Merge remote-tracking branch 'iommu/vfio-notifier-fix' into v5.19/vfio/next

Merge IOMMU dependencies for vfio.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

drivers/amba/bus.c

@@ -20,6 +20,10 @@
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 #include <linux/of_irq.h>
+#include <linux/of_device.h>
+#include <linux/acpi.h>
+#include <linux/iommu.h>
+#include <linux/dma-map-ops.h>
 
 #define to_amba_driver(d)	container_of(d, struct amba_driver, drv)
 
@@ -273,6 +277,36 @@ static void amba_shutdown(struct device *dev)
 		drv->shutdown(to_amba_device(dev));
 }
 
+static int amba_dma_configure(struct device *dev)
+{
+	struct amba_driver *drv = to_amba_driver(dev->driver);
+	enum dev_dma_attr attr;
+	int ret = 0;
+
+	if (dev->of_node) {
+		ret = of_dma_configure(dev, dev->of_node, true);
+	} else if (has_acpi_companion(dev)) {
+		attr = acpi_get_dma_attr(to_acpi_device_node(dev->fwnode));
+		ret = acpi_dma_configure(dev, attr);
+	}
+
+	if (!ret && !drv->driver_managed_dma) {
+		ret = iommu_device_use_default_domain(dev);
+		if (ret)
+			arch_teardown_dma_ops(dev);
+	}
+
+	return ret;
+}
+
+static void amba_dma_cleanup(struct device *dev)
+{
+	struct amba_driver *drv = to_amba_driver(dev->driver);
+
+	if (!drv->driver_managed_dma)
+		iommu_device_unuse_default_domain(dev);
+}
+
 #ifdef CONFIG_PM
 /*
  * Hooks to provide runtime PM of the pclk (bus clock).  It is safe to
@@ -341,7 +375,8 @@ struct bus_type amba_bustype = {
 	.probe		= amba_probe,
 	.remove		= amba_remove,
 	.shutdown	= amba_shutdown,
-	.dma_configure	= platform_dma_configure,
+	.dma_configure	= amba_dma_configure,
+	.dma_cleanup	= amba_dma_cleanup,
 	.pm		= &amba_pm,
 };
 EXPORT_SYMBOL_GPL(amba_bustype);

drivers/base/dd.c

@@ -671,6 +671,8 @@ static int really_probe(struct device *dev, struct device_driver *drv)
 	if (dev->bus)
 		blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
 					     BUS_NOTIFY_DRIVER_NOT_BOUND, dev);
+	if (dev->bus && dev->bus->dma_cleanup)
+		dev->bus->dma_cleanup(dev);
 pinctrl_bind_failed:
 	device_links_no_driver(dev);
 	device_unbind_cleanup(dev);
@@ -1199,6 +1201,9 @@ static void __device_release_driver(struct device *dev, struct device *parent)
 
 		device_remove(dev);
 
+		if (dev->bus && dev->bus->dma_cleanup)
+			dev->bus->dma_cleanup(dev);
+
 		device_links_driver_cleanup(dev);
 		device_unbind_cleanup(dev);
 

drivers/base/platform.c

@@ -30,6 +30,8 @@
 #include <linux/property.h>
 #include <linux/kmemleak.h>
 #include <linux/types.h>
+#include <linux/iommu.h>
+#include <linux/dma-map-ops.h>
 
 #include "base.h"
 #include "power/power.h"
@@ -1454,9 +1456,9 @@ static void platform_shutdown(struct device *_dev)
 		drv->shutdown(dev);
 }
 
-
-int platform_dma_configure(struct device *dev)
+static int platform_dma_configure(struct device *dev)
 {
+	struct platform_driver *drv = to_platform_driver(dev->driver);
 	enum dev_dma_attr attr;
 	int ret = 0;
 
@@ -1467,9 +1469,23 @@ int platform_dma_configure(struct device *dev)
 		ret = acpi_dma_configure(dev, attr);
 	}
 
+	if (!ret && !drv->driver_managed_dma) {
+		ret = iommu_device_use_default_domain(dev);
+		if (ret)
+			arch_teardown_dma_ops(dev);
+	}
+
 	return ret;
 }
 
+static void platform_dma_cleanup(struct device *dev)
+{
+	struct platform_driver *drv = to_platform_driver(dev->driver);
+
+	if (!drv->driver_managed_dma)
+		iommu_device_unuse_default_domain(dev);
+}
+
 static const struct dev_pm_ops platform_dev_pm_ops = {
 	SET_RUNTIME_PM_OPS(pm_generic_runtime_suspend, pm_generic_runtime_resume, NULL)
 	USE_PLATFORM_PM_SLEEP_OPS
@@ -1484,6 +1500,7 @@ struct bus_type platform_bus_type = {
 	.remove		= platform_remove,
 	.shutdown	= platform_shutdown,
 	.dma_configure	= platform_dma_configure,
+	.dma_cleanup	= platform_dma_cleanup,
 	.pm		= &platform_dev_pm_ops,
 };
 EXPORT_SYMBOL_GPL(platform_bus_type);

drivers/bus/fsl-mc/fsl-mc-bus.c

@@ -21,6 +21,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/acpi.h>
 #include <linux/iommu.h>
+#include <linux/dma-map-ops.h>
 
 #include "fsl-mc-private.h"
 
@@ -140,15 +141,33 @@ static int fsl_mc_dma_configure(struct device *dev)
 {
 	struct device *dma_dev = dev;
 	struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev);
+	struct fsl_mc_driver *mc_drv = to_fsl_mc_driver(dev->driver);
 	u32 input_id = mc_dev->icid;
+	int ret;
 
 	while (dev_is_fsl_mc(dma_dev))
 		dma_dev = dma_dev->parent;
 
 	if (dev_of_node(dma_dev))
-		return of_dma_configure_id(dev, dma_dev->of_node, 0, &input_id);
+		ret = of_dma_configure_id(dev, dma_dev->of_node, 0, &input_id);
+	else
+		ret = acpi_dma_configure_id(dev, DEV_DMA_COHERENT, &input_id);
+
+	if (!ret && !mc_drv->driver_managed_dma) {
+		ret = iommu_device_use_default_domain(dev);
+		if (ret)
+			arch_teardown_dma_ops(dev);
+	}
+
+	return ret;
+}
+
+static void fsl_mc_dma_cleanup(struct device *dev)
+{
+	struct fsl_mc_driver *mc_drv = to_fsl_mc_driver(dev->driver);
 
