RE: [RFC PATCH v2 06/19] vdpa: multiple address spaces support

[Gautam Dawar]

-----Original Message-----
From: Eugenio Perez Martin <eperezma@xxxxxxxxxx> 
Sent: Friday, March 4, 2022 1:10 AM
To: Gautam Dawar <gdawar@xxxxxxxxxx>
Cc: Gautam Dawar <gdawar@xxxxxxxxxx>; Martin Petrus Hubertus Habets <martinh@xxxxxxxxxx>; Harpreet Singh Anand <hanand@xxxxxxxxxx>; Tanuj Murlidhar Kamde <tanujk@xxxxxxxxxx>; Jason Wang <jasowang@xxxxxxxxxx>; Michael S. Tsirkin <mst@xxxxxxxxxx>; Zhu Lingshan <lingshan.zhu@xxxxxxxxx>; Stefano Garzarella <sgarzare@xxxxxxxxxx>; Xie Yongji <xieyongji@xxxxxxxxxxxxx>; Eli Cohen <elic@xxxxxxxxxx>; Si-Wei Liu <si-wei.liu@xxxxxxxxxx>; Parav Pandit <parav@xxxxxxxxxx>; Longpeng <longpeng2@xxxxxxxxxx>; virtualization <virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx>; linux-kernel@xxxxxxxxxxxxxxx; kvm list <kvm@xxxxxxxxxxxxxxx>; netdev@xxxxxxxxxxxxxxx
Subject: Re: [RFC PATCH v2 06/19] vdpa: multiple address spaces support

