Received-SPF: pass (google.com: domain of linux-kernel+bounces-158488-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Precedence: bulk
MIME-Version: 1.0
References: <CAK1f24nb6FkipH3OZa0uwbBWkefS3f2BrJ_GTxkS2j6+6bgODQ@mail.gmail.com>
 <20240425085051.74889-1-ioworker0@gmail.com> <49394660-8455-48ec-8ae1-fbd2d590d27a@redhat.com>
 <CAK1f24kaphS9Gz4Nxe-+=iHs_+CpA1Qk7q=pdzUJKc5u-0_qXw@mail.gmail.com> <e75b509a-bf4f-418c-a921-cf3383fc5929@redhat.com>
In-Reply-To: <e75b509a-bf4f-418c-a921-cf3383fc5929@redhat.com>
From: Lance Yang <ioworker0@gmail.com>
Date: Thu, 25 Apr 2024 20:00:23 +0800
Message-ID: <CAK1f24njK_=FFTZyCCcZYPosop=WU8WGZHZRtPOk6zJDp2SdCQ@mail.gmail.com>
Subject: Re: [PATCH v2 1/1] mm/vmscan: avoid split PMD-mapped THP during shrink_folio_list()
To: David Hildenbrand <david@redhat.com>
Cc: ziy@nvidia.com, 21cnbao@gmail.com, akpm@linux-foundation.org, 
	fengwei.yin@intel.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org, 
	maskray@google.com, mhocko@suse.com, minchan@kernel.org, peterx@redhat.com, 
	ryan.roberts@arm.com, shy828301@gmail.com, songmuchun@bytedance.com, 
	wangkefeng.wang@huawei.com, willy@infradead.org, xiehuan09@gmail.com, 
	zokeefe@google.com
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Thu, Apr 25, 2024 at 5:25=E2=80=AFPM David Hildenbrand <david@redhat.com=
> wrote:
>
> >> I was wondering if we can better integrate that into the pagewalk belo=
w.
> >>
> >> That is, don't do the TTU_SPLIT_HUGE_PMD immediately. Start the pagewa=
lk
> >> first. If we walk a PMD, try to unmap it. Only if that fails, split it=
.
> >
> > Nice. Thanks for the suggestion!
> > I'll work on integrating it into the pagewalk as you suggested.
> >
> >>
> >> Less working on "vma + address" and instead directly on PMDs.
> >
> > Yes, some of the work on "vma + address" can be avoided :)
>
> Doing the conditional split while in the pagewalk will be the
> interesting bit to sort out (we temporarily have to drop the PTL and
> start once again from that now-PTE-mapped page table). But it should be
> a reasonable thing to have.

Yep, it's an interesting challenge for me, but definitely worth tackling ;)

>
> Please let us know if you run into bigger issues with that!

Thanks, I'll do my best to sort it out and reach out for help if needed :p

>
> See walk_pmd_range() as an inspiration where we call split_huge_pmd().

Thanks for your suggestion! I'll take a closer look at it.

Thanks again for clarifying!
Lance

>
> --
> Cheers,
>
> David / dhildenb
>