Re: [RFC] respect the referenced bit of KVM guest pages?

From: Minchan Kim
Date: Tue Aug 18 2009 - 07:00:55 EST

On Tue, Aug 18, 2009 at 7:00 PM, Wu Fengguang<fengguang.wu@xxxxxxxxx> wrote:
> On Tue, Aug 18, 2009 at 05:52:47PM +0800, Minchan Kim wrote:
>> On Tue, 18 Aug 2009 17:31:19 +0800
>> Wu Fengguang <fengguang.wu@xxxxxxxxx> wrote:
>>
>> > On Tue, Aug 18, 2009 at 12:17:34PM +0800, Minchan Kim wrote:
>> > > On Tue, 18 Aug 2009 10:34:38 +0800
>> > > Wu Fengguang <fengguang.wu@xxxxxxxxx> wrote:
>> > >
>> > > > Minchan,
>> > > >
>> > > > On Mon, Aug 17, 2009 at 10:33:54PM +0800, Minchan Kim wrote:
>> > > > > On Sun, Aug 16, 2009 at 8:29 PM, Wu Fengguang<fengguang.wu@xxxxxxxxx> wrote:
>> > > > > > On Sun, Aug 16, 2009 at 01:15:02PM +0800, Wu Fengguang wrote:
>> > > > > >> On Sun, Aug 16, 2009 at 11:53:00AM +0800, Rik van Riel wrote:
>> > > > > >> > Wu Fengguang wrote:
>> > > > > >> > > On Fri, Aug 07, 2009 at 05:09:55AM +0800, Jeff Dike wrote:
>> > > > > >> > >> Side question -
>> > > > > >> > >> ÂIs there a good reason for this to be in shrink_active_list()
>> > > > > >> > >> as opposed to __isolate_lru_page?
>> > > > > >> > >>
>> > > > > >> > >> Â Â Â Â Âif (unlikely(!page_evictable(page, NULL))) {
>> > > > > >> > >> Â Â Â Â Â Â Â Â Âputback_lru_page(page);
>> > > > > >> > >> Â Â Â Â Â Â Â Â Âcontinue;
>> > > > > >> > >> Â Â Â Â Â}
>> > > > > >> > >>
>> > > > > >> > >> Maybe we want to minimize the amount of code under the lru lock or
>> > > > > >> > >> avoid duplicate logic in the isolate_page functions.
>> > > > > >> > >
>> > > > > >> > > I guess the quick test means to avoid the expensive page_referenced()
>> > > > > >> > > call that follows it. But that should be mostly one shot cost - the
>> > > > > >> > > unevictable pages are unlikely to cycle in active/inactive list again
>> > > > > >> > > and again.
>> > > > > >> >
>> > > > > >> > Please read what putback_lru_page does.
>> > > > > >> >
>> > > > > >> > It moves the page onto the unevictable list, so that
>> > > > > >> > it will not end up in this scan again.
>> > > > > >>
>> > > > > >> Yes it does. I said 'mostly' because there is a small hole that an
>> > > > > >> unevictable page may be scanned but still not moved to unevictable
>> > > > > >> list: when a page is mapped in two places, the first pte has the
>> > > > > >> referenced bit set, the _second_ VMA has VM_LOCKED bit set, then
>> > > > > >> page_referenced() will return 1 and shrink_page_list() will move it
>> > > > > >> into active list instead of unevictable list. Shall we fix this rare
>> > > > > >> case?
>> > > > >
>> > > > > I think it's not a big deal.
>> > > >
>> > > > Maybe, otherwise I should bring up this issue long time before :)
>> > > >
>> > > > > As you mentioned, it's rare case so there would be few pages in active
>> > > > > list instead of unevictable list.
>> > > >
>> > > > Yes.
>> > > >
>> > > > > When next time to scan comes, we can try to move the pages into
>> > > > > unevictable list, again.
>> > > >
>> > > > Will PG_mlocked be set by then? Otherwise the situation is not likely
>> > > > to change and the VM_LOCKED pages may circulate in active/inactive
>> > > > list for countless times.
>> > >
>> > > PG_mlocked is not important in that case.
>> > > Important thing is VM_LOCKED vma.
>> > > I think below annotaion can help you to understand my point. :)
>> >
>> > Hmm, it looks like pages under VM_LOCKED vma is guaranteed to have
>> > PG_mlocked set, and so will be caught by page_evictable(). Is it?
>>
>> No. I am sorry for making my point not clear.
>> I meant following as.
>> When the next time to scan,
>>
>> shrink_page_list
> Â->
> Â Â Â Â Â Â Â Âreferenced = page_referenced(page, 1,
> Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Âsc->mem_cgroup, &vm_flags);
> Â Â Â Â Â Â Â Â/* In active use or really unfreeable? ÂActivate it. */
> Â Â Â Â Â Â Â Âif (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
> Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Âreferenced && page_mapping_inuse(page))
> Â Â Â Â Â Â Â Â Â Â Â Âgoto activate_locked;
>
>> -> try_to_unmap
> Â Â ~~~~~~~~~~~~ this line won't be reached if page is found to be
> Â Â referenced in the above lines?