-	return acpi_dma_configure_id(dev, DEV_DMA_COHERENT, &input_id);
+	if (!mc_drv->driver_managed_dma)
+		iommu_device_unuse_default_domain(dev);
 }
 
 static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
@@ -312,6 +331,7 @@ struct bus_type fsl_mc_bus_type = {
 	.match = fsl_mc_bus_match,
 	.uevent = fsl_mc_bus_uevent,
 	.dma_configure  = fsl_mc_dma_configure,
+	.dma_cleanup = fsl_mc_dma_cleanup,
 	.dev_groups = fsl_mc_dev_groups,
 	.bus_groups = fsl_mc_bus_groups,
 };

drivers/iommu/iommu.c

@@ -18,7 +18,6 @@
 #include <linux/errno.h>
 #include <linux/iommu.h>
 #include <linux/idr.h>
-#include <linux/notifier.h>
 #include <linux/err.h>
 #include <linux/pci.h>
 #include <linux/bitops.h>
@@ -40,14 +39,16 @@ struct iommu_group {
 	struct kobject *devices_kobj;
 	struct list_head devices;
 	struct mutex mutex;
-	struct blocking_notifier_head notifier;
 	void *iommu_data;
 	void (*iommu_data_release)(void *iommu_data);
 	char *name;
 	int id;
 	struct iommu_domain *default_domain;
+	struct iommu_domain *blocking_domain;
 	struct iommu_domain *domain;
 	struct list_head entry;
+	unsigned int owner_cnt;
+	void *owner;
 };
 
 struct group_device {
@@ -82,8 +83,8 @@ static int __iommu_attach_device(struct iommu_domain *domain,
 				 struct device *dev);
 static int __iommu_attach_group(struct iommu_domain *domain,
 				struct iommu_group *group);
-static void __iommu_detach_group(struct iommu_domain *domain,
-				 struct iommu_group *group);
+static int __iommu_group_set_domain(struct iommu_group *group,
+				    struct iommu_domain *new_domain);
 static int iommu_create_device_direct_mappings(struct iommu_group *group,
 					       struct device *dev);
 static struct iommu_group *iommu_group_get_for_dev(struct device *dev);
@@ -294,7 +295,11 @@ int iommu_probe_device(struct device *dev)
 	mutex_lock(&group->mutex);
 	iommu_alloc_default_domain(group, dev);
 
-	if (group->default_domain) {
+	/*
+	 * If device joined an existing group which has been claimed, don't
+	 * attach the default domain.
+	 */
+	if (group->default_domain && !group->owner) {
 		ret = __iommu_attach_device(group->default_domain, dev);
 		if (ret) {
 			mutex_unlock(&group->mutex);
@@ -599,6 +604,8 @@ static void iommu_group_release(struct kobject *kobj)
 
 	if (group->default_domain)
 		iommu_domain_free(group->default_domain);
+	if (group->blocking_domain)
+		iommu_domain_free(group->blocking_domain);
 
 	kfree(group->name);
 	kfree(group);
@@ -633,7 +640,6 @@ struct iommu_group *iommu_group_alloc(void)
 	mutex_init(&group->mutex);
 	INIT_LIST_HEAD(&group->devices);
 	INIT_LIST_HEAD(&group->entry);
-	BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);
 
 	ret = ida_simple_get(&iommu_group_ida, 0, 0, GFP_KERNEL);
 	if (ret < 0) {
@@ -906,10 +912,6 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev)
 	if (ret)
 		goto err_put_group;
 
-	/* Notify any listeners about change to group. */
-	blocking_notifier_call_chain(&group->notifier,
-				     IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev);
-
 	trace_add_device_to_group(group->id, dev);
 
 	dev_info(dev, "Adding to iommu group %d\n", group->id);
@@ -951,10 +953,6 @@ void iommu_group_remove_device(struct device *dev)
 
 	dev_info(dev, "Removing from iommu group %d\n", group->id);
 
-	/* Pre-notify listeners that a device is being removed. */
-	blocking_notifier_call_chain(&group->notifier,
-				     IOMMU_GROUP_NOTIFY_DEL_DEVICE, dev);
-
 	mutex_lock(&group->mutex);
 	list_for_each_entry(tmp_device, &group->devices, list) {
 		if (tmp_device->dev == dev) {
@@ -1076,36 +1074,6 @@ void iommu_group_put(struct iommu_group *group)
 }
 EXPORT_SYMBOL_GPL(iommu_group_put);
 
-/**
- * iommu_group_register_notifier - Register a notifier for group changes
- * @group: the group to watch
- * @nb: notifier block to signal
- *
- * This function allows iommu group users to track changes in a group.
- * See include/linux/iommu.h for actions sent via this notifier.  Caller
- * should hold a reference to the group throughout notifier registration.
- */
-int iommu_group_register_notifier(struct iommu_group *group,
-				  struct notifier_block *nb)
-{
-	return blocking_notifier_chain_register(&group->notifier, nb);
-}
-EXPORT_SYMBOL_GPL(iommu_group_register_notifier);
-
-/**
- * iommu_group_unregister_notifier - Unregister a notifier
- * @group: the group to watch
- * @nb: notifier block to signal
- *
- * Unregister a previously registered group notifier block.
- */
-int iommu_group_unregister_notifier(struct iommu_group *group,
-				    struct notifier_block *nb)
-{
-	return blocking_notifier_chain_unregister(&group->notifier, nb);
-}
-EXPORT_SYMBOL_GPL(iommu_group_unregister_notifier);
-
 /**
  * iommu_register_device_fault_handler() - Register a device fault handler
  * @dev: the device
@@ -1651,14 +1619,8 @@ static int remove_iommu_group(struct device *dev, void *data)
 static int iommu_bus_notifier(struct notifier_block *nb,
 			      unsigned long action, void *data)
 {
-	unsigned long group_action = 0;
 	struct device *dev = data;
-	struct iommu_group *group;
 
