iommu: Remove deferred attach check from __iommu_detach_device()

At the current moment, __iommu_detach_device() is only called via call
chains that are after the device driver is attached - eg via explicit
attach APIs called by the device driver.

Commit bd421264 ("iommu: Fix deferred domain attachment") has removed
deferred domain attachment check from __iommu_attach_device() path, so it
should just unconditionally work in the __iommu_detach_device() path.

It actually looks like a bug that we were blocking detach on these paths
since the attach was unconditional and the caller is going to free the
(probably) UNAMANGED domain once this returns.

The only place we should be testing for deferred attach is during the
initial point the dma device is linked to the group, and then again
during the dma api calls.
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20230110025408.667767-5-baolu.lu@linux.intel.comSigned-off-by: Joerg Roedel <jroedel@suse.de>

drivers/iommu/iommu.c

@@ -371,6 +371,30 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list
 	return ret;
 }
 
+static bool iommu_is_attach_deferred(struct device *dev)
+{
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
+
+	if (ops->is_attach_deferred)
+		return ops->is_attach_deferred(dev);
+
+	return false;
+}
+
+static int iommu_group_do_dma_first_attach(struct device *dev, void *data)
+{
+	struct iommu_domain *domain = data;
+
+	lockdep_assert_held(&dev->iommu_group->mutex);
+
+	if (iommu_is_attach_deferred(dev)) {
+		dev->iommu->attach_deferred = 1;
+		return 0;
+	}
+
+	return __iommu_attach_device(domain, dev);
+}
+
 int iommu_probe_device(struct device *dev)
 {
 	const struct iommu_ops *ops;
@@ -401,7 +425,7 @@ int iommu_probe_device(struct device *dev)
 	 * attach the default domain.
 	 */
 	if (group->default_domain && !group->owner) {
-		ret = __iommu_attach_device(group->default_domain, dev);
+		ret = iommu_group_do_dma_first_attach(dev, group->default_domain);
 		if (ret) {
 			mutex_unlock(&group->mutex);
 			iommu_group_put(group);
@@ -947,16 +971,6 @@ static int iommu_create_device_direct_mappings(struct iommu_group *group,
 	return ret;
 }
 
-static bool iommu_is_attach_deferred(struct device *dev)
-{
-	const struct iommu_ops *ops = dev_iommu_ops(dev);
-
-	if (ops->is_attach_deferred)
-		return ops->is_attach_deferred(dev);
-
-	return false;
-}
-
 /**
  * iommu_group_add_device - add a device to an iommu group
  * @group: the group into which to add the device (reference should be held)
@@ -1009,8 +1023,8 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev)
 
 	mutex_lock(&group->mutex);
 	list_add_tail(&device->list, &group->devices);
-	if (group->domain  && !iommu_is_attach_deferred(dev))
-		ret = __iommu_attach_device(group->domain, dev);
+	if (group->domain)
+		ret = iommu_group_do_dma_first_attach(dev, group->domain);
 	mutex_unlock(&group->mutex);
 	if (ret)
 		goto err_put_group;
@@ -1776,21 +1790,10 @@ 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;
-	int ret = 0;
-
-	if (!iommu_is_attach_deferred(dev))
-		ret = __iommu_attach_device(domain, dev);
-
-	return ret;
-}
-
-static int __iommu_group_dma_attach(struct iommu_group *group)
+static int __iommu_group_dma_first_attach(struct iommu_group *group)
 {
 	return __iommu_group_for_each_dev(group, group->default_domain,
-					  iommu_group_do_dma_attach);
+					  iommu_group_do_dma_first_attach);
 }
 
 static int iommu_group_do_probe_finalize(struct device *dev, void *data)
@@ -1855,7 +1858,7 @@ int bus_iommu_probe(struct bus_type *bus)
 
 		iommu_group_create_direct_mappings(group);
 
-		ret = __iommu_group_dma_attach(group);
+		ret = __iommu_group_dma_first_attach(group);
 
 		mutex_unlock(&group->mutex);
 
@@ -1987,9 +1990,11 @@ static int __iommu_attach_device(struct iommu_domain *domain,
 		return -ENODEV;
 
 	ret = domain->ops->attach_dev(domain, dev);
-	if (!ret)
-		trace_attach_device_to_domain(dev);
-	return ret;
+	if (ret)
+		return ret;
+	dev->iommu->attach_deferred = 0;
+	trace_attach_device_to_domain(dev);
+	return 0;
 }
 
 /**
@@ -2034,7 +2039,7 @@ EXPORT_SYMBOL_GPL(iommu_attach_device);
 
 int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain)
 {
-	if (iommu_is_attach_deferred(dev))
+	if (dev->iommu && dev->iommu->attach_deferred)
 		return __iommu_attach_device(domain, dev);
 
 	return 0;
@@ -2043,9 +2048,6 @@ int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain)
 static void __iommu_detach_device(struct iommu_domain *domain,
 				  struct device *dev)
 {
-	if (iommu_is_attach_deferred(dev))
-		return;
-
 	domain->ops->detach_dev(domain, dev);
 	trace_detach_device_from_domain(dev);
 }

include/linux/iommu.h

@@ -405,6 +405,7 @@ struct iommu_fault_param {
  * @iommu_dev:	 IOMMU device this device is linked to
  * @priv:	 IOMMU Driver private data
  * @max_pasids:  number of PASIDs this device can consume
+ * @attach_deferred: the dma domain attachment is deferred
  *
  * TODO: migrate other per device data pointers under iommu_dev_data, e.g.
  *	struct iommu_group	*iommu_group;
@@ -417,6 +418,7 @@ struct dev_iommu {
 	struct iommu_device		*iommu_dev;
 	void				*priv;
 	u32				max_pasids;
+	u32				attach_deferred:1;
 };
 
 int iommu_device_register(struct iommu_device *iommu,