linux-kernel - Re: [PATCH vhost 16/16] vdpa/mlx5: Update cvq iotlb mapping on ASID change

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <b6f90921bc239fc0e1fc04dc62e4376fcd622376.camel@nvidia.com>
Date:   Thu, 5 Oct 2023 13:12:11 +0000
From:   Dragos Tatulea <dtatulea@...dia.com>
To:     "eperezma@...hat.com" <eperezma@...hat.com>
CC:     "virtualization@...ts.linux-foundation.org" 
        <virtualization@...ts.linux-foundation.org>,
        Gal Pressman <gal@...dia.com>,
        "mst@...hat.com" <mst@...hat.com>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "jasowang@...hat.com" <jasowang@...hat.com>,
        "xuanzhuo@...ux.alibaba.com" <xuanzhuo@...ux.alibaba.com>
Subject: Re: [PATCH vhost 16/16] vdpa/mlx5: Update cvq iotlb mapping on ASID
 change

On Thu, 2023-10-05 at 12:41 +0200, Eugenio Perez Martin wrote:
> On Thu, Sep 28, 2023 at 6:50 PM Dragos Tatulea <dtatulea@...dia.com> wrote:
> > 
> > For the following sequence:
> > - cvq group is in ASID 0
> > - .set_map(1, cvq_iotlb)
> > - .set_group_asid(cvq_group, 1)
> > 
> > ... the cvq mapping from ASID 0 will be used. This is not always correct
> > behaviour.
> > 
> > This patch adds support for the above mentioned flow by saving the iotlb
> > on each .set_map and updating the cvq iotlb with it on a cvq group change.
> > 
> > Signed-off-by: Dragos Tatulea <dtatulea@...dia.com>
> > ---
> >  drivers/vdpa/mlx5/core/mlx5_vdpa.h |  2 ++
> >  drivers/vdpa/mlx5/core/mr.c        | 26 ++++++++++++++++++++++++++
> >  drivers/vdpa/mlx5/net/mlx5_vnet.c  |  9 ++++++++-
> >  3 files changed, 36 insertions(+), 1 deletion(-)
> > 
> > diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
> > b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
> > index ae09296f4270..db988ced5a5d 100644
> > --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
> > +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
> > @@ -32,6 +32,8 @@ struct mlx5_vdpa_mr {
> >         unsigned long num_directs;
> >         unsigned long num_klms;
> > 
> > +       struct vhost_iotlb *iotlb;
> > +
> >         bool user_mr;
> >  };
> > 
> > diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
> > index a4135c16b5bf..403c08271489 100644
> > --- a/drivers/vdpa/mlx5/core/mr.c
> > +++ b/drivers/vdpa/mlx5/core/mr.c
> > @@ -499,6 +499,8 @@ static void _mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev
> > *mvdev, struct mlx5_vdpa_
> >                 destroy_user_mr(mvdev, mr);
> >         else
> >                 destroy_dma_mr(mvdev, mr);
> > +
> > +       vhost_iotlb_free(mr->iotlb);
> >  }
> > 
> >  void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev,
> > @@ -558,6 +560,30 @@ static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev
> > *mvdev,
> >         else
> >                 err = create_dma_mr(mvdev, mr);
> > 
> > +       if (err)
> > +               return err;
> > +
> > +       mr->iotlb = vhost_iotlb_alloc(0, 0);
> > +       if (!mr->iotlb) {
> > +               err = -ENOMEM;
> > +               goto err_mr;
> > +       }
> > +
> > +       err = dup_iotlb(mr->iotlb, iotlb);
> > +       if (err)
> > +               goto err_iotlb;
> > +
> > +       return 0;
> > +
> > +err_iotlb:
> > +       vhost_iotlb_free(mr->iotlb);
> > +
> > +err_mr:
> > +       if (iotlb)
> > +               destroy_user_mr(mvdev, mr);
> > +       else
> > +               destroy_dma_mr(mvdev, mr);
> > +
> >         return err;
> >  }
> > 
> > diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > index 46441e41892c..fc5d6b989a5a 100644
> > --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > @@ -3154,12 +3154,19 @@ static int mlx5_set_group_asid(struct vdpa_device
> > *vdev, u32 group,
> >                                unsigned int asid)
> >  {
> >         struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
> > +       int err = 0;
> > 
> >         if (group >= MLX5_VDPA_NUMVQ_GROUPS || asid >= MLX5_VDPA_NUM_AS)
> >                 return -EINVAL;
> > 
> >         mvdev->group2asid[group] = asid;
> > -       return 0;
> > +
> > +       mutex_lock(&mvdev->mr_mtx);
> > +       if (group == MLX5_VDPA_CVQ_GROUP && mvdev->mr[asid])
> > +               err = mlx5_vdpa_update_cvq_iotlb(mvdev, mvdev->mr[asid]-
> > >iotlb, asid);
> 
> Do we need to protect here in case userspace sets the same ASID twice?
> mlx5_vdpa_update_cvq_iotlb shouldn't call dup_iotlb with the same src
> and dst.

Why would src and dst be identical? Doesn't dup_iotlb create a copy of src?

That being said, there should be a check in dup_iotlb for dst == src. Not sure
if this is an error or success though...

Thanks,
Dragos
- 
> Apart from that:
> 
> Acked-by: Eugenio Pérez <eperezma@...hat.com>
> 
> > +       mutex_unlock(&mvdev->mr_mtx);
> > +
> > +       return err;
> >  }
> > 
> >  static const struct vdpa_config_ops mlx5_vdpa_ops = {
> > --
> > 2.41.0
> > 
>