[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Fri, 11 Nov 2016 08:48:19 +0530
From: Anshuman Khandual <khandual@...ux.vnet.ibm.com>
To: Naoya Horiguchi <n-horiguchi@...jp.nec.com>
Cc: "linux-mm@...ck.org" <linux-mm@...ck.org>,
"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
Hugh Dickins <hughd@...gle.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Dave Hansen <dave.hansen@...el.com>,
Andrea Arcangeli <aarcange@...hat.com>,
Mel Gorman <mgorman@...hsingularity.net>,
Michal Hocko <mhocko@...nel.org>,
Vlastimil Babka <vbabka@...e.cz>,
Pavel Emelyanov <xemul@...allels.com>,
Zi Yan <zi.yan@...rutgers.edu>,
Balbir Singh <bsingharora@...il.com>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
Naoya Horiguchi <nao.horiguchi@...il.com>
Subject: Re: [PATCH v2 03/12] mm: thp: introduce separate TTU flag for thp
freezing
On 11/10/2016 02:39 PM, Naoya Horiguchi wrote:
> On Thu, Nov 10, 2016 at 02:01:56PM +0530, Anshuman Khandual wrote:
>> > On 11/08/2016 05:01 AM, Naoya Horiguchi wrote:
>>> > > TTU_MIGRATION is used to convert pte into migration entry until thp split
>>> > > completes. This behavior conflicts with thp migration added later patches,
>> >
>> > Hmm, could you please explain why it conflicts with the PMD based
>> > migration without split ? Why TTU_MIGRATION cannot be used to
>> > freeze/hold on the PMD while it's being migrated ?
> try_to_unmap() is used both for thp split (via freeze_page()) and page
> migration (via __unmap_and_move()). In freeze_page(), ttu_flag given for
> head page is like below (assuming anonymous thp):
>
> (TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS | TTU_RMAP_LOCKED | \
> TTU_MIGRATION | TTU_SPLIT_HUGE_PMD)
Right.
>
> and ttu_flag given for tail pages is:
>
> (TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS | TTU_RMAP_LOCKED | \
> TTU_MIGRATION)
Right.
>
> __unmap_and_move() calls try_to_unmap() with ttu_flag:
>
> (TTU_MIGRATION | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS)
>
> Now I'm trying to insert a branch for thp migration at the top of
> try_to_unmap_one() like below
>
>
> static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
> unsigned long address, void *arg)
> {
> ...
> if (flags & TTU_MIGRATION) {
> if (!PageHuge(page) && PageTransCompound(page)) {
> set_pmd_migration_entry(page, vma, address);
> goto out;
> }
> }
>
> , so try_to_unmap() for tail pages called by thp split can go into thp
> migration code path (which converts *pmd* into migration entry), while
> the expectation is to freeze thp (which converts *pte* into migration entry.)
Got it.
>
> I detected this failure as a "bad page state" error in a testcase where
> split_huge_page() is called from queue_pages_pte_range().
>
> Anyway, I'll add this explanation into the patch description in the next post.
Sure, thanks for the explanation.
Powered by blists - more mailing lists