[PATCH v11 13/13] vfio/pci: Inject page response upon response region fill

[Eric Auger <eric.auger@redhat.com>]

When the userspace increments the head of the page response
buffer ring, let's push the response into the iommu layer.
This is done through a workqueue that pops the responses from
the ring buffer and increment the tail.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
 drivers/vfio/pci/vfio_pci.c         | 40 +++++++++++++++++++++++++++++
 drivers/vfio/pci/vfio_pci_private.h |  8 ++++++
 drivers/vfio/pci/vfio_pci_rdwr.c    |  1 +
 3 files changed, 49 insertions(+)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index e9a904ce3f0d..beea70d70151 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -542,6 +542,32 @@ static int vfio_pci_dma_fault_init(struct vfio_pci_device *vdev)
 	return ret;
 }
 
+static void dma_response_inject(struct work_struct *work)
+{
+	struct vfio_pci_dma_fault_response_work *rwork =
+		container_of(work, struct vfio_pci_dma_fault_response_work, inject);
+	struct vfio_region_dma_fault_response *header = rwork->header;
+	struct vfio_pci_device *vdev = rwork->vdev;
+	struct iommu_page_response *resp;
+	u32 tail, head, size;
+
+	mutex_lock(&vdev->fault_response_queue_lock);
+
+	tail = header->tail;
+	head = header->head;
+	size = header->nb_entries;
+
+	while (CIRC_CNT(head, tail, size) >= 1) {
+		resp = (struct iommu_page_response *)(vdev->fault_response_pages + header->offset +
+						tail * header->entry_size);
+
+		/* TODO: properly handle the return value */
+		iommu_page_response(&vdev->pdev->dev, resp);
+		header->tail = tail = (tail + 1) % size;
+	}
+	mutex_unlock(&vdev->fault_response_queue_lock);
+}
+
 #define DMA_FAULT_RESPONSE_RING_LENGTH 512
 
 static int vfio_pci_dma_fault_response_init(struct vfio_pci_device *vdev)
@@ -585,8 +611,22 @@ static int vfio_pci_dma_fault_response_init(struct vfio_pci_device *vdev)
 	header->nb_entries = DMA_FAULT_RESPONSE_RING_LENGTH;
 	header->offset = PAGE_SIZE;
 
+	vdev->response_work = kzalloc(sizeof(*vdev->response_work), GFP_KERNEL);
+	if (!vdev->response_work)
+		goto out;
+	vdev->response_work->header = header;
+	vdev->response_work->vdev = vdev;
+
+	/* launch the thread that will extract the response */
+	INIT_WORK(&vdev->response_work->inject, dma_response_inject);
+	vdev->dma_fault_response_wq =
+		create_singlethread_workqueue("vfio-dma-fault-response");
+	if (!vdev->dma_fault_response_wq)
+		return -ENOMEM;
+
 	return 0;
 out:
+	kfree(vdev->fault_response_pages);
 	vdev->fault_response_pages = NULL;
 	return ret;
 }
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index 035634521cd0..5944f96ced0c 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -52,6 +52,12 @@ struct vfio_pci_irq_ctx {
 	struct irq_bypass_producer	producer;
 };
 
+struct vfio_pci_dma_fault_response_work {
+	struct work_struct inject;
+	struct vfio_region_dma_fault_response *header;
+	struct vfio_pci_device *vdev;
+};
+
 struct vfio_pci_device;
 struct vfio_pci_region;
 
@@ -145,6 +151,8 @@ struct vfio_pci_device {
 	struct eventfd_ctx	*req_trigger;
 	u8			*fault_pages;
 	u8			*fault_response_pages;
+	struct workqueue_struct *dma_fault_response_wq;
+	struct vfio_pci_dma_fault_response_work *response_work;
 	struct mutex		fault_queue_lock;
 	struct mutex		fault_response_queue_lock;
 	struct list_head	dummy_resources_list;
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index efde0793360b..78c494fe35cc 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -430,6 +430,7 @@ size_t vfio_pci_dma_fault_response_rw(struct vfio_pci_device *vdev, char __user
 		mutex_lock(&vdev->fault_response_queue_lock);
 		header->head = new_head;
 		mutex_unlock(&vdev->fault_response_queue_lock);
+		queue_work(vdev->dma_fault_response_wq, &vdev->response_work->inject);
 	} else {
 		if (copy_to_user(buf, base + pos, count))
 			return -EFAULT;
-- 
2.21.3