Merge tag 'iommu-fixes-v6.1-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu fixes from Joerg Roedel:
 "Intel VT-d fixes:

   - IO/TLB flush fix

   - Various pci_dev refcount fixes"

* tag 'iommu-fixes-v6.1-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  iommu/vt-d: Fix PCI device refcount leak in dmar_dev_scope_init()
  iommu/vt-d: Fix PCI device refcount leak in has_external_pci()
  iommu/vt-d: Fix PCI device refcount leak in prq_event_thread()
  iommu/vt-d: Add a fix for devices need extra dtlb flush

drivers/iommu/intel/dmar.c

@@ -820,6 +820,7 @@ int __init dmar_dev_scope_init(void)
 			info = dmar_alloc_pci_notify_info(dev,
 					BUS_NOTIFY_ADD_DEVICE);
 			if (!info) {
+				pci_dev_put(dev);
 				return dmar_dev_scope_status;
 			} else {
 				dmar_pci_bus_add_dev(info);

drivers/iommu/intel/iommu.c

@@ -1396,6 +1396,24 @@ static void domain_update_iotlb(struct dmar_domain *domain)
 	spin_unlock_irqrestore(&domain->lock, flags);
 }
 
+/*
+ * The extra devTLB flush quirk impacts those QAT devices with PCI device
+ * IDs ranging from 0x4940 to 0x4943. It is exempted from risky_device()
+ * check because it applies only to the built-in QAT devices and it doesn't
+ * grant additional privileges.
+ */
+#define BUGGY_QAT_DEVID_MASK 0x494c
+static bool dev_needs_extra_dtlb_flush(struct pci_dev *pdev)
+{
+	if (pdev->vendor != PCI_VENDOR_ID_INTEL)
+		return false;
+
+	if ((pdev->device & 0xfffc) != BUGGY_QAT_DEVID_MASK)
+		return false;
+
+	return true;
+}
+
 static void iommu_enable_pci_caps(struct device_domain_info *info)
 {
 	struct pci_dev *pdev;
@@ -1478,6 +1496,7 @@ static void __iommu_flush_dev_iotlb(struct device_domain_info *info,
 	qdep = info->ats_qdep;
 	qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
 			   qdep, addr, mask);
+	quirk_extra_dev_tlb_flush(info, addr, mask, PASID_RID2PASID, qdep);
 }
 
 static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
@@ -3854,8 +3873,10 @@ static inline bool has_external_pci(void)
 	struct pci_dev *pdev = NULL;
 
 	for_each_pci_dev(pdev)
-		if (pdev->external_facing)
+		if (pdev->external_facing) {
+			pci_dev_put(pdev);
 			return true;
+		}
 
 	return false;
 }
@@ -4490,9 +4511,10 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 	if (dev_is_pci(dev)) {
 		if (ecap_dev_iotlb_support(iommu->ecap) &&
 		    pci_ats_supported(pdev) &&
-		    dmar_ats_supported(pdev, iommu))
+		    dmar_ats_supported(pdev, iommu)) {
 			info->ats_supported = 1;
-
+			info->dtlb_extra_inval = dev_needs_extra_dtlb_flush(pdev);
+		}
 		if (sm_supported(iommu)) {
 			if (pasid_supported(iommu)) {
 				int features = pci_pasid_features(pdev);
@@ -4931,3 +4953,48 @@ static void __init check_tylersburg_isoch(void)
 	pr_warn("Recommended TLB entries for ISOCH unit is 16; your BIOS set %d\n",
 	       vtisochctrl);
 }
+
+/*
+ * Here we deal with a device TLB defect where device may inadvertently issue ATS
+ * invalidation completion before posted writes initiated with translated address
+ * that utilized translations matching the invalidation address range, violating
+ * the invalidation completion ordering.
+ * Therefore, any use cases that cannot guarantee DMA is stopped before unmap is
+ * vulnerable to this defect. In other words, any dTLB invalidation initiated not
+ * under the control of the trusted/privileged host device driver must use this
+ * quirk.
+ * Device TLBs are invalidated under the following six conditions:
+ * 1. Device driver does DMA API unmap IOVA
+ * 2. Device driver unbind a PASID from a process, sva_unbind_device()
+ * 3. PASID is torn down, after PASID cache is flushed. e.g. process
+ *    exit_mmap() due to crash
+ * 4. Under SVA usage, called by mmu_notifier.invalidate_range() where
+ *    VM has to free pages that were unmapped
+ * 5. Userspace driver unmaps a DMA buffer
+ * 6. Cache invalidation in vSVA usage (upcoming)
+ *
+ * For #1 and #2, device drivers are responsible for stopping DMA traffic
+ * before unmap/unbind. For #3, iommu driver gets mmu_notifier to
+ * invalidate TLB the same way as normal user unmap which will use this quirk.
+ * The dTLB invalidation after PASID cache flush does not need this quirk.
+ *
+ * As a reminder, #6 will *NEED* this quirk as we enable nested translation.
+ */
+void quirk_extra_dev_tlb_flush(struct device_domain_info *info,
+			       unsigned long address, unsigned long mask,
+			       u32 pasid, u16 qdep)
+{
+	u16 sid;
+
+	if (likely(!info->dtlb_extra_inval))
+		return;
+
+	sid = PCI_DEVID(info->bus, info->devfn);
+	if (pasid == PASID_RID2PASID) {
+		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
+				   qdep, address, mask);
+	} else {
+		qi_flush_dev_iotlb_pasid(info->iommu, sid, info->pfsid,
+					 pasid, qdep, address, mask);
+	}
+}

