Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <CAPcyv4g8usp8prJ+1bMtyV1xuedp5FKErBp-N8+KzR=rJ-v0QQ@mail.gmail.com>
 <20190815180325.GA4920@redhat.com> <CAPcyv4g4hzcEA=TPYVTiqpbtOoS30ahogRUttCvQAvXQbQjfnw@mail.gmail.com>
 <20190815194339.GC9253@redhat.com> <CAPcyv4jid8_=-8hBpn_Qm=c4S8BapL9B9RGT7e9uu303yH=Yqw@mail.gmail.com>
 <20190815203306.GB25517@redhat.com> <20190815204128.GI22970@mellanox.com>
 <CAPcyv4j_Mxbw+T+yXTMdkrMoS_uxg+TXXgTM_EPBJ8XfXKxytA@mail.gmail.com>
 <20190816004053.GB9929@mellanox.com> <CAPcyv4gMPVmY59aQAT64jQf9qXrACKOuV=DfVs4sNySCXJhkdA@mail.gmail.com>
 <20190816122414.GC5412@mellanox.com>
In-Reply-To: <20190816122414.GC5412@mellanox.com>
From:   Dan Williams <dan.j.williams@intel.com>
Date:   Fri, 16 Aug 2019 10:21:41 -0700
Message-ID: <CAPcyv4jgHF05gdRoOFZORqeOBE9Z7PhagsSD+LVnjH2dc3mrFg@mail.gmail.com>
Subject: Re: [PATCH 04/15] mm: remove the pgmap field from struct hmm_vma_walk
To:     Jason Gunthorpe <jgg@mellanox.com>
Cc:     Jerome Glisse <jglisse@redhat.com>, Christoph Hellwig <hch@lst.de>,
        Ben Skeggs <bskeggs@redhat.com>,
        Felix Kuehling <Felix.Kuehling@amd.com>,
        Ralph Campbell <rcampbell@nvidia.com>,
        "linux-mm@kvack.org" <linux-mm@kvack.org>,
        "nouveau@lists.freedesktop.org" <nouveau@lists.freedesktop.org>,
        "dri-devel@lists.freedesktop.org" <dri-devel@lists.freedesktop.org>,
        "amd-gfx@lists.freedesktop.org" <amd-gfx@lists.freedesktop.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Fri, Aug 16, 2019 at 5:24 AM Jason Gunthorpe <jgg@mellanox.com> wrote:
>
> On Thu, Aug 15, 2019 at 08:54:46PM -0700, Dan Williams wrote:
>
> > > However, this means we cannot do any processing of ZONE_DEVICE pages
> > > outside the driver lock, so eg, doing any DMA map that might rely on
> > > MEMORY_DEVICE_PCI_P2PDMA has to be done in the driver lock, which is
> > > a bit unfortunate.
> >
> > Wouldn't P2PDMA use page pins? Not needing to hold a lock over
> > ZONE_DEVICE page operations was one of the motivations for plumbing
> > get_dev_pagemap() with a percpu-ref.
>
> hmm_range_fault() doesn't use page pins at all, so if a ZONE_DEVICE
> page comes out of it then it needs to use another locking pattern.
>
> If I follow it all right:
>
> We can do a get_dev_pagemap inside the page_walk and touch the pgmap,
> or we can do the 'device mutex && retry' pattern and touch the pgmap
> in the driver, under that lock.
>
> However in all cases the current get_dev_pagemap()'s in the page walk
> are not necessary, and we can delete them.

Yes, as long as 'struct page' instances resulting from that lookup are
not passed outside of that lock.