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

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(+)

>-----Original Message-----
>From: Liu, Yi L <yi.l.liu@intel.com>
>Subject: [PATCH v7 9/9] iommu/vt-d: Add iotlb flush for nested domain
>
>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);

Is it optimal to check if domain attached to iommu before trigger flush?
Or the check is redundant if intel_nested_flush_cache() is the only call site.

Thanks
Zhenzhong

>+	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;
>+
>+		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,
>--
>2.34.1

On 2023/12/27 17:27, Duan, Zhenzhong wrote:
> 
> 
>> -----Original Message-----
>> From: Liu, Yi L <yi.l.liu@intel.com>
>> Subject: [PATCH v7 9/9] iommu/vt-d: Add iotlb flush for nested domain
>>
>> 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);
> 
> Is it optimal to check if domain attached to iommu before trigger flush?
> Or the check is redundant if intel_nested_flush_cache() is the only call site.

I think it is possible that userspace issue an invalidation on a hwpt which
does not have any device attached.. Though this is something stupid. So
checking if any device attached before flushing still makes sense.

> Thanks
> Zhenzhong
> 
>> +	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;
>> +
>> +		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,
>> --
>> 2.34.1
>