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;
Date:   Wed, 31 Aug 2022 14:23:16 -0400
From:   Peter Xu <peterx@redhat.com>
To:     David Hildenbrand <david@redhat.com>
Cc:     John Hubbard <jhubbard@nvidia.com>,
        Jason Gunthorpe <jgg@nvidia.com>, linux-kernel@vger.kernel.org,
        linux-mm@kvack.org, Andrew Morton <akpm@linux-foundation.org>,
        Mel Gorman <mgorman@suse.de>,
        "Matthew Wilcox (Oracle)" <willy@infradead.org>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Hugh Dickins <hughd@google.com>,
        Alistair Popple <apopple@nvidia.com>
Subject: Re: [PATCH v1 2/3] mm/gup: use gup_can_follow_protnone() also in
 GUP-fast
Message-ID: <Yw+nFBgnSH9WWYHv@xz-m1.local>
References: <20220825164659.89824-1-david@redhat.com>
 <20220825164659.89824-3-david@redhat.com>
 <1892f6de-fd22-0e8b-3ff6-4c8641e1c68e@redhat.com>
 <2e20c90d-4d1f-dd83-aa63-9d8d17021263@redhat.com>
 <Yw5a1paQJ9MNdgmW@nvidia.com>
 <9ce3aaaa-71a6-5a81-16a3-36e6763feb91@redhat.com>
 <9a4fe603-950e-785b-6281-2e309256463f@nvidia.com>
 <68b38ac4-c680-b694-21a9-1971396d63b9@redhat.com>
 <Yw+KnRTrZ74qFUAA@xz-m1.local>
 <4d067a99-1112-3b3d-bedf-35c1124904fd@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <4d067a99-1112-3b3d-bedf-35c1124904fd@redhat.com>
Precedence: bulk

On Wed, Aug 31, 2022 at 06:31:23PM +0200, David Hildenbrand wrote:
> >> +	/* Clear/invalidate the PTE before checking for PINs. */
> >> +	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP))
> >> +		smp_mb();
> > 
> > Wondering whether this could be smp_mb__before_atomic().
> 
> We'll read via atomic_read().
> 
> That's a non-RMW operation. smp_mb__before_atomic() only applies to
> RMW (Read Modify Write) operations.

Ah right.

> >> diff --git a/mm/ksm.c b/mm/ksm.c
> >> index d7526c705081..971cf923c0eb 100644
> >> --- a/mm/ksm.c
> >> +++ b/mm/ksm.c
> >> @@ -1091,6 +1091,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
> >>  			goto out_unlock;
> >>  		}
> >>  
> >> +		/* See page_try_share_anon_rmap(): clear PTE first. */
> >>  		if (anon_exclusive && page_try_share_anon_rmap(page)) {
> >>  			set_pte_at(mm, pvmw.address, pvmw.pte, entry);
> >>  			goto out_unlock;
> >> diff --git a/mm/migrate_device.c b/mm/migrate_device.c
> >> index 27fb37d65476..47e955212f15 100644
> >> --- a/mm/migrate_device.c
> >> +++ b/mm/migrate_device.c
> >> @@ -193,20 +193,16 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
> >>  			bool anon_exclusive;
> >>  			pte_t swp_pte;
> >>  
> > 
> > flush_cache_page() missing here?
> 
> Hmm, wouldn't that already be missing on the !anon path right now?

Yes, I think Alistair plans to fix it too in the other patchset.  So either
this will rebase to that or it should fix it too.  Thanks,

-- 
Peter Xu