Merge tag 'iommu-updates-v6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:
 "Core:
   - IOMMU memory usage observability - This will make the memory used
     for IO page tables explicitly visible.
   - Simplify arch_setup_dma_ops()

  Intel VT-d:
   - Consolidate domain cache invalidation
   - Remove private data from page fault message
   - Allocate DMAR fault interrupts locally
   - Cleanup and refactoring

  ARM-SMMUv2:
   - Support for fault debugging hardware on Qualcomm implementations
   - Re-land support for the ->domain_alloc_paging() callback

  ARM-SMMUv3:
   - Improve handling of MSI allocation failure
   - Drop support for the "disable_bypass" cmdline option
   - Major rework of the CD creation code, following on directly from
     the STE rework merged last time around.
   - Add unit tests for the new STE/CD manipulation logic

  AMD-Vi:
   - Final part of SVA changes with generic IO page fault handling

  Renesas IPMMU:
   - Add support for R8A779H0 hardware

  ... and a couple smaller fixes and updates across the sub-tree"

* tag 'iommu-updates-v6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (80 commits)
  iommu/arm-smmu-v3: Make the kunit into a module
  arm64: Properly clean up iommu-dma remnants
  iommu/amd: Enable Guest Translation after reading IOMMU feature register
  iommu/vt-d: Decouple igfx_off from graphic identity mapping
  iommu/amd: Fix compilation error
  iommu/arm-smmu-v3: Add unit tests for arm_smmu_write_entry
  iommu/arm-smmu-v3: Build the whole CD in arm_smmu_make_s1_cd()
  iommu/arm-smmu-v3: Move the CD generation for SVA into a function
  iommu/arm-smmu-v3: Allocate the CD table entry in advance
  iommu/arm-smmu-v3: Make arm_smmu_alloc_cd_ptr()
  iommu/arm-smmu-v3: Consolidate clearing a CD table entry
  iommu/arm-smmu-v3: Move the CD generation for S1 domains into a function
  iommu/arm-smmu-v3: Make CD programming use arm_smmu_write_entry()
  iommu/arm-smmu-v3: Add an ops indirection to the STE code
  iommu/arm-smmu-qcom: Don't build debug features as a kernel module
  iommu/amd: Add SVA domain support
  iommu: Add ops->domain_alloc_sva()
  iommu/amd: Initial SVA support for AMD IOMMU
  iommu/amd: Add support for enable/disable IOPF
  iommu/amd: Add IO page fault notifier handler
  ...

1 files changed, 26 insertions, 22 deletions

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index a95a483def2d..9df7cc75c1bc 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -581,10 +581,11 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list
 		if (list_empty(&group->entry))
 			list_add_tail(&group->entry, group_list);
 	}
-	mutex_unlock(&group->mutex);
 
-	if (dev_is_pci(dev))
-		iommu_dma_set_pci_32bit_workaround(dev);
+	if (group->default_domain)
+		iommu_setup_dma_ops(dev);
+
+	mutex_unlock(&group->mutex);
 
 	return 0;
 
@@ -1828,6 +1829,8 @@ int bus_iommu_probe(const struct bus_type *bus)
 			mutex_unlock(&group->mutex);
 			return ret;
 		}
+		for_each_group_device(group, gdev)
+			iommu_setup_dma_ops(gdev->dev);
 		mutex_unlock(&group->mutex);
 
 		/*
@@ -3066,18 +3069,9 @@ static ssize_t iommu_group_store_type(struct iommu_group *group,
 	if (ret)
 		goto out_unlock;
 
-	/*
-	 * Release the mutex here because ops->probe_finalize() call-back of
-	 * some vendor IOMMU drivers calls arm_iommu_attach_device() which
-	 * in-turn might call back into IOMMU core code, where it tries to take
-	 * group->mutex, resulting in a deadlock.
-	 */
-	mutex_unlock(&group->mutex);
-
 	/* Make sure dma_ops is appropriatley set */
 	for_each_group_device(group, gdev)
-		iommu_group_do_probe_finalize(gdev->dev);
-	return count;
+		iommu_setup_dma_ops(gdev->dev);
 
 out_unlock:
 	mutex_unlock(&group->mutex);
@@ -3317,27 +3311,39 @@ EXPORT_SYMBOL_GPL(iommu_group_dma_owner_claimed);
 static int __iommu_set_group_pasid(struct iommu_domain *domain,
 				   struct iommu_group *group, ioasid_t pasid)
 {
-	struct group_device *device;
-	int ret = 0;
+	struct group_device *device, *last_gdev;
+	int ret;
 
 	for_each_group_device(group, device) {
 		ret = domain->ops->set_dev_pasid(domain, device->dev, pasid);
 		if (ret)
-			break;
+			goto err_revert;
 	}
 
+	return 0;
+
+err_revert:
+	last_gdev = device;
+	for_each_group_device(group, device) {
+		const struct iommu_ops *ops = dev_iommu_ops(device->dev);
+
+		if (device == last_gdev)
+			break;
+		ops->remove_dev_pasid(device->dev, pasid, domain);
+	}
 	return ret;
 }
 
 static void __iommu_remove_group_pasid(struct iommu_group *group,
-				       ioasid_t pasid)
+				       ioasid_t pasid,
+				       struct iommu_domain *domain)
 {
 	struct group_device *device;
 	const struct iommu_ops *ops;
 
 	for_each_group_device(group, device) {
 		ops = dev_iommu_ops(device->dev);
-		ops->remove_dev_pasid(device->dev, pasid);
+		ops->remove_dev_pasid(device->dev, pasid, domain);
 	}
 }
 
@@ -3383,10 +3389,8 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
 	}
 
 	ret = __iommu_set_group_pasid(domain, group, pasid);
-	if (ret) {
-		__iommu_remove_group_pasid(group, pasid);
+	if (ret)
 		xa_erase(&group->pasid_array, pasid);
-	}
 out_unlock:
 	mutex_unlock(&group->mutex);
 	return ret;
@@ -3409,7 +3413,7 @@ void iommu_detach_device_pasid(struct iommu_domain *domain, struct device *dev,
 	struct iommu_group *group = dev->iommu_group;
 
 	mutex_lock(&group->mutex);
-	__iommu_remove_group_pasid(group, pasid);
+	__iommu_remove_group_pasid(group, pasid, domain);
 	WARN_ON(xa_erase(&group->pasid_array, pasid) != domain);
 	mutex_unlock(&group->mutex);
 }