1 files changed, 311 insertions, 149 deletions

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 788119c5b021..ee0932307d64 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -38,17 +38,16 @@
 #include <linux/dmi.h>
 #include <linux/pci-ats.h>
 #include <linux/memblock.h>
-#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/crash_dump.h>
 #include <linux/numa.h>
 #include <asm/irq_remapping.h>
 #include <asm/cacheflush.h>
 #include <asm/iommu.h>
-#include <trace/events/intel_iommu.h>
 
 #include "../irq_remapping.h"
 #include "pasid.h"
+#include "cap_audit.h"
 
 #define ROOT_SIZE		VTD_PAGE_SIZE
 #define CONTEXT_SIZE		VTD_PAGE_SIZE
@@ -317,8 +316,18 @@ struct dmar_atsr_unit {
 	u8 include_all:1;		/* include all ports */
 };
 
+struct dmar_satc_unit {
+	struct list_head list;		/* list of SATC units */
+	struct acpi_dmar_header *hdr;	/* ACPI header */
+	struct dmar_dev_scope *devices;	/* target devices */
+	struct intel_iommu *iommu;	/* the corresponding iommu */
+	int devices_cnt;		/* target device count */
+	u8 atc_required:1;		/* ATS is required */
+};
+
 static LIST_HEAD(dmar_atsr_units);
 static LIST_HEAD(dmar_rmrr_units);
+static LIST_HEAD(dmar_satc_units);
 
 #define for_each_rmrr_units(rmrr) \
 	list_for_each_entry(rmrr, &dmar_rmrr_units, list)
@@ -719,6 +728,8 @@ static int domain_update_device_node(struct dmar_domain *domain)
 	return nid;
 }
 
+static void domain_update_iotlb(struct dmar_domain *domain);
+
 /* Some capabilities may be different across iommus */
 static void domain_update_iommu_cap(struct dmar_domain *domain)
 {
@@ -744,6 +755,8 @@ static void domain_update_iommu_cap(struct dmar_domain *domain)
 		domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw - 1);
 	else
 		domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw);
+
+	domain_update_iotlb(domain);
 }
 
 struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
@@ -1014,8 +1027,11 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 
 			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;
-			if (domain_use_first_level(domain))
+			if (domain_use_first_level(domain)) {
 				pteval |= DMA_FL_PTE_XD | DMA_FL_PTE_US;
+				if (domain->domain.type == IOMMU_DOMAIN_DMA)
+					pteval |= DMA_FL_PTE_ACCESS;
+			}
 			if (cmpxchg64(&pte->val, 0ULL, pteval))
 				/* Someone else set it while we were thinking; use theirs. */
 				free_pgtable_page(tmp_page);
@@ -1464,17 +1480,22 @@ static void domain_update_iotlb(struct dmar_domain *domain)
 
 	assert_spin_locked(&device_domain_lock);
 
-	list_for_each_entry(info, &domain->devices, link) {
-		struct pci_dev *pdev;
-
-		if (!info->dev || !dev_is_pci(info->dev))
-			continue;
-
-		pdev = to_pci_dev(info->dev);
-		if (pdev->ats_enabled) {
+	list_for_each_entry(info, &domain->devices, link)
+		if (info->ats_enabled) {
 			has_iotlb_device = true;
 			break;
 		}
+
+	if (!has_iotlb_device) {
+		struct subdev_domain_info *sinfo;
+
+		list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
+			info = get_domain_info(sinfo->pdev);
+			if (info && info->ats_enabled) {
+				has_iotlb_device = true;
+				break;
+			}
+		}
 	}
 
 	domain->has_iotlb_device = has_iotlb_device;
@@ -1555,25 +1576,37 @@ static void iommu_disable_dev_iotlb(struct device_domain_info *info)
 #endif
 }
 
+static void __iommu_flush_dev_iotlb(struct device_domain_info *info,
+				    u64 addr, unsigned int mask)
+{
+	u16 sid, qdep;
+
+	if (!info || !info->ats_enabled)
+		return;
+
+	sid = info->bus << 8 | info->devfn;
+	qdep = info->ats_qdep;
+	qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
+			   qdep, addr, mask);
+}
+
 static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 				  u64 addr, unsigned mask)
 {
-	u16 sid, qdep;
 	unsigned long flags;
 	struct device_domain_info *info;
+	struct subdev_domain_info *sinfo;
 
 	if (!domain->has_iotlb_device)
 		return;
 
 	spin_lock_irqsave(&device_domain_lock, flags);
-	list_for_each_entry(info, &domain->devices, link) {
-		if (!info->ats_enabled)
-			continue;
+	list_for_each_entry(info, &domain->devices, link)
+		__iommu_flush_dev_iotlb(info, addr, mask);
 
