Re: [RFC simple allocator v2 0/2] Simple allocator

2017-02-14 Thread Mark Brown
On Mon, Feb 13, 2017 at 11:01:14AM -0800, Laura Abbott wrote:
> On 02/13/2017 10:18 AM, Mark Brown wrote:

> > The software defined networking people seemed to think they had a use
> > case for this as well.  They're not entirely upstream of course but
> > still...

> This is the first I've heard of anything like this. Do you have any more
> details/reading?

No, unfortunately it was in a meeting and I was asking for more details
on what specifically the hardware was doing myself.  My understanding is
that it's very similar to the GPU/video needs.


signature.asc
Description: PGP signature


Re: [RFC simple allocator v2 0/2] Simple allocator

2017-02-13 Thread Laura Abbott
On 02/13/2017 10:18 AM, Mark Brown wrote:
> On Mon, Feb 13, 2017 at 03:45:04PM +0100, Benjamin Gaignard wrote:
> 
>> An other question is: do we have others memory regions that could be 
>> interested
>> by this new framework ? I have in mind that some title memory regions could 
>> use
>> it or replace ION heaps (system, carveout, etc...).
>> Maybe it only solve CMA allocation issue, in this case there is no need to 
>> create
>> a new framework but only a dedicated ioctl.
> 
> The software defined networking people seemed to think they had a use
> case for this as well.  They're not entirely upstream of course but
> still...
> 

This is the first I've heard of anything like this. Do you have any more
details/reading?

Thanks,
Laura


Re: [RFC simple allocator v2 0/2] Simple allocator

2017-02-13 Thread Mark Brown
On Mon, Feb 13, 2017 at 03:45:04PM +0100, Benjamin Gaignard wrote:

> An other question is: do we have others memory regions that could be 
> interested
> by this new framework ? I have in mind that some title memory regions could 
> use
> it or replace ION heaps (system, carveout, etc...).
> Maybe it only solve CMA allocation issue, in this case there is no need to 
> create
> a new framework but only a dedicated ioctl.

The software defined networking people seemed to think they had a use
case for this as well.  They're not entirely upstream of course but
still...


signature.asc
Description: PGP signature