On 2019/7/23 下午5:17, Michael S. Tsirkin wrote:
On Tue, Jul 23, 2019 at 03:57:16AM -0400, Jason Wang wrote:
The vhost_set_vring_num_addr() could be called in the middle of
invalidate_range_start() and invalidate_range_end(). If we don't reset
invalidate_count after the un-registering of MMU notifier, the
invalidate_cont will run out of sync (e.g never reach zero). This will
in fact disable the fast accessor path. Fixing by reset the count to
zero.
Reported-by: Michael S. Tsirkin <m...@redhat.com>
Fixes: 7f466032dc9e ("vhost: access vq metadata through kernel virtual address")
Signed-off-by: Jason Wang <jasow...@redhat.com>
---
drivers/vhost/vhost.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 03666b702498..89c9f08b5146 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2074,6 +2074,10 @@ static long vhost_vring_set_num_addr(struct vhost_dev *d,
d->has_notifier = false;
}
+ /* reset invalidate_count in case we are in the middle of
+ * invalidate_start() and invalidate_end().
+ */
+ vq->invalidate_count = 0;
I think that the code is ok but the comments are not very clear:
- we are never in the middle since we just removed the notifier
If I read the code correctly, mmu_notifier_unregister() can only
guarantee to wait for the pending method to complete. So we can have:
invalidate_start()
mmu_notifier_unregister()
invalidate_end()
- the result is not just disabling optimization:
if notifier becomes negative, then later we
can think it's ok to map when it isn't since
notifier is active.
I don't get how it could be negative, the only possible thing is to have
a positive value.
Thanks
vhost_uninit_vq_maps(vq);
#endif
--
2.18.1
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