-		sid = info->bus << 8 | info->devfn;
-		qdep = info->ats_qdep;
-		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
-				qdep, addr, mask);
+	list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
+		info = get_domain_info(sinfo->pdev);
+		__iommu_flush_dev_iotlb(info, addr, mask);
 	}
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
@@ -1841,25 +1874,7 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
  */
 static bool first_level_by_default(void)
 {
-	struct dmar_drhd_unit *drhd;
-	struct intel_iommu *iommu;
-	static int first_level_support = -1;
-
-	if (likely(first_level_support != -1))
-		return first_level_support;
-
-	first_level_support = 1;
-
-	rcu_read_lock();
-	for_each_active_iommu(iommu, drhd) {
-		if (!sm_supported(iommu) || !ecap_flts(iommu->ecap)) {
-			first_level_support = 0;
-			break;
-		}
-	}
-	rcu_read_unlock();
-
-	return first_level_support;
+	return scalable_mode_support() && intel_cap_flts_sanity();
 }
 
 static struct dmar_domain *alloc_domain(int flags)
@@ -1877,6 +1892,7 @@ static struct dmar_domain *alloc_domain(int flags)
 		domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL;
 	domain->has_iotlb_device = false;
 	INIT_LIST_HEAD(&domain->devices);
+	INIT_LIST_HEAD(&domain->subdevices);
 
 	return domain;
 }
@@ -2277,9 +2293,9 @@ static int
 __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 		 unsigned long phys_pfn, unsigned long nr_pages, int prot)
 {
-	struct dma_pte *first_pte = NULL, *pte = NULL;
 	unsigned int largepage_lvl = 0;
 	unsigned long lvl_pages = 0;
+	struct dma_pte *pte = NULL;
 	phys_addr_t pteval;
 	u64 attr;
 
@@ -2289,9 +2305,16 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 		return -EINVAL;
 
 	attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP);
-	if (domain_use_first_level(domain))
+	if (domain_use_first_level(domain)) {
 		attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD | DMA_FL_PTE_US;
 
+		if (domain->domain.type == IOMMU_DOMAIN_DMA) {
+			attr |= DMA_FL_PTE_ACCESS;
+			if (prot & DMA_PTE_WRITE)
+				attr |= DMA_FL_PTE_DIRTY;
+		}
+	}
+
 	pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | attr;
 
 	while (nr_pages > 0) {
@@ -2301,7 +2324,7 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			largepage_lvl = hardware_largepage_caps(domain, iov_pfn,
 					phys_pfn, nr_pages);
 
-			first_pte = pte = pfn_to_dma_pte(domain, iov_pfn, &largepage_lvl);
+			pte = pfn_to_dma_pte(domain, iov_pfn, &largepage_lvl);
 			if (!pte)
 				return -ENOMEM;
 			/* It is large page*/
@@ -2362,34 +2385,14 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 		 * recalculate 'pte' and switch back to smaller pages for the
 		 * end of the mapping, if the trailing size is not enough to
 		 * use another superpage (i.e. nr_pages < lvl_pages).
+		 *
+		 * We leave clflush for the leaf pte changes to iotlb_sync_map()
+		 * callback.
 		 */
 		pte++;
 		if (!nr_pages || first_pte_in_page(pte) ||
-		    (largepage_lvl > 1 && nr_pages < lvl_pages)) {
-			domain_flush_cache(domain, first_pte,
-					   (void *)pte - (void *)first_pte);
+		    (largepage_lvl > 1 && nr_pages < lvl_pages))
 			pte = NULL;
-		}
-	}
-
-	return 0;
-}
-
-static int
-domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
-	       unsigned long phys_pfn, unsigned long nr_pages, int prot)
-{
-	int iommu_id, ret;
-	struct intel_iommu *iommu;
-
-	/* Do the real mapping first */
-	ret = __domain_mapping(domain, iov_pfn, phys_pfn, nr_pages, prot);
-	if (ret)
-		return ret;
-
-	for_each_domain_iommu(iommu_id, domain) {
-		iommu = g_iommus[iommu_id];
-		__mapping_notify_one(iommu, domain, iov_pfn, nr_pages);
 	}
 
 	return 0;
@@ -2547,7 +2550,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 	info->iommu = iommu;
 	info->pasid_table = NULL;
 	info->auxd_enabled = 0;
-	INIT_LIST_HEAD(&info->auxiliary_domains);
+	INIT_LIST_HEAD(&info->subdevices);
 
 	if (dev && dev_is_pci(dev)) {
 		struct pci_dev *pdev = to_pci_dev(info->dev);
@@ -3176,6 +3179,10 @@ static int __init init_dmars(void)
 		goto error;
 	}
 
