Rusty,
I have seen an oops triggered by the following bug statement in
virtio-rng:
if (vq->vq_ops->add_buf(vq, &sg, 0, 1, &random_data) != 0)
BUG();
The problem is that we never called get_buf for complete buffers.
The fix is simple: We have to free the buffer on interrupt to
avoid a virtqueue "overflow".
Christian
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
drivers/char/hw_random/virtio-rng.c | 3 +++
1 file changed, 3 insertions(+)
Index: kvm/drivers/char/hw_random/virtio-rng.c
==================================================================---
kvm.orig/drivers/char/hw_random/virtio-rng.c
+++ kvm/drivers/char/hw_random/virtio-rng.c
@@ -29,6 +29,9 @@ static bool have_data;
static void random_recv_done(struct virtqueue *vq)
{
+ int len = 0;
+ vq->vq_ops->get_buf(vq, &len);
+ BUG_ON(!len);
have_data = true;
/* No need to call disable_cb: there can't be any more since we
--
IBM Deutschland Entwicklung GmbH
Vorsitzender des Aufsichtsrats: Martin Jetter
Gesch?ftsf?hrung: Herbert Kircher
Sitz der Gesellschaft: B?blingen
Registergericht: Amtsgericht Stuttgart, HRB 243294