On Mon, Aug 25, 2025 at 05:46:07AM -0000, Michael van Elst wrote:
> cme...@cmeerw.org (Christof Meerwald) writes:
>
> >So it does look like some kind of race condition, also I thought that
> >should be handled by qemu by first setting the vq->vq_used->flags to 0
> >and then checking vq->vq_used->idx again before relying on
> >notifications being sent.
>
> Maybe a memory ordering issue then ?
Yes, probably - I have added an mfence and not seen any issue since
then (more than 2 days now, with my sync loop running in the
background). BTW, this is on a AMD Ryzen 9 9950X 16-Core Processor
(with 2 CPUs assigned to the VPS).
Index: dev/pci/virtio.c
===================================================================
RCS file: /cvsroot/src/sys/dev/pci/virtio.c,v
retrieving revision 1.63.2.6
diff -u -r1.63.2.6 virtio.c
--- dev/pci/virtio.c 2 Oct 2024 18:20:48 -0000 1.63.2.6
+++ dev/pci/virtio.c 28 Aug 2025 21:42:47 -0000
@@ -38,6 +38,7 @@
#include <sys/device.h>
#include <sys/kmem.h>
#include <sys/module.h>
+#include <x86/cpufunc.h>
#define VIRTIO_PRIVATE
@@ -1244,6 +1248,7 @@
vq->vq_avail->idx = virtio_rw16(sc, vq->vq_avail_idx);
vq_sync_aring_header(sc, vq, BUS_DMASYNC_PREWRITE);
vq->vq_queued++;
+ x86_mfence();
if (sc->sc_active_features & VIRTIO_F_RING_EVENT_IDX) {
vq_sync_uring_avail(sc, vq, BUS_DMASYNC_POSTREAD);
--
https://cmeerw.org sip:cmeerw at cmeerw.org
mailto:cmeerw at cmeerw.org xmpp:cmeerw at cmeerw.org
