Displaying 5 results from an estimated 5 matches for "__pg_hwpoison".
2016 Apr 06
1
[PATCH v3 01/16] mm: use put_page to free page instead of putback_lru_page
...wpoison() doesn't
> >> remove from buddy freelists).
> >
> > check_new_page() in mm/page_alloc.c should prevent reallocation of PageHWPoison.
> > As you pointed out, memory error handler doens't remove it from buddy freelists.
>
> Oh, I see. It's using __PG_HWPOISON wrapper, so I didn't notice it when
> searching. In any case that results in a bad_page() warning, right? Is
> it desirable for a soft-offlined page?
That's right, and the bad_page warning might be too strong for soft offlining.
We can't tell which of memory_failure/soft_offline_...
2016 Apr 06
1
[PATCH v3 01/16] mm: use put_page to free page instead of putback_lru_page
...wpoison() doesn't
> >> remove from buddy freelists).
> >
> > check_new_page() in mm/page_alloc.c should prevent reallocation of PageHWPoison.
> > As you pointed out, memory error handler doens't remove it from buddy freelists.
>
> Oh, I see. It's using __PG_HWPOISON wrapper, so I didn't notice it when
> searching. In any case that results in a bad_page() warning, right? Is
> it desirable for a soft-offlined page?
That's right, and the bad_page warning might be too strong for soft offlining.
We can't tell which of memory_failure/soft_offline_...
2016 Apr 05
2
[PATCH v3 01/16] mm: use put_page to free page instead of putback_lru_page
On Mon, Apr 04, 2016 at 04:46:31PM +0200, Vlastimil Babka wrote:
> On 04/04/2016 06:45 AM, Naoya Horiguchi wrote:
> > On Mon, Apr 04, 2016 at 10:39:17AM +0900, Minchan Kim wrote:
...
> >>>
> >>> Also (but not your fault) the put_page() preceding
> >>> test_set_page_hwpoison(page)) IMHO deserves a comment saying which
> >>> pin we are
2016 Apr 05
2
[PATCH v3 01/16] mm: use put_page to free page instead of putback_lru_page
On Mon, Apr 04, 2016 at 04:46:31PM +0200, Vlastimil Babka wrote:
> On 04/04/2016 06:45 AM, Naoya Horiguchi wrote:
> > On Mon, Apr 04, 2016 at 10:39:17AM +0900, Minchan Kim wrote:
...
> >>>
> >>> Also (but not your fault) the put_page() preceding
> >>> test_set_page_hwpoison(page)) IMHO deserves a comment saying which
> >>> pin we are
2016 Apr 05
0
[PATCH v3 01/16] mm: use put_page to free page instead of putback_lru_page
...;t find it and test_set_page_hwpoison() doesn't
>> remove from buddy freelists).
>
> check_new_page() in mm/page_alloc.c should prevent reallocation of PageHWPoison.
> As you pointed out, memory error handler doens't remove it from buddy freelists.
Oh, I see. It's using __PG_HWPOISON wrapper, so I didn't notice it when
searching. In any case that results in a bad_page() warning, right? Is
it desirable for a soft-offlined page? If we didn't free poisoned pages
to buddy system, they wouldn't trigger this warning.
> BTW, it might be a bit off-topic, but recently I...