+	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);
@@ -3719,6 +3726,57 @@ int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg)
 	return 0;
 }
 
+static struct dmar_satc_unit *dmar_find_satc(struct acpi_dmar_satc *satc)
+{
+	struct dmar_satc_unit *satcu;
+	struct acpi_dmar_satc *tmp;
+
+	list_for_each_entry_rcu(satcu, &dmar_satc_units, list,
+				dmar_rcu_check()) {
+		tmp = (struct acpi_dmar_satc *)satcu->hdr;
+		if (satc->segment != tmp->segment)
+			continue;
+		if (satc->header.length != tmp->header.length)
+			continue;
+		if (memcmp(satc, tmp, satc->header.length) == 0)
+			return satcu;
+	}
+
+	return NULL;
+}
+
+int dmar_parse_one_satc(struct acpi_dmar_header *hdr, void *arg)
+{
+	struct acpi_dmar_satc *satc;
+	struct dmar_satc_unit *satcu;
+
+	if (system_state >= SYSTEM_RUNNING && !intel_iommu_enabled)
+		return 0;
+
+	satc = container_of(hdr, struct acpi_dmar_satc, header);
+	satcu = dmar_find_satc(satc);
+	if (satcu)
+		return 0;
+
+	satcu = kzalloc(sizeof(*satcu) + hdr->length, GFP_KERNEL);
+	if (!satcu)
+		return -ENOMEM;
+
+	satcu->hdr = (void *)(satcu + 1);
+	memcpy(satcu->hdr, hdr, hdr->length);
+	satcu->atc_required = satc->flags & 0x1;
+	satcu->devices = dmar_alloc_dev_scope((void *)(satc + 1),
+					      (void *)satc + satc->header.length,
+					      &satcu->devices_cnt);
+	if (satcu->devices_cnt && !satcu->devices) {
+		kfree(satcu);
+		return -ENOMEM;
+	}
+	list_add_rcu(&satcu->list, &dmar_satc_units);
+
+	return 0;
+}
+
 static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
 {
 	int sp, ret;
@@ -3727,6 +3785,10 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
 	if (g_iommus[iommu->seq_id])
 		return 0;
 
+	ret = intel_cap_audit(CAP_AUDIT_HOTPLUG_DMAR, iommu);
+	if (ret)
+		goto out;
+
 	if (hw_pass_through && !ecap_pass_through(iommu->ecap)) {
 		pr_warn("%s: Doesn't support hardware pass through.\n",
 			iommu->name);
@@ -3822,6 +3884,7 @@ static void intel_iommu_free_dmars(void)
 {
 	struct dmar_rmrr_unit *rmrru, *rmrr_n;
 	struct dmar_atsr_unit *atsru, *atsr_n;
+	struct dmar_satc_unit *satcu, *satc_n;
 
 	list_for_each_entry_safe(rmrru, rmrr_n, &dmar_rmrr_units, list) {
 		list_del(&rmrru->list);
@@ -3833,6 +3896,11 @@ static void intel_iommu_free_dmars(void)
 		list_del(&atsru->list);
 		intel_iommu_free_atsr(atsru);
 	}
+	list_for_each_entry_safe(satcu, satc_n, &dmar_satc_units, list) {
+		list_del(&satcu->list);
+		dmar_free_dev_scope(&satcu->devices, &satcu->devices_cnt);
+		kfree(satcu);
+	}
 }
 
 int dmar_find_matched_atsr_unit(struct pci_dev *dev)
@@ -3884,8 +3952,10 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 	int ret;
 	struct dmar_rmrr_unit *rmrru;
 	struct dmar_atsr_unit *atsru;
+	struct dmar_satc_unit *satcu;
 	struct acpi_dmar_atsr *atsr;
 	struct acpi_dmar_reserved_memory *rmrr;
+	struct acpi_dmar_satc *satc;
 
