iommu: Add recoverable fault reporting

Some IOMMU hardware features, for example PCI PRI and Arm SMMU Stall,
enable recoverable I/O page faults. Allow IOMMU drivers to report PRI Page
Requests and Stall events through the new fault reporting API. The
consumer of the fault can be either an I/O page fault handler in the host,
or a guest OS.

Once handled, the fault must be completed by sending a page response back
to the IOMMU. Add an iommu_page_response() function to complete a page
fault.

There are two ways to extend the userspace API:
* Add a field to iommu_page_response and a flag to
  iommu_page_response::flags describing the validity of this field.
* Introduce a new iommu_page_response_X structure with a different version
  number. The kernel must then support both versions.

Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>

1 files changed, 92 insertions, 2 deletions

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 293a6fa716e0..ac1f29c19e59 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -891,7 +891,14 @@ EXPORT_SYMBOL_GPL(iommu_group_unregister_notifier);
  * @data: private data passed as argument to the handler
  *
  * When an IOMMU fault event is received, this handler gets called with the
- * fault event and data as argument. The handler should return 0 on success.
+ * fault event and data as argument. The handler should return 0 on success. If
+ * the fault is recoverable (IOMMU_FAULT_PAGE_REQ), the consumer should also
+ * complete the fault by calling iommu_page_response() with one of the following
+ * response code:
+ * - IOMMU_PAGE_RESP_SUCCESS: retry the translation
+ * - IOMMU_PAGE_RESP_INVALID: terminate the fault
+ * - IOMMU_PAGE_RESP_FAILURE: terminate the fault and stop reporting
+ *   page faults if possible.
  *
  * Return 0 if the fault handler was installed successfully, or an error.
  */
@@ -921,6 +928,8 @@ int iommu_register_device_fault_handler(struct device *dev,
 	}
 	param->fault_param->handler = handler;
 	param->fault_param->data = data;
+	mutex_init(&param->fault_param->lock);
+	INIT_LIST_HEAD(&param->fault_param->faults);
 
 done_unlock:
 	mutex_unlock(&param->lock);
@@ -951,6 +960,12 @@ int iommu_unregister_device_fault_handler(struct device *dev)
 	if (!param->fault_param)
 		goto unlock;
 
+	/* we cannot unregister handler if there are pending faults */
+	if (!list_empty(&param->fault_param->faults)) {
+		ret = -EBUSY;
+		goto unlock;
+	}
+
 	kfree(param->fault_param);
 	param->fault_param = NULL;
 	put_device(dev);
@@ -967,13 +982,15 @@ EXPORT_SYMBOL_GPL(iommu_unregister_device_fault_handler);
  * @evt: fault event data
  *
  * Called by IOMMU drivers when a fault is detected, typically in a threaded IRQ
- * handler.
+ * handler. When this function fails and the fault is recoverable, it is the
+ * caller's responsibility to complete the fault.
  *
  * Return 0 on success, or an error.
  */
 int iommu_report_device_fault(struct device *dev, struct iommu_fault_event *evt)
 {
 	struct iommu_param *param = dev->iommu_param;
+	struct iommu_fault_event *evt_pending = NULL;
 	struct iommu_fault_param *fparam;
 	int ret = 0;
 
@@ -987,13 +1004,86 @@ int iommu_report_device_fault(struct device *dev, struct iommu_fault_event *evt)
 		ret = -EINVAL;
 		goto done_unlock;
 	}
+
+	if (evt->fault.type == IOMMU_FAULT_PAGE_REQ &&
+	    (evt->fault.prm.flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE)) {
+		evt_pending = kmemdup(evt, sizeof(struct iommu_fault_event),
+				      GFP_KERNEL);
+		if (!evt_pending) {
+			ret = -ENOMEM;
+			goto done_unlock;
+		}
+		mutex_lock(&fparam->lock);
+		list_add_tail(&evt_pending->list, &fparam->faults);
+		mutex_unlock(&fparam->lock);
+	}
+
 	ret = fparam->handler(&evt->fault, fparam->data);
+	if (ret && evt_pending) {
+		mutex_lock(&fparam->lock);
+		list_del(&evt_pending->list);
+		mutex_unlock(&fparam->lock);
+		kfree(evt_pending);
+	}
 done_unlock:
 	mutex_unlock(&param->lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_report_device_fault);
 
+int iommu_page_response(struct device *dev,
+			struct iommu_page_response *msg)
+{
+	bool pasid_valid;
+	int ret = -EINVAL;
+	struct iommu_fault_event *evt;
+	struct iommu_fault_page_request *prm;
+	struct iommu_param *param = dev->iommu_param;
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+
+	if (!domain || !domain->ops->page_response)
+		return -ENODEV;
+
+	if (!param || !param->fault_param)
+		return -EINVAL;
+
+	if (msg->version != IOMMU_PAGE_RESP_VERSION_1 ||
+	    msg->flags & ~IOMMU_PAGE_RESP_PASID_VALID)
+		return -EINVAL;
+
+	/* Only send response if there is a fault report pending */
+	mutex_lock(&param->fault_param->lock);
+	if (list_empty(&param->fault_param->faults)) {
+		dev_warn_ratelimited(dev, "no pending PRQ, drop response\n");
+		goto done_unlock;
+	}
+	/*
+	 * Check if we have a matching page request pending to respond,
+	 * otherwise return -EINVAL
+	 */
+	list_for_each_entry(evt, &param->fault_param->faults, list) {
+		prm = &evt->fault.prm;
+		pasid_valid = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
+
+		if ((pasid_valid && prm->pasid != msg->pasid) ||
+		    prm->grpid != msg->grpid)
+			continue;
+
+		/* Sanitize the reply */
+		msg->flags = pasid_valid ? IOMMU_PAGE_RESP_PASID_VALID : 0;
+
+		ret = domain->ops->page_response(dev, evt, msg);
+		list_del(&evt->list);
+		kfree(evt);
+		break;
+	}
+
+done_unlock:
+	mutex_unlock(&param->fault_param->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_page_response);
+
 /**
  * iommu_group_id - Return ID for a group
  * @group: the group to ID