Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20220624173656.2033256-1-jthoughton@google.com>
 <20220624173656.2033256-5-jthoughton@google.com> <YroYaWVvNZJvtqsH@monkey>
 <Yrvsn66c+UI8ZQlO@FVFYT0MHHV2J.usts.net> <Yry+PPHSat2uN+aG@monkey>
In-Reply-To: <Yry+PPHSat2uN+aG@monkey>
From:   James Houghton <jthoughton@google.com>
Date:   Wed, 29 Jun 2022 14:39:19 -0700
Message-ID: <CADrL8HX9OkuWzpODBzHx-6-7_SLJ1YCCe5HxXdPa4ibqeQZu3A@mail.gmail.com>
Subject: Re: [RFC PATCH 04/26] hugetlb: make huge_pte_lockptr take an explicit
 shift argument.
To:     Mike Kravetz <mike.kravetz@oracle.com>
Cc:     Muchun Song <songmuchun@bytedance.com>,
        Peter Xu <peterx@redhat.com>,
        David Hildenbrand <david@redhat.com>,
        David Rientjes <rientjes@google.com>,
        Axel Rasmussen <axelrasmussen@google.com>,
        Mina Almasry <almasrymina@google.com>,
        Jue Wang <juew@google.com>,
        Manish Mishra <manish.mishra@nutanix.com>,
        "Dr . David Alan Gilbert" <dgilbert@redhat.com>,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Wed, Jun 29, 2022 at 2:04 PM Mike Kravetz <mike.kravetz@oracle.com> wrote:
>
> On 06/29/22 14:09, Muchun Song wrote:
> > On Mon, Jun 27, 2022 at 01:51:53PM -0700, Mike Kravetz wrote:
> > > On 06/24/22 17:36, James Houghton wrote:
> > > > This is needed to handle PTL locking with high-granularity mapping. We
> > > > won't always be using the PMD-level PTL even if we're using the 2M
> > > > hugepage hstate. It's possible that we're dealing with 4K PTEs, in which
> > > > case, we need to lock the PTL for the 4K PTE.
> > >
> > > I'm not really sure why this would be required.
> > > Why not use the PMD level lock for 4K PTEs?  Seems that would scale better
> > > with less contention than using the more coarse mm lock.
> > >
> >
> > Your words make me thing of another question unrelated to this patch.
> > We __know__ that arm64 supports continues PTE HugeTLB. huge_pte_lockptr()
> > did not consider this case, in this case, those HugeTLB pages are contended
> > with mm lock. Seems we should optimize this case. Something like:
> >
> > diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
> > index 0d790fa3f297..68a1e071bfc0 100644
> > --- a/include/linux/hugetlb.h
> > +++ b/include/linux/hugetlb.h
> > @@ -893,7 +893,7 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
> >  static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
> >                                            struct mm_struct *mm, pte_t *pte)
> >  {
> > -       if (huge_page_size(h) == PMD_SIZE)
> > +       if (huge_page_size(h) <= PMD_SIZE)
> >                 return pmd_lockptr(mm, (pmd_t *) pte);
> >         VM_BUG_ON(huge_page_size(h) == PAGE_SIZE);
> >         return &mm->page_table_lock;
> >
> > I did not check if elsewhere needs to be changed as well. Just a primary
> > thought.

I'm not sure if this works. If hugetlb_pte_size(hpte) is PAGE_SIZE,
then `hpte.ptep` will be a pte_t, not a pmd_t -- I assume that breaks
things. So I think, when doing a HugeTLB PT walk down to PAGE_SIZE, we
need to separately keep track of the location of the PMD so that we
can use it to get the PMD lock.

>
> That seems perfectly reasonable to me.
>
> Also unrelated, but using the pmd lock is REQUIRED for pmd sharing.  The
> mm lock is process specific and does not synchronize shared access.  I
> found that out the hard way. :)
>
> --
> Mike Kravetz