6 files changed, 172 insertions, 225 deletions
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index bf1f0c814348..ec2f385ae25b 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -737,7 +737,8 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 				return NULL;
 
 			domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE);
-			pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE;
+			pteval = virt_to_phys(tmp_page) | DMA_PTE_READ |
+				 DMA_PTE_WRITE;
 			if (domain->use_first_level)
 				pteval |= DMA_FL_PTE_US | DMA_FL_PTE_ACCESS;
 
@@ -1172,32 +1173,59 @@ static bool dev_needs_extra_dtlb_flush(struct pci_dev *pdev)
 	return true;
 }
 
-static void iommu_enable_pci_caps(struct device_domain_info *info)
+static void iommu_enable_pci_ats(struct device_domain_info *info)
 {
 	struct pci_dev *pdev;
 
-	if (!dev_is_pci(info->dev))
+	if (!info->ats_supported)
 		return;
 
 	pdev = to_pci_dev(info->dev);
-	if (info->ats_supported && pci_ats_page_aligned(pdev) &&
-	    !pci_enable_ats(pdev, VTD_PAGE_SHIFT))
+	if (!pci_ats_page_aligned(pdev))
+		return;
+
+	if (!pci_enable_ats(pdev, VTD_PAGE_SHIFT))
 		info->ats_enabled = 1;
 }
 
-static void iommu_disable_pci_caps(struct device_domain_info *info)
+static void iommu_disable_pci_ats(struct device_domain_info *info)
+{
+	if (!info->ats_enabled)
+		return;
+
+	pci_disable_ats(to_pci_dev(info->dev));
+	info->ats_enabled = 0;
+}
+
+static void iommu_enable_pci_pri(struct device_domain_info *info)
 {
 	struct pci_dev *pdev;
 
-	if (!dev_is_pci(info->dev))
+	if (!info->ats_enabled || !info->pri_supported)
 		return;
 
 	pdev = to_pci_dev(info->dev);
+	/* PASID is required in PRG Response Message. */
+	if (info->pasid_enabled && !pci_prg_resp_pasid_required(pdev))
+		return;
 
-	if (info->ats_enabled) {
-		pci_disable_ats(pdev);
-		info->ats_enabled = 0;
-	}
+	if (pci_reset_pri(pdev))
+		return;
+
+	if (!pci_enable_pri(pdev, PRQ_DEPTH))
+		info->pri_enabled = 1;
+}
+
+static void iommu_disable_pci_pri(struct device_domain_info *info)
+{
+	if (!info->pri_enabled)
+		return;
+
+	if (WARN_ON(info->iopf_refcount))
+		iopf_queue_remove_device(info->iommu->iopf_queue, info->dev);
+
+	pci_disable_pri(to_pci_dev(info->dev));
+	info->pri_enabled = 0;
 }
 
 static void intel_flush_iotlb_all(struct iommu_domain *domain)
@@ -1556,12 +1584,19 @@ domain_context_mapping(struct dmar_domain *domain, struct device *dev)
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
 	u8 bus = info->bus, devfn = info->devfn;
+	int ret;
 
 	if (!dev_is_pci(dev))
 		return domain_context_mapping_one(domain, iommu, bus, devfn);
 
-	return pci_for_each_dma_alias(to_pci_dev(dev),
-				      domain_context_mapping_cb, domain);
+	ret = pci_for_each_dma_alias(to_pci_dev(dev),
+				     domain_context_mapping_cb, domain);
+	if (ret)
+		return ret;
+
+	iommu_enable_pci_ats(info);
+
+	return 0;
 }
 
 /* Return largest possible superpage level for a given mapping */
@@ -1748,7 +1783,7 @@ static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8
 	context_clear_entry(context);
 	__iommu_flush_cache(iommu, context, sizeof(*context));
 	spin_unlock(&iommu->lock);
-	intel_context_flush_present(info, context, did, true);
+	intel_context_flush_no_pasid(info, context, did);
 }
 
 int __domain_setup_first_level(struct intel_iommu *iommu,
@@ -1843,8 +1878,6 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 	if (ret)
 		goto out_block_translation;
 
-	iommu_enable_pci_caps(info);
-
 	ret = cache_tag_assign_domain(domain, dev, IOMMU_NO_PASID);
 	if (ret)
 		goto out_block_translation;
@@ -2871,16 +2904,19 @@ void intel_iommu_shutdown(void)
 	if (no_iommu || dmar_disabled)
 		return;
 
