| Message ID | 20190723075718.6275-5-jasowang@redhat.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Fixes for meta data acceleration | expand |
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 <mst@redhat.com> > Fixes: 7f466032dc9e ("vhost: access vq metadata through kernel virtual address") > Signed-off-by: Jason Wang <jasowang@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 - 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. > vhost_uninit_vq_maps(vq); > #endif > > -- > 2.18.1
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 <mst@redhat.com> >> Fixes: 7f466032dc9e ("vhost: access vq metadata through kernel virtual address") >> Signed-off-by: Jason Wang <jasowang@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
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; vhost_uninit_vq_maps(vq); #endif
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 <mst@redhat.com> Fixes: 7f466032dc9e ("vhost: access vq metadata through kernel virtual address") Signed-off-by: Jason Wang <jasowang@redhat.com> --- drivers/vhost/vhost.c | 4 ++++ 1 file changed, 4 insertions(+)