Merge tag 'vfio-v4.16-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Mask INTx from user if pdev->irq is zero (Alexey Kardashevskiy)

 - Capability helper cleanup (Alex Williamson)

 - Allow mmaps overlapping MSI-X vector table with region capability
   exposing this feature (Alexey Kardashevskiy)

 - mdev static cleanups (Xiongwei Song)

* tag 'vfio-v4.16-rc1' of git://github.com/awilliam/linux-vfio:
  vfio: mdev: make a couple of functions and structure vfio_mdev_driver static
  vfio-pci: Allow mapping MSIX BAR
  vfio: Simplify capability helper
  vfio-pci: Mask INTx if a device is not capabable of enabling it

drivers/gpu/drm/i915/gvt/kvmgt.c

@@ -1012,6 +1012,8 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd,
 			if (!sparse)
 				return -ENOMEM;
 
+			sparse->header.id = VFIO_REGION_INFO_CAP_SPARSE_MMAP;
+			sparse->header.version = 1;
 			sparse->nr_areas = nr_areas;
 			cap_type_id = VFIO_REGION_INFO_CAP_SPARSE_MMAP;
 			sparse->areas[0].offset =
@@ -1033,7 +1035,9 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd,
 			break;
 		default:
 			{
-				struct vfio_region_info_cap_type cap_type;
+				struct vfio_region_info_cap_type cap_type = {
+					.header.id = VFIO_REGION_INFO_CAP_TYPE,
+					.header.version = 1 };
 
 				if (info.index >= VFIO_PCI_NUM_REGIONS +
 						vgpu->vdev.num_regions)
@@ -1050,8 +1054,8 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd,
 				cap_type.subtype = vgpu->vdev.region[i].subtype;
 
 				ret = vfio_info_add_capability(&caps,
-						VFIO_REGION_INFO_CAP_TYPE,
-						&cap_type);
+							&cap_type.header,
+							sizeof(cap_type));
 				if (ret)
 					return ret;
 			}
@@ -1061,8 +1065,9 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd,
 			switch (cap_type_id) {
 			case VFIO_REGION_INFO_CAP_SPARSE_MMAP:
 				ret = vfio_info_add_capability(&caps,
-					VFIO_REGION_INFO_CAP_SPARSE_MMAP,
-					sparse);
+					&sparse->header, sizeof(*sparse) +
+					(sparse->nr_areas *
+						sizeof(*sparse->areas)));
 				kfree(sparse);
 				if (ret)
 					return ret;

drivers/vfio/mdev/vfio_mdev.c

@@ -111,19 +111,19 @@ static const struct vfio_device_ops vfio_mdev_dev_ops = {
 	.mmap		= vfio_mdev_mmap,
 };
 
-int vfio_mdev_probe(struct device *dev)
+static int vfio_mdev_probe(struct device *dev)
 {
 	struct mdev_device *mdev = to_mdev_device(dev);
 
 	return vfio_add_group_dev(dev, &vfio_mdev_dev_ops, mdev);
 }
 
-void vfio_mdev_remove(struct device *dev)
+static void vfio_mdev_remove(struct device *dev)
 {
 	vfio_del_group_dev(dev);
 }
 
-struct mdev_driver vfio_mdev_driver = {
+static struct mdev_driver vfio_mdev_driver = {
 	.name	= "vfio_mdev",
 	.probe	= vfio_mdev_probe,
 	.remove	= vfio_mdev_remove,

drivers/vfio/pci/vfio_pci.c

@@ -207,6 +207,9 @@ static bool vfio_pci_nointx(struct pci_dev *pdev)
 		}
 	}
 
+	if (!pdev->irq)
+		return true;
+
 	return false;
 }
 
@@ -562,46 +565,15 @@ static int vfio_pci_for_each_slot_or_bus(struct pci_dev *pdev,
 	return walk.ret;
 }
 
-static int msix_sparse_mmap_cap(struct vfio_pci_device *vdev,
-				struct vfio_info_cap *caps)
+static int msix_mmappable_cap(struct vfio_pci_device *vdev,
+			      struct vfio_info_cap *caps)
 {
-	struct vfio_region_info_cap_sparse_mmap *sparse;
-	size_t end, size;
-	int nr_areas = 2, i = 0, ret;
-
-	end = pci_resource_len(vdev->pdev, vdev->msix_bar);
-
-	/* If MSI-X table is aligned to the start or end, only one area */
-	if (((vdev->msix_offset & PAGE_MASK) == 0) ||
-	    (PAGE_ALIGN(vdev->msix_offset + vdev->msix_size) >= end))
-		nr_areas = 1;
-
-	size = sizeof(*sparse) + (nr_areas * sizeof(*sparse->areas));
-
-	sparse = kzalloc(size, GFP_KERNEL);
-	if (!sparse)
-		return -ENOMEM;
-
-	sparse->nr_areas = nr_areas;
-
-	if (vdev->msix_offset & PAGE_MASK) {
-		sparse->areas[i].offset = 0;
-		sparse->areas[i].size = vdev->msix_offset & PAGE_MASK;
-		i++;
-	}
-
-	if (PAGE_ALIGN(vdev->msix_offset + vdev->msix_size) < end) {
-		sparse->areas[i].offset = PAGE_ALIGN(vdev->msix_offset +
-						     vdev->msix_size);
-		sparse->areas[i].size = end - sparse->areas[i].offset;
-		i++;
-	}
-
-	ret = vfio_info_add_capability(caps, VFIO_REGION_INFO_CAP_SPARSE_MMAP,
-				       sparse);
-	kfree(sparse);
+	struct vfio_info_cap_header header = {
+		.id = VFIO_REGION_INFO_CAP_MSIX_MAPPABLE,
+		.version = 1
+	};
 
-	return ret;
+	return vfio_info_add_capability(caps, &header, sizeof(header));
 }
 
 int vfio_pci_register_dev_region(struct vfio_pci_device *vdev,
@@ -692,7 +664,7 @@ static long vfio_pci_ioctl(void *device_data,
 			if (vdev->bar_mmap_supported[info.index]) {
 				info.flags |= VFIO_REGION_INFO_FLAG_MMAP;
 				if (info.index == vdev->msix_bar) {
-					ret = msix_sparse_mmap_cap(vdev, &caps);
+					ret = msix_mmappable_cap(vdev, &caps);
 					if (ret)
 						return ret;
 				}
@@ -741,7 +713,9 @@ static long vfio_pci_ioctl(void *device_data,
 			break;
 		default:
 		{
-			struct vfio_region_info_cap_type cap_type;
+			struct vfio_region_info_cap_type cap_type = {
+					.header.id = VFIO_REGION_INFO_CAP_TYPE,
+					.header.version = 1 };
 
 			if (info.index >=
 			    VFIO_PCI_NUM_REGIONS + vdev->num_regions)
@@ -756,9 +730,8 @@ static long vfio_pci_ioctl(void *device_data,
 			cap_type.type = vdev->region[i].type;
 			cap_type.subtype = vdev->region[i].subtype;
 
-			ret = vfio_info_add_capability(&caps,
-						      VFIO_REGION_INFO_CAP_TYPE,
-						      &cap_type);
+			ret = vfio_info_add_capability(&caps, &cap_type.header,
+						       sizeof(cap_type));
 			if (ret)
 				return ret;
 
@@ -1122,22 +1095,6 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 	if (req_start + req_len > phys_len)
 		return -EINVAL;
 
-	if (index == vdev->msix_bar) {
-		/*
-		 * Disallow mmaps overlapping the MSI-X table; users don't
-		 * get to touch this directly.  We could find somewhere
-		 * else to map the overlap, but page granularity is only
-		 * a recommendation, not a requirement, so the user needs
-		 * to know which bits are real.  Requiring them to mmap
-		 * around the table makes that clear.
-		 */
-
-		/* If neither entirely above nor below, then it overlaps */
-		if (!(req_start >= vdev->msix_offset + vdev->msix_size ||
-		      req_start + req_len <= vdev->msix_offset))
-			return -EINVAL;
-	}
-
 	/*
 	 * Even though we don't make use of the barmap for the mmap,
 	 * we need to request the region and the barmap tracks that.

