netdev - Re: [RFC PATCH 07/11] IB/Verbs: Use management helper has_mcast() and, cap

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Fri, 27 Mar 2015 18:31:26 +0100
From:	Yun Wang <yun.wang@...fitbricks.com>
To:	"ira.weiny" <ira.weiny@...el.com>
Cc:	Jason Gunthorpe <jgunthorpe@...idianresearch.com>,
	Roland Dreier <roland@...nel.org>,
	Sean Hefty <sean.hefty@...el.com>,
	Hal Rosenstock <hal.rosenstock@...il.com>,
	"linux-rdma@...r.kernel.org" <linux-rdma@...r.kernel.org>,
	linux-kernel <linux-kernel@...r.kernel.org>,
	linux-nfs@...r.kernel.org, netdev@...r.kernel.org,
	"J. Bruce Fields" <bfields@...ldses.org>,
	Trond Myklebust <trond.myklebust@...marydata.com>,
	"David S. Miller" <davem@...emloft.net>,
	Or Gerlitz <ogerlitz@...lanox.com>,
	Moni Shoua <monis@...lanox.com>,
	PJ Waskiewicz <pj.waskiewicz@...idfire.com>,
	Tatyana Nikolova <Tatyana.E.Nikolova@...el.com>,
	Yan Burman <yanb@...lanox.com>,
	Jack Morgenstein <jackm@....mellanox.co.il>,
	Bart Van Assche <bvanassche@....org>,
	Yann Droneaud <ydroneaud@...eya.com>,
	Colin Ian King <colin.king@...onical.com>,
	Majd Dibbiny <majd@...lanox.com>,
	Jiri Kosina <jkosina@...e.cz>,
	Matan Barak <matanb@...lanox.com>,
	Alex Estrin <alex.estrin@...el.com>,
	Doug Ledford <dledford@...hat.com>,
	Eric Dumazet <edumazet@...gle.com>,
	Erez Shitrit <erezsh@...lanox.com>,
	Sagi Grimberg <sagig@...lanox.com>,
	Haggai Eran <haggaie@...lanox.com>,
	Shachar Raindel <raindel@...lanox.com>,
	Mike Marciniszyn <mike.marciniszyn@...el.com>,
	Steve Wise <swise@...ngridcomputing.com>,
	Tom Tucker <tom@....us>, Chuck Lever <chuck.lever@...cle.com>
Subject: Re: [RFC PATCH 07/11] IB/Verbs: Use management helper has_mcast()
 and, cap_mcast() for mcast-check

On Fri, Mar 27, 2015 at 6:05 PM, ira.weiny <ira.weiny@...el.com> wrote:
> On Fri, Mar 27, 2015 at 10:28:20AM -0600, Jason Gunthorpe wrote:
>> On Fri, Mar 27, 2015 at 04:46:57PM +0100, Michael Wang wrote:
>> >
[snip]
>> > -            if (rdma_transport_is_ib(id_priv->cma_dev->device)) {
>> > +            if (has_mcast(id_priv->cma_dev->device)) {
>>
>> This might make more sense as cap_ib_multicast / cap_ip_multicast
>
> Agreed.
>

Will be changed in next version :-)

>>
>> >                  switch (rdma_port_get_link_layer(id->device, id->port_num)) {
>> >                  case IB_LINK_LAYER_INFINIBAND:
>> >                      ib_sa_free_multicast(mc->multicast.ib);
>>
>> > diff --git a/drivers/infiniband/core/multicast.c b/drivers/infiniband/core/multicast.c
>> > index 17573ff..ffeaf27 100644
>> > +++ b/drivers/infiniband/core/multicast.c
>> > @@ -780,7 +780,7 @@ static void mcast_event_handler(struct ib_event_handler *handler,
>> >      int index;
>> >
>> >      dev = container_of(handler, struct mcast_device, event_handler);
>> > -    if (!rdma_port_ll_is_ib(dev->device, event->element.port_num))
>> > +    if (!cap_mcast(dev->device, event->element.port_num))
>> >          return;
>>
>> These should probably be cap_ib_sa - that is what they are guarding
>> against.
>>
>> But it seems redudent, since mcast_add_one will already not add a port that is
>> not IB, so mcast_event_handler is not callable. Something to do with
>> rocee/ib switching?
>
> I'm not sure about this either.  This check seems to be necessary only on a
> per-port level.  It does seem apparent that one can't go from Eth to IB.  What
> happens if you go from IB to Eth on the port?

I also feel it's redundant at first glance, but just not sure if it
could be removed, lack of some knowledge :-P

>
>>
>> >      index = event->element.port_num - dev->start_port;
>> > @@ -807,7 +807,7 @@ static void mcast_add_one(struct ib_device *device)
>> >      int i;
>> >      int count = 0;
>> >
>> > -    if (!rdma_transport_is_ib(device))
>> > +    if (!has_mcast(device))
>> >          return;
>>
>> Again, this seems redundant, every port is tested directly below, why
>> is this check needed?
>
> Agreed.  Same as my comments about the SA support.  This is really only
> needed on ports which need to register with the SA (or perhaps some future
> entity) for Mcast support.

I will recheck all the logical around has_XX() see if we can get rid of them ;-)

>
> Also this is part of the ib_sa module and exports the function
> ib_sa_join_multicast.  So that this point it is covered under the
> cap_sa(device, port) call.
>
> So the implementation of cap_mcast at this point is:
>
> cap_mcast(device, port)
> {
>         return cap_sa(device,port);
> }
>

Sounds good :-) will be in next version.

>>
>> Looking at this, I do wonder how a port can dynamically change between
>> rocee and IB.. If the link value changes then mcast_remove_one will
>> not be a perfect reversal of mcast_add_one. Bug?
>>
>> It feels necessary to understand what happens when a port dynamically
>> switches to ethernet on mlx hardware to validate these patches :(
>
> Agreed.

Maybe we can temporarily reserve the old logical, and gradually solve
these problems?

Regards,
Michael Wang


>
> :-(
>
> -- Ira
>
>>
>> Jason
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html