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

[Jason Gunthorpe]

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:

    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