linux1394-devel

DMA to user space

[<And...@no...>]

Hi Andreas and Sebastien,

I was wondering if you could give me some estimate of when to expect DMA
transfer or mapping of iso data to user space? I would really want to have
this for our DV decoder.


Best regards,
Anders Weitman


PS. I'm still trying to get approval for releasing the code for the DV
decoder but it's a difficult issue and the lawyers and patent people are a
bit slow (:



_____________________________________________________________________
Anders Weitman, M.Sc             Phone    : +46 (0)13 4611341
Development Engineer             Fax      : +46 (0)13 4611001
Nokia Home Communications        Mobile   : +46 (0)70 2141319
Diskettgatan 11                  E-mail   : and...@no...
SE-583 35 Linkoping, Sweden      Internet : www.nokia.com/multimedia/

Re: DMA to user space

[Sebastien R. <Seb...@sy...>]

>>>>> "Anders" == Anders Weitman <And...@no...> writes:

Anders> Hi Andreas and Sebastien, I was wondering if you could give me some
Anders> estimate of when to expect DMA transfer or mapping of iso data to user
Anders> space? I would really want to have this for our DV decoder.

I am quite busy right now with my work, so I am not actively working
on this at the moment. If you look at the list archive, a Japanese guy did
write a patch for it, but it has to be modified to work with the
current driver, and I think I will end up rewriting part of it anyway
once I have some time. I will soon need it anyway, so I might work on
this again in a month or two. In the mean time, we will need to
define an API to get this working with the subsystem.

-- 
Sebastien Rougeaux
RSISE, The Australian National University

Re: DMA to user space

[Andreas B. <and...@mu...>]

On Thu, Apr 13, 2000 at 01:05:57PM +0300, And...@no... wrote:
> Hi Andreas and Sebastien,
> 
> I was wondering if you could give me some estimate of when to expect DMA
> transfer or mapping of iso data to user space? I would really want to have
> this for our DV decoder.

Second on my ToDo list (after getting that subsystem initiated
transactions and GUID collecting to work).

The first step to zero copy would be to make the hardware drivers use
subsystem provided buffers for iso receiving instead of their own (and
write code to manage locking and automatic freeing of those buffers in
the subsystem).  After that exists it would be a small step to
actually mapping those buffers to user space.  I don't think
implementing mapping in the current raw1394 would a good idea since it
would have to be rewritten then.

-- 
 Andreas E. Bombe <and...@mu...>    DSA key 0x04880A44
http://home.pages.de/~andreas.bombe/    http://linux1394.sourceforge.net/