On 9/14/2018 2:35 PM, Jason Gunthorpe wrote:
> On Fri, Sep 14, 2018 at 01:45:05PM -0500, Steve Wise wrote:
>
>>>> Since the rdma core currently assigned device name strings, I'm thinking
>>>> to just follow that scheme. This leads to slightly different command
>>>> syntax:
>>>>
>>>> rdma link add TYPE dev DEV
>>>>
>>>> EG: rdma link add rxe dev eth0
>>>>
>>>> Then the kernel would return the resulting ib_device name and index.
>>>
>>> I would rather we specify the ib_device name from userspace from the
>>> start..
>>>
>>
>> Why? This is not current practice for rdma devices: the core names them.
>
> That is a bad practice.. Leon has been working on device renaming like
> netdev has, so it would make no sense to have no name here and have
> renaming down the road.
>
> Jason
>
This causes a slit kink in arbitrarily naming rxe rdma devices. From
providers/rxe/rxe.c:
static const struct verbs_match_ent hca_table[] = {
/* FIXME: rxe needs a more reliable way to detect the rxe device */
VERBS_NAME_MATCH("rxe", NULL),
{},
};
So when I add a new rxe device named "foo0", it gets added fine in the
kernel, but the user space side skips it. It doesn't show up in
ibv_devices or ibv_devinfo for example. But the sysfs entries are there...