On Thu, Feb 24, 2022 at 10:25 PM Gautam Dawar <gautam.dawar@xxxxxxxxxx> wrote:
>
> This patches introduces the multiple address spaces support for vDPA 
> device. This idea is to identify a specific address space via an 
> dedicated identifier - ASID.
>
> During vDPA device allocation, vDPA device driver needs to report the 
> number of address spaces supported by the device then the DMA mapping 
> ops of the vDPA device needs to be extended to support ASID.
>
> This helps to isolate the environments for the virtqueue that will not 
> be assigned directly. E.g in the case of virtio-net, the control 
> virtqueue will not be assigned directly to guest.
>
> As a start, simply claim 1 virtqueue groups and 1 address spaces for 
> all vDPA devices. And vhost-vDPA will simply reject the device with 
> more than 1 virtqueue groups or address spaces.
>
> Signed-off-by: Jason Wang <jasowang@xxxxxxxxxx>
> Signed-off-by: Gautam Dawar <gdawar@xxxxxxxxxx>
> ---
>  drivers/vdpa/ifcvf/ifcvf_main.c   |  2 +-
>  drivers/vdpa/mlx5/net/mlx5_vnet.c |  5 +++--
>  drivers/vdpa/vdpa.c               |  4 +++-
>  drivers/vdpa/vdpa_sim/vdpa_sim.c  | 10 ++++++----
>  drivers/vhost/vdpa.c              | 14 +++++++++-----
>  include/linux/vdpa.h              | 28 +++++++++++++++++++---------
>  6 files changed, 41 insertions(+), 22 deletions(-)
>
> diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c 
> b/drivers/vdpa/ifcvf/ifcvf_main.c index c815a2e62440..a4815c5612f9 
> 100644
> --- a/drivers/vdpa/ifcvf/ifcvf_main.c
> +++ b/drivers/vdpa/ifcvf/ifcvf_main.c
> @@ -513,7 +513,7 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
>         pdev = ifcvf_mgmt_dev->pdev;
>         dev = &pdev->dev;
>         adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
> -                                   dev, &ifc_vdpa_ops, 1, name, false);
> +                                   dev, &ifc_vdpa_ops, 1, 1, name, 
> + false);
>         if (IS_ERR(adapter)) {
>                 IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
>                 return PTR_ERR(adapter); diff --git 
> a/drivers/vdpa/mlx5/net/mlx5_vnet.c 
> b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> index fcfc28460b72..a76417892ef3 100644
> --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> @@ -2282,7 +2282,8 @@ static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev)
>         return mvdev->generation;
>  }
>
> -static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct 
> vhost_iotlb *iotlb)
> +static int mlx5_vdpa_set_map(struct vdpa_device *vdev, unsigned int asid,
> +                            struct vhost_iotlb *iotlb)
>  {
>         struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
>         bool change_map;
> @@ -2581,7 +2582,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
>         }
>
>         ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops,
> -                                1, name, false);
> +                                1, 1, name, false);
>         if (IS_ERR(ndev))
>                 return PTR_ERR(ndev);
>
> diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 
> a07bf0130559..1793dc12b208 100644
> --- a/drivers/vdpa/vdpa.c
> +++ b/drivers/vdpa/vdpa.c
> @@ -160,6 +160,7 @@ static void vdpa_release_dev(struct device *d)
>   * @parent: the parent device
>   * @config: the bus operations that is supported by this device
>   * @ngroups: number of groups supported by this device
> + * @nas: number of address spaces supported by this device
>   * @size: size of the parent structure that contains private data
>   * @name: name of the vdpa device; optional.
>   * @use_va: indicate whether virtual address must be used by this 
> device @@ -172,7 +173,7 @@ static void vdpa_release_dev(struct device *d)
>   */
>  struct vdpa_device *__vdpa_alloc_device(struct device *parent,
>                                         const struct vdpa_config_ops *config,
> -                                       unsigned int ngroups,
> +                                       unsigned int ngroups, unsigned 
> + int nas,
>                                         size_t size, const char *name,
>                                         bool use_va)  { @@ -206,6 
> +207,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
>         vdev->features_valid = false;
>         vdev->use_va = use_va;
>         vdev->ngroups = ngroups;
> +       vdev->nas = nas;
>
>         if (name)
>                 err = dev_set_name(&vdev->dev, "%s", name); diff --git 
> a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
> index c98cb1f869fa..659e2e2e4b0c 100644
> --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
> +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
> @@ -251,7 +251,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)
>                 ops = &vdpasim_config_ops;
>
>         vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1,
> -                                   dev_attr->name, false);
> +                                   1, dev_attr->name, false);
>         if (IS_ERR(vdpasim)) {
>                 ret = PTR_ERR(vdpasim);
>                 goto err_alloc;
> @@ -539,7 +539,7 @@ static struct vdpa_iova_range vdpasim_get_iova_range(struct vdpa_device *vdpa)
>         return range;
>  }
>
> -static int vdpasim_set_map(struct vdpa_device *vdpa,
> +static int vdpasim_set_map(struct vdpa_device *vdpa, unsigned int 
> +asid,
>                            struct vhost_iotlb *iotlb)  {
>         struct vdpasim *vdpasim = vdpa_to_sim(vdpa); @@ -566,7 +566,8 
> @@ static int vdpasim_set_map(struct vdpa_device *vdpa,
>         return ret;
>  }
>
> -static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 
> size,
> +static int vdpasim_dma_map(struct vdpa_device *vdpa, unsigned int asid,
> +                          u64 iova, u64 size,
>                            u64 pa, u32 perm, void *opaque)  {
>         struct vdpasim *vdpasim = vdpa_to_sim(vdpa); @@ -580,7 +581,8 
> @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size,
>         return ret;
>  }
>
> -static int vdpasim_dma_unmap(struct vdpa_device *vdpa, u64 iova, u64 
> size)
> +static int vdpasim_dma_unmap(struct vdpa_device *vdpa, unsigned int asid,
> +                            u64 iova, u64 size)
>  {
>         struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
>
> diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 
> 655ff7029401..6bf755f84d26 100644
> --- a/drivers/vhost/vdpa.c
> +++ b/drivers/vhost/vdpa.c
> @@ -599,10 +599,10 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
>                 return r;
>
>         if (ops->dma_map) {
> -               r = ops->dma_map(vdpa, iova, size, pa, perm, opaque);
> +               r = ops->dma_map(vdpa, 0, iova, size, pa, perm, 
> + opaque);
>         } else if (ops->set_map) {
>                 if (!v->in_batch)
> -                       r = ops->set_map(vdpa, iotlb);
