Re: [PATCH 1/9] [I/OAT] DMA memcpy subsystem

[Olof Johansson]

On Thu, May 25, 2006 at 10:59:40AM -0700, Olof Johansson wrote:

> Is there a specific reason for why you chose to export 3 different
> memcpu calls? They're all just wrapped to the same internals.
>
> It would seem to make sense to have the client do their own
> page_address(page) + offset calculations and just export one function?

Nevermind. I'm too used to 64-bit environments where all memory is
always addressable to the kernel. There's obvious reasons to do it on
32-bit platforms to avoid the extra kernel mapping.


-Olof
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/