On 06/06/2014 05:31 AM, Alex Williamson wrote:
> On Thu, 2014-06-05 at 15:50 +1000, Alexey Kardashevskiy wrote:
>> This turns the sPAPR support on and enables VFIO container use
>> in the kernel.
>>
>> This extends vfio_connect_container to support VFIO_SPAPR_TCE_IOMMU type
>> in the host kernel.
>>
>> This registers a memory listener which sPAPR IOMMU will notify when
>> executing H_PUT_TCE/etc DMA calls. The listener then will notify the host
>> kernel about DMA map/unmap operation via VFIO_IOMMU_MAP_DMA/
>> VFIO_IOMMU_UNMAP_DMA ioctls.
>>
>> This executes VFIO_IOMMU_ENABLE ioctl to make sure that the IOMMU is free
>> of mappings and can be exclusively given to the user. At the moment SPAPR
>> is the only platform requiring this call to be implemented.
>>
>> Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
>> ---
>> Changes:
>> v7:
>> * added more details in commit log
>>
>> v5:
>> * multiple returns converted to gotos
>>
>> v4:
>> * fixed format string to use %m which is a glibc extension:
>> "Print output of strerror(errno). No argument is required."
>> ---
>> hw/misc/vfio.c | 28 ++++++++++++++++++++++++++++
>> 1 file changed, 28 insertions(+)
>>
>> diff --git a/hw/misc/vfio.c b/hw/misc/vfio.c
>> index 99141f3..c8e3aff 100644
>> --- a/hw/misc/vfio.c
>> +++ b/hw/misc/vfio.c
>> @@ -3650,6 +3650,34 @@ static int vfio_connect_container(VFIOGroup *group,
>> AddressSpace *as)
>>
>> container->iommu_data.type1.initialized = true;
>>
>> + } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU)) {
>> + ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd);
>> + if (ret) {
>> + error_report("vfio: failed to set group container: %m");
>> + ret = -errno;
>> + goto free_container_exit;
>> + }
>> +
>> + ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU);
>> + if (ret) {
>> + error_report("vfio: failed to set iommu for container: %m");
>> + ret = -errno;
>> + goto free_container_exit;
>> + }
>> +
>> + ret = ioctl(fd, VFIO_IOMMU_ENABLE);
>
> Where's the matching DISABLE? Do we need a different release wrapper
> that includes a disable? Thanks,
It happens in the host kernel when container fd is closed.
I added VFIO_IOMMU_DISABLE for symmetry but do not really need it.
>
> Alex
>
>> + if (ret) {
>> + error_report("vfio: failed to enable container: %m");
>> + ret = -errno;
>> + goto free_container_exit;
>> + }
>> +
>> + container->iommu_data.type1.listener = vfio_memory_listener;
>> + container->iommu_data.release = vfio_listener_release;
>> +
>> + memory_listener_register(&container->iommu_data.type1.listener,
>> + container->space->as);
>> +
>> } else {
>> error_report("vfio: No available IOMMU models");
>> ret = -EINVAL;
>
>
>
--
Alexey
