diff options
| author | John Baldwin <jhb@FreeBSD.org> | 2026-06-24 19:30:56 +0000 |
|---|---|---|
| committer | John Baldwin <jhb@FreeBSD.org> | 2026-06-24 19:30:56 +0000 |
| commit | 1d99feddd681da05dfa9091870403bc9ceb94550 (patch) | |
| tree | 4320a99697d5b88b1979f5a99183f6da96ea7d83 /sys/ofed | |
| parent | 85893a8399bce2dd66e8693037395e1979277967 (diff) | |
Diffstat (limited to 'sys/ofed')
| -rw-r--r-- | sys/ofed/drivers/infiniband/core/ib_addr.c | 20 | ||||
| -rw-r--r-- | sys/ofed/drivers/infiniband/core/ib_cache.c | 16 | ||||
| -rw-r--r-- | sys/ofed/drivers/infiniband/core/ib_cm.c | 158 | ||||
| -rw-r--r-- | sys/ofed/drivers/infiniband/core/ib_cma.c | 225 | ||||
| -rw-r--r-- | sys/ofed/drivers/infiniband/core/ib_cq.c | 28 | ||||
| -rw-r--r-- | sys/ofed/drivers/infiniband/core/ib_device.c | 16 | ||||
| -rw-r--r-- | sys/ofed/drivers/infiniband/core/ib_sa_query.c | 18 | ||||
| -rw-r--r-- | sys/ofed/drivers/infiniband/core/ib_ucma.c | 19 | ||||
| -rw-r--r-- | sys/ofed/drivers/infiniband/core/ib_user_mad.c | 7 | ||||
| -rw-r--r-- | sys/ofed/drivers/infiniband/core/ib_verbs.c | 200 | ||||
| -rw-r--r-- | sys/ofed/drivers/infiniband/ulp/ipoib/ipoib_main.c | 3 | ||||
| -rw-r--r-- | sys/ofed/include/rdma/ib_addr.h | 41 | ||||
| -rw-r--r-- | sys/ofed/include/rdma/ib_sa.h | 10 | ||||
| -rw-r--r-- | sys/ofed/include/rdma/ib_verbs.h | 36 | ||||
| -rw-r--r-- | sys/ofed/include/rdma/opa_addr.h | 16 | ||||
| -rw-r--r-- | sys/ofed/include/rdma/rdma_cm.h | 19 | ||||
| -rw-r--r-- | sys/ofed/include/rdma/rdma_cm_ib.h | 8 |
17 files changed, 473 insertions, 367 deletions
diff --git a/sys/ofed/drivers/infiniband/core/ib_addr.c b/sys/ofed/drivers/infiniband/core/ib_addr.c index ecacfd6a43dd..2a00e449ecda 100644 --- a/sys/ofed/drivers/infiniband/core/ib_addr.c +++ b/sys/ofed/drivers/infiniband/core/ib_addr.c @@ -877,7 +877,6 @@ void rdma_addr_cancel(struct rdma_dev_addr *addr) EXPORT_SYMBOL(rdma_addr_cancel); struct resolve_cb_context { - struct rdma_dev_addr *addr; struct completion comp; int status; }; @@ -885,33 +884,28 @@ struct resolve_cb_context { static void resolve_cb(int status, struct sockaddr *src_addr, struct rdma_dev_addr *addr, void *context) { - if (!status) - memcpy(((struct resolve_cb_context *)context)->addr, - addr, sizeof(struct rdma_dev_addr)); ((struct resolve_cb_context *)context)->status = status; complete(&((struct resolve_cb_context *)context)->comp); } int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid, const union ib_gid *dgid, - u8 *dmac, if_t dev, + u8 *dmac, if_t ndev, int *hoplimit) { - int ret = 0; struct rdma_dev_addr dev_addr; struct resolve_cb_context ctx; - union rdma_sockaddr sgid_addr, dgid_addr; + int ret; rdma_gid2ip(&sgid_addr._sockaddr, sgid); rdma_gid2ip(&dgid_addr._sockaddr, dgid); memset(&dev_addr, 0, sizeof(dev_addr)); - dev_addr.bound_dev_if = if_getindex(dev); - dev_addr.net = dev_net(dev); + dev_addr.bound_dev_if = if_getindex(ndev); + dev_addr.net = dev_net(ndev); - ctx.addr = &dev_addr; init_completion(&ctx.comp); ret = rdma_resolve_ip(&self, &sgid_addr._sockaddr, &dgid_addr._sockaddr, &dev_addr, 1000, resolve_cb, &ctx); @@ -925,11 +919,9 @@ int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid, return ret; memcpy(dmac, dev_addr.dst_dev_addr, ETH_ALEN); - if (hoplimit) - *hoplimit = dev_addr.hoplimit; - return ret; + *hoplimit = dev_addr.hoplimit; + return 0; } -EXPORT_SYMBOL(rdma_addr_find_l2_eth_by_grh); int addr_init(void) { diff --git a/sys/ofed/drivers/infiniband/core/ib_cache.c b/sys/ofed/drivers/infiniband/core/ib_cache.c index a11b36f06c86..878b2915f25d 100644 --- a/sys/ofed/drivers/infiniband/core/ib_cache.c +++ b/sys/ofed/drivers/infiniband/core/ib_cache.c @@ -579,27 +579,24 @@ static int ib_cache_gid_find_by_filter(struct ib_device *ib_dev, struct