Re: [PATCH v3 3/6] vbus: add a "vbus-proxy" bus model

Re: [PATCH v3 3/6] vbus: add a "vbus-proxy" bus model

[Gregory Haskins]

Yeah, I agree.  I am not advocating we expend energy on this now.  But my thoughts at the time were that that particular problem can be solved at io-setup time with some kind of call to qualify the address.

Iow: a slow path call with the address would return flags on whether iowrite() should do a real io, or a IOoHC.

-greg
 
-----Original Message-----
From: Avi Kivity <avi@redhat.com>
To: Gregory Haskins <GHaskins@novell.com>
Cc:  <mingo@elte.hu>
Cc:  <gregory.haskins@gmail.com>
Cc:  <alacrityvm-devel@lists.sourceforge.net>
Cc:  <mst@redhat.com>
Cc:  <kvm@vger.kernel.org>
Cc:  <linux-kernel@vger.kernel.org>
Cc:  <netdev@vger.kernel.org>

Sent: 8/18/2009 6:29:08 AM
Subject: Re: [PATCH v3 3/6] vbus: add a "vbus-proxy" bus model	 for

On 08/18/2009 03:24 PM, Gregory Haskins wrote:
> (Again on the top post)
>
> No, Avi, nothing has changed to my knowledge.  I just saw that you and Michael were heading down the same path, so I thought I might interject that we've already covered that ground.
>
> As of right now, I am of the opinion that its not worth any change in the short term, and may be worth IOoHC in the long term (primarily so that mmios get a boost)
>    

The primary issue with IOoHC is that while hypercalls are faster than 
emulated mmio, they're much slower than assigned mmio.  So we have to 
distinguish between these two cases, which gets kinda icky.

-- 
error compiling committee.c: too many arguments to function

Re: [PATCH v3 3/6] vbus: add a "vbus-proxy" bus model

[Avi Kivity]

On 08/18/2009 03:36 PM, Gregory Haskins wrote:
> Yeah, I agree.  I am not advocating we expend energy on this now.  But my thoughts at the time were that that particular problem can be solved at io-setup time with some kind of call to qualify the address.
>
> Iow: a slow path call with the address would return flags on whether iowrite() should do a real io, or a IOoHC.
>    

Yes, it could work, though we'd need somewhere to stow this 
information.  IIRC Arnd suggested a bit from the address itself.

-- 
error compiling committee.c: too many arguments to function

Re: [PATCH v3 3/6] vbus: add a "vbus-proxy" bus model

[Gregory Haskins]

[-- Attachment #1: Type: text/plain, Size: 741 bytes --]

Avi Kivity wrote:
> On 08/18/2009 03:36 PM, Gregory Haskins wrote:
>> Yeah, I agree.  I am not advocating we expend energy on this now.  But
>> my thoughts at the time were that that particular problem can be
>> solved at io-setup time with some kind of call to qualify the address.
>>
>> Iow: a slow path call with the address would return flags on whether
>> iowrite() should do a real io, or a IOoHC.
>>    
> 
> Yes, it could work, though we'd need somewhere to stow this
> information.  IIRC Arnd suggested a bit from the address itself.
> 

Yeah, exactly.  I think MMIO is particularly challenging because I don't
know if there are any bits left to use.  But like I said, its a problem
for another day IMO.

-Greg


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 267 bytes --]

Re: [PATCH v3 3/6] vbus: add a "vbus-proxy" bus model

[Avi Kivity]

On 08/18/2009 04:19 PM, Gregory Haskins wrote:
> Yeah, exactly.  I think MMIO is particularly challenging because I don't
> know if there are any bits left to use.  But like I said, its a problem
> for another day IMO.
>    

x86_64 only uses 48 bits out of the 64 bits in a virtual address, so 
there are several guaranteed-unused bits.

-- 
error compiling committee.c: too many arguments to function