[Linaro-open-discussions] RMR spec //(was)RE: Suggested Agenda / timings for Monday 7 Dec call

Lorenzo Pieralisi lorenzo.pieralisi at arm.com
Tue Apr 13 10:34:49 UTC 2021


On Mon, Apr 12, 2021 at 11:43:20AM +0000, Shameerali Kolothum Thodi wrote:
> Hi Lorenzo,
> 
> > -----Original Message-----
> > From: Lorenzo Pieralisi [mailto:lorenzo.pieralisi at arm.com]
> > Sent: 01 February 2021 11:54
> > To: Shameerali Kolothum Thodi <shameerali.kolothum.thodi at huawei.com>
> > Cc: Jonathan Cameron <jonathan.cameron at huawei.com>; wanghuiqiang
> > <wanghuiqiang at huawei.com>; linaro-open-discussions at op-lists.linaro.org
> > Subject: Re: RMR spec //(was)RE: [Linaro-open-discussions] Suggested Agenda
> > / timings for Monday 7 Dec call
> > 
> > On Fri, Jan 29, 2021 at 05:38:58PM +0000, Shameerali Kolothum Thodi wrote:
> > > Hi Lorenzo,
> > >
> > > > > -----Original Message-----
> > > > > From: Linaro-open-discussions
> > > > > [mailto:linaro-open-discussions-bounces at op-lists.linaro.org] On Behalf Of
> > > > > Lorenzo Pieralisi via Linaro-open-discussions
> > > > > Sent: 10 December 2020 09:13
> > > > > To: Jonathan Cameron <jonathan.cameron at huawei.com>
> > > > > Cc: linaro-open-discussions at op-lists.linaro.org
> > > > > Subject: Re: [Linaro-open-discussions] Suggested Agenda / timings for
> > > > Monday
> > > > > 7 Dec call
> > > > >
> > > > > On Thu, Dec 03, 2020 at 01:40:55PM +0000, Jonathan Cameron wrote:
> > > > >
> > > > > [...]
> > > > >
> > > > > > RMR related topics - follow up on last call: Lorenzo Pieralisi (ARM) - 5
> > mins
> > >
> > > Just a quick one on updated RMR spec publication. I see a revision E.a here,
> > >
> > > https://developer.arm.com/documentation/den0049/latest/
> > >
> > > This seems to have addressed all the things we discussed. Is this a
> > > final one officially?  If yes, I couldn't understand why the RMR node
> > > flags are at an offset 8, compared to other nodes where the node
> > > specific data normally starts at offset 16.
> > >
> > > Could you please check and let me know.
> > 
> > You are right, there are a couple of issues that we are fixing and an
> > updated version should be published shortly I will notify you
> > accordingly, apologies (and thank you for spotting it).
> 
> I am trying to respin the RMR series now and after re-reading the RMR part
> of the IORT spec, a bit confused now.
> 
> In section 3.1.1.5, it says "The association of reserved memory ranges
> to stream IDs is always expressed as M:1 for each RMR node....". Does that
> mean the "Number of ID Mappings" for each RMR node should be set to 1?
> 
> Also to confirm, that means if there are multiple stream IDs that requires same
> memory regions to be unity mapped, then we need multiple RMR nodes for each
> stream IDs, right?

You mean an RMR node per streamID and answer is yes to both questions.

Out of curiosity: do you have a use case for multiple streamids
requiring the *same* unity mappings ?

> Further down, it also says, "Each Memory Range descriptor must describe a
> unique range of memory that does not overlap with memory ranges described
> by other descriptors.". So if above is true(ie, M:1), then the statement about
> the unique range is only applicable to the descriptors in a particular RMR node
> and not across the nodes. 

It refers to descriptors within one RMR node, I asked to add a
clarification to the specs.

> 
> Could you please take a look and clarify 

Have I managed to clarify ? Please let me know.

Thanks,
Lorenzo


More information about the Linaro-open-discussions mailing list