Merge tag 'iommu-fixes' of git://git.kernel.org/pub/scm/linux/kernel/…

…git/arm64/linux

Pull iommu fixes from Will Deacon:
 "This is mainly all Intel VT-D stuff, but there are some fixes for AMD
  and ARM as well.

  We've also got the revert I promised during the merge window, which
  removes a temporary hack to accomodate i915 while we transitioned the
  Intel IOMMU driver over to the common DMA-IOMMU API.

  Finally, there are still a couple of other VT-D fixes floating around,
  so I expect to send you another batch of fixes next week.

  Summary:

   - Fix VT-D TLB invalidation for subdevices

   - Fix VT-D use-after-free on subdevice detach

   - Fix VT-D locking so that IRQs are disabled during SVA bind/unbind

   - Fix VT-D address alignment when flushing IOTLB

   - Fix memory leak in VT-D IRQ remapping failure path

   - Revert temporary i915 sglist hack now that it is no longer required

   - Fix sporadic boot failure with Arm SMMU on Qualcomm SM8150

   - Fix NULL dereference in AMD IRQ remapping code with remapping disabled

   - Fix accidental enabling of irqs on AMD resume-from-suspend path

   - Fix some typos in comments"

* tag 'iommu-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  iommu/vt-d: Fix ineffective devTLB invalidation for subdevices
  iommu/vt-d: Fix general protection fault in aux_detach_device()
  iommu/vt-d: Move intel_iommu info from struct intel_svm to struct intel_svm_dev
  iommu/arm-smmu-qcom: Initialize SCTLR of the bypass context
  iommu/vt-d: Fix lockdep splat in sva bind()/unbind()
  Revert "iommu: Add quirk for Intel graphic devices in map_sg"
  iommu/vt-d: Fix misuse of ALIGN in qi_flush_piotlb()
  iommu/amd: Stop irq_remapping_select() matching when remapping is disabled
  iommu/amd: Set iommu->int_enabled consistently when interrupts are set up
  iommu/intel: Fix memleak in intel_irq_remapping_alloc
  iommu/iova: fix 'domain' typos

drivers/iommu/amd/init.c

@@ -1973,8 +1973,6 @@ static int iommu_setup_msi(struct amd_iommu *iommu)
 		return r;
 	}
 
-	iommu->int_enabled = true;
-
 	return 0;
 }
 
@@ -2169,6 +2167,7 @@ static int iommu_init_irq(struct amd_iommu *iommu)
 	if (ret)
 		return ret;
 
+	iommu->int_enabled = true;
 enable_faults:
 	iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
 

drivers/iommu/amd/iommu.c

@@ -3854,6 +3854,9 @@ static int irq_remapping_select(struct irq_domain *d, struct irq_fwspec *fwspec,
 	struct amd_iommu *iommu;
 	int devid = -1;
 
+	if (!amd_iommu_irq_remap)
+		return 0;
+
 	if (x86_fwspec_is_ioapic(fwspec))
 		devid = get_ioapic_devid(fwspec->param[0]);
 	else if (x86_fwspec_is_hpet(fwspec))

drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c

@@ -196,6 +196,8 @@ static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
 
 		set_bit(qsmmu->bypass_cbndx, smmu->context_map);
 
+		arm_smmu_cb_write(smmu, qsmmu->bypass_cbndx, ARM_SMMU_CB_SCTLR, 0);
+
 		reg = FIELD_PREP(ARM_SMMU_CBAR_TYPE, CBAR_TYPE_S1_TRANS_S2_BYPASS);
 		arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBAR(qsmmu->bypass_cbndx), reg);
 	}

drivers/iommu/dma-iommu.c

@@ -863,33 +863,6 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
 	unsigned int cur_len = 0, max_len = dma_get_max_seg_size(dev);
 	int i, count = 0;
 
-	/*
-	 * The Intel graphic driver is used to assume that the returned
-	 * sg list is not combound. This blocks the efforts of converting
-	 * Intel IOMMU driver to dma-iommu api's. Add this quirk to make the
-	 * device driver work and should be removed once it's fixed in i915
-	 * driver.
-	 */
-	if (IS_ENABLED(CONFIG_DRM_I915) && dev_is_pci(dev) &&
-	    to_pci_dev(dev)->vendor == PCI_VENDOR_ID_INTEL &&
-	    (to_pci_dev(dev)->class >> 16) == PCI_BASE_CLASS_DISPLAY) {
-		for_each_sg(sg, s, nents, i) {
-			unsigned int s_iova_off = sg_dma_address(s);
-			unsigned int s_length = sg_dma_len(s);
-			unsigned int s_iova_len = s->length;
-
-			s->offset += s_iova_off;
-			s->length = s_length;
-			sg_dma_address(s) = dma_addr + s_iova_off;
-			sg_dma_len(s) = s_length;
-			dma_addr += s_iova_len;
-
-			pr_info_once("sg combining disabled due to i915 driver\n");
-		}
-
-		return nents;
-	}
-
 	for_each_sg(sg, s, nents, i) {
 		/* Restore this segment's original unaligned fields first */
 		unsigned int s_iova_off = sg_dma_address(s);

drivers/iommu/intel/dmar.c

@@ -1461,8 +1461,8 @@ void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr,
 		int mask = ilog2(__roundup_pow_of_two(npages));
 		unsigned long align = (1ULL << (VTD_PAGE_SHIFT + mask));
 
-		if (WARN_ON_ONCE(!ALIGN(addr, align)))
-			addr &= ~(align - 1);
+		if (WARN_ON_ONCE(!IS_ALIGNED(addr, align)))
+			addr = ALIGN_DOWN(addr, align);
 
 		desc.qw0 = QI_EIOTLB_PASID(pasid) |
 				QI_EIOTLB_DID(did) |

drivers/iommu/intel/iommu.c

@@ -719,6 +719,8 @@ 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 +746,8 @@ 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,
@@ -1464,17 +1468,22 @@ 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 +1564,37 @@ 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);
 }
@@ -1877,6 +1898,7 @@ 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;
 }
@@ -2547,7 +2569,7 @@ 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);
@@ -4475,33 +4497,61 @@ 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;
+
+	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);
+	}
 
-	domain->auxd_refcnt++;
-	list_add(&domain->auxd, &info->auxiliary_domains);
+	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 +4580,19 @@ 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 +4611,9 @@ 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 +4622,10 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 	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 +4645,18 @@ 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,

drivers/iommu/intel/irq_remapping.c

@@ -1353,6 +1353,8 @@ static int intel_irq_remapping_alloc(struct irq_domain *domain,
 		irq_data = irq_domain_get_irq_data(domain, virq + i);
 		irq_cfg = irqd_cfg(irq_data);
 		if (!irq_data || !irq_cfg) {
+			if (!i)
+				kfree(data);
 			ret = -EINVAL;
 			goto out_free_data;
 		}