Indeed! In fact, I was worry about that.
It looks after live lock problem.
But I think it's very small race window so there isn't any report until now.
Let's Cced Lee.

If we have to fix it, how about this ?
This version has small overhead than yours since
there is less shrink_page_list call than page_referenced.

diff --git a/mm/rmap.c b/mm/rmap.c
index ed63894..283266c 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -358,6 +358,7 @@ static int page_referenced_one(struct page *page,
*/
if (vma->vm_flags & VM_LOCKED) {
*mapcount = 1; /* break early from loop */
+ *vm_flags |= VM_LOCKED;
goto out_unmap;
}

diff --git a/mm/vmscan.c b/mm/vmscan.c
index d224b28..d156e1d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -632,7 +632,8 @@ static unsigned long shrink_page_list(struct
list_head *page_list,
sc->mem_cgroup, &vm_flags);
/* In active use or really unfreeable? Activate it. */
if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
- referenced && page_mapping_inuse(page))
+ referenced && page_mapping_inuse(page)
+ && !(vm_flags & VM_LOCKED))
goto activate_locked;




>
> Thanks,
> Fengguang
>
>> Â Â Â -> try_to_unmap_xxx
>> Â Â Â Â Â Â Â -> if (vma->vm_flags & VM_LOCKED)
>> Â Â Â Â Â Â Â -> try_to_mlock_page
>> Â Â Â Â Â Â Â Â Â Â Â -> TestSetPageMlocked
>> Â Â Â Â Â Â Â Â Â Â Â -> putback_lru_page
>>
>> So at last, the page will be located in unevictable list.
>>
>> > Then I was worrying about a null problem. Sorry for the confusion!
>> >
>> > Thanks,
>> > Fengguang
>> >
>> > > ----
>> > >
>> > > /*
>> > > Â* called from munlock()/munmap() path with page supposedly on the LRU.
>> > > Â*
>> > > Â* Note: Âunlike mlock_vma_page(), we can't just clear the PageMlocked
>> > > Â* [in try_to_munlock()] and then attempt to isolate the page. ÂWe must
>> > > Â* isolate the page to keep others from messing with its unevictable
>> > > Â* and mlocked state while trying to munlock. ÂHowever, we pre-clear the
>> > > Â* mlocked state anyway as we might lose the isolation race and we might
>> > > Â* not get another chance to clear PageMlocked. ÂIf we successfully
>> > > Â* isolate the page and try_to_munlock() detects other VM_LOCKED vmas
>> > > Â* mapping the page, it will restore the PageMlocked state, unless the page
>> > > Â* is mapped in a non-linear vma. ÂSo, we go ahead and SetPageMlocked(),
>> > > Â* perhaps redundantly.
>> > > Â* If we lose the isolation race, and the page is mapped by other VM_LOCKED
>> > > Â* vmas, we'll detect this in vmscan--via try_to_munlock() or try_to_unmap()
>> > > Â* either of which will restore the PageMlocked state by calling
>> > > Â* mlock_vma_page() above, if it can grab the vma's mmap sem.
>> > > Â*/
>> > > static void munlock_vma_page(struct page *page)
>> > > {
>> > > ...
>> > >
>> > > --
>> > > Kind regards,
>> > > Minchan Kim
>>
>>
>> --
>> Kind regards,
>> Minchan Kim
>



--
Kind regards,
Minchan Kim
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/