 	if (!intel_iommu_enabled && system_state >= SYSTEM_RUNNING)
 		return 0;
@@ -3926,6 +3996,23 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 				break;
 		}
 	}
+	list_for_each_entry(satcu, &dmar_satc_units, list) {
+		satc = container_of(satcu->hdr, struct acpi_dmar_satc, header);
+		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
+			ret = dmar_insert_dev_scope(info, (void *)(satc + 1),
+					(void *)satc + satc->header.length,
+					satc->segment, satcu->devices,
+					satcu->devices_cnt);
+			if (ret > 0)
+				break;
+			else if (ret < 0)
+				return ret;
+		} else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) {
+			if (dmar_remove_dev_scope(info, satc->segment,
+					satcu->devices, satcu->devices_cnt))
+				break;
+		}
+	}
 
 	return 0;
 }
@@ -4269,6 +4356,9 @@ int __init intel_iommu_init(void)
 	if (list_empty(&dmar_atsr_units))
 		pr_info("No ATSR found\n");
 
+	if (list_empty(&dmar_satc_units))
+		pr_info("No SATC found\n");
+
 	if (dmar_map_gfx)
 		intel_iommu_gfx_mapped = 1;
 
@@ -4475,33 +4565,61 @@ is_aux_domain(struct device *dev, struct iommu_domain *domain)
 			domain->type == IOMMU_DOMAIN_UNMANAGED;
 }
 
-static void auxiliary_link_device(struct dmar_domain *domain,
-				  struct device *dev)
+static inline struct subdev_domain_info *
+lookup_subdev_info(struct dmar_domain *domain, struct device *dev)
+{
+	struct subdev_domain_info *sinfo;
+
+	if (!list_empty(&domain->subdevices)) {
+		list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
+			if (sinfo->pdev == dev)
+				return sinfo;
+		}
+	}
+
+	return NULL;
+}
+
+static int auxiliary_link_device(struct dmar_domain *domain,
+				 struct device *dev)
 {
 	struct device_domain_info *info = get_domain_info(dev);
+	struct subdev_domain_info *sinfo = lookup_subdev_info(domain, dev);
 
 	assert_spin_locked(&device_domain_lock);
 	if (WARN_ON(!info))
-		return;
+		return -EINVAL;
 
-	domain->auxd_refcnt++;
-	list_add(&domain->auxd, &info->auxiliary_domains);
+	if (!sinfo) {
+		sinfo = kzalloc(sizeof(*sinfo), GFP_ATOMIC);
+		sinfo->domain = domain;
+		sinfo->pdev = dev;
+		list_add(&sinfo->link_phys, &info->subdevices);
+		list_add(&sinfo->link_domain, &domain->subdevices);
+	}
+
+	return ++sinfo->users;
 }
 
-static void auxiliary_unlink_device(struct dmar_domain *domain,
-				    struct device *dev)
+static int auxiliary_unlink_device(struct dmar_domain *domain,
+				   struct device *dev)
 {
 	struct device_domain_info *info = get_domain_info(dev);
+	struct subdev_domain_info *sinfo = lookup_subdev_info(domain, dev);
+	int ret;
 
 	assert_spin_locked(&device_domain_lock);
-	if (WARN_ON(!info))
-		return;
+	if (WARN_ON(!info || !sinfo || sinfo->users <= 0))
+		return -EINVAL;
 
-	list_del(&domain->auxd);
-	domain->auxd_refcnt--;
+	ret = --sinfo->users;
+	if (!ret) {
+		list_del(&sinfo->link_phys);
+		list_del(&sinfo->link_domain);
+		kfree(sinfo);
+	}
 
-	if (!domain->auxd_refcnt && domain->default_pasid > 0)
-		ioasid_put(domain->default_pasid);
+	return ret;
 }
 
 static int aux_domain_add_dev(struct dmar_domain *domain,
@@ -4530,6 +4648,19 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 	}
 
 	spin_lock_irqsave(&device_domain_lock, flags);
+	ret = auxiliary_link_device(domain, dev);
+	if (ret <= 0)
+		goto link_failed;
+
+	/*
+	 * Subdevices from the same physical device can be attached to the
+	 * same domain. For such cases, only the first subdevice attachment
+	 * needs to go through the full steps in this function. So if ret >
+	 * 1, just goto out.
+	 */
+	if (ret > 1)
+		goto out;
+
 	/*
 	 * iommu->lock must be held to attach domain to iommu and setup the
 	 * pasid entry for second level translation.
@@ -4548,10 +4679,9 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 						     domain->default_pasid);
 	if (ret)
 		goto table_failed;
-	spin_unlock(&iommu->lock);
-
-	auxiliary_link_device(domain, dev);
 
