This adds a kvm-specific hypervisor call to the pseries machine
which allows to do what amounts to memmove, memcpy and xor over
regions of physical memory such as the framebuffer.
This is the simplest way to get usable framebuffer speed from
SLOF since the framebuffer isn't mapped in the VRMA and
On 21.05.2012, at 09:24, Benjamin Herrenschmidt wrote:
> This adds a kvm-specific hypervisor call to the pseries machine
> which allows to do what amounts to memmove, memcpy and xor over
> regions of physical memory such as the framebuffer.
>
> This is the simplest way to get usable framebuffer
On Mon, 2012-05-21 at 10:38 +0200, Alexander Graf wrote:
> On 21.05.2012, at 09:24, Benjamin Herrenschmidt wrote:
>
> > This adds a kvm-specific hypervisor call to the pseries machine
> > which allows to do what amounts to memmove, memcpy and xor over
> > regions of physical memory such as the fra
On 21.05.2012, at 10:59, Benjamin Herrenschmidt wrote:
> On Mon, 2012-05-21 at 10:38 +0200, Alexander Graf wrote:
>> On 21.05.2012, at 09:24, Benjamin Herrenschmidt wrote:
>>
>>> This adds a kvm-specific hypervisor call to the pseries machine
>>> which allows to do what amounts to memmove, memcp
On 05/21/2012 10:24 AM, Benjamin Herrenschmidt wrote:
> This adds a kvm-specific hypervisor call to the pseries machine
> which allows to do what amounts to memmove, memcpy and xor over
> regions of physical memory such as the framebuffer.
>
> This is the simplest way to get usable framebuffer spee
On Mon, 2012-05-21 at 12:47 +0300, Avi Kivity wrote:
> On 05/21/2012 10:24 AM, Benjamin Herrenschmidt wrote:
> > This adds a kvm-specific hypervisor call to the pseries machine
> > which allows to do what amounts to memmove, memcpy and xor over
> > regions of physical memory such as the framebuffer
On 05/21/2012 01:04 PM, Benjamin Herrenschmidt wrote:
> On Mon, 2012-05-21 at 12:47 +0300, Avi Kivity wrote:
> > On 05/21/2012 10:24 AM, Benjamin Herrenschmidt wrote:
> > > This adds a kvm-specific hypervisor call to the pseries machine
> > > which allows to do what amounts to memmove, memcpy and x
On Mon, 2012-05-21 at 13:07 +0300, Avi Kivity wrote:
> > Now I'm adding another one, so yes, it's looking like a trend :-) I'll
> > look into it, at this stage with only those two, adding some comments in
> > the header might be plenty enough.
>
> Documentation/virtual/kvm/ppc-pv.txt is a nice cen
On 05/21/2012 02:48 PM, Benjamin Herrenschmidt wrote:
> On Mon, 2012-05-21 at 13:07 +0300, Avi Kivity wrote:
> > > Now I'm adding another one, so yes, it's looking like a trend :-) I'll
> > > look into it, at this stage with only those two, adding some comments in
> > > the header might be plenty e
On Mon, 2012-05-21 at 16:55 +0300, Avi Kivity wrote:
>
> Okay. But let's have a spec, even a kvm-private one, and then an
> implementation of that spec, instead of an implementation and some
> documentation added as an afterthought (or not).
>
> > It's a bit like if you had private calls between
On Mon, 2012-05-21 at 16:55 +0300, Avi Kivity wrote:
>
> > As to adding things to PAPR, let's assume for now that this isn't
> > possible :-) Besides, those two hypercalls are pretty specific to
> the
> > way things are implemented in qemu and are in both case more or less
> > private mechanisms u
On 05/25/2012 06:12 AM, Benjamin Herrenschmidt wrote:
>
> BTW. This is a qemu patch, and that hypercall isn't KVM related at all,
> ie, it's implemented in qemu and is used with or without KVM, so
> documenting it in the kernel tree makes little sense. Same goes with
> H_RTAS.
>
> I'll add a doc
On 28.05.2012, at 12:40, Avi Kivity wrote:
> On 05/25/2012 06:12 AM, Benjamin Herrenschmidt wrote:
>>
>> BTW. This is a qemu patch, and that hypercall isn't KVM related at all,
>> ie, it's implemented in qemu and is used with or without KVM, so
>> documenting it in the kernel tree makes little s
On Mon, 2012-05-28 at 13:40 +0300, Avi Kivity wrote:
> Depends. How do you detect it exists? Are you detecting kvm, or qemu,
> or the hypercall itself?
>
> I'd hate us to find ourselves in a maze of disconnected documentation
> with no clear guidelines on when a feature is available and when it
14 matches
Mail list logo
