Re: [PATCH] zero^H^H^H^Hsingle copy pipe

[Manfred Spraul]

Alan Cox wrote:
> 
> > The main problem is that map_user_kiobuf() locks pages into memory.
> > It's a bad idea for pipes. Either we must severely limit the maximum
> 
> You only have to map them for the actual copy.

The current map_user_kiobuf() doesn't have an 'mm' parameter, I can only
use it from the context of the writer.
I could use map_user_kiobuf_mm(), but the kiobuf structure is far too
large, I really don't want a huge structure (> 8 kB?) for a simple 4 kB
single copy transfer.
Including a memset(,0,sizeof(*iobuf) in kiobuf_init().

I think reusing the ptrace interface (access_process_vm()) is the better
solution.

--
	Manfred