1 files changed, 552 insertions, 179 deletions

diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index 1d49aad48c67..ce78c3671539 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -4,6 +4,8 @@
 #include <linux/iommufd.h>
 #include <linux/slab.h>
 #include <linux/iommu.h>
+#include <uapi/linux/iommufd.h>
+#include "../iommu-priv.h"
 
 #include "io_pagetable.h"
 #include "iommufd_private.h"
@@ -15,13 +17,127 @@ MODULE_PARM_DESC(
 	"Allow IOMMUFD to bind to devices even if the platform cannot isolate "
 	"the MSI interrupt window. Enabling this is a security weakness.");
 
+static void iommufd_group_release(struct kref *kref)
+{
+	struct iommufd_group *igroup =
+		container_of(kref, struct iommufd_group, ref);
+
+	WARN_ON(igroup->hwpt || !list_empty(&igroup->device_list));
+
+	xa_cmpxchg(&igroup->ictx->groups, iommu_group_id(igroup->group), igroup,
+		   NULL, GFP_KERNEL);
+	iommu_group_put(igroup->group);
+	mutex_destroy(&igroup->lock);
+	kfree(igroup);
+}
+
+static void iommufd_put_group(struct iommufd_group *group)
+{
+	kref_put(&group->ref, iommufd_group_release);
+}
+
+static bool iommufd_group_try_get(struct iommufd_group *igroup,
+				  struct iommu_group *group)
+{
+	if (!igroup)
+		return false;
+	/*
+	 * group ID's cannot be re-used until the group is put back which does
+	 * not happen if we could get an igroup pointer under the xa_lock.
+	 */
+	if (WARN_ON(igroup->group != group))
+		return false;
+	return kref_get_unless_zero(&igroup->ref);
+}
+
+/*
+ * iommufd needs to store some more data for each iommu_group, we keep a
+ * parallel xarray indexed by iommu_group id to hold this instead of putting it
+ * in the core structure. To keep things simple the iommufd_group memory is
+ * unique within the iommufd_ctx. This makes it easy to check there are no
+ * memory leaks.
+ */
+static struct iommufd_group *iommufd_get_group(struct iommufd_ctx *ictx,
+					       struct device *dev)
+{
+	struct iommufd_group *new_igroup;
+	struct iommufd_group *cur_igroup;
+	struct iommufd_group *igroup;
+	struct iommu_group *group;
+	unsigned int id;
+
+	group = iommu_group_get(dev);
+	if (!group)
+		return ERR_PTR(-ENODEV);
+
+	id = iommu_group_id(group);
+
+	xa_lock(&ictx->groups);
+	igroup = xa_load(&ictx->groups, id);
+	if (iommufd_group_try_get(igroup, group)) {
+		xa_unlock(&ictx->groups);
+		iommu_group_put(group);
+		return igroup;
+	}
+	xa_unlock(&ictx->groups);
+
+	new_igroup = kzalloc(sizeof(*new_igroup), GFP_KERNEL);
+	if (!new_igroup) {
+		iommu_group_put(group);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	kref_init(&new_igroup->ref);
+	mutex_init(&new_igroup->lock);
+	INIT_LIST_HEAD(&new_igroup->device_list);
+	new_igroup->sw_msi_start = PHYS_ADDR_MAX;
+	/* group reference moves into new_igroup */
+	new_igroup->group = group;
+
+	/*
+	 * The ictx is not additionally refcounted here becase all objects using
+	 * an igroup must put it before their destroy completes.
+	 */
+	new_igroup->ictx = ictx;
+
+	/*
+	 * We dropped the lock so igroup is invalid. NULL is a safe and likely
+	 * value to assume for the xa_cmpxchg algorithm.
+	 */
+	cur_igroup = NULL;
+	xa_lock(&ictx->groups);
+	while (true) {
+		igroup = __xa_cmpxchg(&ictx->groups, id, cur_igroup, new_igroup,
+				      GFP_KERNEL);
+		if (xa_is_err(igroup)) {
+			xa_unlock(&ictx->groups);
+			iommufd_put_group(new_igroup);
+			return ERR_PTR(xa_err(igroup));
+		}
+
+		/* new_group was successfully installed */
+		if (cur_igroup == igroup) {
+			xa_unlock(&ictx->groups);
+			return new_igroup;
+		}
+
+		/* Check again if the current group is any good */
+		if (iommufd_group_try_get(igroup, group)) {
+			xa_unlock(&ictx->groups);
+			iommufd_put_group(new_igroup);
+			return igroup;
+		}
+		cur_igroup = igroup;
+	}
+}
+
 void iommufd_device_destroy(struct iommufd_object *obj)
 {
 	struct iommufd_device *idev =
 		container_of(obj, struct iommufd_device, obj);
 
