1 files changed, 121 insertions, 71 deletions

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 3117d99cf83d..eb348c63a8d0 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -25,6 +25,7 @@
 #include <linux/notifier.h>
 #include <linux/export.h>
 #include <linux/irq.h>
+#include <linux/irqchip/irq-msi-lib.h>
 #include <linux/msi.h>
 #include <linux/irqdomain.h>
 #include <linux/percpu.h>
@@ -63,13 +64,6 @@ static const struct iommu_dirty_ops amd_dirty_ops;
 int amd_iommu_max_glx_val = -1;
 
 /*
- * general struct to manage commands send to an IOMMU
- */
-struct iommu_cmd {
-	u32 data[4];
-};
-
-/*
  * AMD IOMMU allows up to 2^16 different protection domains. This is a bitmap
  * to know which ones are already in use.
  */
@@ -634,8 +628,8 @@ static inline void pdev_disable_cap_pasid(struct pci_dev *pdev)
 
 static void pdev_enable_caps(struct pci_dev *pdev)
 {
-	pdev_enable_cap_ats(pdev);
 	pdev_enable_cap_pasid(pdev);
+	pdev_enable_cap_ats(pdev);
 	pdev_enable_cap_pri(pdev);
 }
 
@@ -2424,6 +2418,13 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev)
 					     pci_max_pasids(to_pci_dev(dev)));
 	}
 
+	if (amd_iommu_pgtable == PD_MODE_NONE) {
+		pr_warn_once("%s: DMA translation not supported by iommu.\n",
+			     __func__);
+		iommu_dev = ERR_PTR(-ENODEV);
+		goto out_err;
+	}
+
 out_err:
 
 	iommu_completion_wait(iommu);
@@ -2511,6 +2512,9 @@ static int pdom_setup_pgtable(struct protection_domain *domain,
 	case PD_MODE_V2:
 		fmt = AMD_IOMMU_V2;
 		break;
+	case PD_MODE_NONE:
+		WARN_ON_ONCE(1);
+		return -EPERM;
 	}
 
 	domain->iop.pgtbl.cfg.amd.nid = dev_to_node(dev);
@@ -2524,14 +2528,30 @@ static int pdom_setup_pgtable(struct protection_domain *domain,
 static inline u64 dma_max_address(enum protection_domain_mode pgtable)
 {
 	if (pgtable == PD_MODE_V1)
-		return ~0ULL;
+		return PM_LEVEL_SIZE(amd_iommu_hpt_level);
 
-	/* V2 with 4/5 level page table */
-	return ((1ULL << PM_LEVEL_SHIFT(amd_iommu_gpt_level)) - 1);
+	/*
+	 * V2 with 4/5 level page table. Note that "2.2.6.5 AMD64 4-Kbyte Page
+	 * Translation" shows that the V2 table sign extends the top of the
+	 * address space creating a reserved region in the middle of the
+	 * translation, just like the CPU does. Further Vasant says the docs are
+	 * incomplete and this only applies to non-zero PASIDs. If the AMDv2
+	 * page table is assigned to the 0 PASID then there is no sign extension
+	 * check.
+	 *
+	 * Since the IOMMU must have a fixed geometry, and the core code does
+	 * not understand sign extended addressing, we have to chop off the high
+	 * bit to get consistent behavior with attachments of the domain to any
+	 * PASID.
+	 */
+	return ((1ULL << (PM_LEVEL_SHIFT(amd_iommu_gpt_level) - 1)) - 1);
 }
 
 static bool amd_iommu_hd_support(struct amd_iommu *iommu)
 {
+	if (amd_iommu_hatdis)
+		return false;
+
 	return iommu && (iommu->features & FEATURE_HDSUP);
 }
 
@@ -3804,13 +3824,70 @@ static const struct irq_domain_ops amd_ir_domain_ops = {
 	.deactivate = irq_remapping_deactivate,
 };
 