+	spin_unlock(&iommu->lock);
+out:
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
 	return 0;
@@ -4560,8 +4690,10 @@ table_failed:
 	domain_detach_iommu(domain, iommu);
 attach_failed:
 	spin_unlock(&iommu->lock);
+	auxiliary_unlink_device(domain, dev);
+link_failed:
 	spin_unlock_irqrestore(&device_domain_lock, flags);
-	if (!domain->auxd_refcnt && domain->default_pasid > 0)
+	if (list_empty(&domain->subdevices) && domain->default_pasid > 0)
 		ioasid_put(domain->default_pasid);
 
 	return ret;
@@ -4581,14 +4713,18 @@ static void aux_domain_remove_dev(struct dmar_domain *domain,
 	info = get_domain_info(dev);
 	iommu = info->iommu;
 
-	auxiliary_unlink_device(domain, dev);
-
-	spin_lock(&iommu->lock);
-	intel_pasid_tear_down_entry(iommu, dev, domain->default_pasid, false);
-	domain_detach_iommu(domain, iommu);
-	spin_unlock(&iommu->lock);
+	if (!auxiliary_unlink_device(domain, dev)) {
+		spin_lock(&iommu->lock);
+		intel_pasid_tear_down_entry(iommu, dev,
+					    domain->default_pasid, false);
+		domain_detach_iommu(domain, iommu);
+		spin_unlock(&iommu->lock);
+	}
 
 	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	if (list_empty(&domain->subdevices) && domain->default_pasid > 0)
+		ioasid_put(domain->default_pasid);
 }
 
 static int prepare_domain_attach_device(struct iommu_domain *domain,
@@ -4876,7 +5012,6 @@ static int intel_iommu_map(struct iommu_domain *domain,
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	u64 max_addr;
 	int prot = 0;
-	int ret;
 
 	if (iommu_prot & IOMMU_READ)
 		prot |= DMA_PTE_READ;
@@ -4902,9 +5037,8 @@ static int intel_iommu_map(struct iommu_domain *domain,
 	/* Round up size to next multiple of PAGE_SIZE, if it and
 	   the low bits of hpa would take us onto the next page */
 	size = aligned_nrpages(hpa, size);
-	ret = domain_mapping(dmar_domain, iova >> VTD_PAGE_SHIFT,
-			     hpa >> VTD_PAGE_SHIFT, size, prot);
-	return ret;
+	return __domain_mapping(dmar_domain, iova >> VTD_PAGE_SHIFT,
+				hpa >> VTD_PAGE_SHIFT, size, prot);
 }
 
 static size_t intel_iommu_unmap(struct iommu_domain *domain,
@@ -4973,60 +5107,6 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	return phys;
 }
 
-static inline bool scalable_mode_support(void)
-{
-	struct dmar_drhd_unit *drhd;
-	struct intel_iommu *iommu;
-	bool ret = true;
-
-	rcu_read_lock();
-	for_each_active_iommu(iommu, drhd) {
-		if (!sm_supported(iommu)) {
-			ret = false;
-			break;
-		}
-	}
-	rcu_read_unlock();
-
-	return ret;
-}
-
-static inline bool iommu_pasid_support(void)
-{
-	struct dmar_drhd_unit *drhd;
-	struct intel_iommu *iommu;
-	bool ret = true;
-
-	rcu_read_lock();
-	for_each_active_iommu(iommu, drhd) {
-		if (!pasid_supported(iommu)) {
-			ret = false;
-			break;
-		}
-	}
-	rcu_read_unlock();
-
-	return ret;
-}
-
-static inline bool nested_mode_support(void)
-{
-	struct dmar_drhd_unit *drhd;
-	struct intel_iommu *iommu;
-	bool ret = true;
-
-	rcu_read_lock();
-	for_each_active_iommu(iommu, drhd) {
-		if (!sm_supported(iommu) || !ecap_nest(iommu->ecap)) {
-			ret = false;
-			break;
-		}
-	}
-	rcu_read_unlock();
-
-	return ret;
-}
-
 static bool intel_iommu_capable(enum iommu_cap cap)
 {
 	if (cap == IOMMU_CAP_CACHE_COHERENCY)
@@ -5267,7 +5347,7 @@ intel_iommu_dev_has_feat(struct device *dev, enum iommu_dev_features feat)
 		int ret;
 
