Re: [PATCH rdma-next] RDMA/core: Rely on vendors to set right IOVA

[Leon Romanovsky]

On Wed, Nov 03, 2021 at 09:51:44AM -0300, Jason Gunthorpe wrote:
> On Thu, Oct 28, 2021 at 08:55:22AM +0300, Leon Romanovsky wrote:
> > From: Aharon Landau <aharonl@xxxxxxxxxx>
> > 
> > The vendors set the IOVA of newly created MRs in rereg_user_mr, so don't
> > overwrite it. That ensures that this field is set only if IB_MR_REREG_TRANS
> > flag is provided.
> > 
> > Fixes: 6e0954b11c05 ("RDMA/uverbs: Allow drivers to create a new HW object during rereg_mr")
> > Signed-off-by: Aharon Landau <aharonl@xxxxxxxxxx>
> > Signed-off-by: Leon Romanovsky <leonro@xxxxxxxxxx>
> > ---
> >  drivers/infiniband/core/uverbs_cmd.c | 3 ---
> >  1 file changed, 3 deletions(-)
> 
> I rewrote the commit message:

Thanks a lot.

> 
>     RDMA/core: Require the driver to set the IOVA correctly during rereg_mr
>     
>     If the driver returns a new MR during rereg it has to fill it with the
>     IOVA from the proper source. If IB_MR_REREG_TRANS is set then the IOVA is
>     cmd.hca_va, otherwise the IOVA comes from the old MR. mlx5 for example has
>     two calls inside rereg_mr:
>     
>                     return create_real_mr(new_pd, umem, mr->ibmr.iova,
>                                           new_access_flags);
>     and
>                     return create_real_mr(new_pd, new_umem, iova, new_access_flags);
>     
>     Unconditionally overwriting the iova in the newly allocated MR will
>     corrupt the iova if the first path is used.
>     
>     Remove the redundant initializations from ib_uverbs_rereg_mr().
>     
>     Fixes: 6e0954b11c05 ("RDMA/uverbs: Allow drivers to create a new HW object during rereg_mr")
>     Link: https://lore.kernel.org/r/4b0a31bbc372842613286a10d7a8cbb0ee6069c7.1635400472.git.leonro@xxxxxxxxxx
>     Signed-off-by: Aharon Landau <aharonl@xxxxxxxxxx>
>     Signed-off-by: Leon Romanovsky <leonro@xxxxxxxxxx>
>     Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxx>
> 
> Jason