-	/*
-	 * ADD/DEL call into iommu driver ops if provided, which may
-	 * result in ADD/DEL notifiers to group->notifier
-	 */
 	if (action == BUS_NOTIFY_ADD_DEVICE) {
 		int ret;
 
@@ -1669,34 +1631,6 @@ static int iommu_bus_notifier(struct notifier_block *nb,
 		return NOTIFY_OK;
 	}
 
-	/*
-	 * Remaining BUS_NOTIFYs get filtered and republished to the
-	 * group, if anyone is listening
-	 */
-	group = iommu_group_get(dev);
-	if (!group)
-		return 0;
-
-	switch (action) {
-	case BUS_NOTIFY_BIND_DRIVER:
-		group_action = IOMMU_GROUP_NOTIFY_BIND_DRIVER;
-		break;
-	case BUS_NOTIFY_BOUND_DRIVER:
-		group_action = IOMMU_GROUP_NOTIFY_BOUND_DRIVER;
-		break;
-	case BUS_NOTIFY_UNBIND_DRIVER:
-		group_action = IOMMU_GROUP_NOTIFY_UNBIND_DRIVER;
-		break;
-	case BUS_NOTIFY_UNBOUND_DRIVER:
-		group_action = IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER;
-		break;
-	}
-
-	if (group_action)
-		blocking_notifier_call_chain(&group->notifier,
-					     group_action, dev);
-
-	iommu_group_put(group);
 	return 0;
 }
 
@@ -1983,6 +1917,24 @@ void iommu_domain_free(struct iommu_domain *domain)
 }
 EXPORT_SYMBOL_GPL(iommu_domain_free);
 
+/*
+ * Put the group's domain back to the appropriate core-owned domain - either the
+ * standard kernel-mode DMA configuration or an all-DMA-blocked domain.
+ */
+static void __iommu_group_set_core_domain(struct iommu_group *group)
+{
+	struct iommu_domain *new_domain;
+	int ret;
+
+	if (group->owner)
+		new_domain = group->blocking_domain;
+	else
+		new_domain = group->default_domain;
+
+	ret = __iommu_group_set_domain(group, new_domain);
+	WARN(ret, "iommu driver failed to attach the default/blocking domain");
+}
+
 static int __iommu_attach_device(struct iommu_domain *domain,
 				 struct device *dev)
 {
@@ -2039,9 +1991,6 @@ static void __iommu_detach_device(struct iommu_domain *domain,
 	if (iommu_is_attach_deferred(dev))
 		return;
 
-	if (unlikely(domain->ops->detach_dev == NULL))
-		return;
-
 	domain->ops->detach_dev(domain, dev);
 	trace_detach_device_from_domain(dev);
 }
@@ -2055,12 +2004,10 @@ void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
 		return;
 
 	mutex_lock(&group->mutex);
-	if (iommu_group_device_count(group) != 1) {
-		WARN_ON(1);
+	if (WARN_ON(domain != group->domain) ||
+	    WARN_ON(iommu_group_device_count(group) != 1))
 		goto out_unlock;
-	}
-
-	__iommu_detach_group(domain, group);
+	__iommu_group_set_core_domain(group);
 
 out_unlock:
 	mutex_unlock(&group->mutex);
@@ -2116,7 +2063,8 @@ static int __iommu_attach_group(struct iommu_domain *domain,
 {
 	int ret;
 
-	if (group->default_domain && group->domain != group->default_domain)
+	if (group->domain && group->domain != group->default_domain &&
+	    group->domain != group->blocking_domain)
 		return -EBUSY;
 
 	ret = __iommu_group_for_each_dev(group, domain,
@@ -2148,34 +2096,49 @@ static int iommu_group_do_detach_device(struct device *dev, void *data)
 	return 0;
 }
 
-static void __iommu_detach_group(struct iommu_domain *domain,
-				 struct iommu_group *group)
+static int __iommu_group_set_domain(struct iommu_group *group,
+				    struct iommu_domain *new_domain)
 {
 	int ret;
 
-	if (!group->default_domain) {
-		__iommu_group_for_each_dev(group, domain,
+	if (group->domain == new_domain)
+		return 0;
+
+	/*
+	 * New drivers should support default domains and so the detach_dev() op
+	 * will never be called. Otherwise the NULL domain represents some
+	 * platform specific behavior.
+	 */
+	if (!new_domain) {
+		if (WARN_ON(!group->domain->ops->detach_dev))
+			return -EINVAL;
+		__iommu_group_for_each_dev(group, group->domain,
 					   iommu_group_do_detach_device);
 		group->domain = NULL;
-		return;
+		return 0;
 	}
 
-	if (group->domain == group->default_domain)
-		return;
-
-	/* Detach by re-attaching to the default domain */
-	ret = __iommu_group_for_each_dev(group, group->default_domain,
+	/*
+	 * Changing the domain is done by calling attach_dev() on the new
+	 * domain. This switch does not have to be atomic and DMA can be
+	 * discarded during the transition. DMA must only be able to access
+	 * either new_domain or group->domain, never something else.
+	 *
+	 * Note that this is called in error unwind paths, attaching to a
+	 * domain that has already been attached cannot fail.
+	 */
+	ret = __iommu_group_for_each_dev(group, new_domain,
 					 iommu_group_do_attach_device);
-	if (ret != 0)
-		WARN_ON(1);
-	else
-		group->domain = group->default_domain;
+	if (ret)
+		return ret;
+	group->domain = new_domain;
+	return 0;
 }
 
