From: Moni Shoua <[email protected]> Currently, the IB core and specifically the RDMA-CM assumes that RoCE (IBoE) gids encode related Ethernet netdevice interface MAC address and possibly VLAN id.
Change gids to be treated as they encode interface IP address. Since Ethernet layer 2 address parameters are not longer encoded within gids, had to extend the Infiniband address structures (e.g. ib_ah_attr) with layer 2 address parameters, namely mac and vlan. Signed-off-by: Moni Shoua <[email protected]> Signed-off-by: Or Gerlitz <[email protected]> --- drivers/infiniband/core/cma.c | 40 +++++++++++++++++-------- drivers/infiniband/core/ucma.c | 18 ++--------- include/rdma/ib_addr.h | 61 +++++++++++++++++++++++++++------------ 3 files changed, 73 insertions(+), 46 deletions(-) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 07a7aeb..2162a7a 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -386,7 +386,9 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv) return -EINVAL; mutex_lock(&lock); - iboe_addr_get_sgid(dev_addr, &iboe_gid); + rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, + &iboe_gid); + memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof gid); list_for_each_entry(cma_dev, &dev_list, list) { @@ -601,11 +603,23 @@ EXPORT_SYMBOL(rdma_destroy_qp); static int cma_find_smac_by_sgid(union ib_gid *sgid, u8 *smac) { int ret = 0; - struct in6_addr in6; + struct rdma_dev_addr dev_addr; + union { + struct sockaddr _sockaddr; + struct sockaddr_in _sockaddr_in; + struct sockaddr_in6 _sockaddr_in6; + } gid_addr; + + ret = rdma_gid2ip(&gid_addr._sockaddr, sgid); - memcpy(&in6, sgid, sizeof(in6)); - rdma_get_ll_mac(&in6, smac); + if (ret) + return ret; + memset(&dev_addr, 0, sizeof(dev_addr)); + ret = rdma_translate_ip(&gid_addr._sockaddr, &dev_addr); + if (ret) + return ret; + memcpy(smac, dev_addr.src_dev_addr, ETH_ALEN); return ret; } @@ -1936,10 +1950,10 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) memcpy(route->path_rec->dmac, addr->dev_addr.dst_dev_addr, ETH_ALEN); memcpy(route->path_rec->smac, ndev->dev_addr, ndev->addr_len); - iboe_mac_vlan_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr, - be16_to_cpu(route->path_rec->vlan_id)); - iboe_mac_vlan_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr, - be16_to_cpu(route->path_rec->vlan_id)); + rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, + &route->path_rec->sgid); + rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.dst_addr, + &route->path_rec->dgid); route->path_rec->hop_limit = 1; route->path_rec->reversible = 1; @@ -2106,6 +2120,7 @@ static void addr_handler(int status, struct sockaddr *src_addr, RDMA_CM_ADDR_RESOLVED)) goto out; + memcpy(cma_src_addr(id_priv), src_addr, rdma_addr_size(src_addr)); if (!status && !id_priv->cma_dev) status = cma_acquire_dev(id_priv); @@ -2115,10 +2130,8 @@ static void addr_handler(int status, struct sockaddr *src_addr, goto out; event.event = RDMA_CM_EVENT_ADDR_ERROR; event.status = status; - } else { - memcpy(cma_src_addr(id_priv), src_addr, rdma_addr_size(src_addr)); + } else event.event = RDMA_CM_EVENT_ADDR_RESOLVED; - } if (id_priv->id.event_handler(&id_priv->id, &event)) { cma_exch(id_priv, RDMA_CM_DESTROYING); @@ -2599,6 +2612,7 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) if (ret) goto err1; + memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr)); if (!cma_any_addr(addr)) { ret = cma_translate_addr(addr, &id->route.addr.dev_addr); if (ret) @@ -2609,7 +2623,6 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) goto err1; } - memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr)); if (!