drivers/iommu/intel/iommu.h

@@ -623,6 +623,7 @@ struct device_domain_info {
 	u8 pri_enabled:1;
 	u8 ats_supported:1;
 	u8 ats_enabled:1;
+	u8 dtlb_extra_inval:1;	/* Quirk for devices need extra flush */
 	u8 ats_qdep;
 	struct device *dev; /* it's NULL for PCIe-to-PCI bridge */
 	struct intel_iommu *iommu; /* IOMMU used by this device */
@@ -728,6 +729,9 @@ void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr,
 void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 			      u32 pasid, u16 qdep, u64 addr,
 			      unsigned int size_order);
+void quirk_extra_dev_tlb_flush(struct device_domain_info *info,
+			       unsigned long address, unsigned long pages,
+			       u32 pasid, u16 qdep);
 void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu,
 			  u32 pasid);
 

drivers/iommu/intel/svm.c

@@ -184,10 +184,13 @@ static void __flush_svm_range_dev(struct intel_svm *svm,
 		return;
 
 	qi_flush_piotlb(sdev->iommu, sdev->did, svm->pasid, address, pages, ih);
-	if (info->ats_enabled)
+	if (info->ats_enabled) {
 		qi_flush_dev_iotlb_pasid(sdev->iommu, sdev->sid, info->pfsid,
 					 svm->pasid, sdev->qdep, address,
 					 order_base_2(pages));
+		quirk_extra_dev_tlb_flush(info, address, order_base_2(pages),
+					  svm->pasid, sdev->qdep);
+	}
 }
 
 static void intel_flush_svm_range_dev(struct intel_svm *svm,
@@ -745,12 +748,16 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 		 * If prq is to be handled outside iommu driver via receiver of
 		 * the fault notifiers, we skip the page response here.
 		 */
-		if (!pdev || intel_svm_prq_report(iommu, &pdev->dev, req))
-			handle_bad_prq_event(iommu, req, QI_RESP_INVALID);
+		if (!pdev)
+			goto bad_req;
 
-		trace_prq_report(iommu, &pdev->dev, req->qw_0, req->qw_1,
-				 req->priv_data[0], req->priv_data[1],
-				 iommu->prq_seq_number++);
+		if (intel_svm_prq_report(iommu, &pdev->dev, req))
+			handle_bad_prq_event(iommu, req, QI_RESP_INVALID);
+		else
+			trace_prq_report(iommu, &pdev->dev, req->qw_0, req->qw_1,
+					 req->priv_data[0], req->priv_data[1],
+					 iommu->prq_seq_number++);
+		pci_dev_put(pdev);
 prq_advance:
 		head = (head + sizeof(*req)) & PRQ_RING_MASK;
 	}