Re: [PATCH 6/6] drivers/IB,core: reduce scope of mmap_sem

[Davidlohr Bueso]

On Mon, 21 Jan 2019, Jason Gunthorpe wrote:

> On Mon, Jan 21, 2019 at 09:42:20AM -0800, Davidlohr Bueso wrote:
> > ib_umem_get() uses gup_longterm() and relies on the lock to
> > stabilze the vma_list, so we cannot really get rid of mmap_sem
> > altogether, but now that the counter is atomic, we can get of
> > some complexity that mmap_sem brings with only pinned_vm.
> >
> > Reviewed-by: Ira Weiny <ira.weiny@xxxxxxxxx>
> > Signed-off-by: Davidlohr Bueso <dbueso@xxxxxxx>
> > ---
> >  drivers/infiniband/core/umem.c | 41 ++---------------------------------------
> >  1 file changed, 2 insertions(+), 39 deletions(-)
>
> I think this addresses my comment..
>
> Considering that it is almost all infiniband, I'd rather it go it go
> through the RDMA tree with an ack from mm people? Please advise..

Yeah also Cc'ing Willy who I forgot to add for v2.

> Thanks,
> Jason