Re: [PATCH v6 11/15] vfio/type1: Allow invalidating first-level/stage IOMMU cache

[Auger Eric]

Hi Yi,

On 7/28/20 8:27 AM, Liu Yi L wrote:
> This patch provides an interface allowing the userspace to invalidate
> IOMMU cache for first-level page table. It is required when the first
> level IOMMU page table is not managed by the host kernel in the nested
> translation setup.
> 
> Cc: Kevin Tian <kevin.tian@xxxxxxxxx>
> CC: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
> Cc: Alex Williamson <alex.williamson@xxxxxxxxxx>
> Cc: Eric Auger <eric.auger@xxxxxxxxxx>
> Cc: Jean-Philippe Brucker <jean-philippe@xxxxxxxxxx>
> Cc: Joerg Roedel <joro@xxxxxxxxxx>
> Cc: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
> Signed-off-by: Liu Yi L <yi.l.liu@xxxxxxxxx>
> Signed-off-by: Eric Auger <eric.auger@xxxxxxxxxx>
> Signed-off-by: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
> ---
> v1 -> v2:
> *) rename from "vfio/type1: Flush stage-1 IOMMU cache for nesting type"
> *) rename vfio_cache_inv_fn() to vfio_dev_cache_invalidate_fn()
> *) vfio_dev_cache_inv_fn() always successful
> *) remove VFIO_IOMMU_CACHE_INVALIDATE, and reuse VFIO_IOMMU_NESTING_OP
> ---
>  drivers/vfio/vfio_iommu_type1.c | 42 +++++++++++++++++++++++++++++++++++++++++
>  include/uapi/linux/vfio.h       |  3 +++
>  2 files changed, 45 insertions(+)
> 
> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> index 245436e..bf95a0f 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -3056,6 +3056,45 @@ static long vfio_iommu_handle_pgtbl_op(struct vfio_iommu *iommu,
>  	return ret;
>  }
>  
> +static int vfio_dev_cache_invalidate_fn(struct device *dev, void *data)
> +{
> +	struct domain_capsule *dc = (struct domain_capsule *)data;
> +	unsigned long arg = *(unsigned long *)dc->data;
> +
> +	iommu_uapi_cache_invalidate(dc->domain, dev, (void __user *)arg);
> +	return 0;
> +}
> +
> +static long vfio_iommu_invalidate_cache(struct vfio_iommu *iommu,
> +					unsigned long arg)
> +{
> +	struct domain_capsule dc = { .data = &arg };
> +	struct iommu_nesting_info *info;
> +	int ret;
> +
> +	mutex_lock(&iommu->lock);
> +	/*
> +	 * Cache invalidation is required for any nesting IOMMU,
So why do we expose the IOMMU_NESTING_FEAT_CACHE_INVLD capability? :-)
> +	 * so no need to check system-wide PASID support.
> +	 */
> +	info = iommu->nesting_info;
> +	if (!info || !(info->features & IOMMU_NESTING_FEAT_CACHE_INVLD)) {
> +		ret = -EOPNOTSUPP;
> +		goto out_unlock;
> +	}
> +
> +	ret = vfio_get_nesting_domain_capsule(iommu, &dc);
> +	if (ret)
> +		goto out_unlock;
> +
> +	iommu_group_for_each_dev(dc.group->iommu_group, &dc,
> +				 vfio_dev_cache_invalidate_fn);
> +
> +out_unlock:
> +	mutex_unlock(&iommu->lock);
> +	return ret;
> +}
> +
>  static long vfio_iommu_type1_nesting_op(struct vfio_iommu *iommu,
>  					unsigned long arg)
>  {
> @@ -3078,6 +3117,9 @@ static long vfio_iommu_type1_nesting_op(struct vfio_iommu *iommu,
>  	case VFIO_IOMMU_NESTING_OP_UNBIND_PGTBL:
>  		ret = vfio_iommu_handle_pgtbl_op(iommu, false, arg + minsz);
>  		break;
> +	case VFIO_IOMMU_NESTING_OP_CACHE_INVLD:
> +		ret = vfio_iommu_invalidate_cache(iommu, arg + minsz);
> +		break;
>  	default:
>  		ret = -EINVAL;
>  	}
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index 9501cfb..48e2fb5 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -1225,6 +1225,8 @@ struct vfio_iommu_type1_pasid_request {
>   * +-----------------+-----------------------------------------------+
>   * | UNBIND_PGTBL    |      struct iommu_gpasid_bind_data            |
>   * +-----------------+-----------------------------------------------+
> + * | CACHE_INVLD     |      struct iommu_cache_invalidate_info       |
> + * +-----------------+-----------------------------------------------+
>   *
>   * returns: 0 on success, -errno on failure.
>   */
> @@ -1237,6 +1239,7 @@ struct vfio_iommu_type1_nesting_op {
>  
>  #define VFIO_IOMMU_NESTING_OP_BIND_PGTBL	(0)
>  #define VFIO_IOMMU_NESTING_OP_UNBIND_PGTBL	(1)
> +#define VFIO_IOMMU_NESTING_OP_CACHE_INVLD	(2)
According to my previous comment, you may refine VFIO_NESTING_OP_MASK too

Thanks

Eric
>  
>  #define VFIO_IOMMU_NESTING_OP		_IO(VFIO_TYPE, VFIO_BASE + 19)
>  
>