 void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group)
 {
 	mutex_lock(&group->mutex);
-	__iommu_detach_group(domain, group);
+	__iommu_group_set_core_domain(group);
 	mutex_unlock(&group->mutex);
 }
 EXPORT_SYMBOL_GPL(iommu_detach_group);
@@ -3102,3 +3065,167 @@ static ssize_t iommu_group_store_type(struct iommu_group *group,
 
 	return ret;
 }
+
+/**
+ * iommu_device_use_default_domain() - Device driver wants to handle device
+ *                                     DMA through the kernel DMA API.
+ * @dev: The device.
+ *
+ * The device driver about to bind @dev wants to do DMA through the kernel
+ * DMA API. Return 0 if it is allowed, otherwise an error.
+ */
+int iommu_device_use_default_domain(struct device *dev)
+{
+	struct iommu_group *group = iommu_group_get(dev);
+	int ret = 0;
+
+	if (!group)
+		return 0;
+
+	mutex_lock(&group->mutex);
+	if (group->owner_cnt) {
+		if (group->domain != group->default_domain ||
+		    group->owner) {
+			ret = -EBUSY;
+			goto unlock_out;
+		}
+	}
+
+	group->owner_cnt++;
+
+unlock_out:
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	return ret;
+}
+
+/**
+ * iommu_device_unuse_default_domain() - Device driver stops handling device
+ *                                       DMA through the kernel DMA API.
+ * @dev: The device.
+ *
+ * The device driver doesn't want to do DMA through kernel DMA API anymore.
+ * It must be called after iommu_device_use_default_domain().
+ */
+void iommu_device_unuse_default_domain(struct device *dev)
+{
+	struct iommu_group *group = iommu_group_get(dev);
+
+	if (!group)
+		return;
+
+	mutex_lock(&group->mutex);
+	if (!WARN_ON(!group->owner_cnt))
+		group->owner_cnt--;
+
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+}
+
+static int __iommu_group_alloc_blocking_domain(struct iommu_group *group)
+{
+	struct group_device *dev =
+		list_first_entry(&group->devices, struct group_device, list);
+
+	if (group->blocking_domain)
+		return 0;
+
+	group->blocking_domain =
+		__iommu_domain_alloc(dev->dev->bus, IOMMU_DOMAIN_BLOCKED);
+	if (!group->blocking_domain) {
+		/*
+		 * For drivers that do not yet understand IOMMU_DOMAIN_BLOCKED
+		 * create an empty domain instead.
+		 */
+		group->blocking_domain = __iommu_domain_alloc(
+			dev->dev->bus, IOMMU_DOMAIN_UNMANAGED);
+		if (!group->blocking_domain)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+/**
+ * iommu_group_claim_dma_owner() - Set DMA ownership of a group
+ * @group: The group.
+ * @owner: Caller specified pointer. Used for exclusive ownership.
+ *
+ * This is to support backward compatibility for vfio which manages
+ * the dma ownership in iommu_group level. New invocations on this
+ * interface should be prohibited.
+ */
+int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner)
+{
+	int ret = 0;
+
+	mutex_lock(&group->mutex);
+	if (group->owner_cnt) {
+		ret = -EPERM;
+		goto unlock_out;
+	} else {
+		if (group->domain && group->domain != group->default_domain) {
+			ret = -EBUSY;
+			goto unlock_out;
+		}
+
+		ret = __iommu_group_alloc_blocking_domain(group);
+		if (ret)
+			goto unlock_out;
+
+		ret = __iommu_group_set_domain(group, group->blocking_domain);
+		if (ret)
+			goto unlock_out;
+		group->owner = owner;
+	}
+
+	group->owner_cnt++;
+unlock_out:
+	mutex_unlock(&group->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_group_claim_dma_owner);
+
+/**
+ * iommu_group_release_dma_owner() - Release DMA ownership of a group
+ * @group: The group.
+ *
+ * Release the DMA ownership claimed by iommu_group_claim_dma_owner().
+ */
+void iommu_group_release_dma_owner(struct iommu_group *group)
+{
+	int ret;
+
+	mutex_lock(&group->mutex);
+	if (WARN_ON(!group->owner_cnt || !group->owner))
+		goto unlock_out;
+
+	group->owner_cnt = 0;
+	group->owner = NULL;
+	ret = __iommu_group_set_domain(group, group->default_domain);
+	WARN(ret, "iommu driver failed to attach the default domain");
+
+unlock_out:
+	mutex_unlock(&group->mutex);
+}
+EXPORT_SYMBOL_GPL(iommu_group_release_dma_owner);
+
+/**
+ * iommu_group_dma_owner_claimed() - Query group dma ownership status
+ * @group: The group.
+ *
+ * This provides status query on a given group. It is racy and only for
+ * non-binding status reporting.
+ */
+bool iommu_group_dma_owner_claimed(struct iommu_group *group)
+{
+	unsigned int user;
+
+	mutex_lock(&group->mutex);
+	user = group->owner_cnt;
+	mutex_unlock(&group->mutex);
+
+	return user;
+}
+EXPORT_SYMBOL_GPL(iommu_group_dma_owner_claimed);

drivers/pci/pci-driver.c

@@ -20,6 +20,7 @@
 #include <linux/of_device.h>
 #include <linux/acpi.h>
 #include <linux/dma-map-ops.h>
+#include <linux/iommu.h>
 #include "pci.h"
 #include "pcie/portdrv.h"
 
@@ -1601,6 +1602,7 @@ static int pci_bus_num_vf(struct device *dev)
  */
 static int pci_dma_configure(struct device *dev)
 {
+	struct pci_driver *driver = to_pci_driver(dev->driver);
 	struct device *bridge;
 	int ret = 0;
 
@@ -1616,9 +1618,24 @@ static int pci_dma_configure(struct device *dev)
 	}
 
 	pci_put_host_bridge_device(bridge);
+
+	if (!ret && !driver->driver_managed_dma) {
+		ret = iommu_device_use_default_domain(dev);
+		if (ret)
+			arch_teardown_dma_ops(dev);
+	}
+
 	return ret;
 }
 
