Re: [PATCH 3/4] virtio_ring: introduce a per virtqueue waitqueue

["Michael S. Tsirkin" <mst@redhat.com>]

On Fri, Dec 30, 2022 at 11:43:08AM +0800, Jason Wang wrote:
> On Thu, Dec 29, 2022 at 4:10 PM Michael S. Tsirkin <mst@redhat.com> wrote:
> >
> > On Thu, Dec 29, 2022 at 04:04:13PM +0800, Jason Wang wrote:
> > > On Thu, Dec 29, 2022 at 3:07 PM Michael S. Tsirkin <mst@redhat.com> wrote:
> > > >
> > > > On Wed, Dec 28, 2022 at 07:53:08PM +0800, Jason Wang wrote:
> > > > > On Wed, Dec 28, 2022 at 2:34 PM Jason Wang <jasowang@redhat.com> wrote:
> > > > > >
> > > > > >
> > > > > > 在 2022/12/27 17:38, Michael S. Tsirkin 写道:
> > > > > > > On Tue, Dec 27, 2022 at 05:12:58PM +0800, Jason Wang wrote:
> > > > > > >> 在 2022/12/27 15:33, Michael S. Tsirkin 写道:
> > > > > > >>> On Tue, Dec 27, 2022 at 12:30:35PM +0800, Jason Wang wrote:
> > > > > > >>>>> But device is still going and will later use the buffers.
> > > > > > >>>>>
> > > > > > >>>>> Same for timeout really.
> > > > > > >>>> Avoiding infinite wait/poll is one of the goals, another is to sleep.
> > > > > > >>>> If we think the timeout is hard, we can start from the wait.
> > > > > > >>>>
> > > > > > >>>> Thanks
> > > > > > >>> If the goal is to avoid disrupting traffic while CVQ is in use,
> > > > > > >>> that sounds more reasonable. E.g. someone is turning on promisc,
> > > > > > >>> a spike in CPU usage might be unwelcome.
> > > > > > >>
> > > > > > >> Yes, this would be more obvious is UP is used.
> > > > > > >>
> > > > > > >>
> > > > > > >>> things we should be careful to address then:
> > > > > > >>> 1- debugging. Currently it's easy to see a warning if CPU is stuck
> > > > > > >>>      in a loop for a while, and we also get a backtrace.
> > > > > > >>>      E.g. with this - how do we know who has the RTNL?
> > > > > > >>>      We need to integrate with kernel/watchdog.c for good results
> > > > > > >>>      and to make sure policy is consistent.
> > > > > > >>
> > > > > > >> That's fine, will consider this.
> > > > >
> > > > > So after some investigation, it seems the watchdog.c doesn't help. The
> > > > > only export helper is touch_softlockup_watchdog() which tries to avoid
> > > > > triggering the lockups warning for the known slow path.
> > > >
> > > > I never said you can just use existing exporting APIs. You'll have to
> > > > write new ones :)
> > >
> > > Ok, I thought you wanted to trigger similar warnings as a watchdog.
> > >
> > > Btw, I wonder what kind of logic you want here. If we switch to using
> > > sleep, there won't be soft lockup anymore. A simple wait + timeout +
> > > warning seems sufficient?
> > >
> > > Thanks
> >
> > I'd like to avoid need to teach users new APIs. So watchdog setup to apply
> > to this driver. The warning can be different.
> 
> Right, so it looks to me the only possible setup is the
> watchdog_thres. I plan to trigger the warning every watchdog_thres * 2
> second (as softlockup did).
> 
> And I think it would still make sense to fail, we can start with a
> very long timeout like 1 minutes and break the device. Does this make
> sense?
> 
> Thanks

I'd say we need to make this manageable then. Can't we do it normally
e.g. react to an interrupt to return to userspace?



> >
> >
> > > >
> > > > > And before the patch, we end up with a real infinite loop which could
> > > > > be caught by RCU stall detector which is not the case of the sleep.
> > > > > What we can do is probably do a periodic netdev_err().
> > > > >
> > > > > Thanks
> > > >
> > > > Only with a bad device.
> > > >
> > > > > > >>
> > > > > > >>
> > > > > > >>> 2- overhead. In a very common scenario when device is in hypervisor,
> > > > > > >>>      programming timers etc has a very high overhead, at bootup
> > > > > > >>>      lots of CVQ commands are run and slowing boot down is not nice.
> > > > > > >>>      let's poll for a bit before waiting?
> > > > > > >>
> > > > > > >> Then we go back to the question of choosing a good timeout for poll. And
> > > > > > >> poll seems problematic in the case of UP, scheduler might not have the
> > > > > > >> chance to run.
> > > > > > > Poll just a bit :) Seriously I don't know, but at least check once
> > > > > > > after kick.
> > > > > >
> > > > > >
> > > > > > I think it is what the current code did where the condition will be
> > > > > > check before trying to sleep in the wait_event().
> > > > > >
> > > > > >
> > > > > > >
> > > > > > >>> 3- suprise removal. need to wake up thread in some way. what about
> > > > > > >>>      other cases of device breakage - is there a chance this
> > > > > > >>>      introduces new bugs around that? at least enumerate them please.
> > > > > > >>
> > > > > > >> The current code did:
> > > > > > >>
> > > > > > >> 1) check for vq->broken
> > > > > > >> 2) wakeup during BAD_RING()
> > > > > > >>
> > > > > > >> So we won't end up with a never woke up process which should be fine.
> > > > > > >>
> > > > > > >> Thanks
> > > > > > >
> > > > > > > BTW BAD_RING on removal will trigger dev_err. Not sure that is a good
> > > > > > > idea - can cause crashes if kernel panics on error.
> > > > > >
> > > > > >
> > > > > > Yes, it's better to use __virtqueue_break() instead.
> > > > > >
> > > > > > But consider we will start from a wait first, I will limit the changes
> > > > > > in virtio-net without bothering virtio core.
> > > > > >
> > > > > > Thanks
> > > > > >
> > > > > >
> > > > > > >
> > > > > > >>>
> > > >
> >