Re: [PATCH v3 0/1] mm: introduce put_user_page*(), placeholder versions

[Jan Kara]

On Wed 13-03-19 19:16:51, Christopher Lameter wrote:
> On Tue, 12 Mar 2019, Jerome Glisse wrote:
> 
> > > > This has been discuss extensively already. GUP usage is now widespread in
> > > > multiple drivers, removing that would regress userspace ie break existing
> > > > application. We all know what the rules for that is.
> 
> You are still misstating the issue. In RDMA land GUP is widely used for
> anonyous memory and memory based filesystems. *Not* for real filesystems.

Maybe in your RDMA land. But there are apparently other users which do use
mmap of a file on normal filesystem (e.g. ext4) as a buffer for DMA
(Infiniband does not prohibit this if nothing else, video capture devices
also use very similar pattern of gup-ing pages and using them as video
buffers). And these users are reporting occasional kernel crashes. That's
how this whole effort started. Sadly the DMA to file mmap is working good
enough that people started using it so at this point we cannot just tell:
Sorry it was a mistake to allow this, just rewrite your applications.

Plus we have O_DIRECT io which can use file mmap as a buffer and as Dave
Chinner mentioned there are real applications using this.

So no, we are not going to get away with "just forbid GUP for file backed
pages" which seems to be what you suggest. We might get away with that for
*some* GUP users and you are welcome to do that in the drivers you care
about but definitely not for all.

								Honza
-- 
Jan Kara <jack@xxxxxxxx>
SUSE Labs, CR