+static void pci_dma_cleanup(struct device *dev)
+{
+	struct pci_driver *driver = to_pci_driver(dev->driver);
+
+	if (!driver->driver_managed_dma)
+		iommu_device_unuse_default_domain(dev);
+}
+
 struct bus_type pci_bus_type = {
 	.name		= "pci",
 	.match		= pci_bus_match,
@@ -1632,6 +1649,7 @@ struct bus_type pci_bus_type = {
 	.pm		= PCI_PM_OPS_PTR,
 	.num_vf		= pci_bus_num_vf,
 	.dma_configure	= pci_dma_configure,
+	.dma_cleanup	= pci_dma_cleanup,
 };
 EXPORT_SYMBOL(pci_bus_type);
 

drivers/pci/pci-stub.c

@@ -36,6 +36,7 @@ static struct pci_driver stub_driver = {
 	.name		= "pci-stub",
 	.id_table	= NULL,	/* only dynamic id's */
 	.probe		= pci_stub_probe,
+	.driver_managed_dma = true,
 };
 
 static int __init pci_stub_init(void)

drivers/pci/pcie/portdrv_pci.c

@@ -202,6 +202,8 @@ static struct pci_driver pcie_portdriver = {
 
 	.err_handler	= &pcie_portdrv_err_handler,
 
+	.driver_managed_dma = true,
+
 	.driver.pm	= PCIE_PORTDRV_PM_OPS,
 };
 

drivers/vfio/fsl-mc/vfio_fsl_mc.c

@@ -588,6 +588,7 @@ static struct fsl_mc_driver vfio_fsl_mc_driver = {
 		.name	= "vfio-fsl-mc",
 		.owner	= THIS_MODULE,
 	},
+	.driver_managed_dma = true,
 };
 
 static int __init vfio_fsl_mc_driver_init(void)

drivers/vfio/pci/vfio_pci.c

@@ -196,6 +196,7 @@ static struct pci_driver vfio_pci_driver = {
 	.remove			= vfio_pci_remove,
 	.sriov_configure	= vfio_pci_sriov_configure,
 	.err_handler		= &vfio_pci_core_err_handlers,
+	.driver_managed_dma	= true,
 };
 
 static void __init vfio_pci_fill_ids(void)

drivers/vfio/platform/vfio_amba.c

@@ -95,6 +95,7 @@ static struct amba_driver vfio_amba_driver = {
 		.name = "vfio-amba",
 		.owner = THIS_MODULE,
 	},
+	.driver_managed_dma = true,
 };
 
 module_amba_driver(vfio_amba_driver);

drivers/vfio/platform/vfio_platform.c

@@ -76,6 +76,7 @@ static struct platform_driver vfio_platform_driver = {
 	.driver	= {
 		.name	= "vfio-platform",
 	},
+	.driver_managed_dma = true,
 };
 
 module_platform_driver(vfio_platform_driver);

drivers/vfio/vfio.c

@@ -62,11 +62,6 @@ struct vfio_container {
 	bool				noiommu;
 };
 
-struct vfio_unbound_dev {
-	struct device			*dev;
-	struct list_head		unbound_next;
-};
-
 struct vfio_group {
 	struct device 			dev;
 	struct cdev			cdev;
@@ -76,11 +71,8 @@ struct vfio_group {
 	struct vfio_container		*container;
 	struct list_head		device_list;
 	struct mutex			device_lock;
-	struct notifier_block		nb;
 	struct list_head		vfio_next;
 	struct list_head		container_next;
-	struct list_head		unbound_list;
-	struct mutex			unbound_lock;
 	atomic_t			opened;
 	wait_queue_head_t		container_q;
 	enum vfio_group_type		type;
@@ -281,8 +273,6 @@ void vfio_unregister_iommu_driver(const struct vfio_iommu_driver_ops *ops)
 }
 EXPORT_SYMBOL_GPL(vfio_unregister_iommu_driver);
 
-static int vfio_iommu_group_notifier(struct notifier_block *nb,
-				     unsigned long action, void *data);
 static void vfio_group_get(struct vfio_group *group);
 
 /*
@@ -340,16 +330,8 @@ vfio_group_get_from_iommu(struct iommu_group *iommu_group)
 static void vfio_group_release(struct device *dev)
 {
 	struct vfio_group *group = container_of(dev, struct vfio_group, dev);
-	struct vfio_unbound_dev *unbound, *tmp;
-
-	list_for_each_entry_safe(unbound, tmp,
-				 &group->unbound_list, unbound_next) {
-		list_del(&unbound->unbound_next);
-		kfree(unbound);
-	}
 
 	mutex_destroy(&group->device_lock);
-	mutex_destroy(&group->unbound_lock);
 	iommu_group_put(group->iommu_group);
 	ida_free(&vfio.group_ida, MINOR(group->dev.devt));
 	kfree(group);
@@ -381,8 +363,6 @@ static struct vfio_group *vfio_group_alloc(struct iommu_group *iommu_group,
 	refcount_set(&group->users, 1);
 	INIT_LIST_HEAD(&group->device_list);
 	mutex_init(&group->device_lock);
-	INIT_LIST_HEAD(&group->unbound_list);
-	mutex_init(&group->unbound_lock);
 	init_waitqueue_head(&group->container_q);
 	group->iommu_group = iommu_group;
 	/* put in vfio_group_release() */
@@ -412,13 +392,6 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
 		goto err_put;
 	}
 
-	group->nb.notifier_call = vfio_iommu_group_notifier;
-	err = iommu_group_register_notifier(iommu_group, &group->nb);
-	if (err) {
-		ret = ERR_PTR(err);
-		goto err_put;
-	}
-
 	mutex_lock(&vfio.group_lock);
 
 	/* Did we race creating this group? */
@@ -439,7 +412,6 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
 
 err_unlock:
 	mutex_unlock(&vfio.group_lock);
-	iommu_group_unregister_notifier(group->iommu_group, &group->nb);
 err_put:
 	put_device(&group->dev);
 	return ret;
@@ -464,7 +436,6 @@ static void vfio_group_put(struct vfio_group *group)
 	cdev_device_del(&group->cdev, &group->dev);
 	mutex_unlock(&vfio.group_lock);
 
