iommu/vt-d: Add helper to allocate paging domain

The domain_alloc_user operation is currently implemented by allocating a
paging domain using iommu_domain_alloc(). This is because it needs to fully
initialize the domain before return. Add a helper to do this to avoid using
iommu_domain_alloc().

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20240610085555.88197-16-baolu.lu@linux.intel.com
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Link: https://lore.kernel.org/r/20240702130839.108139-6-baolu.lu@linux.intel.com
Signed-off-by: Will Deacon <will@kernel.org>

1 files changed, 81 insertions, 9 deletions

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 1b5519dfa085..1f0d6892a0b6 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3622,6 +3622,79 @@ static struct iommu_domain blocking_domain = {
 	}
 };
 
+static int iommu_superpage_capability(struct intel_iommu *iommu, bool first_stage)
+{
+	if (!intel_iommu_superpage)
+		return 0;
+
+	if (first_stage)
+		return cap_fl1gp_support(iommu->cap) ? 2 : 1;
+
+	return fls(cap_super_page_val(iommu->cap));
+}
+
+static struct dmar_domain *paging_domain_alloc(struct device *dev, bool first_stage)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	struct dmar_domain *domain;
+	int addr_width;
+
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&domain->devices);
+	INIT_LIST_HEAD(&domain->dev_pasids);
+	INIT_LIST_HEAD(&domain->cache_tags);
+	spin_lock_init(&domain->lock);
+	spin_lock_init(&domain->cache_lock);
+	xa_init(&domain->iommu_array);
+
+	domain->nid = dev_to_node(dev);
+	domain->has_iotlb_device = info->ats_enabled;
+	domain->use_first_level = first_stage;
+
+	/* calculate the address width */
+	addr_width = agaw_to_width(iommu->agaw);
+	if (addr_width > cap_mgaw(iommu->cap))
+		addr_width = cap_mgaw(iommu->cap);
+	domain->gaw = addr_width;
+	domain->agaw = iommu->agaw;
+	domain->max_addr = __DOMAIN_MAX_ADDR(addr_width);
+
+	/* iommu memory access coherency */
+	domain->iommu_coherency = iommu_paging_structure_coherency(iommu);
+
+	/* pagesize bitmap */
+	domain->domain.pgsize_bitmap = SZ_4K;
+	domain->iommu_superpage = iommu_superpage_capability(iommu, first_stage);
+	domain->domain.pgsize_bitmap |= domain_super_pgsize_bitmap(domain);
+
+	/*
+	 * IOVA aperture: First-level translation restricts the input-address
+	 * to a canonical address (i.e., address bits 63:N have the same value
+	 * as address bit [N-1], where N is 48-bits with 4-level paging and
+	 * 57-bits with 5-level paging). Hence, skip bit [N-1].
+	 */
+	domain->domain.geometry.force_aperture = true;
+	domain->domain.geometry.aperture_start = 0;
+	if (first_stage)
+		domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw - 1);
+	else
+		domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw);
+
+	/* always allocate the top pgd */
+	domain->pgd = iommu_alloc_page_node(domain->nid, GFP_KERNEL);
+	if (!domain->pgd) {
+		kfree(domain);
+		return ERR_PTR(-ENOMEM);
+	}
+	domain_flush_cache(domain, domain->pgd, PAGE_SIZE);
+
+	return domain;
+}
+
 static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
 {
 	struct dmar_domain *dmar_domain;
@@ -3684,15 +3757,14 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 	if (user_data || (dirty_tracking && !ssads_supported(iommu)))
 		return ERR_PTR(-EOPNOTSUPP);
 
-	/*
-	 * domain_alloc_user op needs to fully initialize a domain before
-	 * return, so uses iommu_domain_alloc() here for simple.
-	 */
-	domain = iommu_domain_alloc(dev->bus);
-	if (!domain)
-		return ERR_PTR(-ENOMEM);
-
-	dmar_domain = to_dmar_domain(domain);
+	/* Do not use first stage for user domain translation. */
+	dmar_domain = paging_domain_alloc(dev, false);
+	if (IS_ERR(dmar_domain))
+		return ERR_CAST(dmar_domain);
+	domain = &dmar_domain->domain;
+	domain->type = IOMMU_DOMAIN_UNMANAGED;
+	domain->owner = &intel_iommu_ops;
+	domain->ops = intel_iommu_ops.default_domain_ops;
 
 	if (nested_parent) {
 		dmar_domain->nested_parent = true;