iommu/vt-d: Update scalable mode paging structure coherency

The Scalable-mode Page-walk Coherency (SMPWC) field in the VT-d extended
capability register indicates the hardware coherency behavior on paging
structures accessed through the pasid table entry. This is ignored in
current code and using ECAP.C instead which is only valid in legacy mode.
Fix this so that paging structure updates could be manually flushed from
the cache line if hardware page walking is not snooped.

Fixes: 765b6a98 ("iommu/vt-d: Enumerate the scalable mode capability")
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Kevin Tian <kevin.tian@intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Link: https://lore.kernel.org/r/20200622231345.29722-6-baolu.lu@linux.intel.comSigned-off-by: Joerg Roedel <jroedel@suse.de>

drivers/iommu/intel/iommu.c

@@ -612,6 +612,12 @@ struct intel_iommu *domain_get_iommu(struct dmar_domain *domain)
 	return g_iommus[iommu_id];
 }
 
+static inline bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
+{
+	return sm_supported(iommu) ?
+			ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap);
+}
+
 static void domain_update_iommu_coherency(struct dmar_domain *domain)
 {
 	struct dmar_drhd_unit *drhd;
@@ -623,7 +629,7 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain)
 
 	for_each_domain_iommu(i, domain) {
 		found = true;
-		if (!ecap_coherent(g_iommus[i]->ecap)) {
+		if (!iommu_paging_structure_coherency(g_iommus[i])) {
 			domain->iommu_coherency = 0;
 			break;
 		}
@@ -634,7 +640,7 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain)
 	/* No hardware attached; use lowest common denominator */
 	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd) {
-		if (!ecap_coherent(iommu->ecap)) {
+		if (!iommu_paging_structure_coherency(iommu)) {
 			domain->iommu_coherency = 0;
 			break;
 		}
@@ -2094,7 +2100,8 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 
 	context_set_fault_enable(context);
 	context_set_present(context);
-	domain_flush_cache(domain, context, sizeof(*context));
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(context, sizeof(*context));
 
 	/*
 	 * It's a non-present to present mapping. If hardware doesn't cache