Re: [PATCH v7 7/8] iommu/vt-d: Add nested domain allocation

[Jason Gunthorpe]

On Tue, Oct 24, 2023 at 08:14:11AM -0700, Yi Liu wrote:
> From: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
> 
> This adds the support for IOMMU_HWPT_DATA_VTD_S1 type. And 'nested_parent'
> is added to mark the nested parent domain to sanitize the input parent domain.
> 
> Signed-off-by: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
> Signed-off-by: Yi Liu <yi.l.liu@xxxxxxxxx>
> ---
>  drivers/iommu/intel/iommu.c | 67 +++++++++++++++++++++++++------------
>  drivers/iommu/intel/iommu.h |  1 +
>  2 files changed, 46 insertions(+), 22 deletions(-)

I think it should be written like this:

@@ -4077,38 +4082,39 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 			      struct iommu_domain *parent,
 			      const struct iommu_user_data *user_data)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	bool dirty_tracking = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
+	bool nested_parent = flags & IOMMU_HWPT_ALLOC_NEST_PARENT;
+	struct intel_iommu *iommu = info->iommu;
 	struct iommu_domain *domain;
-	struct intel_iommu *iommu;
-	bool dirty_tracking;
+
+	/* Must be NESTING domain */
+	if (parent) {
+		if (!nested_supported(iommu) || flags)
+			return ERR_PTR(-EOPNOTSUPP);
+		return intel_nested_domain_alloc(parent, user_data);
+	}
 
 	if (flags &
 	    (~(IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING)))
 		return ERR_PTR(-EOPNOTSUPP);
-
-	if (parent || user_data)
+	if (nested_parent && !nested_supported(iommu))
 		return ERR_PTR(-EOPNOTSUPP);
-
-	iommu = device_to_iommu(dev, NULL, NULL);
-	if (!iommu)
-		return ERR_PTR(-ENODEV);
-
-	if ((flags & IOMMU_HWPT_ALLOC_NEST_PARENT) && !nested_supported(iommu))
-		return ERR_PTR(-EOPNOTSUPP);
-
-	dirty_tracking = (flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING);
-	if (dirty_tracking && !ssads_supported(iommu))
+	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_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)
-		domain = ERR_PTR(-ENOMEM);
+		return ERR_PTR(-ENOMEM);
 
-	if (!IS_ERR(domain) && dirty_tracking) {
+	if (nested_parent)
+		to_dmar_domain(domain)->nested_parent = true;
+
+	if (dirty_tracking) {
 		if (to_dmar_domain(domain)->use_first_level) {
 			iommu_domain_free(domain);
 			return ERR_PTR(-EOPNOTSUPP);
@@ -4849,6 +4855,7 @@ static void *intel_iommu_hw_info(struct device *dev, u32 *length, u32 *type)
 	if (!vtd)
 		return ERR_PTR(-ENOMEM);
 
+	vtd->flags = IOMMU_HW_INFO_VTD_ERRATA_772415_SPR17;
 	vtd->cap_reg = iommu->cap;
 	vtd->ecap_reg = iommu->ecap;
 	*length = sizeof(*vtd);
diff --git a/drivers/iommu/intel/nested.c b/drivers/iommu/intel/nested.c
index d9197dd72748b1..b5a5563ab32c6b 100644
--- a/drivers/iommu/intel/nested.c
+++ b/drivers/iommu/intel/nested.c
@@ -78,13 +78,21 @@ static const struct iommu_domain_ops intel_nested_domain_ops = {
 	.free			= intel_nested_domain_free,
 };
 
-struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *s2_domain,
+struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
 					       const struct iommu_user_data *user_data)
 {
+	struct dmar_domain *s2_domain = to_dmar_domain(parent);
 	struct iommu_hwpt_vtd_s1 vtd;
 	struct dmar_domain *domain;
 	int ret;
 
+	/* Must be nested domain */
+	if (user_data->type != IOMMU_HWPT_DATA_VTD_S1)
+		return ERR_PTR(-EOPNOTSUPP);
+	if (parent->ops != intel_iommu_ops.default_domain_ops ||
+	    !s2_domain->nested_parent)
+		return ERR_PTR(-EINVAL);
+
 	ret = iommu_copy_struct_from_user(&vtd, user_data,
 					  IOMMU_HWPT_DATA_VTD_S1, __reserved);
 	if (ret)
@@ -95,7 +103,7 @@ struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *s2_domain,
 		return ERR_PTR(-ENOMEM);
 
 	domain->use_first_level = true;
-	domain->s2_domain = to_dmar_domain(s2_domain);
+	domain->s2_domain = s2_domain;
 	domain->s1_pgtbl = vtd.pgtbl_addr;
 	domain->s1_cfg = vtd;
 	domain->domain.ops = &intel_nested_domain_ops;