Merge branch 'for-next/iommu/default-domains' into for-next/iommu/core

Support for changing the default domain type for singleton IOMMU groups
via sysfs when the constituent device is not already bound to a device
driver.

* for-next/iommu/default-domains:
  iommu: Fix htmldocs warnings in sysfs-kernel-iommu_groups
  iommu: Document usage of "/sys/kernel/iommu_groups/<grp_id>/type" file
  iommu: Take lock before reading iommu group default domain type
  iommu: Add support to change default domain of an iommu group
  iommu: Move def_domain type check for untrusted device into core

Documentation/ABI/testing/sysfs-kernel-iommu_groups

@@ -33,3 +33,33 @@ Description:    In case an RMRR is used only by graphics or USB devices
 		it is now exposed as "direct-relaxable" instead of "direct".
 		In device assignment use case, for instance, those RMRR
 		are considered to be relaxable and safe.
+
+What:		/sys/kernel/iommu_groups/<grp_id>/type
+Date:		November 2020
+KernelVersion:	v5.11
+Contact:	Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>
+Description:	/sys/kernel/iommu_groups/<grp_id>/type shows the type of default
+		domain in use by iommu for this group. See include/linux/iommu.h
+		for possible read values. A privileged user could request kernel to
+		change the group type by writing to this file. Valid write values:
+
+		========  ======================================================
+		DMA       All the DMA transactions from the device in this group
+		          are translated by the iommu.
+		identity  All the DMA transactions from the device in this group
+		          are not translated by the iommu.
+		auto      Change to the type the device was booted with.
+		========  ======================================================
+
+		The default domain type of a group may be modified only when
+
+		- The group has only one device.
+		- The device in the group is not bound to any device driver.
+		  So, the users must unbind the appropriate driver before
+		  changing the default domain type.
+
+		Unbinding a device driver will take away the driver's control
+		over the device and if done on devices that host root file
+		system could lead to catastrophic effects (the users might
+		need to reboot the machine to get it to normal state). So, it's
+		expected that the users understand what they're doing.

drivers/iommu/intel/iommu.c

@@ -2916,13 +2916,6 @@ static int device_def_domain_type(struct device *dev)
 	if (dev_is_pci(dev)) {
 		struct pci_dev *pdev = to_pci_dev(dev);
 
-		/*
-		 * Prevent any device marked as untrusted from getting
-		 * placed into the statically identity mapping domain.
-		 */
-		if (pdev->untrusted)
-			return IOMMU_DOMAIN_DMA;
-
 		if ((iommu_identity_mapping & IDENTMAP_AZALIA) && IS_AZALIA(pdev))
 			return IOMMU_DOMAIN_IDENTITY;
 

drivers/iommu/iommu.c

@@ -93,6 +93,8 @@ static void __iommu_detach_group(struct iommu_domain *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);
+static ssize_t iommu_group_store_type(struct iommu_group *group,
+				      const char *buf, size_t count);
 
 #define IOMMU_GROUP_ATTR(_name, _mode, _show, _store)		\
 struct iommu_group_attribute iommu_group_attr_##_name =		\
@@ -499,6 +501,7 @@ static ssize_t iommu_group_show_type(struct iommu_group *group,
 {
 	char *type = "unknown\n";
 
+	mutex_lock(&group->mutex);
 	if (group->default_domain) {
 		switch (group->default_domain->type) {
 		case IOMMU_DOMAIN_BLOCKED:
@@ -515,6 +518,7 @@ static ssize_t iommu_group_show_type(struct iommu_group *group,
 			break;
 		}
 	}
+	mutex_unlock(&group->mutex);
 	strcpy(buf, type);
 
 	return strlen(type);
@@ -525,7 +529,8 @@ static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL);
 static IOMMU_GROUP_ATTR(reserved_regions, 0444,
 			iommu_group_show_resv_regions, NULL);
 
-static IOMMU_GROUP_ATTR(type, 0444, iommu_group_show_type, NULL);
+static IOMMU_GROUP_ATTR(type, 0644, iommu_group_show_type,
+			iommu_group_store_type);
 
 static void iommu_group_release(struct kobject *kobj)
 {
@@ -1460,12 +1465,14 @@ EXPORT_SYMBOL_GPL(fsl_mc_device_group);
 static int iommu_get_def_domain_type(struct device *dev)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
-	unsigned int type = 0;
+
+	if (dev_is_pci(dev) && to_pci_dev(dev)->untrusted)
+		return IOMMU_DOMAIN_DMA;
 
 	if (ops->def_domain_type)
-		type = ops->def_domain_type(dev);
+		return ops->def_domain_type(dev);
 