-int amd_iommu_activate_guest_mode(void *data)
+static void __amd_iommu_update_ga(struct irte_ga *entry, int cpu,
+				  bool ga_log_intr)
+{
+	if (cpu >= 0) {
+		entry->lo.fields_vapic.destination =
+					APICID_TO_IRTE_DEST_LO(cpu);
+		entry->hi.fields.destination =
+					APICID_TO_IRTE_DEST_HI(cpu);
+		entry->lo.fields_vapic.is_run = true;
+		entry->lo.fields_vapic.ga_log_intr = false;
+	} else {
+		entry->lo.fields_vapic.is_run = false;
+		entry->lo.fields_vapic.ga_log_intr = ga_log_intr;
+	}
+}
+
+/*
+ * Update the pCPU information for an IRTE that is configured to post IRQs to
+ * a vCPU, without issuing an IOMMU invalidation for the IRTE.
+ *
+ * If the vCPU is associated with a pCPU (@cpu >= 0), configure the Destination
+ * with the pCPU's APIC ID, set IsRun, and clear GALogIntr.  If the vCPU isn't
+ * associated with a pCPU (@cpu < 0), clear IsRun and set/clear GALogIntr based
+ * on input from the caller (e.g. KVM only requests GALogIntr when the vCPU is
+ * blocking and requires a notification wake event).  I.e. treat vCPUs that are
+ * associated with a pCPU as running.  This API is intended to be used when a
+ * vCPU is scheduled in/out (or stops running for any reason), to do a fast
+ * update of IsRun, GALogIntr, and (conditionally) Destination.
+ *
+ * Per the IOMMU spec, the Destination, IsRun, and GATag fields are not cached
+ * and thus don't require an invalidation to ensure the IOMMU consumes fresh
+ * information.
+ */
+int amd_iommu_update_ga(void *data, int cpu, bool ga_log_intr)
+{
+	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
+	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
+
+	if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)))
+		return -EINVAL;
+
+	if (!entry || !entry->lo.fields_vapic.guest_mode)
+		return 0;
+
+	if (!ir_data->iommu)
+		return -ENODEV;
+
+	__amd_iommu_update_ga(entry, cpu, ga_log_intr);
+
+	return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
+				ir_data->irq_2_irte.index, entry);
+}
+EXPORT_SYMBOL(amd_iommu_update_ga);
+
+int amd_iommu_activate_guest_mode(void *data, int cpu, bool ga_log_intr)
 {
 	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
 	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
 	u64 valid;
 
-	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || !entry)
+	if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)))
+		return -EINVAL;
+
+	if (!entry)
 		return 0;
 
 	valid = entry->lo.fields_vapic.valid;
@@ -3820,11 +3897,12 @@ int amd_iommu_activate_guest_mode(void *data)
 
 	entry->lo.fields_vapic.valid       = valid;
 	entry->lo.fields_vapic.guest_mode  = 1;
-	entry->lo.fields_vapic.ga_log_intr = 1;
 	entry->hi.fields.ga_root_ptr       = ir_data->ga_root_ptr;
 	entry->hi.fields.vector            = ir_data->ga_vector;
 	entry->lo.fields_vapic.ga_tag      = ir_data->ga_tag;
 
+	__amd_iommu_update_ga(entry, cpu, ga_log_intr);
+
 	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
 			      ir_data->irq_2_irte.index, entry);
 }
@@ -3837,8 +3915,10 @@ int amd_iommu_deactivate_guest_mode(void *data)
 	struct irq_cfg *cfg = ir_data->cfg;
 	u64 valid;
 
-	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
-	    !entry || !entry->lo.fields_vapic.guest_mode)
+	if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)))
+		return -EINVAL;
+
+	if (!entry || !entry->lo.fields_vapic.guest_mode)
 		return 0;
 
 	valid = entry->lo.fields_remap.valid;
@@ -3860,11 +3940,10 @@ int amd_iommu_deactivate_guest_mode(void *data)
 }
 EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode);
 
-static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
+static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *info)
 {
 	int ret;
-	struct amd_iommu_pi_data *pi_data = vcpu_info;
-	struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data;
+	struct amd_iommu_pi_data *pi_data = info;
 	struct amd_ir_data *ir_data = data->chip_data;
 	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
 	struct iommu_dev_data *dev_data;
@@ -3885,25 +3964,20 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 		return -EINVAL;
 
 	ir_data->cfg = irqd_cfg(data);
-	pi_data->ir_data = ir_data;
 
