From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Date: Sat, 8 Dec 2018 10:26:04 -0800 From: Christoph Hellwig To: Jerome Glisse Cc: Christoph Hellwig , Dan Williams , John Hubbard , Matthew Wilcox , John Hubbard , Andrew Morton , Linux MM , Jan Kara , tom@talpey.com, Al Viro , benve@cisco.com, Christopher Lameter , "Dalessandro, Dennis" , Doug Ledford , Jason Gunthorpe , Michal Hocko , Mike Marciniszyn , rcampbell@nvidia.com, Linux Kernel Mailing List , linux-fsdevel Subject: Re: [PATCH 1/2] mm: introduce put_user_page*(), placeholder versions Message-ID: <20181208182604.GA24564@infradead.org> References: <20181205011519.GV10377@bombadil.infradead.org> <20181205014441.GA3045@redhat.com> <59ca5c4b-fd5b-1fc6-f891-c7986d91908e@nvidia.com> <7b4733be-13d3-c790-ff1b-ac51b505e9a6@nvidia.com> <20181207191620.GD3293@redhat.com> <3c4d46c0-aced-f96f-1bf3-725d02f11b60@nvidia.com> <20181208163353.GA2952@redhat.com> <20181208164825.GA26154@infradead.org> <20181208174730.GB2952@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20181208174730.GB2952@redhat.com> Sender: owner-linux-mm@kvack.org List-ID: On Sat, Dec 08, 2018 at 12:47:30PM -0500, Jerome Glisse wrote: > Most of the user of GUP are well behave (everything under driver/gpu and > so is mellanox driver and many other) ie they abide by mmu notifier > invalidation call backs. They are a handfull of device driver that thought > they could just do GUP and ignore the mmu notifier part and those are the > one being problematic. So to me it feels like bystander are be shot for no > good reasons. get_user_pages is used by every single direct I/O, and while the race windows in that case are small they very much exists.