Re: [RFC PATCH 07/11] IB/Verbs: Use management helper has_mcast() and, cap_mcast() for mcast-check

[Jason Gunthorpe <jgunthorpe@obsidianresearch.com>]

On Fri, Mar 27, 2015 at 04:46:57PM +0100, Michael Wang wrote:
> 
> Introduce helper has_mcast() and cap_mcast() to help us check if an
> IB device or it's port support Multicast.
> 
> Cc: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
> Cc: Doug Ledford <dledford@redhat.com>
> Cc: Ira Weiny <ira.weiny@intel.com>
> Cc: Sean Hefty <sean.hefty@intel.com>
> Signed-off-by: Michael Wang <yun.wang@profitbricks.com>
>  drivers/infiniband/core/cma.c       |  2 +-
>  drivers/infiniband/core/multicast.c |  8 ++++----
>  include/rdma/ib_verbs.h             | 28 ++++++++++++++++++++++++++++
>  3 files changed, 33 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
> index 276fb76..cbbc85b 100644
> +++ b/drivers/infiniband/core/cma.c
> @@ -3398,7 +3398,7 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr)
>                  ib_detach_mcast(id->qp,
>                          &mc->multicast.ib->rec.mgid,
>                          be16_to_cpu(mc->multicast.ib->rec.mlid));
> -            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

>                  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?

>      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?

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 :(

Jason