From: Moni Shoua <mo...@mellanox.com>
Since RoCEv2 is a protocol over IP header it is required to send IGMP
join and leave requests to the network when joining and leaving
multicast groups.
Signed-off-by: Moni Shoua <mo...@mellanox.com>
Signed-off-by: Somnath Kotur <somnath.ko...@emulex.com>
---
drivers/infiniband/core/cma.c | 78 ++++++++++++++++++++++++++++++++++++++--
1 files changed, 74 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 50635fe..6e658e8 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -38,6 +38,7 @@
#include <linux/in6.h>
#include <linux/mutex.h>
#include <linux/random.h>
+#include <linux/igmp.h>
#include <linux/idr.h>
#include <linux/inetdevice.h>
#include <linux/slab.h>
@@ -185,6 +186,7 @@ struct rdma_id_private {
u8 reuseaddr;
u8 afonly;
enum ib_gid_type gid_type;
+ bool igmp_joined;
};
struct cma_multicast {
@@ -283,6 +285,26 @@ static inline void cma_set_ip_ver(struct cma_hdr *hdr, u8
ip_ver)
hdr->ip_version = (ip_ver << 4) | (hdr->ip_version & 0xF);
}
+static int cma_igmp_send(struct net_device *ndev, union ib_gid *mgid, bool
join)
+{
+ struct in_device *in_dev = NULL;
+
+ if (ndev) {
+ rtnl_lock();
+ in_dev = __in_dev_get_rtnl(ndev);
+ if (in_dev) {
+ if (join)
+ ip_mc_inc_group(in_dev,
+ *(__be32 *)(mgid->raw+12));
+ else
+ ip_mc_dec_group(in_dev,
+ *(__be32 *)(mgid->raw+12));
+ }
+ rtnl_unlock();
+ }
+ return (in_dev) ? 0 : -ENODEV;
+}
+
static void cma_attach_to_dev(struct rdma_id_private *id_priv,
struct cma_device *cma_dev)
{
@@ -585,6 +607,7 @@ struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler
event_handler,
INIT_LIST_HEAD(&id_priv->listen_list);
INIT_LIST_HEAD(&id_priv->mc_list);
get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num);
+ id_priv->igmp_joined = false;
return &id_priv->id;
}
@@ -1076,6 +1099,20 @@ static void cma_leave_mc_groups(struct rdma_id_private
*id_priv)
kfree(mc);
break;
case IB_LINK_LAYER_ETHERNET:
+ if (id_priv->igmp_joined) {
+ struct rdma_dev_addr *dev_addr =
&id_priv->id.route.addr.dev_addr;
+ struct net_device *ndev = NULL;
+
+ if (dev_addr->bound_dev_if)
+ ndev = dev_get_by_index(&init_net,
+
dev_addr->bound_dev_if);
+ if (ndev) {
+ cma_igmp_send(ndev,
+
&mc->multicast.ib->rec.mgid,
+ false);
+ dev_put(ndev);
+ }
+ }
kref_put(&mc->mcref, release_mc);
break;
default:
@@ -3356,7 +3393,7 @@ static int cma_iboe_join_multicast(struct rdma_id_private
*id_priv,
{
struct iboe_mcast_work *work;
struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;
- int err;
+ int err = 0;
struct sockaddr *addr = (struct sockaddr *)&mc->addr;
struct net_device *ndev = NULL;
@@ -3388,13 +3425,31 @@ static int cma_iboe_join_multicast(struct
rdma_id_private *id_priv,
mc->multicast.ib->rec.rate = iboe_get_rate(ndev);
mc->multicast.ib->rec.hop_limit = 1;
mc->multicast.ib->rec.mtu = iboe_get_mtu(ndev->mtu);
+ rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
+ &mc->multicast.ib->rec.port_gid);
+
+ if (addr->sa_family == AF_INET) {
+ u16 sgid_index;
+
+ err = ib_find_cached_gid_by_port(id_priv->cma_dev->device,
+
&mc->multicast.ib->rec.port_gid,
+ IB_GID_TYPE_ROCE_V2,
+ id_priv->id.port_num,
+ &init_net,
dev_addr->bound_dev_if,
+ &sgid_index);
+ if (!err)
+ err = cma_igmp_send(ndev, &mc->multicast.ib->rec.mgid,
true);
+ if (!err) {
+ id_priv->igmp_joined = true;
+ mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
+ }
+ }
dev_put(ndev);
- if (!mc->multicast.ib->rec.mtu) {
+ if (err || !mc->multicast.ib->rec.mtu) {
err = -EINVAL;
goto out2;
}
- rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
- &mc->multicast.ib->rec.port_gid);
+
work->id = id_priv;
work->mc = mc;
INIT_WORK(&work->work, iboe_mcast_work_handler);
@@ -3486,6 +3541,21 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct
sockaddr *addr)
kfree(mc);
break;
case IB_LINK_LAYER_ETHERNET:
+ if (id_priv->igmp_joined) {
+ struct rdma_dev_addr *dev_addr
= &id->route.addr.dev_addr;
+ struct net_device *ndev = NULL;
+
+ if (dev_addr->bound_dev_if)
+ ndev =
dev_get_by_index(&init_net,
+
dev_addr->bound_dev_if);
+ if (ndev) {
+ cma_igmp_send(ndev,
+
&mc->multicast.ib->rec.mgid,
+ false);
+ dev_put(ndev);
+ }
+ id_priv->igmp_joined = false;
+ }
kref_put(&mc->mcref, release_mc);
break;
default:
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