-	down_write(&dmar_global_lock);
+	/*
+	 * All other CPUs were brought down, hotplug interrupts were disabled,
+	 * no lock and RCU checking needed anymore
+	 */
+	list_for_each_entry(drhd, &dmar_drhd_units, list) {
+		iommu = drhd->iommu;
 
-	/* Disable PMRs explicitly here. */
-	for_each_iommu(iommu, drhd)
+		/* Disable PMRs explicitly here. */
 		iommu_disable_protect_mem_regions(iommu);
 
-	/* Make sure the IOMMUs are switched off */
-	intel_disable_iommus();
-
-	up_write(&dmar_global_lock);
+		/* Make sure the IOMMUs are switched off */
+		iommu_disable_translation(iommu);
+	}
 }
 
 static struct intel_iommu *dev_to_intel_iommu(struct device *dev)
@@ -3013,6 +3049,7 @@ static int __init probe_acpi_namespace_devices(void)
 			if (dev->bus != &acpi_bus_type)
 				continue;
 
+			up_read(&dmar_global_lock);
 			adev = to_acpi_device(dev);
 			mutex_lock(&adev->physical_node_lock);
 			list_for_each_entry(pn,
@@ -3022,6 +3059,7 @@ static int __init probe_acpi_namespace_devices(void)
 					break;
 			}
 			mutex_unlock(&adev->physical_node_lock);
+			down_read(&dmar_global_lock);
 
 			if (ret)
 				return ret;
@@ -3205,6 +3243,7 @@ static void domain_context_clear(struct device_domain_info *info)
 
 	pci_for_each_dma_alias(to_pci_dev(info->dev),
 			       &domain_context_clear_one_cb, info);
+	iommu_disable_pci_ats(info);
 }
 
 /*
@@ -3221,7 +3260,6 @@ void device_block_translation(struct device *dev)
 	if (info->domain)
 		cache_tag_unassign_domain(info->domain, dev, IOMMU_NO_PASID);
 
-	iommu_disable_pci_caps(info);
 	if (!dev_is_real_dma_subdevice(dev)) {
 		if (sm_supported(iommu))
 			intel_pasid_tear_down_entry(iommu, dev,
@@ -3756,6 +3794,10 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 	    !pci_enable_pasid(pdev, info->pasid_supported & ~1))
 		info->pasid_enabled = 1;
 
+	if (sm_supported(iommu))
+		iommu_enable_pci_ats(info);
+	iommu_enable_pci_pri(info);
+
 	return &iommu->iommu;
 free_table:
 	intel_pasid_free_table(dev);
@@ -3772,6 +3814,9 @@ static void intel_iommu_release_device(struct device *dev)
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
 
+	iommu_disable_pci_pri(info);
+	iommu_disable_pci_ats(info);
+
 	if (info->pasid_enabled) {
 		pci_disable_pasid(to_pci_dev(dev));
 		info->pasid_enabled = 0;
@@ -3858,151 +3903,41 @@ static struct iommu_group *intel_iommu_device_group(struct device *dev)
 	return generic_device_group(dev);
 }
 
-static int intel_iommu_enable_sva(struct device *dev)
+int intel_iommu_enable_iopf(struct device *dev)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	struct intel_iommu *iommu;
-
-	if (!info || dmar_disabled)
-		return -EINVAL;
-
-	iommu = info->iommu;
-	if (!iommu)
-		return -EINVAL;
-
-	if (!(iommu->flags & VTD_FLAG_SVM_CAPABLE))
-		return -ENODEV;
-
-	if (!info->pasid_enabled || !info->ats_enabled)
-		return -EINVAL;
-
-	/*
-	 * Devices having device-specific I/O fault handling should not
-	 * support PCI/PRI. The IOMMU side has no means to check the
-	 * capability of device-specific IOPF.  Therefore, IOMMU can only
-	 * default that if the device driver enables SVA on a non-PRI
-	 * device, it will handle IOPF in its own way.
-	 */
-	if (!info->pri_supported)
-		return 0;
-
-	/* Devices supporting PRI should have it enabled. */
-	if (!info->pri_enabled)
-		return -EINVAL;
-
-	return 0;
-}
-
-static int context_flip_pri(struct device_domain_info *info, bool enable)
-{
 	struct intel_iommu *iommu = info->iommu;
-	u8 bus = info->bus, devfn = info->devfn;
-	struct context_entry *context;
-	u16 did;
-
-	spin_lock(&iommu->lock);
-	if (context_copied(iommu, bus, devfn)) {
-		spin_unlock(&iommu->lock);
-		return -EINVAL;
-	}
-
-	context = iommu_context_addr(iommu, bus, devfn, false);
-	if (!context || !context_present(context)) {
-		spin_unlock(&iommu->lock);
-		return -ENODEV;
-	}
-	did = context_domain_id(context);
-
-	if (enable)
-		context_set_sm_pre(context);
-	else
-		context_clear_sm_pre(context);
-
-	if (!ecap_coherent(iommu->ecap))
-		clflush_cache_range(context, sizeof(*context));
-	intel_context_flush_present(info, context, did, true);
-	spin_unlock(&iommu->lock);
-
-	return 0;
-}
-
-static int intel_iommu_enable_iopf(struct device *dev)
-{
-	struct pci_dev *pdev = dev_is_pci(dev) ? to_pci_dev(dev) : NULL;
-	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	struct intel_iommu *iommu;
 	int ret;
 
