@@ -239,6 +239,123 @@ group and can access them as follows::
/* Gratuitous device reset and go... */
ioctl(device, VFIO_DEVICE_RESET);
+IOMMUFD and vfio_iommu_type1
+----------------------------
+
+IOMMUFD is the new user API to manage I/O page tables from userspace.
+It intends to be the portal of delivering advanced userspace DMA
+features (nested translation [5], PASID [6], etc.) while being backward
+compatible with the vfio_iommu_type1 driver. Eventually vfio_iommu_type1
+will be deprecated.
+
+With the backward compatibility, no change is required for legacy VFIO
+drivers or applications to connect a VFIO device to IOMMUFD.
+
+ When CONFIG_IOMMUFD_VFIO_CONTAINER=n, VFIO container still provides
+ /dev/vfio/vfio which connects to vfio_iommu_type1. To disable VFIO
+ container and vfio_iommu_type1, the administrator could symbol link
+ /dev/vfio/vfio to /dev/iommu to enable VFIO container emulation
+ in IOMMUFD.
+
+ When CONFIG_IOMMUFD_VFIO_CONTAINER=y, IOMMUFD directly provides
+ /dev/vfio/vfio while the VFIO container and vfio_iommu_type1 are
+ explicitly disabled.
+
+VFIO Device cdev
+----------------
+
+Traditionally user acquires a device fd via VFIO_GROUP_GET_DEVICE_FD
+in a VFIO group.
+
+With CONFIG_VFIO_DEVICE_CDEV=y the user can now acquire a device fd
+by directly opening a character device /dev/vfio/devices/vfioX where
+"X" is the number allocated uniquely by VFIO for registered devices.
+
+The cdev only works with IOMMUFD. Both VFIO drivers and applications
+must adapt to the new cdev security model which requires using
+VFIO_DEVICE_BIND_IOMMUFD to claim DMA ownership before starting to
+actually use the device. Once BIND succeeds then a VFIO device can
+be fully accessed by the user.
+
+VFIO device cdev doesn't rely on VFIO group/container/iommu drivers.
+Hence those modules can be fully compiled out in an environment
+where no legacy VFIO application exists.
+
+So far SPAPR does not support IOMMUFD yet. So it cannot support device
+cdev neither.
+
+Device cdev Example
+-------------------
+
+Assume user wants to access PCI device 0000:6a:01.0::
+
+ $ ls /sys/bus/pci/devices/0000:6a:01.0/vfio-dev/
+ vfio0
+
+This device is therefore represented as vfio0. The user can verify
+its existence::
+
+ $ ls -l /dev/vfio/devices/vfio0
+ crw------- 1 root root 511, 0 Feb 16 01:22 /dev/vfio/devices/vfio0
+ $ cat /sys/bus/pci/devices/0000:6a:01.0/vfio-dev/vfio0/dev
+ 511:0
+ $ ls -l /dev/char/511\:0
+ lrwxrwxrwx 1 root root 21 Feb 16 01:22 /dev/char/511:0 -> ../vfio/devices/vfio0
+
+Then provide the user with access to the device if unprivileged
+operation is desired::
+
+ $ chown user:user /dev/vfio/devices/vfio0
+
+Finally the user could get cdev fd by::
+
+ cdev_fd = open("/dev/vfio/devices/vfio0", O_RDWR);
+
+An opened cdev_fd doesn't give the user any permission of accessing
+the device except binding the cdev_fd to an iommufd. After that point
+then the device is fully accessible including attaching it to an
+IOMMUFD IOAS/HWPT to enable userspace DMA::
+
+ struct vfio_device_bind_iommufd bind = {
+ .argsz = sizeof(bind),
+ .flags = 0,
+ };
+ struct iommu_ioas_alloc alloc_data = {
+ .size = sizeof(alloc_data),
+ .flags = 0,
+ };
+ struct vfio_device_attach_iommufd_pt attach_data = {
+ .argsz = sizeof(attach_data),
+ .flags = 0,
+ };
+ struct iommu_ioas_map map = {
+ .size = sizeof(map),
+ .flags = IOMMU_IOAS_MAP_READABLE |
+ IOMMU_IOAS_MAP_WRITEABLE |
+ IOMMU_IOAS_MAP_FIXED_IOVA,
+ .__reserved = 0,
+ };
+
+ iommufd = open("/dev/iommu", O_RDWR);
+
+ bind.iommufd = iommufd; // negative value means vfio-noiommu mode
+ ioctl(cdev_fd, VFIO_DEVICE_BIND_IOMMUFD, &bind);
+
+ ioctl(iommufd, IOMMU_IOAS_ALLOC, &alloc_data);
+ attach_data.pt_id = alloc_data.out_ioas_id;
+ ioctl(cdev_fd, VFIO_DEVICE_ATTACH_IOMMUFD_PT, &attach_data);
+
+ /* Allocate some space and setup a DMA mapping */
+ map.user_va = (int64_t)mmap(0, 1024 * 1024, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
+ map.iova = 0; /* 1MB starting at 0x0 from device view */
+ map.length = 1024 * 1024;
+ map.ioas_id = alloc_data.out_ioas_id;;
+
+ ioctl(iommufd, IOMMU_IOAS_MAP, &map);
+
+ /* Other device operations as stated in "VFIO Usage Example" */
+
VFIO User API
-------------------------------------------------------------------------------
@@ -566,3 +683,11 @@ This implementation has some specifics:
\-0d.1
00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev 90)
+
+.. [5] Nested translation is an IOMMU feature which supports two stage
+ address translations. This improves the address translation efficiency
+ in IOMMU virtualization.
+
+.. [6] PASID stands for Process Address Space ID, introduced by PCI
+ Express. It is a prerequisite for Shared Virtual Addressing (SVA)
+ and Scalable I/O Virtualization (Scalable IOV).
This gives notes for userspace applications on device cdev usage. Signed-off-by: Yi Liu <yi.l.liu@intel.com> --- Documentation/driver-api/vfio.rst | 125 ++++++++++++++++++++++++++++++ 1 file changed, 125 insertions(+)