Merge tag 'iommu-fixes-v6.13-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux

Pull iommu fixes from Joerg Roedel:

 - Per-domain device-list locking fixes for the AMD IOMMU driver

 - Fix incorrect use of smp_processor_id() in the NVidia-specific part
   of the ARM-SMMU-v3 driver

 - Intel IOMMU driver fixes:
     - Remove cache tags before disabling ATS
     - Avoid draining PRQ in sva mm release path
     - Fix qi_batch NULL pointer with nested parent domain

* tag 'iommu-fixes-v6.13-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux:
  iommu/vt-d: Avoid draining PRQ in sva mm release path
  iommu/vt-d: Fix qi_batch NULL pointer with nested parent domain
  iommu/vt-d: Remove cache tags before disabling ATS
  iommu/amd: Add lockdep asserts for domain->dev_list
  iommu/amd: Put list_add/del(dev_data) back under the domain->lock
  iommu/tegra241-cmdqv: do not use smp_processor_id in preemptible context

Author: torvalds

drivers/iommu/amd/iommu.c

@@ -1415,6 +1415,7 @@ static int domain_flush_pages_v2(struct protection_domain *pdom,
 	struct iommu_cmd cmd;
 	int ret = 0;
 
+	lockdep_assert_held(&pdom->lock);
 	list_for_each_entry(dev_data, &pdom->dev_list, list) {
 		struct amd_iommu *iommu = get_amd_iommu_from_dev(dev_data->dev);
 		u16 domid = dev_data->gcr3_info.domid;
@@ -1464,6 +1465,8 @@ static void __domain_flush_pages(struct protection_domain *domain,
 	ioasid_t pasid = IOMMU_NO_PASID;
 	bool gn = false;
 
+	lockdep_assert_held(&domain->lock);
+
 	if (pdom_is_v2_pgtbl_mode(domain)) {
 		gn = true;
 		ret = domain_flush_pages_v2(domain, address, size);
@@ -1585,6 +1588,8 @@ void amd_iommu_update_and_flush_device_table(struct protection_domain *domain)
 {
 	struct iommu_dev_data *dev_data;
 
+	lockdep_assert_held(&domain->lock);
+
 	list_for_each_entry(dev_data, &domain->dev_list, list) {
 		struct amd_iommu *iommu = rlookup_amd_iommu(dev_data->dev);
 
@@ -2073,6 +2078,7 @@ static int attach_device(struct device *dev,
 	struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev);
 	struct amd_iommu *iommu = get_amd_iommu_from_dev_data(dev_data);
 	struct pci_dev *pdev;
+	unsigned long flags;
 	int ret = 0;
 
 	mutex_lock(&dev_data->mutex);
@@ -2113,7 +2119,9 @@ static int attach_device(struct device *dev,
 
 	/* Update data structures */
 	dev_data->domain = domain;
+	spin_lock_irqsave(&domain->lock, flags);
 	list_add(&dev_data->list, &domain->dev_list);
+	spin_unlock_irqrestore(&domain->lock, flags);
 
 	/* Update device table */
 	dev_update_dte(dev_data, true);
@@ -2160,6 +2168,7 @@ static void detach_device(struct device *dev)
 	/* Flush IOTLB and wait for the flushes to finish */
 	spin_lock_irqsave(&domain->lock, flags);
 	amd_iommu_domain_flush_all(domain);
+	list_del(&dev_data->list);
 	spin_unlock_irqrestore(&domain->lock, flags);
 
 	/* Clear GCR3 table */
@@ -2168,7 +2177,6 @@ static void detach_device(struct device *dev)
 
 	/* Update data structures */
 	dev_data->domain = NULL;
-	list_del(&dev_data->list);
 
 	/* decrease reference counters - needs to happen after the flushes */
 	pdom_detach_iommu(iommu, domain);

drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c

@@ -339,7 +339,7 @@ tegra241_cmdqv_get_cmdq(struct arm_smmu_device *smmu,
 	 * one CPU at a time can enter the process, while the others
 	 * will be spinning at the same lock.
 	 */
-	lidx = smp_processor_id() % cmdqv->num_lvcmdqs_per_vintf;
+	lidx = raw_smp_processor_id() % cmdqv->num_lvcmdqs_per_vintf;
 	vcmdq = vintf->lvcmdqs[lidx];
 	if (!vcmdq || !READ_ONCE(vcmdq->enabled))
 		return NULL;

drivers/iommu/intel/cache.c

@@ -105,12 +105,35 @@ static void cache_tag_unassign(struct dmar_domain *domain, u16 did,
 	spin_unlock_irqrestore(&domain->cache_lock, flags);
 }
 
+/* domain->qi_batch will be freed in iommu_free_domain() path. */
+static int domain_qi_batch_alloc(struct dmar_domain *domain)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&domain->cache_lock, flags);
+	if (domain->qi_batch)
+		goto out_unlock;
+
+	domain->qi_batch = kzalloc(sizeof(*domain->qi_batch), GFP_ATOMIC);
+	if (!domain->qi_batch)
+		ret = -ENOMEM;
+out_unlock:
+	spin_unlock_irqrestore(&domain->cache_lock, flags);
+
+	return ret;
+}
+
 static int __cache_tag_assign_domain(struct dmar_domain *domain, u16 did,
 				     struct device *dev, ioasid_t pasid)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	int ret;
 
+	ret = domain_qi_batch_alloc(domain);
+	if (ret)
+		return ret;
+
 	ret = cache_tag_assign(domain, did, dev, pasid, CACHE_TAG_IOTLB);
 	if (ret || !info->ats_enabled)
 		return ret;
@@ -139,6 +162,10 @@ static int __cache_tag_assign_parent_domain(struct dmar_domain *domain, u16 did,
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	int ret;
 
+	ret = domain_qi_batch_alloc(domain);
+	if (ret)
+		return ret;
+
 	ret = cache_tag_assign(domain, did, dev, pasid, CACHE_TAG_NESTING_IOTLB);
 	if (ret || !info->ats_enabled)
 		return ret;
@@ -190,13 +217,6 @@ int cache_tag_assign_domain(struct dmar_domain *domain,
 	u16 did = domain_get_id_for_dev(domain, dev);
 	int ret;
 
-	/* domain->qi_bach will be freed in iommu_free_domain() path. */
-	if (!domain->qi_batch) {
-		domain->qi_batch = kzalloc(sizeof(*domain->qi_batch), GFP_KERNEL);
-		if (!domain->qi_batch)
-			return -ENOMEM;
-	}
-
 	ret = __cache_tag_assign_domain(domain, did, dev, pasid);
 	if (ret || domain->domain.type != IOMMU_DOMAIN_NESTED)
 		return ret;

drivers/iommu/intel/iommu.c

@@ -3220,6 +3220,9 @@ void device_block_translation(struct device *dev)
 	struct intel_iommu *iommu = info->iommu;
 	unsigned long flags;
 
+	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))
@@ -3236,7 +3239,6 @@ void device_block_translation(struct device *dev)
 	list_del(&info->link);
 	spin_unlock_irqrestore(&info->domain->lock, flags);
 
-	cache_tag_unassign_domain(info->domain, dev, IOMMU_NO_PASID);
 	domain_detach_iommu(info->domain, iommu);
 	info->domain = NULL;
 }

drivers/iommu/intel/pasid.c

@@ -265,7 +265,8 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
 		iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
 
 	devtlb_invalidation_with_pasid(iommu, dev, pasid);
-	intel_iommu_drain_pasid_prq(dev, pasid);
+	if (!fault_ignore)
+		intel_iommu_drain_pasid_prq(dev, pasid);
 }
 
 /*