GPU passthrough: mixed success on Linux, not yet on Windows

[Nick Wolff]

Robert,

I'm hoping that the set of commits done for
https://reviews.freebsd.org/D19646 will fix the pcie reset problems.
Apparently pcie wasn't auto retraining after reset. I don't know if
connected to that review but wanted to let you know.


On Wed, Apr 3, 2019 at 7:42 PM Robert Crowston via freebsd-virtualization <
freebsd-virtualization at freebsd.org> wrote:

> To get Windows to boot I think the only hacks I needed were in bhyve/mem.c
> (this is not production ready!)
>
> Diff'd against 12.0-release
>
> -- /tmp//sh-np.vFXFJd  2019-04-04 00:29:32.752990000 +0100
> +++ mem.c       2019-03-02 22:27:14.500906000 +0000
> @@ -101,20 +101,22 @@
>  }
>
>  static int
> -mmio_rb_add(struct mmio_rb_tree *rbt, struct mmio_rb_range *new)
> +mmio_rb_add(struct mmio_rb_tree *rbt, struct mmio_rb_range *new_element)
>  {
>         struct mmio_rb_range *overlap;
>
> -       overlap = RB_INSERT(mmio_rb_tree, rbt, new);
> +       overlap = RB_INSERT(mmio_rb_tree, rbt, new_element);
>
> +       printf("mmio_rb_add: %lx:%lx\n", new_element->mr_base,
> new_element->mr_end);
> +
>         if (overlap != NULL) {
> -#ifdef RB_DEBUG
> -               printf("overlap detected: new %lx:%lx, tree %lx:%lx\n",
> -                      new->mr_base, new->mr_end,
> +//#ifdef RB_DEBUG
> +               printf("overlap detected: new_element %lx:%lx, tree
> %lx:%lx\n",
> +                      new_element->mr_base, new_element->mr_end,
>                        overlap->mr_base, overlap->mr_end);
> -#endif
> +//#endif
>
> -               return (EEXIST);
> +//             return (EEXIST);
>         }
>
>         return (0);
> @@ -336,6 +338,8 @@
>                 assert((mr->flags & MEM_F_IMMUTABLE) == 0);
>                 RB_REMOVE(mmio_rb_tree, &mmio_rb_root, entry);
>
> +               printf("unregister: %lx:%lx\n", mr->base,
> mr->base+mr->size);
> +
>                 /* flush Per-vCPU cache */
>                 for (i=0; i < VM_MAXCPU; i++) {
>                         if (mmio_hint[i] == entry)
> @@ -348,7 +352,12 @@
>         if (entry)
>                 free(entry);
>
> -       return (err);
> +       if (err)
> +               fprintf( stderr, "Unregister mem errno %d for range
> %lx:%lx.\n", err,
> +                       memp->base, memp->base + memp->size );
> +
> +       return 0;
> +       //return (err);
>  }
>
>
>
>
> ‐‐‐‐‐‐‐ Original Message ‐‐‐‐‐‐‐
> On Thursday, 28 March 2019 22:02, Ruslan Bukin <br at bsdpad.com> wrote:
>
> > Hi Robert:
> >
> > On Sun, Mar 17, 2019 at 04:22:29PM +0000, Robert Crowston via
> freebsd-virtualization wrote:
> >
> > > Is it worth me continuing to hack away at these problems---of course
> I'm happy to share anything I come up with---or is there an official
> solution to GPU support in the pipe about to make my efforts redundant :)?
> >
> > Could you share your patch/hacks somewhere?
> > I would like to try it with AMD graphics card and Windows.
> >
> > Ruslan
>
> _______________________________________________
> freebsd-virtualization at freebsd.org mailing list
> https://lists.freebsd.org/mailman/listinfo/freebsd-virtualization
> To unsubscribe, send any mail to "
> freebsd-virtualization-unsubscribe at freebsd.org"
>