 		if (!dev_is_pci(dev) || dmar_disabled ||
-		    !scalable_mode_support() || !iommu_pasid_support())
+		    !scalable_mode_support() || !pasid_mode_support())
 			return false;
 
 		ret = pci_pasid_features(to_pci_dev(dev));
@@ -5373,6 +5453,36 @@ intel_iommu_domain_set_attr(struct iommu_domain *domain,
 	return ret;
 }
 
+static bool domain_use_flush_queue(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	bool r = true;
+
+	if (intel_iommu_strict)
+		return false;
+
+	/*
+	 * The flush queue implementation does not perform page-selective
+	 * invalidations that are required for efficient TLB flushes in virtual
+	 * environments. The benefit of batching is likely to be much lower than
+	 * the overhead of synchronizing the virtual and physical IOMMU
+	 * page-tables.
+	 */
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (!cap_caching_mode(iommu->cap))
+			continue;
+
+		pr_warn_once("IOMMU batching is disabled due to virtualization");
+		r = false;
+		break;
+	}
+	rcu_read_unlock();
+
+	return r;
+}
+
 static int
 intel_iommu_domain_get_attr(struct iommu_domain *domain,
 			    enum iommu_attr attr, void *data)
@@ -5383,7 +5493,7 @@ intel_iommu_domain_get_attr(struct iommu_domain *domain,
 	case IOMMU_DOMAIN_DMA:
 		switch (attr) {
 		case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
-			*(int *)data = !intel_iommu_strict;
+			*(int *)data = domain_use_flush_queue();
 			return 0;
 		default:
 			return -ENODEV;
@@ -5411,6 +5521,57 @@ static bool risky_device(struct pci_dev *pdev)
 	return false;
 }
 
+static void clflush_sync_map(struct dmar_domain *domain, unsigned long clf_pfn,
+			     unsigned long clf_pages)
+{
+	struct dma_pte *first_pte = NULL, *pte = NULL;
+	unsigned long lvl_pages = 0;
+	int level = 0;
+
+	while (clf_pages > 0) {
+		if (!pte) {
+			level = 0;
+			pte = pfn_to_dma_pte(domain, clf_pfn, &level);
+			if (WARN_ON(!pte))
+				return;
+			first_pte = pte;
+			lvl_pages = lvl_to_nr_pages(level);
+		}
+
+		if (WARN_ON(!lvl_pages || clf_pages < lvl_pages))
+			return;
+
+		clf_pages -= lvl_pages;
+		clf_pfn += lvl_pages;
+		pte++;
+
+		if (!clf_pages || first_pte_in_page(pte) ||
+		    (level > 1 && clf_pages < lvl_pages)) {
+			domain_flush_cache(domain, first_pte,
+					   (void *)pte - (void *)first_pte);
+			pte = NULL;
+		}
+	}
+}
+
+static void intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
+				       unsigned long iova, size_t size)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	unsigned long pages = aligned_nrpages(iova, size);
+	unsigned long pfn = iova >> VTD_PAGE_SHIFT;
+	struct intel_iommu *iommu;
+	int iommu_id;
+
+	if (!dmar_domain->iommu_coherency)
+		clflush_sync_map(dmar_domain, pfn, pages);
+
+	for_each_domain_iommu(iommu_id, dmar_domain) {
+		iommu = g_iommus[iommu_id];
+		__mapping_notify_one(iommu, dmar_domain, pfn, pages);
+	}
+}
+
 const struct iommu_ops intel_iommu_ops = {
 	.capable		= intel_iommu_capable,
 	.domain_alloc		= intel_iommu_domain_alloc,
@@ -5423,6 +5584,7 @@ const struct iommu_ops intel_iommu_ops = {
 	.aux_detach_dev		= intel_iommu_aux_detach_device,
 	.aux_get_pasid		= intel_iommu_aux_get_pasid,
 	.map			= intel_iommu_map,
+	.iotlb_sync_map		= intel_iommu_iotlb_sync_map,
 	.unmap			= intel_iommu_unmap,
 	.flush_iotlb_all        = intel_flush_iotlb_all,
 	.iotlb_sync		= intel_iommu_tlb_sync,