[PATCH v4 20/22] vfio_pci: Allow to mmap the fault queue

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

The Producer Fault region contains the fault queue in the second page.
There is benefit to let the userspace mmap this area. So let's expose
this mmappable area through a sparse mmap entry and implement the mmap
operation.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
 drivers/vfio/pci/vfio_pci.c | 61 +++++++++++++++++++++++++++++++++++--
 1 file changed, 59 insertions(+), 2 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 019c9fd380a5..3aaa14eb5518 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -223,15 +223,70 @@ static const struct vfio_pci_fault_abi fault_abi_versions[] = {
 
 #define NR_FAULT_ABIS ARRAY_SIZE(fault_abi_versions)
 
+static int vfio_pci_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 index, ret;
+
+	index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT);
+
+	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_fault_prod_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_PRODUCER_FAULT,
 		.header.version = 1,
 		.version = NR_FAULT_ABIS,
 	};
-	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 = 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_fault_cons_regops = {
@@ -242,6 +297,7 @@ static const struct vfio_pci_regops vfio_pci_fault_cons_regops = {
 static const struct vfio_pci_regops vfio_pci_fault_prod_regops = {
 	.rw		= vfio_pci_fault_prod_rw,
 	.release	= vfio_pci_fault_release,
+	.mmap		= vfio_pci_fault_mmap,
 	.add_capability = vfio_pci_fault_prod_add_capability,
 };
 
@@ -300,7 +356,8 @@ static int vfio_pci_init_fault_region(struct vfio_pci_device *vdev)
 		VFIO_REGION_TYPE_NESTED,
 		VFIO_REGION_SUBTYPE_NESTED_FAULT_PROD,
 		&vfio_pci_fault_prod_regops, 2 * PAGE_SIZE,
-		VFIO_REGION_INFO_FLAG_READ, vdev->fault_pages);
+		VFIO_REGION_INFO_FLAG_READ | VFIO_REGION_INFO_FLAG_MMAP,
+		vdev->fault_pages);
 	if (ret)
 		goto out;
 
-- 
2.20.1