| Message ID | 162818324222.1511194.15934590640437021149.stgit@omen (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | vfio: device fd address space and vfio-pci mmap invalidation cleanup | expand |
> +void vfio_device_unmap_mapping_range(struct vfio_device *device, > + loff_t start, loff_t len) > +{ > + unmap_mapping_range(device->inode->i_mapping, start, len, true); > +} > +EXPORT_SYMBOL_GPL(vfio_device_unmap_mapping_range); Instead of mirroring the name of unmap_mapping_range maybe give this a name to document the use case? > +extern void vfio_device_unmap_mapping_range(struct vfio_device *device, > + loff_t start, loff_t len); No need for the extern.
On Thu, Aug 05, 2021 at 11:07:22AM -0600, Alex Williamson wrote: > +void vfio_device_unmap_mapping_range(struct vfio_device *device, > + loff_t start, loff_t len) > +{ > + unmap_mapping_range(device->inode->i_mapping, start, len, true); (not a big deal, but still raise this up) It seems to me VFIO MMIO regions do not allow private maps, so even_cow==true should be the same with even_cow==false. even_cow==true will just check the page mapping for each pte even though they should just all match, imho, so logically "false" should work the same and should be tiny-little faster. Thanks, > +} > +EXPORT_SYMBOL_GPL(vfio_device_unmap_mapping_range);
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index b88de89bda31..1e4fc69fee7d 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -560,6 +560,13 @@ static struct inode *vfio_fs_inode_new(void) return inode; } +void vfio_device_unmap_mapping_range(struct vfio_device *device, + loff_t start, loff_t len) +{ + unmap_mapping_range(device->inode->i_mapping, start, len, true); +} +EXPORT_SYMBOL_GPL(vfio_device_unmap_mapping_range); + /** * Device objects - create, release, get, put, search */ diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 90bcc2e9c8eb..712813703e5a 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -66,6 +66,8 @@ int vfio_register_group_dev(struct vfio_device *device); void vfio_unregister_group_dev(struct vfio_device *device); extern struct vfio_device *vfio_device_get_from_dev(struct device *dev); extern void vfio_device_put(struct vfio_device *device); +extern void vfio_device_unmap_mapping_range(struct vfio_device *device, + loff_t start, loff_t len); /* events for the backend driver notify callback */ enum vfio_iommu_notify_type {
Allow bus drivers to use vfio pseudo fs mapping to zap all mmaps across a range of their device files. Signed-off-by: Alex Williamson <alex.williamson@redhat.com> --- drivers/vfio/vfio.c | 7 +++++++ include/linux/vfio.h | 2 ++ 2 files changed, 9 insertions(+)