1 files changed, 109 insertions, 190 deletions
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 79e0da9eb626..ec2f385ae25b 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -29,7 +29,6 @@
 #include "../irq_remapping.h"
 #include "../iommu-pages.h"
 #include "pasid.h"
-#include "cap_audit.h"
 #include "perfmon.h"
 
 #define ROOT_SIZE		VTD_PAGE_SIZE
@@ -738,7 +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;
 
@@ -1173,32 +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)
@@ -1557,12 +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 */
@@ -1749,7 +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,
@@ -1844,8 +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;
@@ -2118,10 +2150,6 @@ static int __init init_dmars(void)
 	struct intel_iommu *iommu;
 	int ret;
 
-	ret = intel_cap_audit(CAP_AUDIT_STATIC_DMAR, NULL);
-	if (ret)
-		goto free_iommu;
-
 	for_each_iommu(iommu, drhd) {
 		if (drhd->ignored) {
 			iommu_disable_translation(iommu);
@@ -2617,10 +2645,6 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
 	struct intel_iommu *iommu = dmaru->iommu;
 	int ret;
 
-	ret = intel_cap_audit(CAP_AUDIT_HOTPLUG_DMAR, iommu);
-	if (ret)
-		goto out;
-
 	/*
 	 * Disable translation if already enabled prior to OS handover.
 	 */
@@ -2880,16 +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)
@@ -3022,6 +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,
@@ -3031,6 +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;
@@ -3155,7 +3184,14 @@ int __init intel_iommu_init(void)
 		iommu_device_sysfs_add(&iommu->iommu, NULL,
 				       intel_iommu_groups,
 				       "%s", iommu->name);
+		/*
+		 * The iommu device probe is protected by the iommu_probe_device_lock.
+		 * Release the dmar_global_lock before entering the device probe path
+		 * to avoid unnecessary lock order splat.
+		 */
+		up_read(&dmar_global_lock);
 		iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL);
+		down_read(&dmar_global_lock);
 
 		iommu_pmu_register(iommu);
 	}
@@ -3207,6 +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);
 }
 
 /*
@@ -3223,7 +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,
@@ -3250,10 +3286,15 @@ static int blocking_domain_attach_dev(struct iommu_domain *domain,
 	return 0;
 }
 
+static int blocking_domain_set_dev_pasid(struct iommu_domain *domain,
+					 struct device *dev, ioasid_t pasid,
+					 struct iommu_domain *old);
+
 static struct iommu_domain blocking_domain = {
 	.type = IOMMU_DOMAIN_BLOCKED,
 	.ops = &(const struct iommu_domain_ops) {
 		.attach_dev	= blocking_domain_attach_dev,
+		.set_dev_pasid	= blocking_domain_set_dev_pasid,
 	}
 };
 
@@ -3342,8 +3383,7 @@ intel_iommu_domain_alloc_paging_flags(struct device *dev, u32 flags,
 	bool first_stage;
 
 	if (flags &
-	    (~(IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING
-	       | IOMMU_HWPT_FAULT_ID_VALID)))
+	    (~(IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING)))
 		return ERR_PTR(-EOPNOTSUPP);
 	if (nested_parent && !nested_supported(iommu))
 		return ERR_PTR(-EOPNOTSUPP);
@@ -3754,6 +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);
@@ -3770,6 +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;
@@ -3856,151 +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
@@ -4011,7 +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;
@@ -4023,7 +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;
@@ -4090,22 +4028,26 @@ void domain_remove_dev_pasid(struct iommu_domain *domain,
 			break;
 		}
 	}
-	WARN_ON_ONCE(!dev_pasid);
 	spin_unlock_irqrestore(&dmar_domain->lock, flags);
 
 	cache_tag_unassign_domain(dmar_domain, dev, pasid);
 	domain_detach_iommu(dmar_domain, iommu);
-	intel_iommu_debugfs_remove_dev_pasid(dev_pasid);
-	kfree(dev_pasid);
+	if (!WARN_ON_ONCE(!dev_pasid)) {
+		intel_iommu_debugfs_remove_dev_pasid(dev_pasid);
+		kfree(dev_pasid);
+	}
 }
 
-static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid,
-					 struct iommu_domain *domain)
+static int blocking_domain_set_dev_pasid(struct iommu_domain *domain,
+					 struct device *dev, ioasid_t pasid,
+					 struct iommu_domain *old)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 
 	intel_pasid_tear_down_entry(info->iommu, dev, pasid, false);
-	domain_remove_dev_pasid(domain, dev, pasid);
+	domain_remove_dev_pasid(old, dev, pasid);
+
+	return 0;
 }
 
 struct dev_pasid_info *
@@ -4379,9 +4321,6 @@ static int context_setup_pass_through_cb(struct pci_dev *pdev, u16 alias, void *
 {
 	struct device *dev = data;
 
-	if (dev != &pdev->dev)
-		return 0;
-
 	return context_setup_pass_through(dev, PCI_BUS_NUM(alias), alias & 0xff);
 }
 
@@ -4407,13 +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;
 }
@@ -4445,21 +4381,6 @@ static struct iommu_domain identity_domain = {
 	},
 };
 
-static struct iommu_domain *intel_iommu_domain_alloc_paging(struct device *dev)
-{
-	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	struct intel_iommu *iommu = info->iommu;
-	struct dmar_domain *dmar_domain;
-	bool first_stage;
-
-	first_stage = first_level_by_default(iommu);
-	dmar_domain = paging_domain_alloc(dev, first_stage);
-	if (IS_ERR(dmar_domain))
-		return ERR_CAST(dmar_domain);
-
-	return &dmar_domain->domain;
-}
-
 const struct iommu_ops intel_iommu_ops = {
 	.blocked_domain		= &blocking_domain,
 	.release_domain		= &blocking_domain,
@@ -4468,7 +4389,6 @@ const struct iommu_ops intel_iommu_ops = {
 	.hw_info		= intel_iommu_hw_info,
 	.domain_alloc_paging_flags = intel_iommu_domain_alloc_paging_flags,
 	.domain_alloc_sva	= intel_svm_domain_alloc,
-	.domain_alloc_paging	= intel_iommu_domain_alloc_paging,
 	.domain_alloc_nested	= intel_iommu_domain_alloc_nested,
 	.probe_device		= intel_iommu_probe_device,
 	.release_device		= intel_iommu_release_device,
@@ -4478,7 +4398,6 @@ const struct iommu_ops intel_iommu_ops = {
 	.dev_disable_feat	= intel_iommu_dev_disable_feat,
 	.is_attach_deferred	= intel_iommu_is_attach_deferred,
 	.def_domain_type	= device_def_domain_type,
-	.remove_dev_pasid	= intel_iommu_remove_dev_pasid,
 	.pgsize_bitmap		= SZ_4K,
 	.page_response		= intel_iommu_page_response,
 	.default_domain_ops = &(const struct iommu_domain_ops) {