Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Thu, 10 Jun 2021 12:06:17 +0300
From:   "Kirill A. Shutemov" <kirill@shutemov.name>
To:     Hugh Dickins <hughd@google.com>
Cc:     Andrew Morton <akpm@linux-foundation.org>,
        "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
        Yang Shi <shy828301@gmail.com>,
        Wang Yugui <wangyugui@e16-tech.com>,
        Matthew Wilcox <willy@infradead.org>,
        Alistair Popple <apopple@nvidia.com>,
        Ralph Campbell <rcampbell@nvidia.com>, Zi Yan <ziy@nvidia.com>,
        Peter Xu <peterx@redhat.com>, Will Deacon <will@kernel.org>,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 03/11] mm: page_vma_mapped_walk(): use pmd_read_atomic()
Message-ID: <20210610090617.e6qutzzj3jxcseyi@box.shutemov.name>
References: <589b358c-febc-c88e-d4c2-7834b37fa7bf@google.com>
 <594c1f0-d396-5346-1f36-606872cddb18@google.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <594c1f0-d396-5346-1f36-606872cddb18@google.com>
Precedence: bulk

On Wed, Jun 09, 2021 at 11:38:11PM -0700, Hugh Dickins wrote:
> page_vma_mapped_walk() cleanup: use pmd_read_atomic() with barrier()
> instead of READ_ONCE() for pmde: some architectures (e.g. i386 with PAE)
> have a multi-word pmd entry, for which READ_ONCE() is not good enough.
> 
> Signed-off-by: Hugh Dickins <hughd@google.com>
> Cc: <stable@vger.kernel.org>
> ---
>  mm/page_vma_mapped.c | 5 ++++-
>  1 file changed, 4 insertions(+), 1 deletion(-)
> 
> diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
> index 7c0504641fb8..973c3c4e72cc 100644
> --- a/mm/page_vma_mapped.c
> +++ b/mm/page_vma_mapped.c
> @@ -182,13 +182,16 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
>  	pud = pud_offset(p4d, pvmw->address);
>  	if (!pud_present(*pud))
>  		return false;
> +
>  	pvmw->pmd = pmd_offset(pud, pvmw->address);
>  	/*
>  	 * Make sure the pmd value isn't cached in a register by the
>  	 * compiler and used as a stale value after we've observed a
>  	 * subsequent update.
>  	 */
> -	pmde = READ_ONCE(*pvmw->pmd);
> +	pmde = pmd_read_atomic(pvmw->pmd);
> +	barrier();
> +

Hm. It makes me wounder if barrier() has to be part of pmd_read_atomic().
mm/hmm.c uses the same pattern as you are and I tend to think that the
rest of pmd_read_atomic() users may be broken.

Am I wrong?

-- 
 Kirill A. Shutemov