From: Jason Gunthorpe <jgg@ziepe.ca>
To: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Cc: linux-rdma@vger.kernel.org
Subject: Re: RDMA subsystem namespace related questions (was Re: Finding the namespace of a struct ib_device)
Date: Fri, 2 Oct 2020 11:04:45 -0300 [thread overview]
Message-ID: <20201002140445.GJ9916@ziepe.ca> (raw)
In-Reply-To: <2859e4a8-777b-48a5-d3c6-2f2effbebef9@oracle.com>
On Wed, Sep 30, 2020 at 06:32:28PM +0800, Ka-Cheong Poon wrote:
> After the aforementioned check on a namespace, what can the client
> do? It still needs to use the existing ib_register_client() to
> register with RDMA subsystem. And after registration, it will get
> notifications for all add/remove upcalls on devices not related
> to the namespace it is interested in. The client can work around
> this if there is a supported way to find out the namespace of a
> device, hence the original proposal of having rdma_dev_to_netns().
Yes, the client would have to check the netns and abort client
registration.
Arguably many of our current clients are wrong in this area since they
only work on init_net anyhow.
It would make sense to introduce a rdma_dev_to_netns() and use it to
block clients on ULPs that use the CM outside init_net.
> that namespace to use it. If there are a large number of namespaces,
> there won't be enough devices to assign to all of them (e.g. the
> hardware I have access to only supports up to 24 VFs). The shared
> mode can be used in this case. Could you please explain what needs
> to be done to support a large number of namespaces in exclusive
> mode?
Modern HW supports many more than 24 VFs, this is the expected
interface
> BTW, if exclusive mode is the future, it may make sense to have
> something like rdma_[un]register_net_client().
I don't think we need this
> > > A new connection comes in and the event handler is called for an
> > > RDMA_CM_EVENT_CONNECT_REQUEST event. There is no obvious namespace info regarding
> > > the event. It seems that the only way to find out the namespace info is to
> > > use the context of struct rdma_cm_id.
> >
> > The rdma_cm_id has only a single namespace, the ULP knows what it is
> > because it created it. A listening ID can't spawn new IDs in different
> > namespaces.
>
> The problem is that the handler is not given the listener's
> rdma_cm_id when it is called. It is only given the new rdma_cm_id.
The new cm_id starts with the same ->context as the listener, the ULP should
use this to pass any data, such as the namespace.
> > It seems like a ULP error to drive cm_id lifetime entirely from the
> > per-net stuff.
>
> It is not an ULP error. While there are many reasons to delete
> a listener, it is not necessary for the listener to die unless the
> namespace is going away.
It certainly currently is.
I'm skeptical ULPs should be doing per-ns stuff like that. A ns aware
ULP should fundamentally be linked to some FD and the ns to use should
derived from the process that FD is linked to. Keeping per-ns stuff
seems wrong.
Jason
next prev parent reply other threads:[~2020-10-02 14:04 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-03 14:02 Finding the namespace of a struct ib_device Ka-Cheong Poon
2020-09-03 17:39 ` Jason Gunthorpe
2020-09-04 4:01 ` Ka-Cheong Poon
2020-09-04 11:32 ` Jason Gunthorpe
2020-09-04 14:02 ` Ka-Cheong Poon
2020-09-06 7:44 ` Leon Romanovsky
2020-09-07 3:33 ` Ka-Cheong Poon
2020-09-07 7:18 ` Leon Romanovsky
2020-09-07 8:24 ` Ka-Cheong Poon
2020-09-07 9:04 ` Leon Romanovsky
2020-09-07 9:28 ` Ka-Cheong Poon
2020-09-07 10:22 ` Leon Romanovsky
2020-09-07 13:48 ` Ka-Cheong Poon
2020-09-29 16:57 ` RDMA subsystem namespace related questions (was Re: Finding the namespace of a struct ib_device) Ka-Cheong Poon
2020-09-29 17:40 ` Jason Gunthorpe
2020-09-30 10:32 ` Ka-Cheong Poon
2020-10-02 14:04 ` Jason Gunthorpe [this message]
2020-10-05 10:27 ` Ka-Cheong Poon
2020-10-05 13:16 ` Jason Gunthorpe
2020-10-05 13:57 ` Ka-Cheong Poon
2020-10-05 14:25 ` Jason Gunthorpe
2020-10-05 15:02 ` Ka-Cheong Poon
2020-10-05 15:45 ` Jason Gunthorpe
2020-10-06 9:36 ` Ka-Cheong Poon
2020-10-06 12:46 ` Jason Gunthorpe
2020-10-07 8:38 ` Ka-Cheong Poon
2020-10-07 11:16 ` Leon Romanovsky
2020-10-08 10:22 ` Ka-Cheong Poon
2020-10-08 10:36 ` Leon Romanovsky
2020-10-08 11:08 ` Ka-Cheong Poon
2020-10-08 16:08 ` Jason Gunthorpe
2020-10-08 16:21 ` Chuck Lever
2020-10-08 16:46 ` Jason Gunthorpe
2020-10-09 4:49 ` Ka-Cheong Poon
2020-10-09 14:39 ` Jason Gunthorpe
2020-10-09 14:48 ` Chuck Lever
2020-10-09 14:57 ` Jason Gunthorpe
2020-10-09 15:00 ` Chuck Lever
2020-10-09 15:07 ` Jason Gunthorpe
2020-10-09 15:27 ` Chuck Lever
2020-10-09 15:34 ` Jason Gunthorpe
2020-10-09 15:52 ` Chuck Lever
2020-10-12 8:20 ` Ka-Cheong Poon
2020-10-16 18:54 ` Jason Gunthorpe
2020-10-16 20:49 ` Chuck Lever
2020-10-19 18:31 ` Jason Gunthorpe
2020-10-07 12:28 ` Jason Gunthorpe
2020-10-08 10:49 ` Ka-Cheong Poon
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201002140445.GJ9916@ziepe.ca \
--to=jgg@ziepe.ca \
--cc=ka-cheong.poon@oracle.com \
--cc=linux-rdma@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).