Received-SPF: pass (google.com: domain of linux-kernel+bounces-174311-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Precedence: bulk
MIME-Version: 1.0
References: <20240501042700.83974-1-ioworker0@gmail.com> <20240501042700.83974-3-ioworker0@gmail.com>
 <0077A412-0AF1-4022-8F49-EE77AE601ECB@nvidia.com> <CAK1f24mRVam3w9CZkq4O0smGUTVUQfdvA48mqsU+NKxMUxdz1A@mail.gmail.com>
 <B1DA2DA4-AFEA-4541-8DFC-0D815249A064@nvidia.com> <CAK1f24mpt+ZGow4LLdXKZcwopmkZDrM_eh15SnkEgpiBXTmOwA@mail.gmail.com>
 <10BA9EED-A2BB-44C2-B80A-26527CDFFA50@nvidia.com> <1B2017A4-A252-4C1F-9608-D43ECEAD53B1@nvidia.com>
 <20240508155253.GK4650@nvidia.com> <30469615-2DDC-467E-A810-5EE8E1CFCB43@nvidia.com>
 <20240508163526.GM4650@nvidia.com>
In-Reply-To: <20240508163526.GM4650@nvidia.com>
From: Lance Yang <ioworker0@gmail.com>
Date: Thu, 9 May 2024 16:56:23 +0800
Message-ID: <CAK1f24knjnKkHDp+bRkpfWqe6v5-GPJF=sSWPo6zQUydT9aMaw@mail.gmail.com>
Subject: Re: [PATCH v4 2/3] mm/rmap: integrate PMD-mapped folio splitting into
 pagewalk loop
To: Jason Gunthorpe <jgg@nvidia.com>
Cc: Zi Yan <ziy@nvidia.com>, Alistair Popple <apopple@nvidia.com>, akpm@linux-foundation.org, 
	willy@infradead.org, sj@kernel.org, maskray@google.com, ryan.roberts@arm.com, 
	david@redhat.com, 21cnbao@gmail.com, mhocko@suse.com, fengwei.yin@intel.com, 
	zokeefe@google.com, shy828301@gmail.com, xiehuan09@gmail.com, 
	libang.li@antgroup.com, wangkefeng.wang@huawei.com, songmuchun@bytedance.com, 
	peterx@redhat.com, minchan@kernel.org, linux-mm@kvack.org, 
	linux-kernel@vger.kernel.org, Baolin Wang <baolin.wang@linux.alibaba.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

Hey Jason,

Thanks a lot for clarifying!

On Thu, May 9, 2024 at 12:35=E2=80=AFAM Jason Gunthorpe <jgg@nvidia.com> wr=
ote:
>
> On Wed, May 08, 2024 at 12:22:08PM -0400, Zi Yan wrote:
> > On 8 May 2024, at 11:52, Jason Gunthorpe wrote:
> >
> > > On Wed, May 08, 2024 at 10:56:34AM -0400, Zi Yan wrote:
> > >
> > >> Lance is improving try_to_unmap_one() to support unmapping PMD THP a=
s a whole,
> > >> so he moves split_huge_pmd_address() inside while (page_vma_mapped_w=
alk(&pvmw))
> > >> and after mmu_notifier_invalidate_range_start() as split_huge_pmd_lo=
cked()
> > >> and does not include the mmu notifier ops inside split_huge_pmd_addr=
ess().
> > >> I wonder if that could cause issues, since the mmu_notifier_invalida=
te_range_start()
> > >> before the while loop only has range of the original address and
> > >> split huge pmd can affect the entire PMD address range and these two=
 ranges
> > >> might not be the same.
> > >
> > > That does not sound entirely good..
> > >
> > > I suppose it depends on what split does, if the MM page table has the
> > > same translation before and after split then perhaps no invalidation
> > > is even necessary.
> >
> > Before split, it is a PMD mapping to a PMD THP (order-9). After split,
> > they are 512 PTEs mapping to the same THP. Unless the secondary TLB
> > does not support PMD mapping and use 512 PTEs instead, it seems to
> > be an issue from my understanding.
>
> I may not recall fully, but I don't think any secondaries are
> so sensitive to the PMD/PTE distinction.. At least the ones using
> hmm_range_fault() are not.
>
> When the PTE eventually comes up for invalidation then the secondary
> should wipe out any granual they may have captured.
>
> Though, perhaps KVM should be checked carefully.

Agreed. IIUC,  the secondary mappings are teardown in
mmu_notifier_invalidate_range_start() and allowed to be established again
only mmu_notifier_invalidate_range_end(), then all modifications will be
picked up by the secondary MMU. I just image that the secondary MMU
like a TLB, where you only invalidate, and then it will be refilled later (=
after
mmu_notifier_invalidate_range_end()).

Thanks again for the lesson!
Lance

>
> > In terms of two mmu_notifier ranges, first is in the split_huge_pmd_add=
ress()[1]
> > and second is in try_to_unmap_one()[2]. When try_to_unmap_one() is unma=
pping
> > a subpage in the middle of a PMD THP, the former notifies about the PMD=
 range
> > change due to one PMD split into 512 PTEs and the latter only needs to =
notify
> > about the invalidation of the unmapped PTE. I do not think the latter c=
an
> > replace the former, although a potential optimization can be that the l=
atter
> > can be removed as it is included in the range of the former.
>
> I think we probably don't need both, either size might be fine, but
> the larger size is definately fine..
>
> > Regarding Lance's current code change, is it OK to change mmu_notifier =
range
> > after mmu_notifier_invalidate_range_start()?
>
> No, it cannot be changed during a start/stop transaction.
>
> Jason
>
>