3 files changed, 38 insertions, 4 deletions

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 038a66388564..b300f72cf01e 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1957,6 +1957,18 @@ static bool dev_is_real_dma_subdevice(struct device *dev)
 	       pci_real_dma_dev(to_pci_dev(dev)) != to_pci_dev(dev);
 }
 
+static bool domain_need_iotlb_sync_map(struct dmar_domain *domain,
+				       struct intel_iommu *iommu)
+{
+	if (cap_caching_mode(iommu->cap) && !domain->use_first_level)
+		return true;
+
+	if (rwbf_quirk || cap_rwbf(iommu->cap))
+		return true;
+
+	return false;
+}
+
 static int dmar_domain_attach_device(struct dmar_domain *domain,
 				     struct device *dev)
 {
@@ -1970,6 +1982,7 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 		return ret;
 
 	info->domain = domain;
+	info->domain_attached = true;
 	spin_lock_irqsave(&domain->lock, flags);
 	list_add(&info->link, &domain->devices);
 	spin_unlock_irqrestore(&domain->lock, flags);
@@ -1993,6 +2006,8 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 	if (ret)
 		goto out_block_translation;
 
+	domain->iotlb_sync_map |= domain_need_iotlb_sync_map(domain, iommu);
+
 	return 0;
 
 out_block_translation:
@@ -3381,6 +3396,10 @@ void device_block_translation(struct device *dev)
 	struct intel_iommu *iommu = info->iommu;
 	unsigned long flags;
 
+	/* Device in DMA blocking state. Noting to do. */
+	if (!info->domain_attached)
+		return;
+
 	if (info->domain)
 		cache_tag_unassign_domain(info->domain, dev, IOMMU_NO_PASID);
 
@@ -3393,6 +3412,9 @@ void device_block_translation(struct device *dev)
 			domain_context_clear(info);
 	}
 
+	/* Device now in DMA blocking state. */
+	info->domain_attached = false;
+
 	if (!info->domain)
 		return;
 
@@ -4270,7 +4292,10 @@ static bool risky_device(struct pci_dev *pdev)
 static int intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 				      unsigned long iova, size_t size)
 {
-	cache_tag_flush_range_np(to_dmar_domain(domain), iova, iova + size - 1);
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+
+	if (dmar_domain->iotlb_sync_map)
+		cache_tag_flush_range_np(dmar_domain, iova, iova + size - 1);
 
 	return 0;
 }
@@ -4589,6 +4614,9 @@ static int identity_domain_attach_dev(struct iommu_domain *domain, struct device
 		ret = device_setup_pass_through(dev);
 	}
 
+	if (!ret)
+		info->domain_attached = true;
+
 	return ret;
 }
 
@@ -4666,6 +4694,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_igfx);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_igfx);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_igfx);
 
+/* QM57/QS57 integrated gfx malfunctions with dmar */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_iommu_igfx);
+
 /* Broadwell igfx malfunctions with dmar */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1606, quirk_iommu_igfx);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160B, quirk_iommu_igfx);
@@ -4743,7 +4774,6 @@ static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
 	}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_gtt);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0062, quirk_calpella_no_shadow_gtt);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x006a, quirk_calpella_no_shadow_gtt);
 
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 1497f3112b12..f521155fb793 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -614,6 +614,9 @@ struct dmar_domain {
 	u8 has_mappings:1;		/* Has mappings configured through
 					 * iommu_map() interface.
 					 */
+	u8 iotlb_sync_map:1;		/* Need to flush IOTLB cache or write
+					 * buffer when creating mappings.
+					 */
 
 	spinlock_t lock;		/* Protect device tracking lists */
 	struct list_head devices;	/* all devices' list */
@@ -776,6 +779,7 @@ struct device_domain_info {
 	u8 ats_supported:1;
 	u8 ats_enabled:1;
 	u8 dtlb_extra_inval:1;	/* Quirk for devices need extra flush */
+	u8 domain_attached:1;	/* Device has domain attached */
 	u8 ats_qdep;
 	struct device *dev; /* it's NULL for PCIe-to-PCI bridge */
 	struct intel_iommu *iommu; /* IOMMU used by this device */
diff --git a/drivers/iommu/intel/nested.c b/drivers/iommu/intel/nested.c
index 433c58944401..3b5251034a87 100644
--- a/drivers/iommu/intel/nested.c
+++ b/drivers/iommu/intel/nested.c
@@ -27,8 +27,7 @@ static int intel_nested_attach_dev(struct iommu_domain *domain,
 	unsigned long flags;
 	int ret = 0;
 
-	if (info->domain)
-		device_block_translation(dev);
+	device_block_translation(dev);
 
 	if (iommu->agaw < dmar_domain->s2_domain->agaw) {
 		dev_err_ratelimited(dev, "Adjusted guest address width not compatible\n");
@@ -62,6 +61,7 @@ static int intel_nested_attach_dev(struct iommu_domain *domain,
 		goto unassign_tag;
 
 	info->domain = dmar_domain;
+	info->domain_attached = true;
 	spin_lock_irqsave(&dmar_domain->lock, flags);
 	list_add(&info->link, &dmar_domain->devices);
 	spin_unlock_irqrestore(&dmar_domain->lock, flags);