Re: [PATCH v3 1/4] mm: introduce get_user_pages_longterm

2017-12-04 Thread Dan Williams
On Mon, Dec 4, 2017 at 1:31 AM, Michal Hocko wrote: > > On Fri 01-12-17 08:29:53, Dan Williams wrote: > > On Fri, Dec 1, 2017 at 8:02 AM, Jason Gunthorpe wrote: > > > > > > On Fri, Dec 01, 2017 at 11:12:18AM +0100, Michal Hocko wrote: > > > > On Thu 30-11-17 12:01:17, Jason Gunthorpe wrote: > > >

Re: [PATCH v3 1/4] mm: introduce get_user_pages_longterm

2017-12-04 Thread Michal Hocko
On Fri 01-12-17 08:29:53, Dan Williams wrote: > On Fri, Dec 1, 2017 at 8:02 AM, Jason Gunthorpe wrote: > > > > On Fri, Dec 01, 2017 at 11:12:18AM +0100, Michal Hocko wrote: > > > On Thu 30-11-17 12:01:17, Jason Gunthorpe wrote: > > > > On Thu, Nov 30, 2017 at 10:32:42AM -0800, Dan Williams wrote:

Re: [PATCH v3 1/4] mm: introduce get_user_pages_longterm

2017-12-01 Thread Dan Williams
On Fri, Dec 1, 2017 at 8:02 AM, Jason Gunthorpe wrote: > > On Fri, Dec 01, 2017 at 11:12:18AM +0100, Michal Hocko wrote: > > On Thu 30-11-17 12:01:17, Jason Gunthorpe wrote: > > > On Thu, Nov 30, 2017 at 10:32:42AM -0800, Dan Williams wrote: > > > > > Who and how many LRU pages can pin that way an

Re: [PATCH v3 1/4] mm: introduce get_user_pages_longterm

2017-12-01 Thread Michal Hocko
On Thu 30-11-17 12:01:17, Jason Gunthorpe wrote: > On Thu, Nov 30, 2017 at 10:32:42AM -0800, Dan Williams wrote: > > > Who and how many LRU pages can pin that way and how do you prevent nasty > > > users to DoS systems this way? > > > > I assume this is something the RDMA community has had to cont

Re: [PATCH v3 1/4] mm: introduce get_user_pages_longterm

2017-11-30 Thread Dan Williams
[ adding linux-rdma ] On Thu, Nov 30, 2017 at 10:17 AM, Michal Hocko wrote: > > On Thu 30-11-17 10:03:26, Dan Williams wrote: > > On Thu, Nov 30, 2017 at 9:42 AM, Michal Hocko wrote: > > > > > > On Thu 30-11-17 08:39:51, Dan Williams wrote: > > > > On Thu, Nov 30, 2017 at 1:53 AM, Michal Hocko

Re: [PATCH v3 1/4] mm: introduce get_user_pages_longterm

2017-11-30 Thread Michal Hocko
On Thu 30-11-17 10:03:26, Dan Williams wrote: > On Thu, Nov 30, 2017 at 9:42 AM, Michal Hocko wrote: > > > > On Thu 30-11-17 08:39:51, Dan Williams wrote: > > > On Thu, Nov 30, 2017 at 1:53 AM, Michal Hocko wrote: > > > > On Wed 29-11-17 10:05:35, Dan Williams wrote: > > > >> Until there is a sol

Re: [PATCH v3 1/4] mm: introduce get_user_pages_longterm

2017-11-30 Thread Dan Williams
On Thu, Nov 30, 2017 at 9:42 AM, Michal Hocko wrote: > > On Thu 30-11-17 08:39:51, Dan Williams wrote: > > On Thu, Nov 30, 2017 at 1:53 AM, Michal Hocko wrote: > > > On Wed 29-11-17 10:05:35, Dan Williams wrote: > > >> Until there is a solution to the dma-to-dax vs truncate problem it is > > >> n

Re: [PATCH v3 1/4] mm: introduce get_user_pages_longterm

2017-11-30 Thread Michal Hocko
On Thu 30-11-17 08:39:51, Dan Williams wrote: > On Thu, Nov 30, 2017 at 1:53 AM, Michal Hocko wrote: > > On Wed 29-11-17 10:05:35, Dan Williams wrote: > >> Until there is a solution to the dma-to-dax vs truncate problem it is > >> not safe to allow long standing memory registrations against > >> f

Re: [PATCH v3 1/4] mm: introduce get_user_pages_longterm

2017-11-30 Thread Dan Williams
On Thu, Nov 30, 2017 at 1:53 AM, Michal Hocko wrote: > On Wed 29-11-17 10:05:35, Dan Williams wrote: >> Until there is a solution to the dma-to-dax vs truncate problem it is >> not safe to allow long standing memory registrations against >> filesytem-dax vmas. Device-dax vmas do not have this prob

Re: [PATCH v3 1/4] mm: introduce get_user_pages_longterm

2017-11-30 Thread Michal Hocko
On Wed 29-11-17 10:05:35, Dan Williams wrote: > Until there is a solution to the dma-to-dax vs truncate problem it is > not safe to allow long standing memory registrations against > filesytem-dax vmas. Device-dax vmas do not have this problem and are > explicitly allowed. > > This is temporary un

[PATCH v3 1/4] mm: introduce get_user_pages_longterm

2017-11-29 Thread Dan Williams
Until there is a solution to the dma-to-dax vs truncate problem it is not safe to allow long standing memory registrations against filesytem-dax vmas. Device-dax vmas do not have this problem and are explicitly allowed. This is temporary until a "memory registration with layout-lease" mechanism ca