-	if (!pdev || !info || !info->ats_enabled || !info->pri_supported)
+	if (!info->pri_enabled)
 		return -ENODEV;
 
-	if (info->pri_enabled)
-		return -EBUSY;
-
-	iommu = info->iommu;
-	if (!iommu)
-		return -EINVAL;
-
-	/* PASID is required in PRG Response Message. */
-	if (info->pasid_enabled && !pci_prg_resp_pasid_required(pdev))
-		return -EINVAL;
-
-	ret = pci_reset_pri(pdev);
-	if (ret)
-		return ret;
+	if (info->iopf_refcount) {
+		info->iopf_refcount++;
+		return 0;
+	}
 
 	ret = iopf_queue_add_device(iommu->iopf_queue, dev);
 	if (ret)
 		return ret;
 
-	ret = context_flip_pri(info, true);
-	if (ret)
-		goto err_remove_device;
-
-	ret = pci_enable_pri(pdev, PRQ_DEPTH);
-	if (ret)
-		goto err_clear_pri;
-
-	info->pri_enabled = 1;
+	info->iopf_refcount = 1;
 
 	return 0;
-err_clear_pri:
-	context_flip_pri(info, false);
-err_remove_device:
-	iopf_queue_remove_device(iommu->iopf_queue, dev);
-
-	return ret;
 }
 
-static int intel_iommu_disable_iopf(struct device *dev)
+void intel_iommu_disable_iopf(struct device *dev)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
 
-	if (!info->pri_enabled)
-		return -EINVAL;
+	if (WARN_ON(!info->pri_enabled || !info->iopf_refcount))
+		return;
 
-	/* Disable new PRI reception: */
-	context_flip_pri(info, false);
+	if (--info->iopf_refcount)
+		return;
 
-	/*
-	 * Remove device from fault queue and acknowledge all outstanding
-	 * PRQs to the device:
-	 */
 	iopf_queue_remove_device(iommu->iopf_queue, dev);
-
-	/*
-	 * PCIe spec states that by clearing PRI enable bit, the Page
-	 * Request Interface will not issue new page requests, but has
-	 * outstanding page requests that have been transmitted or are
-	 * queued for transmission. This is supposed to be called after
-	 * the device driver has stopped DMA, all PASIDs have been
-	 * unbound and the outstanding PRQs have been drained.
-	 */
-	pci_disable_pri(to_pci_dev(dev));
-	info->pri_enabled = 0;
-
-	return 0;
 }
 
 static int
@@ -4013,7 +3948,7 @@ intel_iommu_dev_enable_feat(struct device *dev, enum iommu_dev_features feat)
 		return intel_iommu_enable_iopf(dev);
 
 	case IOMMU_DEV_FEAT_SVA:
-		return intel_iommu_enable_sva(dev);
+		return 0;
 
 	default:
 		return -ENODEV;
@@ -4025,7 +3960,8 @@ intel_iommu_dev_disable_feat(struct device *dev, enum iommu_dev_features feat)
 {
 	switch (feat) {
 	case IOMMU_DEV_FEAT_IOPF:
-		return intel_iommu_disable_iopf(dev);
+		intel_iommu_disable_iopf(dev);
+		return 0;
 
 	case IOMMU_DEV_FEAT_SVA:
 		return 0;
@@ -4410,13 +4346,10 @@ static int identity_domain_attach_dev(struct iommu_domain *domain, struct device
 	if (dev_is_real_dma_subdevice(dev))
 		return 0;
 
