Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

[Baolu Lu <baolu.lu@linux.intel.com>]

On 2022/5/24 21:44, Jason Gunthorpe wrote:
>> +{
>> +	struct iommu_sva_domain *sva_domain;
>> +	struct iommu_domain *domain;
>> +
>> +	if (!bus->iommu_ops || !bus->iommu_ops->sva_domain_ops)
>> +		return ERR_PTR(-ENODEV);
>> +
>> +	sva_domain = kzalloc(sizeof(*sva_domain), GFP_KERNEL);
>> +	if (!sva_domain)
>> +		return ERR_PTR(-ENOMEM);
>> +
>> +	mmgrab(mm);
>> +	sva_domain->mm = mm;
>> +
>> +	domain = &sva_domain->domain;
>> +	domain->type = IOMMU_DOMAIN_SVA;
>> +	domain->ops = bus->iommu_ops->sva_domain_ops;
>> +
>> +	return domain;
>> +}
>> +
>> +void iommu_sva_free_domain(struct iommu_domain *domain)
>> +{
>> +	struct iommu_sva_domain *sva_domain = to_sva_domain(domain);
>> +
>> +	mmdrop(sva_domain->mm);
>> +	kfree(sva_domain);
>> +}
> No callback to the driver?

Should do this in the next version. This version added an sva-specific
iommu_domain_ops pointer in iommu_ops. This is not the right way to go.

> 
>> +int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev,
>> +			 ioasid_t pasid)
>> +{
> Why does this function exist? Just call iommu_set_device_pasid()

Yes, agreed.

> 
>> +int iommu_set_device_pasid(struct iommu_domain *domain, struct device *dev,
>> +			   ioasid_t pasid)
>> +{
> Here you can continue to use attach/detach language as at this API
> level we expect strict pairing..

Sure.

> 
> 
>> +void iommu_block_device_pasid(struct iommu_domain *domain, struct device *dev,
>> +			      ioasid_t pasid)
>> +{
>> +	struct iommu_group *group = iommu_group_get(dev);
>> +
>> +	mutex_lock(&group->mutex);
>> +	domain->ops->block_dev_pasid(domain, dev, pasid);
>> +	xa_erase(&group->pasid_array, pasid);
>> +	mutex_unlock(&group->mutex);
> Should be the blocking domain.

As we discussed, we should change above to blocking domain when the
blocking domain is supported on at least Intel and arm-smmu-v3 drivers.
I have started the work for Intel driver support.

Best regards,
baolu