On Wed, Apr 15, 2020 at 05:46:33PM -0700, Linus Torvalds wrote:> On Tue, Apr 14, 2020 at 9:36 AM Michael S. Tsirkin <mst at redhat.com> wrote: > > > > virtio: fixes, cleanups > > Looking at this, about 75% of it looks like it should have come in > during the merge window, not now. > > LinusWell it's all just fallout from commit 61b89f23f854f458b8e23719978df58260f051ed Author: Michael S. Tsirkin <mst at redhat.com> Date: Mon Apr 6 08:42:55 2020 -0400 vhost: force spec specified alignment on types which I didn't know we need until things landed upstream and people started testing with weird configs. That forced changes to a header file and the rest followed. We could just ignore -mabi=apcs-gnu build being broken for this release - is that preferable? Pls let me know. -- MST
On Thu, Apr 16, 2020 at 5:20 AM Michael S. Tsirkin <mst at redhat.com> wrote:> Well it's all just fallout fromWhat? No. Half of it seems to be the moving of "struct vring" around to other headers and stuff. And then that is done very confusingly too, using two different structures both called "struct vring". No way can I pull that kind of craziness as a "fix". Linus
On Thu, Apr 16, 2020 at 10:01:51AM -0700, Linus Torvalds wrote:> On Thu, Apr 16, 2020 at 5:20 AM Michael S. Tsirkin <mst at redhat.com> wrote: > > Well it's all just fallout from > > What? No. Half of it seems to be the moving of "struct vring" around > to other headers and stuff. > > And then that is done very confusingly too, using two different > structures both called "struct vring". > > No way can I pull that kind of craziness as a "fix". > > LinusOK, I'll just disable vhost on that config for now - it was suggested previously. Thanks for the comment and sorry about geeting it wrong! -- MST