluster_size = 4;
+        s->qdev.blocksize = 2048;
     } else {
-        s->cluster_size = 1;
+        s->qdev.blocksize = s->qdev.conf.logical_block_size;
     }
-    s->qdev.blocksize = 512 * s->cluster_size;
+    s->cluster_size = s->qdev.blocksize / 512;
+
     s->qdev.type = TYPE_DISK;
     bdrv_get_geometry(s->bs, &nb_sectors);
     nb_sectors /= s->cluster_size;
diff --git a/hw/virtio-blk.c b/hw/virtio-blk.c
index 8939bb2529..9915840887 100644
--- a/hw/virtio-blk.c
+++ b/hw/virtio-blk.c
@@ -27,6 +27,7 @@ typedef struct VirtIOBlock
     void *rq;
     QEMUBH *bh;
     BlockConf *conf;
+    unsigned short sector_mask;
 } VirtIOBlock;
 
 static VirtIOBlock *to_virtio_blk(VirtIODevice *vdev)
@@ -250,6 +251,11 @@ static void virtio_blk_handle_flush(VirtIOBlockReq *req)
 static void virtio_blk_handle_write(BlockRequest *blkreq, int *num_writes,
     VirtIOBlockReq *req, BlockDriverState **old_bs)
 {
+    if (req->out->sector & req->dev->sector_mask) {
+        virtio_blk_rw_complete(req, -EIO);
+        return;
+    }
+
     if (req->dev->bs != *old_bs || *num_writes == 32) {
         if (*old_bs != NULL) {
             do_multiwrite(*old_bs, blkreq, *num_writes);
@@ -272,6 +278,11 @@ static void virtio_blk_handle_read(VirtIOBlockReq *req)
 {
     BlockDriverAIOCB *acb;
 
+    if (req->out->sector & req->dev->sector_mask) {
+        virtio_blk_rw_complete(req, -EIO);
+        return;
+    }
+
     acb = bdrv_aio_readv(req->dev->bs, req->out->sector, &req->qiov,
                          req->qiov.size / 512, virtio_blk_rw_complete, req);
     if (!acb) {
@@ -404,12 +415,13 @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
     stl_raw(&blkcfg.seg_max, 128 - 2);
     stw_raw(&blkcfg.cylinders, cylinders);
     blkcfg.heads = heads;
-    blkcfg.sectors = secs;
+    blkcfg.sectors = secs & ~s->sector_mask;
+    blkcfg.blk_size = s->conf->logical_block_size;
     blkcfg.size_max = 0;
     blkcfg.physical_block_exp = get_physical_block_exp(s->conf);
     blkcfg.alignment_offset = 0;
-    blkcfg.min_io_size = s->conf->min_io_size / 512;
-    blkcfg.opt_io_size = s->conf->opt_io_size / 512;
+    blkcfg.min_io_size = s->conf->min_io_size / blkcfg.blk_size;
+    blkcfg.opt_io_size = s->conf->opt_io_size / blkcfg.blk_size;
     memcpy(config, &blkcfg, sizeof(struct virtio_blk_config));
 }
 
@@ -420,6 +432,7 @@ static uint32_t virtio_blk_get_features(VirtIODevice *vdev, uint32_t features)
     features |= (1 << VIRTIO_BLK_F_SEG_MAX);
     features |= (1 << VIRTIO_BLK_F_GEOMETRY);
     features |= (1 << VIRTIO_BLK_F_TOPOLOGY);
+    features |= (1 << VIRTIO_BLK_F_BLK_SIZE);
 
     if (bdrv_enable_write_cache(s->bs))
         features |= (1 << VIRTIO_BLK_F_WCACHE);
@@ -479,6 +492,7 @@ VirtIODevice *virtio_blk_init(DeviceState *dev, BlockConf *conf)
     s->bs = conf->dinfo->bdrv;
     s->conf = conf;
     s->rq = NULL;
+    s->sector_mask = (s->conf->logical_block_size / 512) - 1;
     bdrv_guess_geometry(s->bs, &cylinders, &heads, &secs);
     bdrv_set_geometry_hint(s->bs, cylinders, heads, secs);
 
diff --git a/hw/virtio-blk.h b/hw/virtio-blk.h
index f675375399..7a7ece3d93 100644
--- a/hw/virtio-blk.h
+++ b/hw/virtio-blk.h
@@ -42,7 +42,7 @@ struct virtio_blk_config
     uint16_t cylinders;
     uint8_t heads;
     uint8_t sectors;
-    uint32_t _blk_size;    /* structure pad, currently unused */
+    uint32_t blk_size;
     uint8_t physical_block_exp;
     uint8_t alignment_offset;
     uint16_t min_io_size;