Re: [PATCH v7 9/9] iommu/vt-d: Add iotlb flush for nested domain

["Yang, Weijiang" <weijiang.yang@intel.com>]

On 12/21/2023 11:39 PM, Yi Liu wrote:
> From: Lu Baolu <baolu.lu@linux.intel.com>
>
> This implements the .cache_invalidate_user() callback to support iotlb
> flush for nested domain.
>
> Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
> Co-developed-by: Yi Liu <yi.l.liu@intel.com>
> Signed-off-by: Yi Liu <yi.l.liu@intel.com>
> ---
>   drivers/iommu/intel/nested.c | 116 +++++++++++++++++++++++++++++++++++
>   1 file changed, 116 insertions(+)
>
> diff --git a/drivers/iommu/intel/nested.c b/drivers/iommu/intel/nested.c
> index b5a5563ab32c..c665e2647045 100644
> --- a/drivers/iommu/intel/nested.c
> +++ b/drivers/iommu/intel/nested.c
> @@ -73,9 +73,125 @@ static void intel_nested_domain_free(struct iommu_domain *domain)
>   	kfree(to_dmar_domain(domain));
>   }
>   
> +static void nested_flush_pasid_iotlb(struct intel_iommu *iommu,
> +				     struct dmar_domain *domain, u64 addr,
> +				     unsigned long npages, bool ih)
> +{
> +	u16 did = domain_id_iommu(domain, iommu);
> +	unsigned long flags;
> +
> +	spin_lock_irqsave(&domain->lock, flags);
> +	if (!list_empty(&domain->devices))
> +		qi_flush_piotlb(iommu, did, IOMMU_NO_PASID, addr,
> +				npages, ih, NULL);
> +	spin_unlock_irqrestore(&domain->lock, flags);
> +}
> +
> +static void nested_flush_dev_iotlb(struct dmar_domain *domain, u64 addr,
> +				   unsigned mask, u32 *fault)
> +{
> +	struct device_domain_info *info;
> +	unsigned long flags;
> +	u16 sid, qdep;
> +
> +	spin_lock_irqsave(&domain->lock, flags);
> +	list_for_each_entry(info, &domain->devices, link) {
> +		if (!info->ats_enabled)
> +			continue;
> +		sid = info->bus << 8 | info->devfn;
> +		qdep = info->ats_qdep;
> +		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
> +				   qdep, addr, mask, fault);
> +		quirk_extra_dev_tlb_flush(info, addr, mask,
> +					  IOMMU_NO_PASID, qdep);
> +	}
> +	spin_unlock_irqrestore(&domain->lock, flags);
> +}
> +
> +static void intel_nested_flush_cache(struct dmar_domain *domain, u64 addr,
> +				     unsigned long npages, u32 *error)
> +{
> +	struct iommu_domain_info *info;
> +	unsigned long i;
> +	unsigned mask;
> +	u32 fault = 0;
> +
> +	if (npages == U64_MAX)
> +		mask = 64 - VTD_PAGE_SHIFT;
> +	else
> +		mask = ilog2(__roundup_pow_of_two(npages));
> +
> +	xa_for_each(&domain->iommu_array, i, info) {
> +		nested_flush_pasid_iotlb(info->iommu, domain, addr, npages, 0);
> +
> +		if (domain->has_iotlb_device)
> +			continue;

Shouldn't this be if (!domain->has_iotlb_device)?
> +
> +		nested_flush_dev_iotlb(domain, addr, mask, &fault);
> +		if (fault & (DMA_FSTS_ITE | DMA_FSTS_ICE))
> +			break;
> +	}
> +
> +	if (fault & DMA_FSTS_ICE)
> +		*error |= IOMMU_HWPT_INVALIDATE_VTD_S1_ICE;
> +	if (fault & DMA_FSTS_ITE)
> +		*error |= IOMMU_HWPT_INVALIDATE_VTD_S1_ITE;
> +}
> +
> +static int intel_nested_cache_invalidate_user(struct iommu_domain *domain,
> +					      struct iommu_user_data_array *array)
> +{
> +	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
> +	struct iommu_hwpt_vtd_s1_invalidate inv_entry;
> +	u32 processed = 0;
> +	int ret = 0;
> +	u32 index;
> +
> +	if (array->type != IOMMU_HWPT_INVALIDATE_DATA_VTD_S1) {
> +		ret = -EINVAL;
> +		goto out;
> +	}
> +
> +	for (index = 0; index < array->entry_num; index++) {
> +		ret = iommu_copy_struct_from_user_array(&inv_entry, array,
> +							IOMMU_HWPT_INVALIDATE_DATA_VTD_S1,
> +							index, inv_error);
> +		if (ret)
> +			break;
> +
> +		if (inv_entry.flags & ~IOMMU_VTD_INV_FLAGS_LEAF) {
> +			ret = -EOPNOTSUPP;
> +			break;
> +		}
> +
> +		if (!IS_ALIGNED(inv_entry.addr, VTD_PAGE_SIZE) ||
> +		    ((inv_entry.npages == U64_MAX) && inv_entry.addr)) {
> +			ret = -EINVAL;
> +			break;
> +		}
> +
> +		inv_entry.inv_error = 0;
> +		intel_nested_flush_cache(dmar_domain, inv_entry.addr,
> +					 inv_entry.npages, &inv_entry.inv_error);
> +
> +		ret = iommu_respond_struct_to_user_array(array, index,
> +							 (void *)&inv_entry,
> +							 sizeof(inv_entry));
> +		if (ret)
> +			break;
> +
> +		processed++;
> +	}
> +
> +out:
> +	array->entry_num = processed;
> +	return ret;
> +}
> +
>   static const struct iommu_domain_ops intel_nested_domain_ops = {
>   	.attach_dev		= intel_nested_attach_dev,
>   	.free			= intel_nested_domain_free,
> +	.cache_invalidate_user	= intel_nested_cache_invalidate_user,
>   };
>   
>   struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,