lkml.org 
[lkml]   [2013]   [Aug]   [7]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRE: [PATCH v8 06/12] ARM: dts: Add description of System MMU of Exynos SoCs
Date
> -----Original Message-----
> From: grundler@google.com [mailto:grundler@google.com] On Behalf Of Grant Grundler
> Sent: Wednesday, August 07, 2013 1:07 AM
> To: Marek Szyprowski
>
> Hi Marek,
>
> On Tue, Aug 6, 2013 at 6:17 AM, Marek Szyprowski
> <m.szyprowski@samsung.com> wrote:
> ...
> > IMHO it is much better to have a simple driver, which binds to a single
> > IOMMU controller and leave it to the driver whether to have a same virtual address
> > space for all parts of FIMC-IS or MFC submodules/memory ports or not.
>
> I understand this part. I having written the IOMMU support for 4
> different IOMMUs, all of which had exactly one IO Page Table and one
> IOMMU shared by many devices.
>
> > Just make sure that it will be possible to attach more than one sysmmu
> > controller to one iommu domain.
>
> I don't understand how this is possible. Can someone explain this
> better in the IOMMU documentation please?

System MMU is dedicated to a master H/W such as FIMD and FIMC.
Thus, attaching a master H/W to an iommu domain can be thought as
attaching a System MMU to an iommu domain even though such thinking
is not correct view of the relationship between iommu domain and
System MMU.

>
> "iommu domain" to me means one virtual IO address space for attached
> devices that can master DMA transactions. The IOMMU then uses it's IO
> Page Table to translate the DMA address to the system physical address
> space and forwards the transaction.
>
> What is the role of the sysmmu in all of this?
> Is the sysmmu just the MMU (or collection of MMU) for host DRAM?
> Or is sysmmu responsible for "other stuff"? (clocks, power domains, MMU, etc)
>
System MMU is responsible for address translation of traffic from a
master H/W which the System MMU is dedicated to.

> I can understand we might have multiple MMUs in a system...e.g. every
> range of memory might have it's own MMU. But they share the same
> physical address space and generally live under one page table.
> Because of "one page table" I would consider them one entity from the
> the IOMMUs perspective.

Sorry, I don't understand.
Do you mean you are thinking that it is better to share one page table
by all IOMMUs in a system?

Thank you,
KyongHo
>
> thanks,
> grant



\
 
 \ /
  Last update: 2013-08-07 14:21    [W:0.080 / U:0.080 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site