1 files changed, 282 insertions, 27 deletions

diff --git a/drivers/iommu/intel-pasid.c b/drivers/iommu/intel-pasid.c
index 22b30f10b396..c81f0f17c6ba 100644
--- a/drivers/iommu/intel-pasid.c
+++ b/drivers/iommu/intel-pasid.c
@@ -27,6 +27,63 @@
 static DEFINE_SPINLOCK(pasid_lock);
 u32 intel_pasid_max_id = PASID_MAX;
 
+int vcmd_alloc_pasid(struct intel_iommu *iommu, unsigned int *pasid)
+{
+	unsigned long flags;
+	u8 status_code;
+	int ret = 0;
+	u64 res;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+	dmar_writeq(iommu->reg + DMAR_VCMD_REG, VCMD_CMD_ALLOC);
+	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
+		      !(res & VCMD_VRSP_IP), res);
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
+
+	status_code = VCMD_VRSP_SC(res);
+	switch (status_code) {
+	case VCMD_VRSP_SC_SUCCESS:
+		*pasid = VCMD_VRSP_RESULT_PASID(res);
+		break;
+	case VCMD_VRSP_SC_NO_PASID_AVAIL:
+		pr_info("IOMMU: %s: No PASID available\n", iommu->name);
+		ret = -ENOSPC;
+		break;
+	default:
+		ret = -ENODEV;
+		pr_warn("IOMMU: %s: Unexpected error code %d\n",
+			iommu->name, status_code);
+	}
+
+	return ret;
+}
+
+void vcmd_free_pasid(struct intel_iommu *iommu, unsigned int pasid)
+{
+	unsigned long flags;
+	u8 status_code;
+	u64 res;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+	dmar_writeq(iommu->reg + DMAR_VCMD_REG,
+		    VCMD_CMD_OPERAND(pasid) | VCMD_CMD_FREE);
+	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
+		      !(res & VCMD_VRSP_IP), res);
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
+
+	status_code = VCMD_VRSP_SC(res);
+	switch (status_code) {
+	case VCMD_VRSP_SC_SUCCESS:
+		break;
+	case VCMD_VRSP_SC_INVALID_PASID:
+		pr_info("IOMMU: %s: Invalid PASID\n", iommu->name);
+		break;
+	default:
+		pr_warn("IOMMU: %s: Unexpected error code %d\n",
+			iommu->name, status_code);
+	}
+}
+
 /*
  * Per device pasid table management:
  */
@@ -94,7 +151,7 @@ int intel_pasid_alloc_table(struct device *dev)
 	int size;
 
 	might_sleep();
-	info = dev->archdata.iommu;
+	info = get_domain_info(dev);
 	if (WARN_ON(!info || !dev_is_pci(dev) || info->pasid_table))
 		return -EINVAL;
 
@@ -141,7 +198,7 @@ void intel_pasid_free_table(struct device *dev)
 	struct pasid_entry *table;
 	int i, max_pde;
 
-	info = dev->archdata.iommu;
+	info = get_domain_info(dev);
 	if (!info || !dev_is_pci(dev) || !info->pasid_table)
 		return;
 
@@ -167,7 +224,7 @@ struct pasid_table *intel_pasid_get_table(struct device *dev)
 {
 	struct device_domain_info *info;
 
-	info = dev->archdata.iommu;
+	info = get_domain_info(dev);
 	if (!info)
 		return NULL;
 
@@ -178,7 +235,7 @@ int intel_pasid_get_dev_max_id(struct device *dev)
 {
 	struct device_domain_info *info;
 
-	info = dev->archdata.iommu;
+	info = get_domain_info(dev);
 	if (!info || !info->pasid_table)
 		return 0;
 
@@ -199,7 +256,7 @@ struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid)
 		return NULL;
 
 	dir = pasid_table->table;
-	info = dev->archdata.iommu;
+	info = get_domain_info(dev);
 	dir_index = pasid >> PASID_PDE_SHIFT;
 	index = pasid & PASID_PTE_MASK;
 
@@ -235,7 +292,20 @@ static inline void pasid_clear_entry(struct pasid_entry *pe)
 	WRITE_ONCE(pe->val[7], 0);
 }
 
-static void intel_pasid_clear_entry(struct device *dev, int pasid)
+static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
+{
+	WRITE_ONCE(pe->val[0], PASID_PTE_FPD);
+	WRITE_ONCE(pe->val[1], 0);
+	WRITE_ONCE(pe->val[2], 0);
+	WRITE_ONCE(pe->val[3], 0);
+	WRITE_ONCE(pe->val[4], 0);
+	WRITE_ONCE(pe->val[5], 0);
+	WRITE_ONCE(pe->val[6], 0);
+	WRITE_ONCE(pe->val[7], 0);
+}
+
+static void
+intel_pasid_clear_entry(struct device *dev, int pasid, bool fault_ignore)
 {
 	struct pasid_entry *pe;
 