-	iommu_group_unregister_notifier(group->iommu_group, &group->nb);
 	put_device(&group->dev);
 }
 
@@ -504,175 +475,6 @@ static struct vfio_device *vfio_group_get_device(struct vfio_group *group,
 	return NULL;
 }
 
-/*
- * Some drivers, like pci-stub, are only used to prevent other drivers from
- * claiming a device and are therefore perfectly legitimate for a user owned
- * group.  The pci-stub driver has no dependencies on DMA or the IOVA mapping
- * of the device, but it does prevent the user from having direct access to
- * the device, which is useful in some circumstances.
- *
- * We also assume that we can include PCI interconnect devices, ie. bridges.
- * IOMMU grouping on PCI necessitates that if we lack isolation on a bridge
- * then all of the downstream devices will be part of the same IOMMU group as
- * the bridge.  Thus, if placing the bridge into the user owned IOVA space
- * breaks anything, it only does so for user owned devices downstream.  Note
- * that error notification via MSI can be affected for platforms that handle
- * MSI within the same IOVA space as DMA.
- */
-static const char * const vfio_driver_allowed[] = { "pci-stub" };
-
-static bool vfio_dev_driver_allowed(struct device *dev,
-				    struct device_driver *drv)
-{
-	if (dev_is_pci(dev)) {
-		struct pci_dev *pdev = to_pci_dev(dev);
-
-		if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
-			return true;
-	}
-
-	return match_string(vfio_driver_allowed,
-			    ARRAY_SIZE(vfio_driver_allowed),
-			    drv->name) >= 0;
-}
-
-/*
- * A vfio group is viable for use by userspace if all devices are in
- * one of the following states:
- *  - driver-less
- *  - bound to a vfio driver
- *  - bound to an otherwise allowed driver
- *  - a PCI interconnect device
- *
- * We use two methods to determine whether a device is bound to a vfio
- * driver.  The first is to test whether the device exists in the vfio
- * group.  The second is to test if the device exists on the group
- * unbound_list, indicating it's in the middle of transitioning from
- * a vfio driver to driver-less.
- */
-static int vfio_dev_viable(struct device *dev, void *data)
-{
-	struct vfio_group *group = data;
-	struct vfio_device *device;
-	struct device_driver *drv = READ_ONCE(dev->driver);
-	struct vfio_unbound_dev *unbound;
-	int ret = -EINVAL;
-
-	mutex_lock(&group->unbound_lock);
-	list_for_each_entry(unbound, &group->unbound_list, unbound_next) {
-		if (dev == unbound->dev) {
-			ret = 0;
-			break;
-		}
-	}
-	mutex_unlock(&group->unbound_lock);
-
-	if (!ret || !drv || vfio_dev_driver_allowed(dev, drv))
-		return 0;
-
-	device = vfio_group_get_device(group, dev);
-	if (device) {
-		vfio_device_put(device);
-		return 0;
-	}
-
-	return ret;
-}
-
-/*
- * Async device support
- */
-static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev)
-{
-	struct vfio_device *device;
-
-	/* Do we already know about it?  We shouldn't */
-	device = vfio_group_get_device(group, dev);
-	if (WARN_ON_ONCE(device)) {
-		vfio_device_put(device);
-		return 0;
-	}
-
-	/* Nothing to do for idle groups */
-	if (!atomic_read(&group->container_users))
-		return 0;
-
-	/* TODO Prevent device auto probing */
-	dev_WARN(dev, "Device added to live group %d!\n",
-		 iommu_group_id(group->iommu_group));
-
-	return 0;
-}
-
-static int vfio_group_nb_verify(struct vfio_group *group, struct device *dev)
-{
-	/* We don't care what happens when the group isn't in use */
-	if (!atomic_read(&group->container_users))
-		return 0;
-
-	return vfio_dev_viable(dev, group);
-}
-
-static int vfio_iommu_group_notifier(struct notifier_block *nb,
-				     unsigned long action, void *data)
-{
-	struct vfio_group *group = container_of(nb, struct vfio_group, nb);
-	struct device *dev = data;
-	struct vfio_unbound_dev *unbound;
-
-	switch (action) {
-	case IOMMU_GROUP_NOTIFY_ADD_DEVICE:
-		vfio_group_nb_add_dev(group, dev);
-		break;
-	case IOMMU_GROUP_NOTIFY_DEL_DEVICE:
-		/*
-		 * Nothing to do here.  If the device is in use, then the
-		 * vfio sub-driver should block the remove callback until
-		 * it is unused.  If the device is unused or attached to a
-		 * stub driver, then it should be released and we don't
-		 * care that it will be going away.
-		 */
-		break;
-	case IOMMU_GROUP_NOTIFY_BIND_DRIVER:
-		dev_dbg(dev, "%s: group %d binding to driver\n", __func__,
-			iommu_group_id(group->iommu_group));
-		break;
-	case IOMMU_GROUP_NOTIFY_BOUND_DRIVER:
-		dev_dbg(dev, "%s: group %d bound to driver %s\n", __func__,
-			iommu_group_id(group->iommu_group), dev->driver->name);
-		BUG_ON(vfio_group_nb_verify(group, dev));
-		break;
-	case IOMMU_GROUP_NOTIFY_UNBIND_DRIVER:
-		dev_dbg(dev, "%s: group %d unbinding from driver %s\n",
-			__func__, iommu_group_id(group->iommu_group),
-			dev->driver->name);
-		break;
-	case IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER:
-		dev_dbg(dev, "%s: group %d unbound from driver\n", __func__,
-			iommu_group_id(group->iommu_group));
-		/*
-		 * XXX An unbound device in a live group is ok, but we'd
-		 * really like to avoid the above BUG_ON by preventing other
-		 * drivers from binding to it.  Once that occurs, we have to
-		 * stop the system to maintain isolation.  At a minimum, we'd
-		 * want a toggle to disable driver auto probe for this device.
-		 */
-
-		mutex_lock(&group->unbound_lock);
-		list_for_each_entry(unbound,
-				    &group->unbound_list, unbound_next) {
-			if (dev == unbound->dev) {
-				list_del(&unbound->unbound_next);
-				kfree(unbound);
-				break;
-			}
-		}
-		mutex_unlock(&group->unbound_lock);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
 /*
  * VFIO driver API
  */
@@ -850,29 +652,10 @@ static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
 void vfio_unregister_group_dev(struct vfio_device *device)
 {
 	struct vfio_group *group = device->group;
-	struct vfio_unbound_dev *unbound;
 	unsigned int i = 0;
 	bool interrupted = false;
 	long rc;
 