-	if (sm_supported(iommu)) {
+	if (sm_supported(iommu))
 		ret = intel_pasid_setup_pass_through(iommu, dev, IOMMU_NO_PASID);
-		if (!ret)
-			iommu_enable_pci_caps(info);
-	} else {
+	else
 		ret = device_setup_pass_through(dev);
-	}
 
 	return ret;
 }
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 6ea7bbe26b19..c4916886da5a 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -774,6 +774,7 @@ struct device_domain_info {
 	u8 ats_enabled:1;
 	u8 dtlb_extra_inval:1;	/* Quirk for devices need extra flush */
 	u8 ats_qdep;
+	unsigned int iopf_refcount;
 	struct device *dev; /* it's NULL for PCIe-to-PCI bridge */
 	struct intel_iommu *iommu; /* IOMMU used by this device */
 	struct dmar_domain *domain; /* pointer to domain */
@@ -953,25 +954,6 @@ static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
 	return 1UL << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
 }
 
-/* VT-d pages must always be _smaller_ than MM pages. Otherwise things
-   are never going to work. */
-static inline unsigned long mm_to_dma_pfn_start(unsigned long mm_pfn)
-{
-	return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT);
-}
-static inline unsigned long mm_to_dma_pfn_end(unsigned long mm_pfn)
-{
-	return ((mm_pfn + 1) << (PAGE_SHIFT - VTD_PAGE_SHIFT)) - 1;
-}
-static inline unsigned long page_to_dma_pfn(struct page *pg)
-{
-	return mm_to_dma_pfn_start(page_to_pfn(pg));
-}
-static inline unsigned long virt_to_dma_pfn(void *p)
-{
-	return page_to_dma_pfn(virt_to_page(p));
-}
-
 static inline void context_set_present(struct context_entry *context)
 {
 	context->lo |= 1;
@@ -1304,9 +1286,8 @@ void cache_tag_flush_all(struct dmar_domain *domain);
 void cache_tag_flush_range_np(struct dmar_domain *domain, unsigned long start,
 			      unsigned long end);
 
-void intel_context_flush_present(struct device_domain_info *info,
-				 struct context_entry *context,
-				 u16 did, bool affect_domains);
+void intel_context_flush_no_pasid(struct device_domain_info *info,
+				  struct context_entry *context, u16 did);
 
 int intel_iommu_enable_prq(struct intel_iommu *iommu);
 int intel_iommu_finish_prq(struct intel_iommu *iommu);
@@ -1314,6 +1295,9 @@ void intel_iommu_page_response(struct device *dev, struct iopf_fault *evt,
 			       struct iommu_page_response *msg);
 void intel_iommu_drain_pasid_prq(struct device *dev, u32 pasid);
 
+int intel_iommu_enable_iopf(struct device *dev);
+void intel_iommu_disable_iopf(struct device *dev);
+
 #ifdef CONFIG_INTEL_IOMMU_SVM
 void intel_svm_check(struct intel_iommu *iommu);
 struct iommu_domain *intel_svm_domain_alloc(struct device *dev,
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index ad795c772f21..ea3ca5203919 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -25,11 +25,6 @@
 #include "../irq_remapping.h"
 #include "../iommu-pages.h"
 
-enum irq_mode {
-	IRQ_REMAPPING,
-	IRQ_POSTING,
-};
-
 struct ioapic_scope {
 	struct intel_iommu *iommu;
 	unsigned int id;
@@ -49,8 +44,8 @@ struct irq_2_iommu {
 	u16 irte_index;
 	u16 sub_handle;
 	u8  irte_mask;
-	enum irq_mode mode;
 	bool posted_msi;
+	bool posted_vcpu;
 };
 
 struct intel_ir_data {
@@ -138,7 +133,6 @@ static int alloc_irte(struct intel_iommu *iommu,
 		irq_iommu->irte_index =  index;
 		irq_iommu->sub_handle = 0;
 		irq_iommu->irte_mask = mask;
-		irq_iommu->mode = IRQ_REMAPPING;
 	}
 	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
@@ -193,8 +187,6 @@ static int modify_irte(struct irq_2_iommu *irq_iommu,
 
 	rc = qi_flush_iec(iommu, index, 0);
 
