Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Thu, 4 Jul 2019 13:25:34 +0200
From:   Gerd Hoffmann <kraxel@redhat.com>
To:     Chia-I Wu <olvaffe@gmail.com>
Cc:     ML dri-devel <dri-devel@lists.freedesktop.org>,
        Gurchetan Singh <gurchetansingh@chromium.org>,
        David Airlie <airlied@linux.ie>,
        Daniel Vetter <daniel@ffwll.ch>,
        "open list:VIRTIO GPU DRIVER" 
        <virtualization@lists.linux-foundation.org>,
        open list <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v6 08/18] drm/virtio: rework virtio_gpu_execbuffer_ioctl
 fencing
Message-ID: <20190704112534.v7icsuverf7wrbjq@sirius.home.kraxel.org>
References: <20190702141903.1131-1-kraxel@redhat.com>
 <20190702141903.1131-9-kraxel@redhat.com>
 <CAPaKu7QP=A2kV_kqcT20Pmc831HviaBJN1RpOFoa=V1g6SmE_g@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CAPaKu7QP=A2kV_kqcT20Pmc831HviaBJN1RpOFoa=V1g6SmE_g@mail.gmail.com>
User-Agent: NeoMutt/20180716
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

  Hi,

> >         if (fence)
> >                 virtio_gpu_fence_emit(vgdev, hdr, fence);
> > +       if (vbuf->objs) {
> > +               virtio_gpu_array_add_fence(vbuf->objs, &fence->f);
> > +               virtio_gpu_array_unlock_resv(vbuf->objs);
> > +       }
> This is with the spinlock held.  Maybe we should move the
> virtio_gpu_array_unlock_resv call out of the critical section.

That would bring back the race ...

> I am actually more concerned about virtio_gpu_array_add_fence, but it
> is also harder to move.  Should we add a kref to the object array?

Yep, refcounting would be the other way to fix the race.

> This bothers me because I recently ran into a CPU-bound game with very
> bad lock contention here.

Hmm.  Any clue where this comes from?  Multiple threads competing for
virtio buffers I guess?  Maybe we should have larger virtqueues?

cheers,
  Gerd