Re: Potential problem with the page_mapping macro and flush_dcache_page()

[Andrew Morton <akpm@osdl.org>]

James Bottomley <James.Bottomley@SteelEye.com> wrote:
>
> > > OK, I confess to not ever having looked at that ... does it use
>  > > get_user_pages() as well?
>  > 
>  > I believe so, Andrew knows...
> 
>  OK I'll wait to see what he says.

<he'd made some procmailrc changes and had thought that linux-arch was
rather quiet lately>

Yes, direct-io does get_user_pages() and then uses submit_bio() to
read/write the pages.

So it should fall under

 2) device DMA, where the L2 cache eviction done by the device DMA
    will pull out the D-cache entries, or if the block I/O is via PIO
    it will do cache flushing in there, as per some asm-*/ide.h
    implementations of __ide_ins*()/__ide_outs*()

umm, except in the case where direct-io hit a file hole.  In that case we
memset the user's page and use flush_dcache_page().  And that's most likely
an anonymous page.