iommu: Improve iopf_queue_remove_device()

Convert iopf_queue_remove_device() to return void instead of an error code,
as the return value is never used. This removal helper is designed to be
never-failed, so there's no need for error handling.

Ack all outstanding page requests from the device with the response code of
IOMMU_PAGE_RESP_INVALID, indicating device should not attempt any retry.

Add comments to this helper explaining the steps involved in removing a
device from the iopf queue and disabling its PRI. The individual drivers
are expected to be adjusted accordingly. Here we just define the expected
behaviors of the individual iommu driver from the core's perspective.

Suggested-by: Jason Gunthorpe <[email protected]>
Signed-off-by: Lu Baolu <[email protected]>
Reviewed-by: Jason Gunthorpe <[email protected]>
Tested-by: Yan Zhao <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Joerg Roedel <[email protected]>

Author: LuBaolu

drivers/iommu/intel/iommu.c

@@ -4455,12 +4455,7 @@ static int intel_iommu_disable_iopf(struct device *dev)
 	 */
 	pci_disable_pri(to_pci_dev(dev));
 	info->pri_enabled = 0;
-
-	/*
-	 * With PRI disabled and outstanding PRQs drained, removing device
-	 * from iopf queue should never fail.
-	 */
-	WARN_ON(iopf_queue_remove_device(iommu->iopf_queue, dev));
+	iopf_queue_remove_device(iommu->iopf_queue, dev);
 
 	return 0;
 }

drivers/iommu/io-pgfault.c

@@ -448,50 +448,67 @@ EXPORT_SYMBOL_GPL(iopf_queue_add_device);
  * @queue: IOPF queue
  * @dev: device to remove
  *
- * Caller makes sure that no more faults are reported for this device.
+ * Removing a device from an iopf_queue. It's recommended to follow these
+ * steps when removing a device:
  *
- * Return: 0 on success and <0 on error.
+ * - Disable new PRI reception: Turn off PRI generation in the IOMMU hardware
+ *   and flush any hardware page request queues. This should be done before
+ *   calling into this helper.
+ * - Acknowledge all outstanding PRQs to the device: Respond to all outstanding
+ *   page requests with IOMMU_PAGE_RESP_INVALID, indicating the device should
+ *   not retry. This helper function handles this.
+ * - Disable PRI on the device: After calling this helper, the caller could
+ *   then disable PRI on the device.
+ *
+ * Calling iopf_queue_remove_device() essentially disassociates the device.
+ * The fault_param might still exist, but iommu_page_response() will do
+ * nothing. The device fault parameter reference count has been properly
+ * passed from iommu_report_device_fault() to the fault handling work, and
+ * will eventually be released after iommu_page_response().
  */
-int iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev)
+void iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev)
 {
-	int ret = 0;
 	struct iopf_fault *iopf, *next;
+	struct iommu_page_response resp;
 	struct dev_iommu *param = dev->iommu;
 	struct iommu_fault_param *fault_param;
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
 
 	mutex_lock(&queue->lock);
 	mutex_lock(&param->lock);
 	fault_param = rcu_dereference_check(param->fault_param,
 					    lockdep_is_held(&param->lock));
-	if (!fault_param) {
-		ret = -ENODEV;
-		goto unlock;
-	}
 
-	if (fault_param->queue != queue) {
-		ret = -EINVAL;
+	if (WARN_ON(!fault_param || fault_param->queue != queue))
 		goto unlock;
-	}
 
-	if (!list_empty(&fault_param->faults)) {
-		ret = -EBUSY;
-		goto unlock;
-	}
+	mutex_lock(&fault_param->lock);
+	list_for_each_entry_safe(iopf, next, &fault_param->partial, list)
+		kfree(iopf);
 
-	list_del(&fault_param->queue_list);
+	list_for_each_entry_safe(iopf, next, &fault_param->faults, list) {
+		memset(&resp, 0, sizeof(struct iommu_page_response));
+		resp.pasid = iopf->fault.prm.pasid;
+		resp.grpid = iopf->fault.prm.grpid;
+		resp.code = IOMMU_PAGE_RESP_INVALID;
 
-	/* Just in case some faults are still stuck */
-	list_for_each_entry_safe(iopf, next, &fault_param->partial, list)
+		if (iopf->fault.prm.flags & IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID)
+			resp.flags = IOMMU_PAGE_RESP_PASID_VALID;
+
+		ops->page_response(dev, iopf, &resp);
+		list_del(&iopf->list);
 		kfree(iopf);
+	}
+	mutex_unlock(&fault_param->lock);
+
+	list_del(&fault_param->queue_list);
 
 	/* dec the ref owned by iopf_queue_add_device() */
 	rcu_assign_pointer(param->fault_param, NULL);
 	iopf_put_dev_fault_param(fault_param);
 unlock:
 	mutex_unlock(&param->lock);
 	mutex_unlock(&queue->lock);
-
-	return ret;
 }
 EXPORT_SYMBOL_GPL(iopf_queue_remove_device);
 

include/linux/iommu.h

@@ -1542,7 +1542,7 @@ iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm)
 
 #ifdef CONFIG_IOMMU_IOPF
 int iopf_queue_add_device(struct iopf_queue *queue, struct device *dev);
-int iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev);
+void iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev);
 int iopf_queue_flush_dev(struct device *dev);
 struct iopf_queue *iopf_queue_alloc(const char *name);
 void iopf_queue_free(struct iopf_queue *queue);
@@ -1558,10 +1558,9 @@ iopf_queue_add_device(struct iopf_queue *queue, struct device *dev)
 	return -ENODEV;
 }
 
-static inline int
+static inline void
 iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev)
 {
-	return -ENODEV;
 }
 
 static inline int iopf_queue_flush_dev(struct device *dev)