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:   Wed, 2 Sep 2020 16:57:39 -0300
From:   Jason Gunthorpe <jgg@ziepe.ca>
To:     Zi Yan <ziy@nvidia.com>
Cc:     linux-mm@kvack.org, Roman Gushchin <guro@fb.com>,
        Rik van Riel <riel@surriel.com>,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
        Matthew Wilcox <willy@infradead.org>,
        Shakeel Butt <shakeelb@google.com>,
        Yang Shi <yang.shi@linux.alibaba.com>,
        David Nellans <dnellans@nvidia.com>,
        linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH 00/16] 1GB THP support on x86_64
Message-ID: <20200902195739.GI24045@ziepe.ca>
References: <20200902180628.4052244-1-zi.yan@sent.com>
 <20200902184053.GF24045@ziepe.ca>
 <E78A0F18-223C-44A8-BCBA-73CF7AF6F8A5@nvidia.com>
 <20200902184852.GH24045@ziepe.ca>
 <C5EFA1CC-311C-47D5-9506-D087D9AE58D1@nvidia.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <C5EFA1CC-311C-47D5-9506-D087D9AE58D1@nvidia.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, Sep 02, 2020 at 03:05:39PM -0400, Zi Yan wrote:
> On 2 Sep 2020, at 14:48, Jason Gunthorpe wrote:
> 
> > On Wed, Sep 02, 2020 at 02:45:37PM -0400, Zi Yan wrote:
> >
> >>> Surprised this doesn't touch mm/pagewalk.c ?
> >>
> >> 1GB PUD page support is present for DAX purpose, so the code is there
> >> in mm/pagewalk.c already. I only needed to supply ops->pud_entry when using
> >> the functions in mm/pagewalk.c. :)
> >
> > Yes, but doesn't this change what is possible under the mmap_sem
> > without the page table locks?
> >
> > ie I would expect some thing like pmd_trans_unstable() to be required
> > as well for lockless walkers. (and I don't think the pmd code is 100%
> > right either)
> >
> 
> Right. I missed that. Thanks for pointing it out.
> The code like this, right?

Technically all those *pud's are racy too, the design here with the
_unstable function call always seemed weird. I strongly suspect it
should mirror how get_user_pages_fast works for lockless walking

Jason