iommu: Don't call .probe_finalize() under group->mutex

The .probe_finalize() call-back of some IOMMU drivers calls into
arm_iommu_attach_device(). This function will call back into the
IOMMU core code, where it tries to take group->mutex again, resulting
in a deadlock.

As there is no reason why .probe_finalize() needs to be called under
that mutex, move it after the lock has been released to fix the
deadlock.

Fixes: deac0b3b ("iommu: Split off default domain allocation from group assignment")
Reported-by: Yong Wu <yong.wu@mediatek.com>
Tested-by: Yong Wu <yong.wu@mediatek.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Cc: Yong Wu <yong.wu@mediatek.com>
Link: https://lore.kernel.org/r/20200519132824.15163-1-joro@8bytes.org

drivers/iommu/iommu.c

@@ -1674,17 +1674,8 @@ static void probe_alloc_default_domain(struct bus_type *bus,
 static int iommu_group_do_dma_attach(struct device *dev, void *data)
 {
 	struct iommu_domain *domain = data;
-	const struct iommu_ops *ops;
-	int ret;
-
-	ret = __iommu_attach_device(domain, dev);
-
-	ops = domain->ops;
-
-	if (ret == 0 && ops->probe_finalize)
-		ops->probe_finalize(dev);
 
-	return ret;
+	return __iommu_attach_device(domain, dev);
 }
 
 static int __iommu_group_dma_attach(struct iommu_group *group)
@@ -1693,6 +1684,21 @@ static int __iommu_group_dma_attach(struct iommu_group *group)
 					  iommu_group_do_dma_attach);
 }
 
+static int iommu_group_do_probe_finalize(struct device *dev, void *data)
+{
+	struct iommu_domain *domain = data;
+
+	if (domain->ops->probe_finalize)
+		domain->ops->probe_finalize(dev);
+
+	return 0;
+}
+
+static void __iommu_group_dma_finalize(struct iommu_group *group)
+{
+	__iommu_group_for_each_dev(group, group->default_domain,
+				   iommu_group_do_probe_finalize);
+}
 static int iommu_do_create_direct_mappings(struct device *dev, void *data)
 {
 	struct iommu_group *group = data;
@@ -1745,6 +1751,8 @@ int bus_iommu_probe(struct bus_type *bus)
 
 		if (ret)
 			break;
+
+		__iommu_group_dma_finalize(group);
 	}
 
 	return ret;