vfio: Define device specific region type capability

To this point vfio has only provided an interface to the user that
allows them to determine the number of regions and specifics about
each region.  What the region represents is left to the vfio bus
driver.  vfio-pci chooses to use fixed indexes for fixed resources,
index 0 is BAR0, 1 is BAR1,... 7 is config space, etc.  This works
pretty well since all PCI devices have these regions, even if they
don't necessarily populate all of them.  Then we start to add things
like VGA, which only certain device even support.  We added this the
same way, but now we've wasted a region index, and due to our offset
implementation the corresponding address space, for all devices.

Rather than continuing that process, let's try to make regions self
describing by including a capability that defines their type.  For
vfio-pci we'll make the current VFIO_PCI_NUM_REGIONS fixed, defining
the end of the static indexes and the beginning of self describing
regions.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index fde7b1e609482847c2e59dc3ec4507276d1ac4da..1c37a0e500c69d4cd7fceec1b21b84c019cee212 100644 (file)
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -252,6 +252,34 @@ struct vfio_region_info_cap_sparse_mmap {
        struct vfio_region_sparse_mmap_area areas[];
 };
 
+/*
+ * The device specific type capability allows regions unique to a specific
+ * device or class of devices to be exposed.  This helps solve the problem for
+ * vfio bus drivers of defining which region indexes correspond to which region
+ * on the device, without needing to resort to static indexes, as done by
+ * vfio-pci.  For instance, if we were to go back in time, we might remove
+ * VFIO_PCI_VGA_REGION_INDEX and let vfio-pci simply define that all indexes
+ * greater than or equal to VFIO_PCI_NUM_REGIONS are device specific and we'd
+ * make a "VGA" device specific type to describe the VGA access space.  This
+ * means that non-VGA devices wouldn't need to waste this index, and thus the
+ * address space associated with it due to implementation of device file
+ * descriptor offsets in vfio-pci.
+ *
+ * The current implementation is now part of the user ABI, so we can't use this
+ * for VGA, but there are other upcoming use cases, such as opregions for Intel
+ * IGD devices and framebuffers for vGPU devices.  We missed VGA, but we'll
+ * use this for future additions.
+ *
+ * The structure below defines version 1 of this capability.
+ */
+#define VFIO_REGION_INFO_CAP_TYPE      2
+
+struct vfio_region_info_cap_type {
+       struct vfio_info_cap_header header;
+       __u32 type;     /* global per bus driver */
+       __u32 subtype;  /* type specific */
+};
+
 /**
  * VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9,
  *                                 struct vfio_irq_info)
@@ -387,7 +415,8 @@ enum {
         * between described ranges are unimplemented.
         */
        VFIO_PCI_VGA_REGION_INDEX,
-       VFIO_PCI_NUM_REGIONS
+       VFIO_PCI_NUM_REGIONS = 9 /* Fixed user ABI, region indexes >=9 use */
+                                /* device specific cap to define content. */
 };
 
 enum {