@@ -252,6 +252,8 @@ static int addr4_resolve(struct sockaddr_in *src_in,
if (rt->rt_uses_gateway)
addr->network = RDMA_NETWORK_IPV4;
+ addr->hoplimit = ip4_dst_hoplimit(&rt->dst);
+
*prt = rt;
return 0;
out:
@@ -295,6 +297,8 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
if (rt->rt6i_flags & RTF_GATEWAY)
addr->network = RDMA_NETWORK_IPV6;
+ addr->hoplimit = ip6_dst_hoplimit(dst);
+
*pdst = dst;
return 0;
put:
@@ -542,7 +546,8 @@ static void resolve_cb(int status, struct sockaddr *src_addr,
int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid,
const union ib_gid *dgid,
- u8 *dmac, u16 *vlan_id, int *if_index)
+ u8 *dmac, u16 *vlan_id, int *if_index,
+ int *hoplimit)
{
int ret = 0;
struct rdma_dev_addr dev_addr;
@@ -581,6 +586,8 @@ int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid,
*if_index = dev_addr.bound_dev_if;
if (vlan_id)
*vlan_id = rdma_vlan_dev_vlan_id(dev);
+ if (hoplimit)
+ *hoplimit = dev_addr.hoplimit;
dev_put(dev);
return ret;
}
@@ -1641,6 +1641,7 @@ static int cm_req_handler(struct cm_work *work)
cm_format_paths_from_req(req_msg, &work->path[0], &work->path[1]);
memcpy(work->path[0].dmac, cm_id_priv->av.ah_attr.dmac, ETH_ALEN);
+ work->path[0].hop_limit = cm_id_priv->av.ah_attr.grh.hop_limit;
ret = ib_get_cached_gid(work->port->cm_dev->ib_device,
work->port->port_num,
cm_id_priv->av.ah_attr.grh.sgid_index,
@@ -2424,7 +2424,6 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
{
struct rdma_route *route = &id_priv->id.route;
struct rdma_addr *addr = &route->addr;
- enum ib_gid_type network_gid_type;
struct cma_work *work;
int ret;
struct net_device *ndev = NULL;
@@ -2478,14 +2477,13 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
&route->path_rec->dgid);
/* Use the hint from IP Stack to select GID Type */
- network_gid_type = ib_network_to_gid_type(addr->dev_addr.network);
- if (addr->dev_addr.network != RDMA_NETWORK_IB) {
- route->path_rec->gid_type = network_gid_type;
+ if (route->path_rec->gid_type < ib_network_to_gid_type(addr->dev_addr.network))
+ route->path_rec->gid_type = ib_network_to_gid_type(addr->dev_addr.network);
+ if (((struct sockaddr *)&id_priv->id.route.addr.dst_addr)->sa_family != AF_IB)
/* TODO: get the hoplimit from the inet/inet6 device */
- route->path_rec->hop_limit = IPV6_DEFAULT_HOPLIMIT;
- } else {
+ route->path_rec->hop_limit = addr->dev_addr.hoplimit;
+ else
route->path_rec->hop_limit = 1;
- }
route->path_rec->reversible = 1;
route->path_rec->pkey = cpu_to_be16(0xffff);
route->path_rec->mtu_selector = IB_SA_EQ;
@@ -434,6 +434,7 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
int ret;
enum rdma_network_type net_type = RDMA_NETWORK_IB;
enum ib_gid_type gid_type = IB_GID_TYPE_IB;
+ int hoplimit = grh->hop_limit;
union ib_gid dgid;
union ib_gid sgid;
@@ -471,7 +472,7 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
ah_attr->dmac,
wc->wc_flags & IB_WC_WITH_VLAN ?
NULL : &vlan_id,
- &if_index);
+ &if_index, &hoplimit);
if (ret) {
dev_put(idev);
return ret;
@@ -520,7 +521,7 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
ah_attr->grh.sgid_index = (u8) gid_index;
flow_class = be32_to_cpu(grh->version_tclass_flow);
ah_attr->grh.flow_label = flow_class & 0xFFFFF;
- ah_attr->grh.hop_limit = 0xFF;
+ ah_attr->grh.hop_limit = hoplimit;
ah_attr->grh.traffic_class = (flow_class >> 20) & 0xFF;
}
return 0;
@@ -1138,6 +1139,7 @@ int ib_resolve_eth_dmac(struct ib_qp *qp,
union ib_gid sgid;
struct ib_gid_attr sgid_attr;
int ifindex;
+ int hop_limit;
ret = ib_query_gid(qp->device,
qp_attr->ah_attr.port_num,
@@ -1149,21 +1151,17 @@ int ib_resolve_eth_dmac(struct ib_qp *qp,
ret = -ENXIO;
goto out;
}
- if (sgid_attr.gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
- /* TODO: get the hoplimit from the inet/inet6
- * device
- */
- qp_attr->ah_attr.grh.hop_limit =
- IPV6_DEFAULT_HOPLIMIT;
ifindex = sgid_attr.ndev->ifindex;
ret = rdma_addr_find_l2_eth_by_grh(&sgid,
&qp_attr->ah_attr.grh.dgid,
qp_attr->ah_attr.dmac,
- NULL, &ifindex);
+ NULL, &ifindex, &hop_limit);
dev_put(sgid_attr.ndev);
+
+ qp_attr->ah_attr.grh.hop_limit = hop_limit;
}
}
out:
@@ -154,7 +154,8 @@ struct ib_ah *ocrdma_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr)
(!rdma_link_local_addr((struct in6_addr *)attr->grh.dgid.raw))) {
status = rdma_addr_find_l2_eth_by_grh(&sgid, &attr->grh.dgid,
attr->dmac, &vlan_tag,
- &sgid_attr.ndev->ifindex);
+ &sgid_attr.ndev->ifindex,
+ NULL);
if (status) {
pr_err("%s(): Failed to resolve dmac from gid."
"status = %d\n", __func__, status);
@@ -84,6 +84,7 @@ struct rdma_dev_addr {
enum rdma_transport_type transport;
struct net *net;
enum rdma_network_type network;
+ int hoplimit;
};
/**
@@ -132,7 +133,8 @@ int rdma_addr_size(struct sockaddr *addr);
int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id);
int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid,
const union ib_gid *dgid,
- u8 *smac, u16 *vlan_id, int *if_index);
+ u8 *smac, u16 *vlan_id, int *if_index,
+ int *hoplimit);
static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr)
{
Previously, IPV6_DEFAULT_HOPLIMIT was used as the hop limit value for RoCE. Fixing that by taking ip4_dst_hoplimit and ip6_dst_hoplimit as hop limit values. Signed-off-by: Matan Barak <matanb@mellanox.com> --- drivers/infiniband/core/addr.c | 9 ++++++++- drivers/infiniband/core/cm.c | 1 + drivers/infiniband/core/cma.c | 12 +++++------- drivers/infiniband/core/verbs.c | 16 +++++++--------- drivers/infiniband/hw/ocrdma/ocrdma_ah.c | 3 ++- include/rdma/ib_addr.h | 4 +++- 6 files changed, 26 insertions(+), 19 deletions(-)