 	iommu_device_release_dma_owner(idev->dev);
-	iommu_group_put(idev->group);
+	iommufd_put_group(idev->igroup);
 	if (!iommufd_selftest_is_mock_dev(idev->dev))
 		iommufd_ctx_put(idev->ictx);
 }
@@ -46,7 +162,7 @@ struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx,
 					   struct device *dev, u32 *id)
 {
 	struct iommufd_device *idev;
-	struct iommu_group *group;
+	struct iommufd_group *igroup;
 	int rc;
 
 	/*
@@ -56,9 +172,29 @@ struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx,
 	if (!device_iommu_capable(dev, IOMMU_CAP_CACHE_COHERENCY))
 		return ERR_PTR(-EINVAL);
 
-	group = iommu_group_get(dev);
-	if (!group)
-		return ERR_PTR(-ENODEV);
+	igroup = iommufd_get_group(ictx, dev);
+	if (IS_ERR(igroup))
+		return ERR_CAST(igroup);
+
+	/*
+	 * For historical compat with VFIO the insecure interrupt path is
+	 * allowed if the module parameter is set. Secure/Isolated means that a
+	 * MemWr operation from the device (eg a simple DMA) cannot trigger an
+	 * interrupt outside this iommufd context.
+	 */
+	if (!iommufd_selftest_is_mock_dev(dev) &&
+	    !iommu_group_has_isolated_msi(igroup->group)) {
+		if (!allow_unsafe_interrupts) {
+			rc = -EPERM;
+			goto out_group_put;
+		}
+
+		dev_warn(
+			dev,
+			"MSI interrupts are not secure, they cannot be isolated by the platform. "
+			"Check that platform features like interrupt remapping are enabled. "
+			"Use the \"allow_unsafe_interrupts\" module parameter to override\n");
+	}
 
 	rc = iommu_device_claim_dma_owner(dev, ictx);
 	if (rc)
@@ -77,8 +213,8 @@ struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx,
 		device_iommu_capable(dev, IOMMU_CAP_ENFORCE_CACHE_COHERENCY);
 	/* The calling driver is a user until iommufd_device_unbind() */
 	refcount_inc(&idev->obj.users);
-	/* group refcount moves into iommufd_device */
-	idev->group = group;
+	/* igroup refcount moves into iommufd_device */
+	idev->igroup = igroup;
 
 	/*
 	 * If the caller fails after this success it must call
@@ -93,7 +229,7 @@ struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx,
 out_release_owner:
 	iommu_device_release_dma_owner(dev);
 out_group_put:
-	iommu_group_put(group);
+	iommufd_put_group(igroup);
 	return ERR_PTR(rc);
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_device_bind, IOMMUFD);
@@ -118,7 +254,8 @@ bool iommufd_ctx_has_group(struct iommufd_ctx *ictx, struct iommu_group *group)
 	xa_lock(&ictx->objects);
 	xa_for_each(&ictx->objects, index, obj) {
 		if (obj->type == IOMMUFD_OBJ_DEVICE &&
-		    container_of(obj, struct iommufd_device, obj)->group == group) {
+		    container_of(obj, struct iommufd_device, obj)
+				    ->igroup->group == group) {
 			xa_unlock(&ictx->objects);
 			return true;
 		}
@@ -155,10 +292,10 @@ u32 iommufd_device_to_id(struct iommufd_device *idev)
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_device_to_id, IOMMUFD);
 
-static int iommufd_device_setup_msi(struct iommufd_device *idev,
-				    struct iommufd_hw_pagetable *hwpt,
-				    phys_addr_t sw_msi_start)
+static int iommufd_group_setup_msi(struct iommufd_group *igroup,
+				   struct iommufd_hw_pagetable *hwpt)
 {
+	phys_addr_t sw_msi_start = igroup->sw_msi_start;
 	int rc;
 
