Re: How to map high memory for block io

[Jens Axboe <axboe@suse.de>]

On Fri, Jan 27 2006, Pierre Ossman wrote:
> Russell King wrote:
> >
> > I don't see what the problem is.  A sg entry is a list of struct page
> > pointers, an offset, and a size.  As such, it can't describe a transfer
> > which crosses a page because such a structure does not imply that one
> > struct page follows another struct page.
> >
> >   
> 
> If the pages do not strictly follow each other then there is a lot of
> broken code in the kernel. drivers/mmc/mmci.c and drivers/block/ub.c
> being two occurences since both assume they can access the entire entry
> through a single mapping.

Assuming that page idx and idx + 1 in a bio are contigious is a very bad
one, no one has ever made any such guarantees. Besides, if you kmap()
it, things change. The pages in a bio have nothing to do with each
other, they are usually just a consequence of how the page cache ended
up allocating. So completely random usually, once you get a little
fragmentation.

Are you sure you are reading that code correctly? Code making such
assumptions would be breaking pretty quickly.

-- 
Jens Axboe