diff options
Diffstat (limited to 'Documentation/vfio.txt')
| -rw-r--r-- | Documentation/vfio.txt | 75 |
1 files changed, 69 insertions, 6 deletions
diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt index 8eda3635a17d..b9ca02370d46 100644 --- a/Documentation/vfio.txt +++ b/Documentation/vfio.txt @@ -167,17 +167,17 @@ group and can access them as follows: int container, group, device, i; struct vfio_group_status group_status = { .argsz = sizeof(group_status) }; - struct vfio_iommu_x86_info iommu_info = { .argsz = sizeof(iommu_info) }; - struct vfio_iommu_x86_dma_map dma_map = { .argsz = sizeof(dma_map) }; + struct vfio_iommu_type1_info iommu_info = { .argsz = sizeof(iommu_info) }; + struct vfio_iommu_type1_dma_map dma_map = { .argsz = sizeof(dma_map) }; struct vfio_device_info device_info = { .argsz = sizeof(device_info) }; /* Create a new container */ - container = open("/dev/vfio/vfio, O_RDWR); + container = open("/dev/vfio/vfio", O_RDWR); if (ioctl(container, VFIO_GET_API_VERSION) != VFIO_API_VERSION) /* Unknown API version */ - if (!ioctl(container, VFIO_CHECK_EXTENSION, VFIO_X86_IOMMU)) + if (!ioctl(container, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU)) /* Doesn't support the IOMMU driver we want. */ /* Open the group */ @@ -193,7 +193,7 @@ group and can access them as follows: ioctl(group, VFIO_GROUP_SET_CONTAINER, &container); /* Enable the IOMMU model we want */ - ioctl(container, VFIO_SET_IOMMU, VFIO_X86_IOMMU) + ioctl(container, VFIO_SET_IOMMU, VFIO_TYPE1_IOMMU); /* Get addition IOMMU info */ ioctl(container, VFIO_IOMMU_GET_INFO, &iommu_info); @@ -229,7 +229,7 @@ group and can access them as follows: irq.index = i; - ioctl(device, VFIO_DEVICE_GET_IRQ_INFO, ®); + ioctl(device, VFIO_DEVICE_GET_IRQ_INFO, &irq); /* Setup IRQs... eventfds, VFIO_DEVICE_SET_IRQS */ } @@ -283,6 +283,69 @@ a direct pass through for VFIO_DEVICE_* ioctls. The read/write/mmap interfaces implement the device region access defined by the device's own VFIO_DEVICE_GET_REGION_INFO ioctl. + +PPC64 sPAPR implementation note +------------------------------------------------------------------------------- + +This implementation has some specifics: + +1) Only one IOMMU group per container is supported as an IOMMU group +represents the minimal entity which isolation can be guaranteed for and +groups are allocated statically, one per a Partitionable Endpoint (PE) +(PE is often a PCI domain but not always). + +2) The hardware supports so called DMA windows - the PCI address range +within which DMA transfer is allowed, any attempt to access address space +out of the window leads to the whole PE isolation. + +3) PPC64 guests are paravirtualized but not fully emulated. There is an API +to map/unmap pages for DMA, and it normally maps 1..32 pages per call and +currently there is no way to reduce the number of calls. In order to make things +faster, the map/unmap handling has been implemented in real mode which provides +an excellent performance which has limitations such as inability to do +locked pages accounting in real time. + +So 3 additional ioctls have been added: + + VFIO_IOMMU_SPAPR_TCE_GET_INFO - returns the size and the start + of the DMA window on the PCI bus. + + VFIO_IOMMU_ENABLE - enables the container. The locked pages accounting + is done at this point. This lets user first to know what + the DMA window is and adjust rlimit before doing any real job. + + VFIO_IOMMU_DISABLE - disables the container. + + +The code flow from the example above should be slightly changed: + + ..... + /* Add the group to the container */ + ioctl(group, VFIO_GROUP_SET_CONTAINER, &container); + + /* Enable the IOMMU model we want */ + ioctl(container, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU) + + /* Get addition sPAPR IOMMU info */ + vfio_iommu_spapr_tce_info spapr_iommu_info; + ioctl(container, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &spapr_iommu_info); + + if (ioctl(container, VFIO_IOMMU_ENABLE)) + /* Cannot enable container, may be low rlimit */ + + /* Allocate some space and setup a DMA mapping */ + dma_map.vaddr = mmap(0, 1024 * 1024, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); + + dma_map.size = 1024 * 1024; + dma_map.iova = 0; /* 1MB starting at 0x0 from device view */ + dma_map.flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE; + + /* Check here is .iova/.size are within DMA window from spapr_iommu_info */ + + ioctl(container, VFIO_IOMMU_MAP_DMA, &dma_map); + ..... + ------------------------------------------------------------------------------- [1] VFIO was originally an acronym for "Virtual Function I/O" in its |