 	/*
@@ -185,128 +322,192 @@ static int iommufd_device_setup_msi(struct iommufd_device *idev,
 		 */
 		hwpt->msi_cookie = true;
 	}
-
-	/*
-	 * For historical compat with VFIO the insecure interrupt path is
-	 * allowed if the module parameter is set. Insecure means that a MemWr
-	 * operation from the device (eg a simple DMA) cannot trigger an
-	 * interrupt outside this iommufd context.
-	 */
-	if (!iommufd_selftest_is_mock_dev(idev->dev) &&
-	    !iommu_group_has_isolated_msi(idev->group)) {
-		if (!allow_unsafe_interrupts)
-			return -EPERM;
-
-		dev_warn(
-			idev->dev,
-			"MSI interrupts are not secure, they cannot be isolated by the platform. "
-			"Check that platform features like interrupt remapping are enabled. "
-			"Use the \"allow_unsafe_interrupts\" module parameter to override\n");
-	}
 	return 0;
 }
 
-static bool iommufd_hw_pagetable_has_group(struct iommufd_hw_pagetable *hwpt,
-					   struct iommu_group *group)
-{
-	struct iommufd_device *cur_dev;
-
-	lockdep_assert_held(&hwpt->devices_lock);
-
-	list_for_each_entry(cur_dev, &hwpt->devices, devices_item)
-		if (cur_dev->group == group)
-			return true;
-	return false;
-}
-
 int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 				struct iommufd_device *idev)
 {
-	phys_addr_t sw_msi_start = PHYS_ADDR_MAX;
 	int rc;
 
-	lockdep_assert_held(&hwpt->devices_lock);
-
-	if (WARN_ON(idev->hwpt))
-		return -EINVAL;
+	mutex_lock(&idev->igroup->lock);
 
-	/*
-	 * Try to upgrade the domain we have, it is an iommu driver bug to
-	 * report IOMMU_CAP_ENFORCE_CACHE_COHERENCY but fail
-	 * enforce_cache_coherency when there are no devices attached to the
-	 * domain.
-	 */
-	if (idev->enforce_cache_coherency && !hwpt->enforce_cache_coherency) {
-		if (hwpt->domain->ops->enforce_cache_coherency)
-			hwpt->enforce_cache_coherency =
-				hwpt->domain->ops->enforce_cache_coherency(
-					hwpt->domain);
-		if (!hwpt->enforce_cache_coherency) {
-			WARN_ON(list_empty(&hwpt->devices));
-			return -EINVAL;
-		}
+	if (idev->igroup->hwpt != NULL && idev->igroup->hwpt != hwpt) {
+		rc = -EINVAL;
+		goto err_unlock;
 	}
 
-	rc = iopt_table_enforce_group_resv_regions(&hwpt->ioas->iopt, idev->dev,
-						   idev->group, &sw_msi_start);
-	if (rc)
-		return rc;
+	/* Try to upgrade the domain we have */
+	if (idev->enforce_cache_coherency) {
+		rc = iommufd_hw_pagetable_enforce_cc(hwpt);
+		if (rc)
+			goto err_unlock;
+	}
 
-	rc = iommufd_device_setup_msi(idev, hwpt, sw_msi_start);
+	rc = iopt_table_enforce_dev_resv_regions(&hwpt->ioas->iopt, idev->dev,
+						 &idev->igroup->sw_msi_start);
 	if (rc)
-		goto err_unresv;
+		goto err_unlock;
 
 	/*
-	 * FIXME: Hack around missing a device-centric iommu api, only attach to
-	 * the group once for the first device that is in the group.
+	 * Only attach to the group once for the first device that is in the
+	 * group. All the other devices will follow this attachment. The user
+	 * should attach every device individually to the hwpt as the per-device
+	 * reserved regions are only updated during individual device
+	 * attachment.
 	 */
-	if (!iommufd_hw_pagetable_has_group(hwpt, idev->group)) {
-		rc = iommu_attach_group(hwpt->domain, idev->group);
+	if (list_empty(&idev->igroup->device_list)) {
+		rc = iommufd_group_setup_msi(idev->igroup, hwpt);
 		if (rc)
 			goto err_unresv;
+
+		rc = iommu_attach_group(hwpt->domain, idev->igroup->group);
+		if (rc)
+			goto err_unresv;
+		idev->igroup->hwpt = hwpt;
 	}
+	refcount_inc(&hwpt->obj.users);
+	list_add_tail(&idev->group_item, &idev->igroup->device_list);
+	mutex_unlock(&idev->igroup->lock);
 	return 0;
 err_unresv:
 	iopt_remove_reserved_iova(&hwpt->ioas->iopt, idev->dev);
+err_unlock:
+	mutex_unlock(&idev->igroup->lock);
 	return rc;
 }
 
