On Mon, Jun 17, 2019 at 05:51:16PM +0900, Naoya Horiguchi wrote:
> madvise(MADV_SOFT_OFFLINE) often returns -EBUSY when calling soft offline
> for hugepages with overcommitting enabled. That was caused by the suboptimal
> code in current soft-offline code. See the following part:
> 
>     ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
>                             MIGRATE_SYNC, MR_MEMORY_FAILURE);
>     if (ret) {
>             ...
>     } else {
>             /*
>              * We set PG_hwpoison only when the migration source hugepage
>              * was successfully dissolved, because otherwise hwpoisoned
>              * hugepage remains on free hugepage list, then userspace will
>              * find it as SIGBUS by allocation failure. That's not expected
>              * in soft-offlining.
>              */
>             ret = dissolve_free_huge_page(page);
>             if (!ret) {
>                     if (set_hwpoison_free_buddy_page(page))
>                             num_poisoned_pages_inc();
>             }
>     }
>     return ret;

Hi Naoya,

just a nit:

> 
> Here dissolve_free_huge_page() returns -EBUSY if the migration source page
> was freed into buddy in migrate_pages(), but even in that case we actually
> has a chance that set_hwpoison_free_buddy_page() succeeds. So that means
> current code gives up offlining too early now.

Maybe it is me that I am not really familiar with hugetlb code, but having had
a comment pointing out that the releasing of overcommited hugetlb pages into the
buddy allocator happens in migrate_pages()->put_page()->free_huge_page() would
have been great.

> 
> dissolve_free_huge_page() checks that a given hugepage is suitable for
> dissolving, where we should return success for !PageHuge() case because
> the given hugepage is considered as already dissolved.
> 
> This change also affects other callers of dissolve_free_huge_page(),
> which are cleaned up together.
> 
> Reported-by: Chen, Jerry T <jerry.t.c...@intel.com>
> Tested-by: Chen, Jerry T <jerry.t.c...@intel.com>
> Signed-off-by: Naoya Horiguchi <n-horigu...@ah.jp.nec.com>
> Fixes: 6bc9b56433b76 ("mm: fix race on soft-offlining")
> Cc: <sta...@vger.kernel.org> # v4.19+

Reviewed-by: Oscar Salvador <osalva...@suse.de>

-- 
Oscar Salvador
SUSE L3

Reply via email to