Re: [RFC PATCH 07/11] IB/Verbs: Use management helper has_mcast() and, cap_mcast() for mcast-check
From: Jason Gunthorpe <hidden>
Date: 2015-03-27 16:28:32
Also in:
linux-nfs, linux-rdma, lkml
On Fri, Mar 27, 2015 at 04:46:57PM +0100, Michael Wang wrote:
quoted hunk ↗ jump to hunk
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-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org> Cc: Doug Ledford <redacted> Cc: Ira Weiny <redacted> Cc: Sean Hefty <redacted> Signed-off-by: Michael Wang <redacted> 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);quoted hunk ↗ jump to hunk
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?
quoted hunk ↗ jump to hunk
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 -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html