On Wed, Sep 12, 2018 at 01:21:57PM +0200, Christoffer Dall wrote:
> On Wed, Sep 12, 2018 at 12:16:26PM +0100, Dave Martin wrote:
> > On Wed, Sep 12, 2018 at 12:17:04PM +0200, Christoffer Dall wrote:
[...]
> > > I think the point was actually to avoid saving/restoring FPEXC32_EL2
> > > when VFP
On Wed, Sep 12, 2018 at 12:16:26PM +0100, Dave Martin wrote:
> On Wed, Sep 12, 2018 at 12:17:04PM +0200, Christoffer Dall wrote:
> > On Wed, Sep 05, 2018 at 02:19:13PM +0100, Dave Martin wrote:
> > > Currently FPEXC32_EL2 is handled specially when context-switching.
> > > This made sense for arm,
On Wed, Sep 12, 2018 at 12:17:04PM +0200, Christoffer Dall wrote:
> On Wed, Sep 05, 2018 at 02:19:13PM +0100, Dave Martin wrote:
> > Currently FPEXC32_EL2 is handled specially when context-switching.
> > This made sense for arm, where FPEXC affects host execution
> > (including VFP/SIMD register
On Wed, Sep 05, 2018 at 02:19:13PM +0100, Dave Martin wrote:
> Currently FPEXC32_EL2 is handled specially when context-switching.
> This made sense for arm, where FPEXC affects host execution
> (including VFP/SIMD register save/restore at Hyp).
I think the point was actually to avoid