-	/*
-	 * When the device is removed from the group, the group suddenly
-	 * becomes non-viable; the device has a driver (until the unbind
-	 * completes), but it's not present in the group.  This is bad news
-	 * for any external users that need to re-acquire a group reference
-	 * in order to match and release their existing reference.  To
-	 * solve this, we track such devices on the unbound_list to bridge
-	 * the gap until they're fully unbound.
-	 */
-	unbound = kzalloc(sizeof(*unbound), GFP_KERNEL);
-	if (unbound) {
-		unbound->dev = device->dev;
-		mutex_lock(&group->unbound_lock);
-		list_add(&unbound->unbound_next, &group->unbound_list);
-		mutex_unlock(&group->unbound_lock);
-	}
-	WARN_ON(!unbound);
-
 	vfio_device_put(device);
 	rc = try_wait_for_completion(&device->comp);
 	while (rc <= 0) {
@@ -1159,6 +942,8 @@ static void __vfio_group_unset_container(struct vfio_group *group)
 		driver->ops->detach_group(container->iommu_data,
 					  group->iommu_group);
 
+	iommu_group_release_dma_owner(group->iommu_group);
+
 	group->container = NULL;
 	wake_up(&group->container_q);
 	list_del(&group->container_next);
@@ -1243,13 +1028,19 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd)
 		goto unlock_out;
 	}
 
+	ret = iommu_group_claim_dma_owner(group->iommu_group, f.file);
+	if (ret)
+		goto unlock_out;
+
 	driver = container->iommu_driver;
 	if (driver) {
 		ret = driver->ops->attach_group(container->iommu_data,
 						group->iommu_group,
 						group->type);
-		if (ret)
+		if (ret) {
+			iommu_group_release_dma_owner(group->iommu_group);
 			goto unlock_out;
+		}
 	}
 
 	group->container = container;
@@ -1266,12 +1057,6 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd)
 	return ret;
 }
 
-static bool vfio_group_viable(struct vfio_group *group)
-{
-	return (iommu_group_for_each_dev(group->iommu_group,
-					 group, vfio_dev_viable) == 0);
-}
-
 static int vfio_group_add_container_user(struct vfio_group *group)
 {
 	if (!atomic_inc_not_zero(&group->container_users))
@@ -1281,7 +1066,7 @@ static int vfio_group_add_container_user(struct vfio_group *group)
 		atomic_dec(&group->container_users);
 		return -EPERM;
 	}
-	if (!group->container->iommu_driver || !vfio_group_viable(group)) {
+	if (!group->container->iommu_driver) {
 		atomic_dec(&group->container_users);
 		return -EINVAL;
 	}
@@ -1305,7 +1090,7 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
 	int ret = 0;
 
 	if (0 == atomic_read(&group->container_users) ||
-	    !group->container->iommu_driver || !vfio_group_viable(group))
+	    !group->container->iommu_driver)
 		return -EINVAL;
 
 	if (group->type == VFIO_NO_IOMMU && !capable(CAP_SYS_RAWIO))
@@ -1397,11 +1182,11 @@ static long vfio_group_fops_unl_ioctl(struct file *filep,
 
 		status.flags = 0;
 
-		if (vfio_group_viable(group))
-			status.flags |= VFIO_GROUP_FLAGS_VIABLE;
-
 		if (group->container)
-			status.flags |= VFIO_GROUP_FLAGS_CONTAINER_SET;
+			status.flags |= VFIO_GROUP_FLAGS_CONTAINER_SET |
+					VFIO_GROUP_FLAGS_VIABLE;
+		else if (!iommu_group_dma_owner_claimed(group->iommu_group))
+			status.flags |= VFIO_GROUP_FLAGS_VIABLE;
 
 		if (copy_to_user((void __user *)arg, &status, minsz))
 			return -EFAULT;

include/linux/amba/bus.h

@@ -79,6 +79,14 @@ struct amba_driver {
 	void			(*remove)(struct amba_device *);
 	void			(*shutdown)(struct amba_device *);
 	const struct amba_id	*id_table;
+	/*
+	 * For most device drivers, no need to care about this flag as long as
+	 * all DMAs are handled through the kernel DMA API. For some special
+	 * ones, for example VFIO drivers, they know how to manage the DMA
+	 * themselves and set this flag so that the IOMMU layer will allow them
+	 * to setup and manage their own I/O address space.
+	 */
+	bool driver_managed_dma;
 };
 
 /*

include/linux/device/bus.h

@@ -59,6 +59,8 @@ struct fwnode_handle;
  *		bus supports.
  * @dma_configure:	Called to setup DMA configuration on a device on
  *			this bus.
+ * @dma_cleanup:	Called to cleanup DMA configuration on a device on
+ *			this bus.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
  * @iommu_ops:  IOMMU specific operations for this bus, used to attach IOMMU
@@ -103,6 +105,7 @@ struct bus_type {
 	int (*num_vf)(struct device *dev);
 
 	int (*dma_configure)(struct device *dev);
+	void (*dma_cleanup)(struct device *dev);
 
 	const struct dev_pm_ops *pm;
 

include/linux/fsl/mc.h

@@ -32,6 +32,13 @@ struct fsl_mc_io;
  * @shutdown: Function called at shutdown time to quiesce the device
  * @suspend: Function called when a device is stopped
  * @resume: Function called when a device is resumed
+ * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA.
+ *		For most device drivers, no need to care about this flag
+ *		as long as all DMAs are handled through the kernel DMA API.
+ *		For some special ones, for example VFIO drivers, they know
+ *		how to manage the DMA themselves and set this flag so that
+ *		the IOMMU layer will allow them to setup and manage their
+ *		own I/O address space.
  *
  * Generic DPAA device driver object for device drivers that are registered
  * with a DPRC bus. This structure is to be embedded in each device-specific
@@ -45,6 +52,7 @@ struct fsl_mc_driver {
 	void (*shutdown)(struct fsl_mc_device *dev);
 	int (*suspend)(struct fsl_mc_device *dev, pm_message_t state);
 	int (*resume)(struct fsl_mc_device *dev);
+	bool driver_managed_dma;
 };
 
