linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
* what protects page lru list?
@ 2011-08-19 20:41 Rajesh Ghanekar
  2011-08-20 13:27 ` Johannes Weiner
  0 siblings, 1 reply; 3+ messages in thread
From: Rajesh Ghanekar @ 2011-08-19 20:41 UTC (permalink / raw)
  To: linux-mm

Hi,
   I am confused with what protects page->lru? Is it both zone->lru_lock or
zone->lock? I can see it being protected either by lru_lock or lock.
Are their any
rules where to use lru_lock and where to use lock?

   I did google but couldn't find anything. Sorry if its already discusses
elsewhere, but I couldn't locate any.

- Rajesh

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: what protects page lru list?
  2011-08-19 20:41 what protects page lru list? Rajesh Ghanekar
@ 2011-08-20 13:27 ` Johannes Weiner
  2011-08-20 18:45   ` Rajesh Ghanekar
  0 siblings, 1 reply; 3+ messages in thread
From: Johannes Weiner @ 2011-08-20 13:27 UTC (permalink / raw)
  To: Rajesh Ghanekar; +Cc: linux-mm

On Sat, Aug 20, 2011 at 02:11:53AM +0530, Rajesh Ghanekar wrote:
> Hi,
>    I am confused with what protects page->lru? Is it both zone->lru_lock or
> zone->lock? I can see it being protected either by lru_lock or lock.

It's not so much about page->lru but the actual list the page is
linked to.

The zone's lists of unallocated pages are protected by zone->lock,
while the LRU lists with the pages for userspace are protected by
zone->lru_lock.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: what protects page lru list?
  2011-08-20 13:27 ` Johannes Weiner
@ 2011-08-20 18:45   ` Rajesh Ghanekar
  0 siblings, 0 replies; 3+ messages in thread
From: Rajesh Ghanekar @ 2011-08-20 18:45 UTC (permalink / raw)
  To: Johannes Weiner; +Cc: linux-mm

Thanks Johannes. It makes sense. I was searching for any code in
which pages is on free list and being operated with lru_lock. But as
you said only pages on LRU lists are operated by lru_lock.

I am facing a panic in __rmqueue at list_del where the struct page
is corrupted or probably the free_list is corrupted. The kernel is
2.6.32.43.xxx from SLES11SP1. I will first see if any of the other code
(proprietary) running is not broken.

- Rajesh

On Sat, Aug 20, 2011 at 6:57 PM, Johannes Weiner <jweiner@redhat.com> wrote:
> On Sat, Aug 20, 2011 at 02:11:53AM +0530, Rajesh Ghanekar wrote:
>> Hi,
>>    I am confused with what protects page->lru? Is it both zone->lru_lock or
>> zone->lock? I can see it being protected either by lru_lock or lock.
>
> It's not so much about page->lru but the actual list the page is
> linked to.
>
> The zone's lists of unallocated pages are protected by zone->lock,
> while the LRU lists with the pages for userspace are protected by
> zone->lru_lock.
>

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2011-08-20 18:45 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2011-08-19 20:41 what protects page lru list? Rajesh Ghanekar
2011-08-20 13:27 ` Johannes Weiner
2011-08-20 18:45   ` Rajesh Ghanekar

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox