[PATCH v10 06/11] vfio/pci: Allow to mmap the fault queue

[Eric Auger <eric.auger@xxxxxxxxxx>]

The DMA FAULT region contains the fault ring buffer.
There is benefit to let the userspace mmap this area.
Expose this mmappable area through a sparse mmap entry
and implement the mmap operation.

Signed-off-by: Eric Auger <eric.auger@xxxxxxxxxx>

---

v8 -> v9:
- remove unused index local variable in vfio_pci_fault_mmap
---
 drivers/vfio/pci/vfio_pci.c | 61 +++++++++++++++++++++++++++++++++++--
 1 file changed, 58 insertions(+), 3 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 69595c240baf..3c99f6f3825b 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -266,21 +266,75 @@ static void vfio_pci_dma_fault_release(struct vfio_pci_device *vdev,
 {
 }
 
+static int vfio_pci_dma_fault_mmap(struct vfio_pci_device *vdev,
+				   struct vfio_pci_region *region,
+				   struct vm_area_struct *vma)
+{
+	u64 phys_len, req_len, pgoff, req_start;
+	unsigned long long addr;
+	unsigned int ret;
+
+	phys_len = region->size;
+
+	req_len = vma->vm_end - vma->vm_start;
+	pgoff = vma->vm_pgoff &
+		((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1);
+	req_start = pgoff << PAGE_SHIFT;
+
+	/* only the second page of the producer fault region is mmappable */
+	if (req_start < PAGE_SIZE)
+		return -EINVAL;
+
+	if (req_start + req_len > phys_len)
+		return -EINVAL;
+
+	addr = virt_to_phys(vdev->fault_pages);
+	vma->vm_private_data = vdev;
+	vma->vm_pgoff = (addr >> PAGE_SHIFT) + pgoff;
+
+	ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+			      req_len, vma->vm_page_prot);
+	return ret;
+}
+
 static int vfio_pci_dma_fault_add_capability(struct vfio_pci_device *vdev,
 					     struct vfio_pci_region *region,
 					     struct vfio_info_cap *caps)
 {
+	struct vfio_region_info_cap_sparse_mmap *sparse = NULL;
 	struct vfio_region_info_cap_fault cap = {
 		.header.id = VFIO_REGION_INFO_CAP_DMA_FAULT,
 		.header.version = 1,
 		.version = 1,
 	};
-	return vfio_info_add_capability(caps, &cap.header, sizeof(cap));
+	size_t size = sizeof(*sparse) + sizeof(*sparse->areas);
+	int ret;
+
+	ret = vfio_info_add_capability(caps, &cap.header, sizeof(cap));
+	if (ret)
+		return ret;
+
+	sparse = kzalloc(size, GFP_KERNEL);
+	if (!sparse)
+		return -ENOMEM;
+
+	sparse->header.id = VFIO_REGION_INFO_CAP_SPARSE_MMAP;
+	sparse->header.version = 1;
+	sparse->nr_areas = 1;
+	sparse->areas[0].offset = PAGE_SIZE;
+	sparse->areas[0].size = region->size - PAGE_SIZE;
+
+	ret = vfio_info_add_capability(caps, &sparse->header, size);
+	if (ret)
+		kfree(sparse);
+
+	return ret;
 }
 
 static const struct vfio_pci_regops vfio_pci_dma_fault_regops = {
 	.rw		= vfio_pci_dma_fault_rw,
 	.release	= vfio_pci_dma_fault_release,
+	.mmap		= vfio_pci_dma_fault_mmap,
 	.add_capability = vfio_pci_dma_fault_add_capability,
 };
 
@@ -341,7 +395,8 @@ static int vfio_pci_init_dma_fault_region(struct vfio_pci_device *vdev)
 		VFIO_REGION_TYPE_NESTED,
 		VFIO_REGION_SUBTYPE_NESTED_DMA_FAULT,
 		&vfio_pci_dma_fault_regops, size,
-		VFIO_REGION_INFO_FLAG_READ | VFIO_REGION_INFO_FLAG_WRITE,
+		VFIO_REGION_INFO_FLAG_READ | VFIO_REGION_INFO_FLAG_WRITE |
+		VFIO_REGION_INFO_FLAG_MMAP,
 		vdev->fault_pages);
 	if (ret)
 		goto out;
@@ -349,7 +404,7 @@ static int vfio_pci_init_dma_fault_region(struct vfio_pci_device *vdev)
 	header = (struct vfio_region_dma_fault *)vdev->fault_pages;
 	header->entry_size = sizeof(struct iommu_fault);
 	header->nb_entries = DMA_FAULT_RING_LENGTH;
-	header->offset = sizeof(struct vfio_region_dma_fault);
+	header->offset = PAGE_SIZE;
 
 	ret = iommu_register_device_fault_handler(&vdev->pdev->dev,
 					vfio_pci_iommu_dev_fault_handler,
-- 
2.20.1