drivers/vfio/vfio.c

@@ -1857,63 +1857,19 @@ void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset)
 }
 EXPORT_SYMBOL(vfio_info_cap_shift);
 
-static int sparse_mmap_cap(struct vfio_info_cap *caps, void *cap_type)
+int vfio_info_add_capability(struct vfio_info_cap *caps,
+			     struct vfio_info_cap_header *cap, size_t size)
 {
 	struct vfio_info_cap_header *header;
-	struct vfio_region_info_cap_sparse_mmap *sparse_cap, *sparse = cap_type;
-	size_t size;
 
-	size = sizeof(*sparse) + sparse->nr_areas *  sizeof(*sparse->areas);
-	header = vfio_info_cap_add(caps, size,
-				   VFIO_REGION_INFO_CAP_SPARSE_MMAP, 1);
+	header = vfio_info_cap_add(caps, size, cap->id, cap->version);
 	if (IS_ERR(header))
 		return PTR_ERR(header);
 
-	sparse_cap = container_of(header,
-			struct vfio_region_info_cap_sparse_mmap, header);
-	sparse_cap->nr_areas = sparse->nr_areas;
-	memcpy(sparse_cap->areas, sparse->areas,
-	       sparse->nr_areas * sizeof(*sparse->areas));
-	return 0;
-}
-
-static int region_type_cap(struct vfio_info_cap *caps, void *cap_type)
-{
-	struct vfio_info_cap_header *header;
-	struct vfio_region_info_cap_type *type_cap, *cap = cap_type;
+	memcpy(header + 1, cap + 1, size - sizeof(*header));
 
-	header = vfio_info_cap_add(caps, sizeof(*cap),
-				   VFIO_REGION_INFO_CAP_TYPE, 1);
-	if (IS_ERR(header))
-		return PTR_ERR(header);
-
-	type_cap = container_of(header, struct vfio_region_info_cap_type,
-				header);
-	type_cap->type = cap->type;
-	type_cap->subtype = cap->subtype;
 	return 0;
 }
-
-int vfio_info_add_capability(struct vfio_info_cap *caps, int cap_type_id,
-			     void *cap_type)
-{
-	int ret = -EINVAL;
-
-	if (!cap_type)
-		return 0;
-
-	switch (cap_type_id) {
-	case VFIO_REGION_INFO_CAP_SPARSE_MMAP:
-		ret = sparse_mmap_cap(caps, cap_type);
-		break;
-
-	case VFIO_REGION_INFO_CAP_TYPE:
-		ret = region_type_cap(caps, cap_type);
-		break;
-	}
-
-	return ret;
-}
 EXPORT_SYMBOL(vfio_info_add_capability);
 
 int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, int num_irqs,

include/linux/vfio.h

@@ -145,7 +145,8 @@ extern struct vfio_info_cap_header *vfio_info_cap_add(
 extern void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset);
 
 extern int vfio_info_add_capability(struct vfio_info_cap *caps,
-				    int cap_type_id, void *cap_type);
+				    struct vfio_info_cap_header *cap,
+				    size_t size);
 
 extern int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr,
 					      int num_irqs, int max_irq_type,

include/uapi/linux/vfio.h

@@ -301,6 +301,16 @@ struct vfio_region_info_cap_type {
 #define VFIO_REGION_SUBTYPE_INTEL_IGD_HOST_CFG	(2)
 #define VFIO_REGION_SUBTYPE_INTEL_IGD_LPC_CFG	(3)
 
+/*
+ * The MSIX mappable capability informs that MSIX data of a BAR can be mmapped
+ * which allows direct access to non-MSIX registers which happened to be within
+ * the same system page.
+ *
+ * Even though the userspace gets direct access to the MSIX data, the existing
+ * VFIO_DEVICE_SET_IRQS interface must still be used for MSIX configuration.
+ */
+#define VFIO_REGION_INFO_CAP_MSIX_MAPPABLE	3
+
 /**
  * VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9,
  *				    struct vfio_irq_info)