 #define to_fsl_mc_driver(_drv) \

include/linux/iommu.h

@@ -407,13 +407,6 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev)
 	return dev->iommu->iommu_dev->ops;
 }
 
-#define IOMMU_GROUP_NOTIFY_ADD_DEVICE		1 /* Device added */
-#define IOMMU_GROUP_NOTIFY_DEL_DEVICE		2 /* Pre Device removed */
-#define IOMMU_GROUP_NOTIFY_BIND_DRIVER		3 /* Pre Driver bind */
-#define IOMMU_GROUP_NOTIFY_BOUND_DRIVER		4 /* Post Driver bind */
-#define IOMMU_GROUP_NOTIFY_UNBIND_DRIVER	5 /* Pre Driver unbind */
-#define IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER	6 /* Post Driver unbind */
-
 extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops);
 extern int bus_iommu_probe(struct bus_type *bus);
 extern bool iommu_present(struct bus_type *bus);
@@ -478,10 +471,6 @@ extern int iommu_group_for_each_dev(struct iommu_group *group, void *data,
 extern struct iommu_group *iommu_group_get(struct device *dev);
 extern struct iommu_group *iommu_group_ref_get(struct iommu_group *group);
 extern void iommu_group_put(struct iommu_group *group);
-extern int iommu_group_register_notifier(struct iommu_group *group,
-					 struct notifier_block *nb);
-extern int iommu_group_unregister_notifier(struct iommu_group *group,
-					   struct notifier_block *nb);
 extern int iommu_register_device_fault_handler(struct device *dev,
 					iommu_dev_fault_handler_t handler,
 					void *data);
@@ -675,6 +664,13 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev,
 void iommu_sva_unbind_device(struct iommu_sva *handle);
 u32 iommu_sva_get_pasid(struct iommu_sva *handle);
 
+int iommu_device_use_default_domain(struct device *dev);
+void iommu_device_unuse_default_domain(struct device *dev);
+
+int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner);
+void iommu_group_release_dma_owner(struct iommu_group *group);
+bool iommu_group_dma_owner_claimed(struct iommu_group *group);
+
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
@@ -871,18 +867,6 @@ static inline void iommu_group_put(struct iommu_group *group)
 {
 }
 
-static inline int iommu_group_register_notifier(struct iommu_group *group,
-						struct notifier_block *nb)
-{
-	return -ENODEV;
-}
-
-static inline int iommu_group_unregister_notifier(struct iommu_group *group,
-						  struct notifier_block *nb)
-{
-	return 0;
-}
-
 static inline
 int iommu_register_device_fault_handler(struct device *dev,
 					iommu_dev_fault_handler_t handler,
@@ -1031,6 +1015,30 @@ static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev)
 {
 	return NULL;
 }
+
+static inline int iommu_device_use_default_domain(struct device *dev)
+{
+	return 0;
+}
+
+static inline void iommu_device_unuse_default_domain(struct device *dev)
+{
+}
+
+static inline int
+iommu_group_claim_dma_owner(struct iommu_group *group, void *owner)
+{
+	return -ENODEV;
+}
+
+static inline void iommu_group_release_dma_owner(struct iommu_group *group)
+{
+}
+
+static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group)
+{
+	return false;
+}
 #endif /* CONFIG_IOMMU_API */
 
 /**

include/linux/pci.h

@@ -895,6 +895,13 @@ struct module;
  *              created once it is bound to the driver.
  * @driver:	Driver model structure.
  * @dynids:	List of dynamically added device IDs.
+ * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA.
+ *		For most device drivers, no need to care about this flag
+ *		as long as all DMAs are handled through the kernel DMA API.
+ *		For some special ones, for example VFIO drivers, they know
+ *		how to manage the DMA themselves and set this flag so that
+ *		the IOMMU layer will allow them to setup and manage their
+ *		own I/O address space.
  */
 struct pci_driver {
 	struct list_head	node;
@@ -913,6 +920,7 @@ struct pci_driver {
 	const struct attribute_group **dev_groups;
 	struct device_driver	driver;
 	struct pci_dynids	dynids;
+	bool driver_managed_dma;
 };
 
 static inline struct pci_driver *to_pci_driver(struct device_driver *drv)

include/linux/platform_device.h

@@ -210,6 +210,14 @@ struct platform_driver {
 	struct device_driver driver;
 	const struct platform_device_id *id_table;
 	bool prevent_deferred_probe;
+	/*
+	 * For most device drivers, no need to care about this flag as long as
+	 * all DMAs are handled through the kernel DMA API. For some special
+	 * ones, for example VFIO drivers, they know how to manage the DMA
+	 * themselves and set this flag so that the IOMMU layer will allow them
+	 * to setup and manage their own I/O address space.
+	 */
+	bool driver_managed_dma;
 };
 
 #define to_platform_driver(drv)	(container_of((drv), struct platform_driver, \
@@ -328,8 +336,6 @@ extern int platform_pm_restore(struct device *dev);
 #define platform_pm_restore		NULL
 #endif
 
-extern int platform_dma_configure(struct device *dev);
-
 #ifdef CONFIG_PM_SLEEP
 #define USE_PLATFORM_PM_SLEEP_OPS \
 	.suspend = platform_pm_suspend, \