> +                       r = ops->set_map(vdpa, 0, iotlb);
>         } else {
>                 r = iommu_map(v->domain, iova, pa, size,
>                               perm_to_iommu_flags(perm)); @@ -628,10 
> +628,10 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v,
>         vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1);
>
>         if (ops->dma_map) {
> -               ops->dma_unmap(vdpa, iova, size);
> +               ops->dma_unmap(vdpa, 0, iova, size);
>         } else if (ops->set_map) {
>                 if (!v->in_batch)
> -                       ops->set_map(vdpa, iotlb);
> +                       ops->set_map(vdpa, 0, iotlb);
>         } else {
>                 iommu_unmap(v->domain, iova, size);
>         }
> @@ -863,7 +863,7 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,
>                 break;
>         case VHOST_IOTLB_BATCH_END:
>                 if (v->in_batch && ops->set_map)
> -                       ops->set_map(vdpa, iotlb);
> +                       ops->set_map(vdpa, 0, iotlb);
>                 v->in_batch = false;
>                 break;
>         default:
> @@ -1128,6 +1128,10 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
>         int minor;
>         int r;
>
> +       /* Only support 1 address space and 1 groups */
> +       if (vdpa->ngroups != 1 || vdpa->nas != 1)
> +               return -EOPNOTSUPP;
> +
>         v = kzalloc(sizeof(*v), GFP_KERNEL | __GFP_RETRY_MAYFAIL);
>         if (!v)
>                 return -ENOMEM;
> diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 
> 026b7ad72ed7..de22ca1a8ef3 100644
> --- a/include/linux/vdpa.h
> +++ b/include/linux/vdpa.h
> @@ -69,6 +69,8 @@ struct vdpa_mgmt_dev;
>   * @cf_mutex: Protects get and set access to configuration layout.
>   * @index: device index
>   * @features_valid: were features initialized? for legacy guests
> + * @ngroups: the number of virtqueue groups
> + * @nas: the number of address spaces
>   * @use_va: indicate whether virtual address must be used by this device
>   * @nvqs: maximum number of supported virtqueues
>   * @mdev: management device pointer; caller must setup when 
> registering device as part @@ -86,6 +88,7 @@ struct vdpa_device {
>         int nvqs;
>         struct vdpa_mgmt_dev *mdev;
>         unsigned int ngroups;
> +       unsigned int nas;
>  };
>
>  /**
> @@ -240,6 +243,7 @@ struct vdpa_map_file {
>   *                             Needed for device that using device
>   *                             specific DMA translation (on-chip IOMMU)
>   *                             @vdev: vdpa device
> + *                             @asid: address space identifier
>   *                             @iotlb: vhost memory mapping to be
>   *                             used by the vDPA
>   *                             Returns integer: success (0) or error (< 0)
> @@ -248,6 +252,7 @@ struct vdpa_map_file {
>   *                             specific DMA translation (on-chip IOMMU)
>   *                             and preferring incremental map.
>   *                             @vdev: vdpa device
> + *                             @asid: address space identifier
>   *                             @iova: iova to be mapped
>   *                             @size: size of the area
>   *                             @pa: physical address for the map
> @@ -259,6 +264,7 @@ struct vdpa_map_file {
>   *                             specific DMA translation (on-chip IOMMU)
>   *                             and preferring incremental unmap.
>   *                             @vdev: vdpa device
> + *                             @asid: address space identifier
>   *                             @iova: iova to be unmapped
>   *                             @size: size of the area
>   *                             Returns integer: success (0) or error (< 0)
> @@ -309,10 +315,12 @@ struct vdpa_config_ops {
>         struct vdpa_iova_range (*get_iova_range)(struct vdpa_device 
> *vdev);
>
>         /* DMA ops */
> -       int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb);
> -       int (*dma_map)(struct vdpa_device *vdev, u64 iova, u64 size,
> -                      u64 pa, u32 perm, void *opaque);
> -       int (*dma_unmap)(struct vdpa_device *vdev, u64 iova, u64 size);
> +       int (*set_map)(struct vdpa_device *vdev, unsigned int asid,
> +                      struct vhost_iotlb *iotlb);
> +       int (*dma_map)(struct vdpa_device *vdev, unsigned int asid,
> +                      u64 iova, u64 size, u64 pa, u32 perm, void *opaque);
> +       int (*dma_unmap)(struct vdpa_device *vdev, unsigned int asid,
> +                        u64 iova, u64 size);
>
>         /* Free device resources */
>         void (*free)(struct vdpa_device *vdev); @@ -320,7 +328,7 @@ 
> struct vdpa_config_ops {
>
>  struct vdpa_device *__vdpa_alloc_device(struct device *parent,
>                                         const struct vdpa_config_ops *config,
> -                                       unsigned int ngroups,
> +                                       unsigned int ngroups, unsigned 
> + int nas,
>                                         size_t size, const char *name,
>                                         bool use_va);
>
> @@ -332,17 +340,19 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
>   * @parent: the parent device
>   * @config: the bus operations that is supported by this device
>   * @ngroups: the number of virtqueue groups supported by this device
> + * @nas: the number of address spaces
>   * @name: name of the vdpa device
>   * @use_va: indicate whether virtual address must be used by this device
>   *
>   * Return allocated data structure or ERR_PTR upon error
>   */
> -#define vdpa_alloc_device(dev_struct, member, parent, config, ngroups, name, use_va)   \
> +#define vdpa_alloc_device(dev_struct, member, parent, config, ngroups, nas, \
> +                         name, use_va) \
>                           container_of((__vdpa_alloc_device( \
> -                                      parent, config, ngroups, \
> -                                      sizeof(dev_struct) + \
> +                                      parent, config, ngroups, nas, \
> +                                      (sizeof(dev_struct) + \

Maybe too nitpick or I'm missing something, but do we need to add the parentheses around (sizeof(dev_struct) + BUILD_BUG_ON_ZERO(...)) ?
[GD>>] Yes, that's required as without it checkpatch reports "ERROR: Macros with complex values should be enclosed in parentheses"

>                                        BUILD_BUG_ON_ZERO(offsetof( \
> -                                      dev_struct, member)), name, use_va)), \
> +                                      dev_struct, member))), name, 
> + use_va)), \
>                                        dev_struct, member)
>
>  int vdpa_register_device(struct vdpa_device *vdev, int nvqs);
> --
> 2.25.0
>