-void iommufd_hw_pagetable_detach(struct iommufd_hw_pagetable *hwpt,
-				 struct iommufd_device *idev)
+struct iommufd_hw_pagetable *
+iommufd_hw_pagetable_detach(struct iommufd_device *idev)
 {
-	if (!iommufd_hw_pagetable_has_group(hwpt, idev->group))
-		iommu_detach_group(hwpt->domain, idev->group);
+	struct iommufd_hw_pagetable *hwpt = idev->igroup->hwpt;
+
+	mutex_lock(&idev->igroup->lock);
+	list_del(&idev->group_item);
+	if (list_empty(&idev->igroup->device_list)) {
+		iommu_detach_group(hwpt->domain, idev->igroup->group);
+		idev->igroup->hwpt = NULL;
+	}
 	iopt_remove_reserved_iova(&hwpt->ioas->iopt, idev->dev);
+	mutex_unlock(&idev->igroup->lock);
+
+	/* Caller must destroy hwpt */
+	return hwpt;
 }
 
-static int iommufd_device_do_attach(struct iommufd_device *idev,
-				    struct iommufd_hw_pagetable *hwpt)
+static struct iommufd_hw_pagetable *
+iommufd_device_do_attach(struct iommufd_device *idev,
+			 struct iommufd_hw_pagetable *hwpt)
 {
 	int rc;
 
-	mutex_lock(&hwpt->devices_lock);
 	rc = iommufd_hw_pagetable_attach(hwpt, idev);
 	if (rc)
-		goto out_unlock;
+		return ERR_PTR(rc);
+	return NULL;
+}
 
-	idev->hwpt = hwpt;
-	refcount_inc(&hwpt->obj.users);
-	list_add(&idev->devices_item, &hwpt->devices);
-out_unlock:
-	mutex_unlock(&hwpt->devices_lock);
-	return rc;
+static struct iommufd_hw_pagetable *
+iommufd_device_do_replace(struct iommufd_device *idev,
+			  struct iommufd_hw_pagetable *hwpt)
+{
+	struct iommufd_group *igroup = idev->igroup;
+	struct iommufd_hw_pagetable *old_hwpt;
+	unsigned int num_devices = 0;
+	struct iommufd_device *cur;
+	int rc;
+
+	mutex_lock(&idev->igroup->lock);
+
+	if (igroup->hwpt == NULL) {
+		rc = -EINVAL;
+		goto err_unlock;
+	}
+
+	if (hwpt == igroup->hwpt) {
+		mutex_unlock(&idev->igroup->lock);
+		return NULL;
+	}
+
+	/* Try to upgrade the domain we have */
+	list_for_each_entry(cur, &igroup->device_list, group_item) {
+		num_devices++;
+		if (cur->enforce_cache_coherency) {
+			rc = iommufd_hw_pagetable_enforce_cc(hwpt);
+			if (rc)
+				goto err_unlock;
+		}
+	}
+
+	old_hwpt = igroup->hwpt;
+	if (hwpt->ioas != old_hwpt->ioas) {
+		list_for_each_entry(cur, &igroup->device_list, group_item) {
+			rc = iopt_table_enforce_dev_resv_regions(
+				&hwpt->ioas->iopt, cur->dev, NULL);
+			if (rc)
+				goto err_unresv;
+		}
+	}
+
+	rc = iommufd_group_setup_msi(idev->igroup, hwpt);
+	if (rc)
+		goto err_unresv;
+
+	rc = iommu_group_replace_domain(igroup->group, hwpt->domain);
+	if (rc)
+		goto err_unresv;
+
+	if (hwpt->ioas != old_hwpt->ioas) {
+		list_for_each_entry(cur, &igroup->device_list, group_item)
+			iopt_remove_reserved_iova(&old_hwpt->ioas->iopt,
+						  cur->dev);
+	}
+
+	igroup->hwpt = hwpt;
+
+	/*
+	 * Move the refcounts held by the device_list to the new hwpt. Retain a
+	 * refcount for this thread as the caller will free it.
+	 */
+	refcount_add(num_devices, &hwpt->obj.users);
+	if (num_devices > 1)
+		WARN_ON(refcount_sub_and_test(num_devices - 1,
+					      &old_hwpt->obj.users));
+	mutex_unlock(&idev->igroup->lock);
+
+	/* Caller must destroy old_hwpt */
+	return old_hwpt;
+err_unresv:
+	list_for_each_entry(cur, &igroup->device_list, group_item)
+		iopt_remove_reserved_iova(&hwpt->ioas->iopt, cur->dev);
+err_unlock:
+	mutex_unlock(&idev->igroup->lock);
+	return ERR_PTR(rc);
 }
 
