* ccio-dma q about io pdir: is there a kernel mem space never paged?
@ 2008-07-21 12:28 Joel Soete
2008-07-21 14:58 ` Kyle McMartin
0 siblings, 1 reply; 2+ messages in thread
From: Joel Soete @ 2008-07-21 12:28 UTC (permalink / raw)
To: linux-parisc
Hello all,
Re-reading: <http://www.hpl.hp.com/hpjournal/96feb/feb96a6.pdf>
I noticed another detail:
sic "Recall that the I/O page directory contains all active address translations and must be memory-resident."
Those key words "must be memory-resident" would mean to me never paged (in/out)?
Even thought I read ./include/linux/gfp.h, it's not clear to me which could be the gfp_mask I can use in:
ioc->pdir_base = (u64 *)__get_free_pages(GFP_KERNEL,
get_order(ioc->pdir_size));
to advise kernel to never paging this I/O page directory?
Any idea?
Tia,
J.
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: ccio-dma q about io pdir: is there a kernel mem space never paged?
2008-07-21 12:28 ccio-dma q about io pdir: is there a kernel mem space never paged? Joel Soete
@ 2008-07-21 14:58 ` Kyle McMartin
0 siblings, 0 replies; 2+ messages in thread
From: Kyle McMartin @ 2008-07-21 14:58 UTC (permalink / raw)
To: Joel Soete; +Cc: linux-parisc
On Mon, Jul 21, 2008 at 12:28:56PM +0000, Joel Soete wrote:
>
The kernel is never paged out. Just think, if you page out the swapper,
how could you page anything back in?
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2008-07-21 14:58 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2008-07-21 12:28 ccio-dma q about io pdir: is there a kernel mem space never paged? Joel Soete
2008-07-21 14:58 ` Kyle McMartin
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.