@@ -243,7 +313,10 @@ static void intel_pasid_clear_entry(struct device *dev, int pasid)
 	if (WARN_ON(!pe))
 		return;
 
-	pasid_clear_entry(pe);
+	if (fault_ignore && pasid_pte_is_present(pe))
+		pasid_clear_entry_with_fpd(pe);
+	else
+		pasid_clear_entry(pe);
 }
 
 static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits)
@@ -359,18 +432,29 @@ 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)
 {
 	struct qi_desc desc;
 
-	desc.qw0 = QI_PC_DID(did) | QI_PC_PASID_SEL | QI_PC_PASID(pasid);
+	desc.qw0 = QI_PC_DID(did) | QI_PC_GRAN(QI_PC_PASID_SEL) |
+		QI_PC_PASID(pasid) | QI_PC_TYPE;
 	desc.qw1 = 0;
 	desc.qw2 = 0;
 	desc.qw3 = 0;
 
-	qi_submit_sync(&desc, iommu);
+	qi_submit_sync(iommu, &desc, 1, 0);
 }
 
 static void
@@ -384,7 +468,7 @@ iotlb_invalidation_with_pasid(struct intel_iommu *iommu, u16 did, u32 pasid)
 	desc.qw2 = 0;
 	desc.qw3 = 0;
 
-	qi_submit_sync(&desc, iommu);
+	qi_submit_sync(iommu, &desc, 1, 0);
 }
 
 static void
@@ -394,7 +478,7 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
 	struct device_domain_info *info;
 	u16 sid, qdep, pfsid;
 
-	info = dev->archdata.iommu;
+	info = get_domain_info(dev);
 	if (!info || !info->ats_enabled)
 		return;
 
@@ -405,8 +489,8 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
 	qi_flush_dev_iotlb(iommu, sid, pfsid, qdep, 0, 64 - VTD_PAGE_SHIFT);
 }
 
-void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
-				 struct device *dev, int pasid)
+void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
+				 int pasid, bool fault_ignore)
 {
 	struct pasid_entry *pte;
 	u16 did;
@@ -416,7 +500,7 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 		return;
 
 	did = pasid_get_domain_id(pte);
-	intel_pasid_clear_entry(dev, pasid);
+	intel_pasid_clear_entry(dev, pasid, fault_ignore);
 
 	if (!ecap_coherent(iommu->ecap))
 		clflush_cache_range(pte, sizeof(*pte));
@@ -492,7 +576,7 @@ 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);
 
@@ -500,6 +584,25 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 }
 
 /*
+ * Skip top levels of page tables for iommu which has less agaw
+ * than default. Unnecessary for PT mode.
+ */
+static inline int iommu_skip_agaw(struct dmar_domain *domain,
+				  struct intel_iommu *iommu,
+				  struct dma_pte **pgd)
+{
+	int agaw;
+
+	for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
+		*pgd = phys_to_virt(dma_pte_addr(*pgd));
+		if (!dma_pte_present(*pgd))
+			return -EINVAL;
+	}
+
+	return agaw;
+}
+
+/*
  * Set up the scalable mode pasid entry for second only translation type.
  */
 int intel_pasid_setup_second_level(struct intel_iommu *iommu,
@@ -522,17 +625,11 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 		return -EINVAL;
 	}
 
-	/*
-	 * Skip top levels of page tables for iommu which has less agaw
-	 * than default. Unnecessary for PT mode.
-	 */
 	pgd = domain->pgd;
-	for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
-		pgd = phys_to_virt(dma_pte_addr(pgd));
-		if (!dma_pte_present(pgd)) {
-			dev_err(dev, "Invalid domain page table\n");
-			return -EINVAL;
-		}
+	agaw = iommu_skip_agaw(domain, iommu, &pgd);
+	if (agaw < 0) {
+		dev_err(dev, "Invalid domain page table\n");
+		return -EINVAL;
 	}
 
 	pgd_val = virt_to_phys(pgd);
@@ -548,7 +645,7 @@ 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));
 
@@ -582,7 +679,7 @@ 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));
 
@@ -596,3 +693,161 @@ 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 ((uintptr_t)gpgd > domain->max_addr) {
+		dev_err_ratelimited(dev,
+				    "Guest PGD %lx not supported, max %llx\n",
+				    (uintptr_t)gpgd, domain->max_addr);
+		return -EINVAL;
+	}
+	pasid_set_flptr(pte, (uintptr_t)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;
+}