-	pi_data->prev_ga_tag = ir_data->cached_ga_tag;
-	if (pi_data->is_guest_mode) {
-		ir_data->ga_root_ptr = (pi_data->base >> 12);
-		ir_data->ga_vector = vcpu_pi_info->vector;
+	if (pi_data) {
+		pi_data->ir_data = ir_data;
+
+		ir_data->ga_root_ptr = (pi_data->vapic_addr >> 12);
+		ir_data->ga_vector = pi_data->vector;
 		ir_data->ga_tag = pi_data->ga_tag;
-		ret = amd_iommu_activate_guest_mode(ir_data);
-		if (!ret)
-			ir_data->cached_ga_tag = pi_data->ga_tag;
+		if (pi_data->is_guest_mode)
+			ret = amd_iommu_activate_guest_mode(ir_data, pi_data->cpu,
+							    pi_data->ga_log_intr);
+		else
+			ret = amd_iommu_deactivate_guest_mode(ir_data);
 	} else {
 		ret = amd_iommu_deactivate_guest_mode(ir_data);
-
-		/*
-		 * This communicates the ga_tag back to the caller
-		 * so that it can do all the necessary clean up.
-		 */
-		if (!ret)
-			ir_data->cached_ga_tag = 0;
 	}
 
 	return ret;
@@ -3970,54 +4044,30 @@ static struct irq_chip amd_ir_chip = {
 
 static const struct msi_parent_ops amdvi_msi_parent_ops = {
 	.supported_flags	= X86_VECTOR_MSI_FLAGS_SUPPORTED | MSI_FLAG_MULTI_PCI_MSI,
+	.bus_select_token	= DOMAIN_BUS_AMDVI,
+	.bus_select_mask	= MATCH_PCI_MSI,
 	.prefix			= "IR-",
 	.init_dev_msi_info	= msi_parent_init_dev_msi_info,
 };
 
 int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
 {
-	struct fwnode_handle *fn;
+	struct irq_domain_info info = {
+		.fwnode		= irq_domain_alloc_named_id_fwnode("AMD-IR", iommu->index),
+		.ops		= &amd_ir_domain_ops,
+		.domain_flags	= IRQ_DOMAIN_FLAG_ISOLATED_MSI,
+		.host_data	= iommu,
+		.parent		= arch_get_ir_parent_domain(),
+	};
 
-	fn = irq_domain_alloc_named_id_fwnode("AMD-IR", iommu->index);
-	if (!fn)
+	if (!info.fwnode)
 		return -ENOMEM;
-	iommu->ir_domain = irq_domain_create_hierarchy(arch_get_ir_parent_domain(), 0, 0,
-						       fn, &amd_ir_domain_ops, iommu);
+
+	iommu->ir_domain = msi_create_parent_irq_domain(&info, &amdvi_msi_parent_ops);
 	if (!iommu->ir_domain) {
-		irq_domain_free_fwnode(fn);
+		irq_domain_free_fwnode(info.fwnode);
 		return -ENOMEM;
 	}
-
-	irq_domain_update_bus_token(iommu->ir_domain,  DOMAIN_BUS_AMDVI);
-	iommu->ir_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT |
-				   IRQ_DOMAIN_FLAG_ISOLATED_MSI;
-	iommu->ir_domain->msi_parent_ops = &amdvi_msi_parent_ops;
-
 	return 0;
 }
-
-int amd_iommu_update_ga(int cpu, bool is_run, void *data)
-{
-	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
-	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
-
-	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
-	    !entry || !entry->lo.fields_vapic.guest_mode)
-		return 0;
-
-	if (!ir_data->iommu)
-		return -ENODEV;
-
-	if (cpu >= 0) {
-		entry->lo.fields_vapic.destination =
-					APICID_TO_IRTE_DEST_LO(cpu);
-		entry->hi.fields.destination =
-					APICID_TO_IRTE_DEST_HI(cpu);
-	}
-	entry->lo.fields_vapic.is_run = is_run;
-
-	return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
-				ir_data->irq_2_irte.index, entry);
-}
-EXPORT_SYMBOL(amd_iommu_update_ga);
 #endif