-	return (type == 0) ? iommu_def_domain_type : type;
+	return 0;
 }
 
 static int iommu_group_alloc_default_domain(struct bus_type *bus,
@@ -1507,7 +1514,7 @@ static int iommu_alloc_default_domain(struct iommu_group *group,
 	if (group->default_domain)
 		return 0;
 
-	type = iommu_get_def_domain_type(dev);
+	type = iommu_get_def_domain_type(dev) ? : iommu_def_domain_type;
 
 	return iommu_group_alloc_default_domain(dev->bus, group, type);
 }
@@ -1645,12 +1652,8 @@ struct __group_domain_type {
 
 static int probe_get_default_domain_type(struct device *dev, void *data)
 {
-	const struct iommu_ops *ops = dev->bus->iommu_ops;
 	struct __group_domain_type *gtype = data;
-	unsigned int type = 0;
+	unsigned int type = iommu_get_def_domain_type(dev);
-
-	if (ops->def_domain_type)
-		type = ops->def_domain_type(dev);
 
 	if (type) {
 		if (gtype->type && gtype->type != type) {
@@ -3029,3 +3032,228 @@ u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 	return ops->sva_get_pasid(handle);
 }
 EXPORT_SYMBOL_GPL(iommu_sva_get_pasid);
+
+/*
+ * Changes the default domain of an iommu group that has *only* one device
+ *
+ * @group: The group for which the default domain should be changed
+ * @prev_dev: The device in the group (this is used to make sure that the device
+ *	 hasn't changed after the caller has called this function)
+ * @type: The type of the new default domain that gets associated with the group
+ *
+ * Returns 0 on success and error code on failure
+ *
+ * Note:
+ * 1. Presently, this function is called only when user requests to change the
+ *    group's default domain type through /sys/kernel/iommu_groups/<grp_id>/type
+ *    Please take a closer look if intended to use for other purposes.
+ */
+static int iommu_change_dev_def_domain(struct iommu_group *group,
+				       struct device *prev_dev, int type)
+{
+	struct iommu_domain *prev_dom;
+	struct group_device *grp_dev;
+	int ret, dev_def_dom;
+	struct device *dev;
+
+	if (!group)
+		return -EINVAL;
+
+	mutex_lock(&group->mutex);
+
+	if (group->default_domain != group->domain) {
+		dev_err_ratelimited(prev_dev, "Group not assigned to default domain\n");
+		ret = -EBUSY;
+		goto out;
+	}
+
+	/*
+	 * iommu group wasn't locked while acquiring device lock in
+	 * iommu_group_store_type(). So, make sure that the device count hasn't
+	 * changed while acquiring device lock.
+	 *
+	 * Changing default domain of an iommu group with two or more devices
+	 * isn't supported because there could be a potential deadlock. Consider
+	 * the following scenario. T1 is trying to acquire device locks of all
+	 * the devices in the group and before it could acquire all of them,
+	 * there could be another thread T2 (from different sub-system and use
+	 * case) that has already acquired some of the device locks and might be
+	 * waiting for T1 to release other device locks.
+	 */
+	if (iommu_group_device_count(group) != 1) {
+		dev_err_ratelimited(prev_dev, "Cannot change default domain: Group has more than one device\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* Since group has only one device */
+	grp_dev = list_first_entry(&group->devices, struct group_device, list);
+	dev = grp_dev->dev;
+
+	if (prev_dev != dev) {
+		dev_err_ratelimited(prev_dev, "Cannot change default domain: Device has been changed\n");
+		ret = -EBUSY;
+		goto out;
+	}
+
+	prev_dom = group->default_domain;
+	if (!prev_dom) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	dev_def_dom = iommu_get_def_domain_type(dev);
+	if (!type) {
+		/*
+		 * If the user hasn't requested any specific type of domain and
+		 * if the device supports both the domains, then default to the
+		 * domain the device was booted with
+		 */
+		type = dev_def_dom ? : iommu_def_domain_type;
+	} else if (dev_def_dom && type != dev_def_dom) {
+		dev_err_ratelimited(prev_dev, "Device cannot be in %s domain\n",
+				    iommu_domain_type_str(type));
