The domain_alloc_user ops should always allocate a guest-compatible page
table unless specific allocation flags are specified.

Currently, IOMMU_HWPT_ALLOC_NEST_PARENT and IOMMU_HWPT_ALLOC_DIRTY_TRACKING
require special handling, as both require hardware support for scalable
mode and second-stage translation. In such cases, the driver should select
a second-stage page table for the paging domain.

Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/intel/iommu.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index bad9593f2464..2b5027dd0c96 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3297,6 +3297,7 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 	struct intel_iommu *iommu = info->iommu;
 	struct dmar_domain *dmar_domain;
 	struct iommu_domain *domain;
+	bool first_stage;
 
 	/* Must be NESTING domain */
 	if (parent) {
@@ -3313,8 +3314,20 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 	if (user_data || (dirty_tracking && !ssads_supported(iommu)))
 		return ERR_PTR(-EOPNOTSUPP);
 
-	/* Do not use first stage for user domain translation. */
-	dmar_domain = paging_domain_alloc(dev, false);
+	/*
+	 * Always allocate the guest compatible page table unless
+	 * IOMMU_HWPT_ALLOC_NEST_PARENT or IOMMU_HWPT_ALLOC_DIRTY_TRACKING
+	 * is specified.
+	 */
+	if (nested_parent || dirty_tracking) {
+		if (!sm_supported(iommu) || !ecap_slts(iommu->ecap))
+			return ERR_PTR(-EOPNOTSUPP);
+		first_stage = false;
+	} else {
+		first_stage = first_level_by_default(iommu);
+	}
+
+	dmar_domain = paging_domain_alloc(dev, first_stage);
 	if (IS_ERR(dmar_domain))
 		return ERR_CAST(dmar_domain);
 	domain = &dmar_domain->domain;
-- 
2.43.0