+typedef struct iommufd_hw_pagetable *(*attach_fn)(
+	struct iommufd_device *idev, struct iommufd_hw_pagetable *hwpt);
+
 /*
  * When automatically managing the domains we search for a compatible domain in
  * the iopt and if one is found use it, otherwise create a new domain.
  * Automatic domain selection will never pick a manually created domain.
  */
-static int iommufd_device_auto_get_domain(struct iommufd_device *idev,
-					  struct iommufd_ioas *ioas)
+static struct iommufd_hw_pagetable *
+iommufd_device_auto_get_domain(struct iommufd_device *idev,
+			       struct iommufd_ioas *ioas, u32 *pt_id,
+			       attach_fn do_attach)
 {
+	/*
+	 * iommufd_hw_pagetable_attach() is called by
+	 * iommufd_hw_pagetable_alloc() in immediate attachment mode, same as
+	 * iommufd_device_do_attach(). So if we are in this mode then we prefer
+	 * to use the immediate_attach path as it supports drivers that can't
+	 * directly allocate a domain.
+	 */
+	bool immediate_attach = do_attach == iommufd_device_do_attach;
+	struct iommufd_hw_pagetable *destroy_hwpt;
 	struct iommufd_hw_pagetable *hwpt;
-	int rc;
 
 	/*
 	 * There is no differentiation when domains are allocated, so any domain
@@ -320,50 +521,58 @@ static int iommufd_device_auto_get_domain(struct iommufd_device *idev,
 
 		if (!iommufd_lock_obj(&hwpt->obj))
 			continue;
-		rc = iommufd_device_do_attach(idev, hwpt);
+		destroy_hwpt = (*do_attach)(idev, hwpt);
+		if (IS_ERR(destroy_hwpt)) {
+			iommufd_put_object(&hwpt->obj);
+			/*
+			 * -EINVAL means the domain is incompatible with the
+			 * device. Other error codes should propagate to
+			 * userspace as failure. Success means the domain is
+			 * attached.
+			 */
+			if (PTR_ERR(destroy_hwpt) == -EINVAL)
+				continue;
+			goto out_unlock;
+		}
+		*pt_id = hwpt->obj.id;
 		iommufd_put_object(&hwpt->obj);
-
-		/*
-		 * -EINVAL means the domain is incompatible with the device.
-		 * Other error codes should propagate to userspace as failure.
-		 * Success means the domain is attached.
-		 */
-		if (rc == -EINVAL)
-			continue;
 		goto out_unlock;
 	}
 
-	hwpt = iommufd_hw_pagetable_alloc(idev->ictx, ioas, idev, true);
+	hwpt = iommufd_hw_pagetable_alloc(idev->ictx, ioas, idev,
+					  immediate_attach);
 	if (IS_ERR(hwpt)) {
-		rc = PTR_ERR(hwpt);
+		destroy_hwpt = ERR_CAST(hwpt);
 		goto out_unlock;
 	}
+
+	if (!immediate_attach) {
+		destroy_hwpt = (*do_attach)(idev, hwpt);
+		if (IS_ERR(destroy_hwpt))
+			goto out_abort;
+	} else {
+		destroy_hwpt = NULL;
+	}
+
 	hwpt->auto_domain = true;
+	*pt_id = hwpt->obj.id;
 
-	mutex_unlock(&ioas->mutex);
 	iommufd_object_finalize(idev->ictx, &hwpt->obj);
-	return 0;
+	mutex_unlock(&ioas->mutex);
+	return destroy_hwpt;
+
+out_abort:
+	iommufd_object_abort_and_destroy(idev->ictx, &hwpt->obj);
 out_unlock:
 	mutex_unlock(&ioas->mutex);
-	return rc;
+	return destroy_hwpt;
 }
 
-/**
- * iommufd_device_attach - Connect a device from an iommu_domain
- * @idev: device to attach
- * @pt_id: Input a IOMMUFD_OBJ_IOAS, or IOMMUFD_OBJ_HW_PAGETABLE
- *         Output the IOMMUFD_OBJ_HW_PAGETABLE ID
- *
- * This connects the device to an iommu_domain, either automatically or manually
- * selected. Once this completes the device could do DMA.
- *
- * The caller should return the resulting pt_id back to userspace.
- * This function is undone by calling iommufd_device_detach().
- */
-int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id)
+static int iommufd_device_change_pt(struct iommufd_device *idev, u32 *pt_id,
+				    attach_fn do_attach)
 {
+	struct iommufd_hw_pagetable *destroy_hwpt;
 	struct iommufd_object *pt_obj;
-	int rc;
 
 	pt_obj = iommufd_get_object(idev->ictx, *pt_id, IOMMUFD_OBJ_ANY);
 	if (IS_ERR(pt_obj))
@@ -374,8 +583,8 @@ int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id)
 		struct iommufd_hw_pagetable *hwpt =
 			container_of(pt_obj, struct iommufd_hw_pagetable, obj);
 
-		rc = iommufd_device_do_attach(idev, hwpt);
-		if (rc)
+		destroy_hwpt = (*do_attach)(idev, hwpt);
+		if (IS_ERR(destroy_hwpt))
 			goto out_put_pt_obj;
 		break;
 	}
@@ -383,27 +592,80 @@ int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id)
 		struct iommufd_ioas *ioas =
 			container_of(pt_obj, struct iommufd_ioas, obj);
 
-		rc = iommufd_device_auto_get_domain(idev, ioas);
-		if (rc)
+		destroy_hwpt = iommufd_device_auto_get_domain(idev, ioas, pt_id,
+							      do_attach);
+		if (IS_ERR(destroy_hwpt))
 			goto out_put_pt_obj;
 		break;
 	}
 	default:
-		rc = -EINVAL;
+		destroy_hwpt = ERR_PTR(-EINVAL);
 		goto out_put_pt_obj;
 	}
+	iommufd_put_object(pt_obj);
 
-	refcount_inc(&idev->obj.users);
-	*pt_id = idev->hwpt->obj.id;
-	rc = 0;
+	/* This destruction has to be after we unlock everything */
+	if (destroy_hwpt)
+		iommufd_hw_pagetable_put(idev->ictx, destroy_hwpt);
+	return 0;
 
 out_put_pt_obj:
 	iommufd_put_object(pt_obj);
-	return rc;
+	return PTR_ERR(destroy_hwpt);
+}
+
+/**
+ * iommufd_device_attach - Connect a device to an iommu_domain
+ * @idev: device to attach
+ * @pt_id: Input a IOMMUFD_OBJ_IOAS, or IOMMUFD_OBJ_HW_PAGETABLE
+ *         Output the IOMMUFD_OBJ_HW_PAGETABLE ID
+ *
+ * This connects the device to an iommu_domain, either automatically or manually
+ * selected. Once this completes the device could do DMA.
+ *
+ * The caller should return the resulting pt_id back to userspace.
+ * This function is undone by calling iommufd_device_detach().
+ */
+int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id)
+{
+	int rc;
+
+	rc = iommufd_device_change_pt(idev, pt_id, &iommufd_device_do_attach);
+	if (rc)
+		return rc;
+
+	/*
+	 * Pairs with iommufd_device_detach() - catches caller bugs attempting
+	 * to destroy a device with an attachment.
+	 */
+	refcount_inc(&idev->obj.users);
+	return 0;
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_device_attach, IOMMUFD);
 
 /**
+ * iommufd_device_replace - Change the device's iommu_domain
+ * @idev: device to change
+ * @pt_id: Input a IOMMUFD_OBJ_IOAS, or IOMMUFD_OBJ_HW_PAGETABLE
+ *         Output the IOMMUFD_OBJ_HW_PAGETABLE ID
+ *
+ * This is the same as::
+ *
+ *   iommufd_device_detach();
+ *   iommufd_device_attach();
+ *
+ * If it fails then no change is made to the attachment. The iommu driver may
+ * implement this so there is no disruption in translation. This can only be
+ * called if iommufd_device_attach() has already succeeded.
+ */
+int iommufd_device_replace(struct iommufd_device *idev, u32 *pt_id)
+{
+	return iommufd_device_change_pt(idev, pt_id,
+					&iommufd_device_do_replace);
+}
+EXPORT_SYMBOL_NS_GPL(iommufd_device_replace, IOMMUFD);
+
+/**
  * iommufd_device_detach - Disconnect a device to an iommu_domain
  * @idev: device to detach
  *
@@ -412,33 +674,87 @@ EXPORT_SYMBOL_NS_GPL(iommufd_device_attach, IOMMUFD);
  */
 void iommufd_device_detach(struct iommufd_device *idev)
 {
-	struct iommufd_hw_pagetable *hwpt = idev->hwpt;
-
-	mutex_lock(&hwpt->devices_lock);
-	list_del(&idev->devices_item);
-	idev->hwpt = NULL;
-	iommufd_hw_pagetable_detach(hwpt, idev);
-	mutex_unlock(&hwpt->devices_lock);
-
-	if (hwpt->auto_domain)
-		iommufd_object_deref_user(idev->ictx, &hwpt->obj);
-	else
-		refcount_dec(&hwpt->obj.users);
+	struct iommufd_hw_pagetable *hwpt;
 
+	hwpt = iommufd_hw_pagetable_detach(idev);
+	iommufd_hw_pagetable_put(idev->ictx, hwpt);
 	refcount_dec(&idev->obj.users);
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_device_detach, IOMMUFD);
 
+/*
+ * On success, it will refcount_inc() at a valid new_ioas and refcount_dec() at
+ * a valid cur_ioas (access->ioas). A caller passing in a valid new_ioas should
+ * call iommufd_put_object() if it does an iommufd_get_object() for a new_ioas.
+ */
+static int iommufd_access_change_ioas(struct iommufd_access *access,
+				      struct iommufd_ioas *new_ioas)
+{
+	u32 iopt_access_list_id = access->iopt_access_list_id;
+	struct iommufd_ioas *cur_ioas = access->ioas;
+	int rc;
+
+	lockdep_assert_held(&access->ioas_lock);
+
+	/* We are racing with a concurrent detach, bail */
+	if (cur_ioas != access->ioas_unpin)
+		return -EBUSY;
+
+	if (cur_ioas == new_ioas)
+		return 0;
+
+	/*
+	 * Set ioas to NULL to block any further iommufd_access_pin_pages().
+	 * iommufd_access_unpin_pages() can continue using access->ioas_unpin.
+	 */
+	access->ioas = NULL;
+
+	if (new_ioas) {
+		rc = iopt_add_access(&new_ioas->iopt, access);
+		if (rc) {
+			access->ioas = cur_ioas;
+			return rc;
+		}
+		refcount_inc(&new_ioas->obj.users);
+	}
+
+	if (cur_ioas) {
+		if (access->ops->unmap) {
+			mutex_unlock(&access->ioas_lock);
+			access->ops->unmap(access->data, 0, ULONG_MAX);
+			mutex_lock(&access->ioas_lock);
+		}
+		iopt_remove_access(&cur_ioas->iopt, access, iopt_access_list_id);
+		refcount_dec(&cur_ioas->obj.users);
+	}
+
+	access->ioas = new_ioas;
+	access->ioas_unpin = new_ioas;
+
+	return 0;
+}
+
+static int iommufd_access_change_ioas_id(struct iommufd_access *access, u32 id)
+{
+	struct iommufd_ioas *ioas = iommufd_get_ioas(access->ictx, id);
+	int rc;
+
+	if (IS_ERR(ioas))
+		return PTR_ERR(ioas);
+	rc = iommufd_access_change_ioas(access, ioas);
+	iommufd_put_object(&ioas->obj);
+	return rc;
+}
+
 void iommufd_access_destroy_object(struct iommufd_object *obj)
 {
 	struct iommufd_access *access =
 		container_of(obj, struct iommufd_access, obj);
 
-	if (access->ioas) {
-		iopt_remove_access(&access->ioas->iopt, access);
-		refcount_dec(&access->ioas->obj.users);
-		access->ioas = NULL;
-	}
+	mutex_lock(&access->ioas_lock);
+	if (access->ioas)
+		WARN_ON(iommufd_access_change_ioas(access, NULL));
+	mutex_unlock(&access->ioas_lock);
 	iommufd_ctx_put(access->ictx);
 }
 
@@ -502,61 +818,46 @@ EXPORT_SYMBOL_NS_GPL(iommufd_access_destroy, IOMMUFD);
 
 void iommufd_access_detach(struct iommufd_access *access)
 {
-	struct iommufd_ioas *cur_ioas = access->ioas;
-
 	mutex_lock(&access->ioas_lock);
-	if (WARN_ON(!access->ioas))
-		goto out;
-	/*
-	 * Set ioas to NULL to block any further iommufd_access_pin_pages().
-	 * iommufd_access_unpin_pages() can continue using access->ioas_unpin.
-	 */
-	access->ioas = NULL;
-
-	if (access->ops->unmap) {
+	if (WARN_ON(!access->ioas)) {
 		mutex_unlock(&access->ioas_lock);
-		access->ops->unmap(access->data, 0, ULONG_MAX);
-		mutex_lock(&access->ioas_lock);
+		return;
 	}
-	iopt_remove_access(&cur_ioas->iopt, access);
-	refcount_dec(&cur_ioas->obj.users);
-out:
-	access->ioas_unpin = NULL;
+	WARN_ON(iommufd_access_change_ioas(access, NULL));
 	mutex_unlock(&access->ioas_lock);
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_access_detach, IOMMUFD);
 
 int iommufd_access_attach(struct iommufd_access *access, u32 ioas_id)
 {
-	struct iommufd_ioas *new_ioas;
-	int rc = 0;
+	int rc;
 
 	mutex_lock(&access->ioas_lock);
-	if (WARN_ON(access->ioas || access->ioas_unpin)) {
+	if (WARN_ON(access->ioas)) {
 		mutex_unlock(&access->ioas_lock);
 		return -EINVAL;
 	}
 
-	new_ioas = iommufd_get_ioas(access->ictx, ioas_id);
-	if (IS_ERR(new_ioas)) {
-		mutex_unlock(&access->ioas_lock);
-		return PTR_ERR(new_ioas);
-	}
+	rc = iommufd_access_change_ioas_id(access, ioas_id);
+	mutex_unlock(&access->ioas_lock);
+	return rc;
+}
+EXPORT_SYMBOL_NS_GPL(iommufd_access_attach, IOMMUFD);
+
+int iommufd_access_replace(struct iommufd_access *access, u32 ioas_id)
+{
+	int rc;
 
-	rc = iopt_add_access(&new_ioas->iopt, access);
-	if (rc) {
+	mutex_lock(&access->ioas_lock);
+	if (!access->ioas) {
 		mutex_unlock(&access->ioas_lock);
-		iommufd_put_object(&new_ioas->obj);
-		return rc;
+		return -ENOENT;
 	}
-	iommufd_ref_to_users(&new_ioas->obj);
-
-	access->ioas = new_ioas;
-	access->ioas_unpin = new_ioas;
+	rc = iommufd_access_change_ioas_id(access, ioas_id);
 	mutex_unlock(&access->ioas_lock);
-	return 0;
+	return rc;
 }
-EXPORT_SYMBOL_NS_GPL(iommufd_access_attach, IOMMUFD);
+EXPORT_SYMBOL_NS_GPL(iommufd_access_replace, IOMMUFD);
 
 /**
  * iommufd_access_notify_unmap - Notify users of an iopt to stop using it
@@ -819,3 +1120,75 @@ err_out:
 	return rc;
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_access_rw, IOMMUFD);
+
+int iommufd_get_hw_info(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_hw_info *cmd = ucmd->cmd;
+	void __user *user_ptr = u64_to_user_ptr(cmd->data_uptr);
+	const struct iommu_ops *ops;
+	struct iommufd_device *idev;
+	unsigned int data_len;
+	unsigned int copy_len;
+	void *data;
+	int rc;
+
+	if (cmd->flags || cmd->__reserved)
+		return -EOPNOTSUPP;
+
+	idev = iommufd_get_device(ucmd, cmd->dev_id);
+	if (IS_ERR(idev))
+		return PTR_ERR(idev);
+
+	ops = dev_iommu_ops(idev->dev);
+	if (ops->hw_info) {
+		data = ops->hw_info(idev->dev, &data_len, &cmd->out_data_type);
+		if (IS_ERR(data)) {
+			rc = PTR_ERR(data);
+			goto out_put;
+		}
+
+		/*
+		 * drivers that have hw_info callback should have a unique
+		 * iommu_hw_info_type.
+		 */
+		if (WARN_ON_ONCE(cmd->out_data_type ==
+				 IOMMU_HW_INFO_TYPE_NONE)) {
+			rc = -ENODEV;
+			goto out_free;
+		}
+	} else {
+		cmd->out_data_type = IOMMU_HW_INFO_TYPE_NONE;
+		data_len = 0;
+		data = NULL;
+	}
+
+	copy_len = min(cmd->data_len, data_len);
+	if (copy_to_user(user_ptr, data, copy_len)) {
+		rc = -EFAULT;
+		goto out_free;
+	}
+
+	/*
+	 * Zero the trailing bytes if the user buffer is bigger than the
+	 * data size kernel actually has.
+	 */
+	if (copy_len < cmd->data_len) {
+		if (clear_user(user_ptr + copy_len, cmd->data_len - copy_len)) {
+			rc = -EFAULT;
+			goto out_free;
+		}
+	}
+
+	/*
+	 * We return the length the kernel supports so userspace may know what
+	 * the kernel capability is. It could be larger than the input buffer.
+	 */
+	cmd->data_len = data_len;
+
+	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
+out_free:
+	kfree(data);
+out_put:
+	iommufd_put_object(&idev->obj);
+	return rc;
+}