[Qemu-devel] [PATCH 2/2] virtio-blk: do not relay a previous driver's WCE configuration to the current

[Paolo Bonzini <pbonzini@redhat.com>]

The following sequence happens:
- the SeaBIOS virtio-blk driver does not support the WCE feature, which
causes QEMU to disable writeback caching

- the Linux virtio-blk driver resets the device, finds WCE is available
but writeback caching is disabled; tells block layer to not send cache
flush commands

- the Linux virtio-blk driver sets the DRIVER_OK bit, which causes
writeback caching to be re-enabled, but the Linux virtio-blk driver does
not know of this side effect and cache flushes remain disabled

The bug is at the third step.  If the guest does know about CONFIG_WCE,
QEMU should ignore the WCE feature's state.  The guest will control the
cache mode solely using configuration space.  This change makes Linux
do flushes correctly, but Linux will keep SeaBIOS's writethrough mode.

Hence, whenever the guest is reset, the cache mode of the disk should
be reset to whatever was specified in the "-drive" option.  With this
change, the Linux virtio-blk driver finds that writeback caching is
enabled, and tells the block layer to send cache flush commands
appropriately.

Reported-by: Rusty Russell <rusty@au1.ibm.com
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 hw/block/virtio-blk.c          | 8 ++++++--
 include/hw/virtio/virtio-blk.h | 1 +
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index e2f55cc..6ed9666 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -460,9 +460,9 @@ static void virtio_blk_dma_restart_cb(void *opaque, int running,
 
 static void virtio_blk_reset(VirtIODevice *vdev)
 {
-#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
     VirtIOBlock *s = VIRTIO_BLK(vdev);
 
+#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
     if (s->dataplane) {
         virtio_blk_data_plane_stop(s->dataplane);
     }
@@ -473,6 +473,7 @@ static void virtio_blk_reset(VirtIODevice *vdev)
      * are per-device request lists.
      */
     bdrv_drain_all();
+    bdrv_set_enable_write_cache(s->bs, s->original_wce);
 }
 
 /* coalesce internal state, copy to pci i/o region 0
@@ -564,7 +565,10 @@ static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
     }
 
     features = vdev->guest_features;
-    bdrv_set_enable_write_cache(s->bs, !!(features & (1 << VIRTIO_BLK_F_WCE)));
+    if (!(features & (1 << VIRTIO_BLK_F_CONFIG_WCE))) {
+        bdrv_set_enable_write_cache(s->bs,
+                                    !!(features & (1 << VIRTIO_BLK_F_WCE)));
+    }
 }
 
 static void virtio_blk_save(QEMUFile *f, void *opaque)
@@ -674,6 +678,7 @@ static int virtio_blk_device_init(VirtIODevice *vdev)
     }
 
     blkconf_serial(&blk->conf, &blk->serial);
+    s->original_wce = bdrv_enable_write_cache(blk->conf.bs);
     if (blkconf_geometry(&blk->conf, NULL, 65535, 255, 255) < 0) {
         return -1;
     }
diff --git a/include/hw/virtio/virtio-blk.h b/include/hw/virtio/virtio-blk.h
index b87cf49..41885da 100644
--- a/include/hw/virtio/virtio-blk.h
+++ b/include/hw/virtio/virtio-blk.h
@@ -123,6 +123,7 @@ typedef struct VirtIOBlock {
     BlockConf *conf;
     VirtIOBlkConf blk;
     unsigned short sector_mask;
+    bool original_wce;
     VMChangeStateEntry *change;
 #ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
     Notifier migration_state_notifier;
-- 
1.8.3.1