iommu/vt-d: Add nested translation helper function

Nested translation mode is supported in VT-d 3.0 Spec.CH 3.8.
With PASID granular translation type set to 0x11b, translation
result from the first level(FL) also subject to a second level(SL)
page table translation. This mode is used for SVA virtualization,
where FL performs guest virtual to guest physical translation and
SL performs guest physical to host physical translation.

This patch adds a helper function for setting up nested translation
where second level comes from a domain and first level comes from
a guest PGD.

Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/20200516062101.29541-4-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>

1 files changed, 171 insertions, 3 deletions

diff --git a/drivers/iommu/intel-pasid.c b/drivers/iommu/intel-pasid.c
index d9cea3011b58..c7fa1b79eaf7 100644
--- a/drivers/iommu/intel-pasid.c
+++ b/drivers/iommu/intel-pasid.c
@@ -359,6 +359,16 @@ pasid_set_flpm(struct pasid_entry *pe, u64 value)
 	pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2);
 }
 
+/*
+ * Setup the Extended Access Flag Enable (EAFE) field (Bit 135)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_eafe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7);
+}
+
 static void
 pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu,
 				    u16 did, int pasid)
@@ -492,7 +502,7 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
 
 	/* Setup Present and PASID Granular Transfer Type: */
-	pasid_set_translation_type(pte, 1);
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_FL_ONLY);
 	pasid_set_present(pte);
 	pasid_flush_caches(iommu, pte, pasid, did);
 
@@ -561,7 +571,7 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 	pasid_set_domain_id(pte, did);
 	pasid_set_slptr(pte, pgd_val);
 	pasid_set_address_width(pte, agaw);
-	pasid_set_translation_type(pte, 2);
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_SL_ONLY);
 	pasid_set_fault_enable(pte);
 	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
 
@@ -595,7 +605,7 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 	pasid_clear_entry(pte);
 	pasid_set_domain_id(pte, did);
 	pasid_set_address_width(pte, iommu->agaw);
-	pasid_set_translation_type(pte, 4);
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_PT);
 	pasid_set_fault_enable(pte);
 	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
 
@@ -609,3 +619,161 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 
 	return 0;
 }
+
+static int
+intel_pasid_setup_bind_data(struct intel_iommu *iommu, struct pasid_entry *pte,
+			    struct iommu_gpasid_bind_data_vtd *pasid_data)
+{
+	/*
+	 * Not all guest PASID table entry fields are passed down during bind,
+	 * here we only set up the ones that are dependent on guest settings.
+	 * Execution related bits such as NXE, SMEP are not supported.
+	 * Other fields, such as snoop related, are set based on host needs
+	 * regardless of guest settings.
+	 */
+	if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_SRE) {
+		if (!ecap_srs(iommu->ecap)) {
+			pr_err_ratelimited("No supervisor request support on %s\n",
+					   iommu->name);
+			return -EINVAL;
+		}
+		pasid_set_sre(pte);
+	}
+
+	if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_EAFE) {
+		if (!ecap_eafs(iommu->ecap)) {
+			pr_err_ratelimited("No extended access flag support on %s\n",
+					   iommu->name);
+			return -EINVAL;
+		}
+		pasid_set_eafe(pte);
+	}
+
+	/*
+	 * Memory type is only applicable to devices inside processor coherent
+	 * domain. Will add MTS support once coherent devices are available.
+	 */
+	if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_MTS_MASK) {
+		pr_warn_ratelimited("No memory type support %s\n",
+				    iommu->name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * intel_pasid_setup_nested() - Set up PASID entry for nested translation.
+ * This could be used for guest shared virtual address. In this case, the
+ * first level page tables are used for GVA-GPA translation in the guest,
+ * second level page tables are used for GPA-HPA translation.
+ *
+ * @iommu:      IOMMU which the device belong to
+ * @dev:        Device to be set up for translation
+ * @gpgd:       FLPTPTR: First Level Page translation pointer in GPA
+ * @pasid:      PASID to be programmed in the device PASID table
+ * @pasid_data: Additional PASID info from the guest bind request
+ * @domain:     Domain info for setting up second level page tables
+ * @addr_width: Address width of the first level (guest)
+ */
+int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
+			     pgd_t *gpgd, int pasid,
+			     struct iommu_gpasid_bind_data_vtd *pasid_data,
+			     struct dmar_domain *domain, int addr_width)
+{
+	struct pasid_entry *pte;
+	struct dma_pte *pgd;
+	int ret = 0;
+	u64 pgd_val;
+	int agaw;
+	u16 did;
+
+	if (!ecap_nest(iommu->ecap)) {
+		pr_err_ratelimited("IOMMU: %s: No nested translation support\n",
+				   iommu->name);
+		return -EINVAL;
+	}
+
+	if (!(domain->flags & DOMAIN_FLAG_NESTING_MODE)) {
+		pr_err_ratelimited("Domain is not in nesting mode, %x\n",
+				   domain->flags);
+		return -EINVAL;
+	}
+
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (WARN_ON(!pte))
+		return -EINVAL;
+
+	/*
+	 * Caller must ensure PASID entry is not in use, i.e. not bind the
+	 * same PASID to the same device twice.
+	 */
+	if (pasid_pte_is_present(pte))
+		return -EBUSY;
+
+	pasid_clear_entry(pte);
+
+	/* Sanity checking performed by caller to make sure address
+	 * width matching in two dimensions:
+	 * 1. CPU vs. IOMMU
+	 * 2. Guest vs. Host.
+	 */
+	switch (addr_width) {
+#ifdef CONFIG_X86
+	case ADDR_WIDTH_5LEVEL:
+		if (!cpu_feature_enabled(X86_FEATURE_LA57) ||
+		    !cap_5lp_support(iommu->cap)) {
+			dev_err_ratelimited(dev,
+					    "5-level paging not supported\n");
+			return -EINVAL;
+		}
+
+		pasid_set_flpm(pte, 1);
+		break;
+#endif
+	case ADDR_WIDTH_4LEVEL:
+		pasid_set_flpm(pte, 0);
+		break;
+	default:
+		dev_err_ratelimited(dev, "Invalid guest address width %d\n",
+				    addr_width);
+		return -EINVAL;
+	}
+
+	/* First level PGD is in GPA, must be supported by the second level */
+	if ((unsigned long long)gpgd > domain->max_addr) {
+		dev_err_ratelimited(dev,
+				    "Guest PGD %llx not supported, max %llx\n",
+				    (unsigned long long)gpgd, domain->max_addr);
+		return -EINVAL;
+	}
+	pasid_set_flptr(pte, (u64)gpgd);
+
+	ret = intel_pasid_setup_bind_data(iommu, pte, pasid_data);
+	if (ret)
+		return ret;
+
+	/* Setup the second level based on the given domain */
+	pgd = domain->pgd;
+
+	agaw = iommu_skip_agaw(domain, iommu, &pgd);
+	if (agaw < 0) {
+		dev_err_ratelimited(dev, "Invalid domain page table\n");
+		return -EINVAL;
+	}
+	pgd_val = virt_to_phys(pgd);
+	pasid_set_slptr(pte, pgd_val);
+	pasid_set_fault_enable(pte);
+
+	did = domain->iommu_did[iommu->seq_id];
+	pasid_set_domain_id(pte, did);
+
+	pasid_set_address_width(pte, agaw);
+	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_NESTED);
+	pasid_set_present(pte);
+	pasid_flush_caches(iommu, pte, pasid, did);
+
+	return ret;
+}