Dom0 IO handling

Dom0 IO handling

[maheen butt]

[-- Attachment #1.1: Type: text/plain, Size: 466 bytes --]

Hi all,

I'm investigating the source code of Xenified kernel. From documentations related to 

Xen told me that all guest domains run in less privilege mode ( ring 1 in case of x86).
Dom0 is also running in ring 1. But it can have direct access to IO devices. It means 

Dom0 has a special bahaviour that it is running in ring1 but can directly access IO devices.
How Dom0 access IO devices directly?
how can I relate this special way of Dom0 with its source code?

[-- Attachment #1.2: Type: text/html, Size: 1595 bytes --]

[-- Attachment #2: Type: text/plain, Size: 126 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel

Re: Dom0 IO handling

[George Shuklin]

[-- Attachment #1.1: Type: text/plain, Size: 949 bytes --]

AFAIK dom0 is pv-domain.
All interrupts are handled by xen and passed down to dom0 via events 
(kinda internal  xen interrupt-like stuff). PV kernel accepts them and 
process as normal interrupts.

Is Xen use IOMMU to protect itself from misbehave devices or not... I'm 
not sure.

On 11.10.2012 10:16, maheen butt wrote:
> Hi all,
>
> I'm investigating the source code of Xenified kernel. From 
> documentations related to
> Xen told me that all guest domains run in less privilege mode ( ring 1 
> in case of x86).
> Dom0 is also running in ring 1. But it can have direct access to IO 
> devices. It means
> Dom0 has a special bahaviour that it is running in ring1 but can 
> directly access IO devices.
> How Dom0 access IO devices directly?
> how can I relate this special way of Dom0 with its source code?
>
>
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> http://lists.xen.org/xen-devel

[-- Attachment #1.2: Type: text/html, Size: 2925 bytes --]

[-- Attachment #2: Type: text/plain, Size: 126 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel