Automatic merge of 'master' into merge (2023-12-10 10:26)

drivers/iommu/iommufd/device.c

@@ -571,7 +571,7 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev,
 			continue;
 		destroy_hwpt = (*do_attach)(idev, hwpt);
 		if (IS_ERR(destroy_hwpt)) {
-			iommufd_put_object(&hwpt->obj);
+			iommufd_put_object(idev->ictx, &hwpt->obj);
 			/*
 			 * -EINVAL means the domain is incompatible with the
 			 * device. Other error codes should propagate to
@@ -583,7 +583,7 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev,
 			goto out_unlock;
 		}
 		*pt_id = hwpt->obj.id;
-		iommufd_put_object(&hwpt->obj);
+		iommufd_put_object(idev->ictx, &hwpt->obj);
 		goto out_unlock;
 	}
 
@@ -652,15 +652,15 @@ static int iommufd_device_change_pt(struct iommufd_device *idev, u32 *pt_id,
 		destroy_hwpt = ERR_PTR(-EINVAL);
 		goto out_put_pt_obj;
 	}
-	iommufd_put_object(pt_obj);
+	iommufd_put_object(idev->ictx, pt_obj);
 
 	/* 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);
+	iommufd_put_object(idev->ictx, pt_obj);
 	return PTR_ERR(destroy_hwpt);
 }
 
@@ -792,7 +792,7 @@ static int iommufd_access_change_ioas_id(struct iommufd_access *access, u32 id)
 	if (IS_ERR(ioas))
 		return PTR_ERR(ioas);
 	rc = iommufd_access_change_ioas(access, ioas);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(access->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -941,7 +941,7 @@ void iommufd_access_notify_unmap(struct io_pagetable *iopt, unsigned long iova,
 
 		access->ops->unmap(access->data, iova, length);
 
-		iommufd_put_object(&access->obj);
+		iommufd_put_object(access->ictx, &access->obj);
 		xa_lock(&ioas->iopt.access_list);
 	}
 	xa_unlock(&ioas->iopt.access_list);
@@ -1243,6 +1243,6 @@ int iommufd_get_hw_info(struct iommufd_ucmd *ucmd)
 out_free:
 	kfree(data);
 out_put:
-	iommufd_put_object(&idev->obj);
+	iommufd_put_object(ucmd->ictx, &idev->obj);
 	return rc;
 }

drivers/iommu/iommufd/hw_pagetable.c

@@ -318,9 +318,9 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd)
 	if (ioas)
 		mutex_unlock(&ioas->mutex);
 out_put_pt:
-	iommufd_put_object(pt_obj);
+	iommufd_put_object(ucmd->ictx, pt_obj);
 out_put_idev:
-	iommufd_put_object(&idev->obj);
+	iommufd_put_object(ucmd->ictx, &idev->obj);
 	return rc;
 }
 
@@ -345,7 +345,7 @@ int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd)
 	rc = iopt_set_dirty_tracking(&ioas->iopt, hwpt_paging->common.domain,
 				     enable);
 
-	iommufd_put_object(&hwpt_paging->common.obj);
+	iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
 	return rc;
 }
 
@@ -368,6 +368,6 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd)
 	rc = iopt_read_and_clear_dirty_data(
 		&ioas->iopt, hwpt_paging->common.domain, cmd->flags, cmd);
 
-	iommufd_put_object(&hwpt_paging->common.obj);
+	iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
 	return rc;
 }

drivers/iommu/iommufd/ioas.c

@@ -105,7 +105,7 @@ int iommufd_ioas_iova_ranges(struct iommufd_ucmd *ucmd)
 		rc = -EMSGSIZE;
 out_put:
 	up_read(&ioas->iopt.iova_rwsem);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -175,7 +175,7 @@ int iommufd_ioas_allow_iovas(struct iommufd_ucmd *ucmd)
 		interval_tree_remove(node, &allowed_iova);
 		kfree(container_of(node, struct iopt_allowed, node));
 	}
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -228,7 +228,7 @@ int iommufd_ioas_map(struct iommufd_ucmd *ucmd)
 	cmd->iova = iova;
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 out_put:
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -258,7 +258,7 @@ int iommufd_ioas_copy(struct iommufd_ucmd *ucmd)
 		return PTR_ERR(src_ioas);
 	rc = iopt_get_pages(&src_ioas->iopt, cmd->src_iova, cmd->length,
 			    &pages_list);
-	iommufd_put_object(&src_ioas->obj);
+	iommufd_put_object(ucmd->ictx, &src_ioas->obj);
 	if (rc)
 		return rc;
 
@@ -279,7 +279,7 @@ int iommufd_ioas_copy(struct iommufd_ucmd *ucmd)
 	cmd->dst_iova = iova;
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 out_put_dst:
-	iommufd_put_object(&dst_ioas->obj);
+	iommufd_put_object(ucmd->ictx, &dst_ioas->obj);
 out_pages:
 	iopt_free_pages_list(&pages_list);
 	return rc;
@@ -315,7 +315,7 @@ int iommufd_ioas_unmap(struct iommufd_ucmd *ucmd)
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 
 out_put:
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -393,6 +393,6 @@ int iommufd_ioas_option(struct iommufd_ucmd *ucmd)
 		rc = -EOPNOTSUPP;
 	}
 
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }

drivers/iommu/iommufd/iommufd_private.h

@@ -21,6 +21,7 @@ struct iommufd_ctx {
 	struct file *file;
 	struct xarray objects;
 	struct xarray groups;
+	wait_queue_head_t destroy_wait;
 
 	u8 account_mode;
 	/* Compatibility with VFIO no iommu */
@@ -135,47 +136,90 @@ enum iommufd_object_type {
 
 /* Base struct for all objects with a userspace ID handle. */
 struct iommufd_object {
-	struct rw_semaphore destroy_rwsem;
+	refcount_t shortterm_users;
 	refcount_t users;
 	enum iommufd_object_type type;
 	unsigned int id;
 };
 
 static inline bool iommufd_lock_obj(struct iommufd_object *obj)
 {
-	if (!down_read_trylock(&obj->destroy_rwsem))
+	if (!refcount_inc_not_zero(&obj->users))
 		return false;
-	if (!refcount_inc_not_zero(&obj->users)) {
-		up_read(&obj->destroy_rwsem);
+	if (!refcount_inc_not_zero(&obj->shortterm_users)) {
+		/*
+		 * If the caller doesn't already have a ref on obj this must be
+		 * called under the xa_lock. Otherwise the caller is holding a
+		 * ref on users. Thus it cannot be one before this decrement.
+		 */
+		refcount_dec(&obj->users);
 		return false;
 	}
 	return true;
 }
 
 struct iommufd_object *iommufd_get_object(struct iommufd_ctx *ictx, u32 id,
 					  enum iommufd_object_type type);
-static inline void iommufd_put_object(struct iommufd_object *obj)
+static inline void iommufd_put_object(struct iommufd_ctx *ictx,
+				      struct iommufd_object *obj)
 {
+	/*
+	 * Users first, then shortterm so that REMOVE_WAIT_SHORTTERM never sees
+	 * a spurious !0 users with a 0 shortterm_users.
+	 */
 	refcount_dec(&obj->users);
-	up_read(&obj->destroy_rwsem);
+	if (refcount_dec_and_test(&obj->shortterm_users))
+		wake_up_interruptible_all(&ictx->destroy_wait);
 }
 
 void iommufd_object_abort(struct iommufd_ctx *ictx, struct iommufd_object *obj);
 void iommufd_object_abort_and_destroy(struct iommufd_ctx *ictx,
 				      struct iommufd_object *obj);
 void iommufd_object_finalize(struct iommufd_ctx *ictx,
 			     struct iommufd_object *obj);
-void __iommufd_object_destroy_user(struct iommufd_ctx *ictx,
-				   struct iommufd_object *obj, bool allow_fail);
+
+enum {
+	REMOVE_WAIT_SHORTTERM = 1,
+};
+int iommufd_object_remove(struct iommufd_ctx *ictx,
+			  struct iommufd_object *to_destroy, u32 id,
+			  unsigned int flags);
+
+/*
+ * The caller holds a users refcount and wants to destroy the object. At this
+ * point the caller has no shortterm_users reference and at least the xarray
+ * will be holding one.
+ */
 static inline void iommufd_object_destroy_user(struct iommufd_ctx *ictx,
 					       struct iommufd_object *obj)
 {
-	__iommufd_object_destroy_user(ictx, obj, false);
+	int ret;
+
+	ret = iommufd_object_remove(ictx, obj, obj->id, REMOVE_WAIT_SHORTTERM);
+
+	/*
+	 * If there is a bug and we couldn't destroy the object then we did put
+	 * back the caller's users refcount and will eventually try to free it
+	 * again during close.
+	 */
+	WARN_ON(ret);
 }
-static inline void iommufd_object_deref_user(struct iommufd_ctx *ictx,
-					     struct iommufd_object *obj)
+
+/*
+ * The HWPT allocated by autodomains is used in possibly many devices and
+ * is automatically destroyed when its refcount reaches zero.
+ *
+ * If userspace uses the HWPT manually, even for a short term, then it will
+ * disrupt this refcounting and the auto-free in the kernel will not work.
+ * Userspace that tries to use the automatically allocated HWPT must be careful
+ * to ensure that it is consistently destroyed, eg by not racing accesses
+ * and by not attaching an automatic HWPT to a device manually.
+ */
+static inline void
+iommufd_object_put_and_try_destroy(struct iommufd_ctx *ictx,
+				   struct iommufd_object *obj)
 {
-	__iommufd_object_destroy_user(ictx, obj, true);
+	iommufd_object_remove(ictx, obj, obj->id, 0);
 }
 
 struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
@@ -311,7 +355,7 @@ static inline void iommufd_hw_pagetable_put(struct iommufd_ctx *ictx,
 		lockdep_assert_not_held(&hwpt_paging->ioas->mutex);
 
 		if (hwpt_paging->auto_domain) {
-			iommufd_object_deref_user(ictx, &hwpt->obj);
+			iommufd_object_put_and_try_destroy(ictx, &hwpt->obj);
 			return;
 		}
 	}