(id_priv->options & (1 << CMA_OPTION_AFONLY))) { if (addr->sa_family == AF_INET) id_priv->afonly = 1; @@ -3337,7 +3350,8 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, err = -EINVAL; goto out2; } - iboe_addr_get_sgid(dev_addr, &mc->multicast.ib->rec.port_gid); + 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); diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index b0f189b..7e7da86 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -655,24 +655,14 @@ static void ucma_copy_ib_route(struct rdma_ucm_query_route_resp *resp, static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp, struct rdma_route *route) { - struct rdma_dev_addr *dev_addr; - struct net_device *dev; - u16 vid = 0; resp->num_paths = route->num_paths; switch (route->num_paths) { case 0: - dev_addr = &route->addr.dev_addr; - dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if); - if (dev) { - vid = rdma_vlan_dev_vlan_id(dev); - dev_put(dev); - } - - iboe_mac_vlan_to_ll((union ib_gid *) &resp->ib_route[0].dgid, - dev_addr->dst_dev_addr, vid); - iboe_addr_get_sgid(dev_addr, - (union ib_gid *) &resp->ib_route[0].sgid); + rdma_ip2gid((struct sockaddr *)&route->addr.dst_addr, + (union ib_gid *)&resp->ib_route[0].dgid); + rdma_ip2gid((struct sockaddr *)&route->addr.src_addr, + (union ib_gid *)&resp->ib_route[0].sgid); resp->ib_route[0].pkey = cpu_to_be16(0xffff); break; case 2: diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h index f3ac0f2..f3d91cc 100644 --- a/include/rdma/ib_addr.h +++ b/include/rdma/ib_addr.h @@ -38,8 +38,12 @@ #include <linux/in6.h> #include <linux/if_arp.h> #include <linux/netdevice.h> +#include <linux/inetdevice.h> #include <linux/socket.h> #include <linux/if_vlan.h> +#include <net/ipv6.h> +#include <net/if_inet6.h> +#include <net/ip.h> #include <rdma/ib_verbs.h> #include <rdma/ib_pack.h> @@ -126,41 +130,60 @@ static inline int rdma_addr_gid_offset(struct rdma_dev_addr *dev_addr) return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0; } -static inline void iboe_mac_vlan_to_ll(union ib_gid *gid, u8 *mac, u16 vid) +static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev) { - memset(gid->raw, 0, 16); - *((__be32 *) gid->raw) = cpu_to_be32(0xfe800000); - if (vid < 0x1000) { - gid->raw[12] = vid & 0xff; - gid->raw[11] = vid >> 8; - } else { - gid->raw[12] = 0xfe; - gid->raw[11] = 0xff; + return dev->priv_flags & IFF_802_1Q_VLAN ? + vlan_dev_vlan_id(dev) : 0xffff; +} + +static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid) +{ + switch (addr->sa_family) { + case AF_INET: + ipv6_addr_set_v4mapped(((struct sockaddr_in *) + addr)->sin_addr.s_addr, + (struct in6_addr *)gid); + break; + case AF_INET6: + memcpy(gid->raw, &((struct sockaddr_in6 *)addr)->sin6_addr, 16); + break; + default: + return -EINVAL; } - memcpy(gid->raw + 13, mac + 3, 3); - memcpy(gid->raw + 8, mac, 3); - gid->raw[8] ^= 2; + return 0; } -static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev) +/* Important - sockaddr should be a union of sockaddr_in and sockaddr_in6 */ +static inline int rdma_gid2ip(struct sockaddr *out, union ib_gid *gid) { - return dev->priv_flags & IFF_802_1Q_VLAN ? - vlan_dev_vlan_id(dev) : 0xffff; + if (ipv6_addr_v4mapped((struct in6_addr *)gid)) { + struct sockaddr_in *out_in = (struct sockaddr_in *)out; + memset(out_in, 0, sizeof(*out_in)); + out_in->sin_family = AF_INET; + memcpy(&out_in->sin_addr.s_addr, gid->raw + 12, 4); + } else { + struct sockaddr_in6 *out_in = (struct sockaddr_in6 *)out; + memset(out_in, 0, sizeof(*out_in)); + out_in->sin6_family = AF_INET6; + memcpy(&out_in->sin6_addr.s6_addr, gid->raw, 16); + } + return 0; } static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { struct net_device *dev; - u16 vid = 0xffff; + struct in_device *ip4; dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if); if (dev) { - vid = rdma_vlan_dev_vlan_id(dev); + ip4 = (struct in_device *)dev->ip_ptr; + if (ip4 && ip4->ifa_list && ip4->ifa_list->ifa_address) + ipv6_addr_set_v4mapped(ip4->ifa_list->ifa_address, + (struct in6_addr *)gid); dev_put(dev); } - - iboe_mac_vlan_to_ll(gid, dev_addr->src_dev_addr, vid); } static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) -- 1.7.1 -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
