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>
---
drivers/infiniband/core/cma.c | 96 ++++++++++++++++++++++++++++++++++---
drivers/infiniband/core/multicast.c | 17 ++++++-
include/rdma/ib_sa.h | 2 +
3 files changed, 106 insertions(+), 9 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 8fab267..c30bfe3 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>
@@ -304,6 +305,7 @@ struct cma_multicast {
void *context;
struct sockaddr_storage addr;
struct kref mcref;
+ bool igmp_joined;
};
struct cma_work {
@@ -400,6 +402,26 @@ 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)
{
@@ -1535,8 +1557,24 @@ static void cma_leave_mc_groups(struct rdma_id_private
*id_priv)
id_priv->id.port_num)) {
ib_sa_free_multicast(mc->multicast.ib);
kfree(mc);
- } else
+ } else {
+ if (mc->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);
+ }
}
}
@@ -3656,12 +3694,23 @@ static int cma_ib_mc_handler(int status, struct
ib_sa_multicast *multicast)
event.status = status;
event.param.ud.private_data = mc->context;
if (!status) {
+ struct rdma_dev_addr *dev_addr =
+ &id_priv->id.route.addr.dev_addr;
+ struct net_device *ndev =
+ dev_get_by_index(&init_net, dev_addr->bound_dev_if);
+ enum ib_gid_type gid_type =
+ id_priv->cma_dev->default_gid_type[id_priv->id.port_num
-
+ rdma_start_port(id_priv->cma_dev->device)];
+
event.event = RDMA_CM_EVENT_MULTICAST_JOIN;
ib_init_ah_from_mcmember(id_priv->id.device,
id_priv->id.port_num, &multicast->rec,
+ ndev, gid_type,
&event.param.ud.ah_attr);
event.param.ud.qp_num = 0xFFFFFF;
event.param.ud.qkey = be32_to_cpu(multicast->rec.qkey);
+ if (ndev)
+ dev_put(ndev);
} else
event.event = RDMA_CM_EVENT_MULTICAST_ERROR;
@@ -3794,9 +3843,10 @@ 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;
+ enum ib_gid_type gid_type;
if (cma_zero_addr((struct sockaddr *)&mc->addr))
return -EINVAL;
@@ -3826,9 +3876,25 @@ 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);
+
+ gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num -
+ rdma_start_port(id_priv->cma_dev->device)];
+ if (addr->sa_family == AF_INET) {
+ if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
+ err = cma_igmp_send(ndev, &mc->multicast.ib->rec.mgid,
+ true);
+ if (!err) {
+ mc->igmp_joined = true;
+ mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
+ }
+ } else {
+ if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
+ err = -ENOTSUPP;
+ }
dev_put(ndev);
- if (!mc->multicast.ib->rec.mtu) {
- err = -EINVAL;
+ if (err || !mc->multicast.ib->rec.mtu) {
+ if (!err)
+ err = -EINVAL;
goto out2;
}
rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
@@ -3867,7 +3933,7 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct
sockaddr *addr,
memcpy(&mc->addr, addr, rdma_addr_size(addr));
mc->context = context;
mc->id_priv = id_priv;
-
+ mc->igmp_joined = false;
spin_lock(&id_priv->lock);
list_add(&mc->list, &id_priv->mc_list);
spin_unlock(&id_priv->lock);
@@ -3912,9 +3978,25 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct
sockaddr *addr)
if (rdma_cap_ib_mcast(id->device, id->port_num)) {
ib_sa_free_multicast(mc->multicast.ib);
kfree(mc);
- } else if (rdma_protocol_roce(id->device, id->port_num))
+ } else if (rdma_protocol_roce(id->device,
id->port_num)) {
+ if (mc->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);
+ }
+ mc->igmp_joined = false;
+ }
kref_put(&mc->mcref, release_mc);
-
+ }
return;
}
}
diff --git a/drivers/infiniband/core/multicast.c
b/drivers/infiniband/core/multicast.c
index 6911ae6..250937c 100644
--- a/drivers/infiniband/core/multicast.c
+++ b/drivers/infiniband/core/multicast.c
@@ -723,14 +723,27 @@ EXPORT_SYMBOL(ib_sa_get_mcmember_rec);
int ib_init_ah_from_mcmember(struct ib_device *device, u8 port_num,
struct ib_sa_mcmember_rec *rec,
+ struct net_device *ndev,
+ enum ib_gid_type gid_type,
struct ib_ah_attr *ah_attr)
{
int ret;
u16 gid_index;
u8 p;
- ret = ib_find_cached_gid(device, &rec->port_gid, IB_GID_TYPE_IB,
- NULL, &p, &gid_index);
+ if (rdma_protocol_roce(device, port_num)) {
+ ret = ib_find_cached_gid_by_port(device, &rec->port_gid,
+ gid_type, port_num,
+ ndev,
+ &gid_index);
+ } else if (rdma_protocol_ib(device, port_num)) {
+ ret = ib_find_cached_gid(device, &rec->port_gid,
+ IB_GID_TYPE_IB, NULL, &p,
+ &gid_index);
+ } else {
+ ret = -EINVAL;
+ }
+
if (ret)
return ret;
diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h
index 0a40ed2..cdc1c81 100644
--- a/include/rdma/ib_sa.h
+++ b/include/rdma/ib_sa.h
@@ -403,6 +403,8 @@ int ib_sa_get_mcmember_rec(struct ib_device *device, u8
port_num,
*/
int ib_init_ah_from_mcmember(struct ib_device *device, u8 port_num,
struct ib_sa_mcmember_rec *rec,
+ struct net_device *ndev,
+ enum ib_gid_type gid_type,
struct ib_ah_attr *ah_attr);
/**
--
2.1.0
--
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