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * Switch to a new domain only if the requested domain type is different
+	 * from the existing default domain type
+	 */
+	if (prev_dom->type == type) {
+		ret = 0;
+		goto out;
+	}
+
+	/* Sets group->default_domain to the newly allocated domain */
+	ret = iommu_group_alloc_default_domain(dev->bus, group, type);
+	if (ret)
+		goto out;
+
+	ret = iommu_create_device_direct_mappings(group, dev);
+	if (ret)
+		goto free_new_domain;
+
+	ret = __iommu_attach_device(group->default_domain, dev);
+	if (ret)
+		goto free_new_domain;
+
+	group->domain = group->default_domain;
+
+	/*
+	 * 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 */
+	iommu_group_do_probe_finalize(dev, group->default_domain);
+	iommu_domain_free(prev_dom);
+	return 0;
+
+free_new_domain:
+	iommu_domain_free(group->default_domain);
+	group->default_domain = prev_dom;
+	group->domain = prev_dom;
+
+out:
+	mutex_unlock(&group->mutex);
+
+	return ret;
+}
+
+/*
+ * Changing the default domain through sysfs requires the users to ubind the
+ * drivers from the devices in the iommu group. Return failure if this doesn't
+ * meet.
+ *
+ * We need to consider the race between this and the device release path.
+ * device_lock(dev) is used here to guarantee that the device release path
+ * will not be entered at the same time.
+ */
+static ssize_t iommu_group_store_type(struct iommu_group *group,
+				      const char *buf, size_t count)
+{
+	struct group_device *grp_dev;
+	struct device *dev;
+	int ret, req_type;
+
+	if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
+		return -EACCES;
+
+	if (WARN_ON(!group))
+		return -EINVAL;
+
+	if (sysfs_streq(buf, "identity"))
+		req_type = IOMMU_DOMAIN_IDENTITY;
+	else if (sysfs_streq(buf, "DMA"))
+		req_type = IOMMU_DOMAIN_DMA;
+	else if (sysfs_streq(buf, "auto"))
+		req_type = 0;
+	else
+		return -EINVAL;
+
+	/*
+	 * Lock/Unlock the group mutex here before device lock to
+	 * 1. Make sure that the iommu group has only one device (this is a
+	 *    prerequisite for step 2)
+	 * 2. Get struct *dev which is needed to lock device
+	 */
+	mutex_lock(&group->mutex);
+	if (iommu_group_device_count(group) != 1) {
+		mutex_unlock(&group->mutex);
+		pr_err_ratelimited("Cannot change default domain: Group has more than one device\n");
+		return -EINVAL;
+	}
+
+	/* Since group has only one device */
+	grp_dev = list_first_entry(&group->devices, struct group_device, list);
+	dev = grp_dev->dev;
+	get_device(dev);
+
+	/*
+	 * Don't hold the group mutex because taking group mutex first and then
+	 * the device lock could potentially cause a deadlock as below. Assume
+	 * two threads T1 and T2. T1 is trying to change default domain of an
+	 * iommu group and T2 is trying to hot unplug a device or release [1] VF
+	 * of a PCIe device which is in the same iommu group. T1 takes group
+	 * mutex and before it could take device lock assume T2 has taken device
+	 * lock and is yet to take group mutex. Now, both the threads will be
+	 * waiting for the other thread to release lock. Below, lock order was
+	 * suggested.
+	 * device_lock(dev);
+	 *	mutex_lock(&group->mutex);
+	 *		iommu_change_dev_def_domain();
+	 *	mutex_unlock(&group->mutex);
+	 * device_unlock(dev);
+	 *
+	 * [1] Typical device release path
+	 * device_lock() from device/driver core code
+	 *  -> bus_notifier()
+	 *   -> iommu_bus_notifier()
+	 *    -> iommu_release_device()
+	 *     -> ops->release_device() vendor driver calls back iommu core code
+	 *      -> mutex_lock() from iommu core code
+	 */
+	mutex_unlock(&group->mutex);
+
+	/* Check if the device in the group still has a driver bound to it */
+	device_lock(dev);
+	if (device_is_bound(dev)) {
+		pr_err_ratelimited("Device is still bound to driver\n");
+		ret = -EBUSY;
+		goto out;
+	}
+
+	ret = iommu_change_dev_def_domain(group, dev, req_type);
+	ret = ret ?: count;
+
+out:
+	device_unlock(dev);
+	put_device(dev);
+
+	return ret;
+}