-	/* Update iommu mode according to the IRTE mode */
-	irq_iommu->mode = irte->pst ? IRQ_POSTING : IRQ_REMAPPING;
 	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
 	return rc;
@@ -1169,7 +1161,26 @@ static void intel_ir_reconfigure_irte_posted(struct irq_data *irqd)
 static inline void intel_ir_reconfigure_irte_posted(struct irq_data *irqd) {}
 #endif
 
-static void intel_ir_reconfigure_irte(struct irq_data *irqd, bool force)
+static void __intel_ir_reconfigure_irte(struct irq_data *irqd, bool force_host)
+{
+	struct intel_ir_data *ir_data = irqd->chip_data;
+
+	/*
+	 * Don't modify IRTEs for IRQs that are being posted to vCPUs if the
+	 * host CPU affinity changes.
+	 */
+	if (ir_data->irq_2_iommu.posted_vcpu && !force_host)
+		return;
+
+	ir_data->irq_2_iommu.posted_vcpu = false;
+
+	if (ir_data->irq_2_iommu.posted_msi)
+		intel_ir_reconfigure_irte_posted(irqd);
+	else
+		modify_irte(&ir_data->irq_2_iommu, &ir_data->irte_entry);
+}
+
+static void intel_ir_reconfigure_irte(struct irq_data *irqd, bool force_host)
 {
 	struct intel_ir_data *ir_data = irqd->chip_data;
 	struct irte *irte = &ir_data->irte_entry;
@@ -1182,10 +1193,7 @@ static void intel_ir_reconfigure_irte(struct irq_data *irqd, bool force)
 	irte->vector = cfg->vector;
 	irte->dest_id = IRTE_DEST(cfg->dest_apicid);
 
-	if (ir_data->irq_2_iommu.posted_msi)
-		intel_ir_reconfigure_irte_posted(irqd);
-	else if (force || ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
-		modify_irte(&ir_data->irq_2_iommu, irte);
+	__intel_ir_reconfigure_irte(irqd, force_host);
 }
 
 /*
@@ -1240,7 +1248,7 @@ static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info)
 
 	/* stop posting interrupts, back to the default mode */
 	if (!vcpu_pi_info) {
-		modify_irte(&ir_data->irq_2_iommu, &ir_data->irte_entry);
+		__intel_ir_reconfigure_irte(data, true);
 	} else {
 		struct irte irte_pi;
 
@@ -1263,6 +1271,7 @@ static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info)
 		irte_pi.pda_h = (vcpu_pi_info->pi_desc_addr >> 32) &
 				~(-1UL << PDA_HIGH_BIT);
 
+		ir_data->irq_2_iommu.posted_vcpu = true;
 		modify_irte(&ir_data->irq_2_iommu, &irte_pi);
 	}
 
@@ -1489,6 +1498,9 @@ static void intel_irq_remapping_deactivate(struct irq_domain *domain,
 	struct intel_ir_data *data = irq_data->chip_data;
 	struct irte entry;
 
+	WARN_ON_ONCE(data->irq_2_iommu.posted_vcpu);
+	data->irq_2_iommu.posted_vcpu = false;
+
 	memset(&entry, 0, sizeof(entry));
 	modify_irte(&data->irq_2_iommu, &entry);
 }
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index fb59a7d35958..7ee18bb48bd4 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -932,7 +932,7 @@ static void device_pasid_table_teardown(struct device *dev, u8 bus, u8 devfn)
 	context_clear_entry(context);
 	__iommu_flush_cache(iommu, context, sizeof(*context));
 	spin_unlock(&iommu->lock);
-	intel_context_flush_present(info, context, did, false);
+	intel_context_flush_no_pasid(info, context, did);
 }
 
 static int pci_pasid_table_teardown(struct pci_dev *pdev, u16 alias, void *data)
@@ -992,6 +992,8 @@ static int context_entry_set_pasid_table(struct context_entry *context,
 		context_set_sm_dte(context);
 	if (info->pasid_supported)
 		context_set_pasid(context);
+	if (info->pri_supported)
+		context_set_sm_pre(context);
 
 	context_set_fault_enable(context);
 	context_set_present(context);
@@ -1117,17 +1119,15 @@ static void __context_flush_dev_iotlb(struct device_domain_info *info)
 
