Messages in this thread | | | From | "Marciniszyn, Mike" <> | Subject | RE: [PATCH 23/26] ib: Convert qib_get_user_pages() to get_user_pages_unlocked() | Date | Fri, 4 Oct 2013 13:46:57 +0000 |
| |
Inadvertent send!
Mike
> -----Original Message----- > From: Marciniszyn, Mike > Sent: Friday, October 04, 2013 9:39 AM > To: Jan Kara > Cc: LKML; linux-mm@kvack.org; infinipath; Roland Dreier; linux- > rdma@vger.kernel.org > Subject: RE: [PATCH 23/26] ib: Convert qib_get_user_pages() to > get_user_pages_unlocked() > > > > > -----Original Message----- > > From: Jan Kara [mailto:jack@suse.cz] > > Sent: Wednesday, October 02, 2013 11:39 AM > > To: Marciniszyn, Mike > > Cc: Jan Kara; LKML; linux-mm@kvack.org; infinipath; Roland Dreier; > > linux- rdma@vger.kernel.org > > Subject: Re: [PATCH 23/26] ib: Convert qib_get_user_pages() to > > get_user_pages_unlocked() > > > > On Wed 02-10-13 15:32:47, Marciniszyn, Mike wrote: > > > > > The risk of GUP fast is the loss of the "force" arg on GUP fast, > > > > > which I don't see as significant give our use case. > > > > Yes. I was discussing with Roland some time ago whether the > > > > force argument is needed and he said it is. So I kept the > > > > arguments of > > > > get_user_pages() intact and just simplified the locking... > > > > > > The PSM side of the code is a more traditional use of GUP (like > > > direct I/O), so I think it is a different use case than the locking > > > for IB memory regions. > > Ah, I see. Whatever suits you best. I don't really care as long as > > get_user_pages() locking doesn't leak into IB drivers :) > > > > Honza > > -- > > Jan Kara <jack@suse.cz> > > SUSE Labs, CR
| |