Re: [PATCH 1/1] Userspace I/O (UIO): Add support for userspace DMA

[Earl Chew <earl_chew@agilent.com>]

I'm taking another look at the changes that were submitted in

http://lkml.org/lkml/2008/12/3/453

to see if they can be made more palatable.


In http://lkml.org/lkml/2008/12/4/64 you wrote:

> Why not create another special device that will give you DMA memory when
> you mmap it? That would also allow you to obtain the physical address
> without this utter horrid hack of writing it in the mmap'ed memory.
> 
> /dev/uioN-dma would seem like a fine name for that.


I understand the main objection was the hack to return the physical
address of the allocated DMA buffer within the buffer itself amongst
some other things.

Your suggestion was to create /dev/uioN-dma for the purpose of
allocating DMA memory.

I'm having trouble figuring out how this would help to return the
physical (bus) address of the DMA memory in a more elegant manner.

What idea did you have for the userspace program to obtain
the physical (bus) of the allocated DMA memory buffer?


Earl