 /*
  * Cache invalidations after change in a context table entry that was present
- * according to the Spec 6.5.3.3 (Guidance to Software for Invalidations). If
- * IOMMU is in scalable mode and all PASID table entries of the device were
- * non-present, set flush_domains to false. Otherwise, true.
+ * according to the Spec 6.5.3.3 (Guidance to Software for Invalidations).
+ * This helper can only be used when IOMMU is working in the legacy mode or
+ * IOMMU is in scalable mode but all PASID table entries of the device are
+ * non-present.
  */
-void intel_context_flush_present(struct device_domain_info *info,
-				 struct context_entry *context,
-				 u16 did, bool flush_domains)
+void intel_context_flush_no_pasid(struct device_domain_info *info,
+				  struct context_entry *context, u16 did)
 {
 	struct intel_iommu *iommu = info->iommu;
-	struct pasid_entry *pte;
-	int i;
 
 	/*
 	 * Device-selective context-cache invalidation. The Domain-ID field
@@ -1150,30 +1150,5 @@ void intel_context_flush_present(struct device_domain_info *info,
 		return;
 	}
 
-	/*
-	 * For scalable mode:
-	 * - Domain-selective PASID-cache invalidation to affected domains
-	 * - Domain-selective IOTLB invalidation to affected domains
-	 * - Global Device-TLB invalidation to affected functions
-	 */
-	if (flush_domains) {
-		/*
-		 * If the IOMMU is running in scalable mode and there might
-		 * be potential PASID translations, the caller should hold
-		 * the lock to ensure that context changes and cache flushes
-		 * are atomic.
-		 */
-		assert_spin_locked(&iommu->lock);
-		for (i = 0; i < info->pasid_table->max_pasid; i++) {
-			pte = intel_pasid_get_entry(info->dev, i);
-			if (!pte || !pasid_pte_is_present(pte))
-				continue;
-
-			did = pasid_get_domain_id(pte);
-			qi_flush_pasid_cache(iommu, did, QI_PC_ALL_PASIDS, 0);
-			iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
-		}
-	}
-
 	__context_flush_dev_iotlb(info);
 }
diff --git a/drivers/iommu/intel/prq.c b/drivers/iommu/intel/prq.c
index 064194399b38..5b6a64d96850 100644
--- a/drivers/iommu/intel/prq.c
+++ b/drivers/iommu/intel/prq.c
@@ -67,7 +67,7 @@ void intel_iommu_drain_pasid_prq(struct device *dev, u32 pasid)
 	u16 sid, did;
 
 	info = dev_iommu_priv_get(dev);
-	if (!info->pri_enabled)
+	if (!info->iopf_refcount)
 		return;
 
 	iommu = info->iommu;
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index f5569347591f..ba93123cb4eb 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -110,6 +110,41 @@ static const struct mmu_notifier_ops intel_mmuops = {
 	.free_notifier = intel_mm_free_notifier,
 };
 
+static int intel_iommu_sva_supported(struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu;
+
+	if (!info || dmar_disabled)
+		return -EINVAL;
+
+	iommu = info->iommu;
+	if (!iommu)
+		return -EINVAL;
+
+	if (!(iommu->flags & VTD_FLAG_SVM_CAPABLE))
+		return -ENODEV;
+
+	if (!info->pasid_enabled || !info->ats_enabled)
+		return -EINVAL;
+
+	/*
+	 * Devices having device-specific I/O fault handling should not
+	 * support PCI/PRI. The IOMMU side has no means to check the
+	 * capability of device-specific IOPF.  Therefore, IOMMU can only
+	 * default that if the device driver enables SVA on a non-PRI
+	 * device, it will handle IOPF in its own way.
+	 */
+	if (!info->pri_supported)
+		return 0;
+
+	/* Devices supporting PRI should have it enabled. */
+	if (!info->pri_enabled)
+		return -EINVAL;
+
+	return 0;
+}
+
 static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 				   struct device *dev, ioasid_t pasid,
 				   struct iommu_domain *old)
@@ -121,6 +156,10 @@ static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 	unsigned long sflags;
 	int ret = 0;
 
+	ret = intel_iommu_sva_supported(dev);
+	if (ret)
+		return ret;
+
 	dev_pasid = domain_add_dev_pasid(domain, dev, pasid);
 	if (IS_ERR(dev_pasid))
 		return PTR_ERR(dev_pasid);
@@ -161,6 +200,10 @@ struct iommu_domain *intel_svm_domain_alloc(struct device *dev,
 	struct dmar_domain *domain;
 	int ret;
 
+	ret = intel_iommu_sva_supported(dev);
+	if (ret)
+		return ERR_PTR(ret);
+
 	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
 	if (!domain)
 		return ERR_PTR(-ENOMEM);