ib_gid_attr attr; if (table->data_vec[i].props & GID_TABLE_ENTRY_INVALID) - goto next; + continue; if (memcmp(gid, &table->data_vec[i].gid, sizeof(*gid))) - goto next; + continue; memcpy(&attr, &table->data_vec[i].attr, sizeof(attr)); - if (filter(gid, &attr, context)) + if (filter(gid, &attr, context)) { found = true; - -next: - if (found) + if (index) + *index = i; break; + } } read_unlock_irqrestore(&table->rwlock, flags); if (!found) return -ENOENT; - - if (index) - *index = i; return 0; } @@ -899,7 +896,6 @@ int ib_find_gid_by_filter(struct ib_device *device, port_num, filter, context, index); } -EXPORT_SYMBOL(ib_find_gid_by_filter); int ib_get_cached_pkey(struct ib_device *device, u8 port_num, diff --git a/sys/ofed/drivers/infiniband/core/ib_cm.c b/sys/ofed/drivers/infiniband/core/ib_cm.c index be29881c73c9..215849d0ae18 100644 --- a/sys/ofed/drivers/infiniband/core/ib_cm.c +++ b/sys/ofed/drivers/infiniband/core/ib_cm.c @@ -474,9 +474,9 @@ static int cm_init_av_for_lap(struct cm_port *port, struct ib_wc *wc, * used for sending any responses. If initialization is successful, * than new ah_attr is used by overwriting old one. */ - ret = ib_init_ah_from_wc(port->cm_dev->ib_device, - port->port_num, wc, - grh, &new_ah_attr); + ret = ib_init_ah_attr_from_wc(port->cm_dev->ib_device, + port->port_num, wc, + grh, &new_ah_attr); if (ret) return ret; @@ -489,8 +489,9 @@ static int cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc, { av->port = port; av->pkey_index = wc->pkey_index; - return ib_init_ah_from_wc(port->cm_dev->ib_device, port->port_num, wc, - grh, &av->ah_attr); + return ib_init_ah_attr_from_wc(port->cm_dev->ib_device, + port->port_num, wc, + grh, &av->ah_attr); } static int cm_init_av_by_path(struct sa_path_rec *path, struct cm_av *av, @@ -526,8 +527,8 @@ static int cm_init_av_by_path(struct sa_path_rec *path, struct cm_av *av, return ret; av->port = port; - ret = ib_init_ah_from_path(cm_dev->ib_device, port->port_num, - path, &av->ah_attr); + ret = ib_init_ah_attr_from_path(cm_dev->ib_device, port->port_num, + path, &av->ah_attr); if (ret) return ret; @@ -1588,6 +1589,37 @@ static u16 cm_get_bth_pkey(struct cm_work *work) return pkey; } +/** + * Convert OPA SGID to IB SGID + * ULPs (such as IPoIB) do not understand OPA GIDs and will + * reject them as the local_gid will not match the sgid. Therefore, + * change the pathrec's SGID to an IB SGID. + * + * @work: Work completion + * @path: Path record + */ +static void cm_opa_to_ib_sgid(struct cm_work *work, + struct sa_path_rec *path) +{ + struct ib_device *dev = work->port->cm_dev->ib_device; + struct ib_gid_attr gid_attr; + u8 port_num = work->port->port_num; + + if (rdma_cap_opa_ah(dev, port_num) && + (ib_is_opa_gid(&path->sgid))) { + union ib_gid sgid; + + if (ib_get_cached_gid(dev, port_num, 0, + &sgid, &gid_attr)) { + dev_warn(&dev->dev, + "Error updating sgid in CM request\n"); + return; + } + + path->sgid = sgid; + } +} + static void cm_format_req_event(struct cm_work *work, struct cm_id_private *cm_id_priv, struct ib_cm_id *listen_id) @@ -1601,10 +1633,13 @@ static void cm_format_req_event(struct cm_work *work, param->bth_pkey = cm_get_bth_pkey(work); param->port = cm_id_priv->av.port->port_num; param->primary_path = &work->path[0]; - if (cm_req_has_alt_path(req_msg)) + cm_opa_to_ib_sgid(work, param->primary_path); + if (cm_req_has_alt_path(req_msg)) { param->alternate_path = &work->path[1]; - else + cm_opa_to_ib_sgid(work, param->alternate_path); + } else { param->alternate_path = NULL; + } param->remote_ca_guid = req_msg->local_ca_guid; param->remote_qkey = be32_to_cpu(req_msg->local_qkey); param->remote_qpn = be32_to_cpu(cm_req_get_local_qpn(req_msg)); @@ -1891,56 +1926,50 @@ static int cm_req_handler(struct cm_work *work) work->port->port_num, grh->sgid_index, &gid, &gid_attr); - if (!ret) { - if (gid_attr.ndev) { - work->path[0].rec_type = - sa_conv_gid_to_pathrec_type(gid_attr.gid_type); - sa_path_set_ifindex(&work->path[0], - if_getindex(gid_attr.ndev)); - sa_path_set_ndev(&work->path[0], - dev_net(gid_attr.ndev)); - dev_put(gid_attr.ndev); - } else { - cm_path_set_rec_type(work->port->cm_dev->ib_device, - work->port->port_num, - &work->path[0], - &req_msg->primary_local_gid); - } - if (cm_req_has_alt_path(req_msg)) - work->path[1].rec_type = work->path[0].rec_type; - cm_format_paths_from_req(req_msg, &work->path[0], - &work->path[1]); - if (cm_id_priv->av.ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE) - sa_path_set_dmac(&work->path[0], - cm_id_priv->av.ah_attr.roce.dmac); - work->path[0].hop_limit = grh->hop_limit; - ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av, - cm_id_priv); - } if (ret) { - int err = ib_get_cached_gid(work->port->cm_dev->ib_device, - work->port->port_num, 0, - &work->path[0].sgid, - &gid_attr); - if (!err && gid_attr.ndev) { - work->path[0].rec_type = - sa_conv_gid_to_pathrec_type(gid_attr.gid_type); - sa_path_set_ifindex(&work->path[0], - if_getindex(gid_attr.ndev)); - sa_path_set_ndev(&work->path[0], - dev_net(gid_attr.ndev)); - dev_put(gid_attr.ndev); - } else { - cm_path_set_rec_type(work->port->cm_dev->ib_device, - work->port->port_num, - &work->path[0], - &req_msg->primary_local_gid); - } - if (cm_req_has_alt_path(req_msg)) - work->path[1].rec_type = work->path[0].rec_type; - ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID, - &work->path[0].sgid, sizeof work->path[0].sgid, - NULL, 0); + ib_send_cm_rej(cm_id, IB_CM_REJ_UNSUPPORTED, NULL, 0, NULL, 0); + goto rejected; + } + + if (gid_attr.ndev) { + work->path[0].rec_type = + sa_conv_gid_to_pathrec_type(gid_attr.gid_type); + sa_path_set_ifindex(&work->path[0], + if_getindex(gid_attr.ndev)); + sa_path_set_ndev(&work->path[0], + dev_net(gid_attr.ndev)); + dev_put(gid_attr.ndev); + } else { + cm_path_set_rec_type(work->port->cm_dev->ib_device, + work->port->port_num, + &work->path[0], + &req_msg->primary_local_gid); + } + if (cm_req_has_alt_path(req_msg)) + work->path[1].rec_type = work->path[0].rec_type; + cm_format_paths_from_req(req_msg, &work->path[0], + &work->path[1]); + if (cm_id_priv->av.ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE) + sa_path_set_dmac(&work->path[0], + cm_id_priv->av.ah_attr.roce.dmac); + work->path[0].hop_limit = grh->hop_limit; + ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av, + cm_id_priv); + if (ret) { + int err; + + err = ib_get_cached_gid(work->port->cm_dev->ib_device, + work->port->port_num, 0, + &work->path[0].sgid, + NULL); + if (err) + ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID, + NULL, 0, NULL, 0); + else + ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID, + &work->path[0].sgid, + sizeof(work->path[0].sgid), + NULL, 0); goto rejected; } if (cm_req_has_alt_path(req_msg)) { @@ -1949,7 +1978,7 @@ static int cm_req_handler(struct cm_work *work) if (ret) { ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_ALT_GID, &work->path[0].sgid, - sizeof work->path[0].sgid, NULL, 0); + sizeof(work->path[0].sgid), NULL, 0); goto rejected; } } @@ -3123,6 +3152,12 @@ static int cm_lap_handler(struct cm_work *work) if (!cm_id_priv) return -EINVAL; + ret = cm_init_av_for_response(work->port, work->mad_recv_wc->wc, + work->mad_recv_wc->recv_buf.grh, + &cm_id_priv->av); + if (ret) + goto deref; + param = &work->cm_event.param.lap_rcvd; memset(&work->path[0], 0, sizeof(work->path[1])); cm_path_set_rec_type(work->port->cm_dev->ib_device, @@ -3169,11 +3204,6 @@ static int cm_lap_handler(struct cm_work *work) cm_id_priv->id.lap_state = IB_CM_LAP_RCVD; cm_id_priv->tid = lap_msg->hdr.tid; - ret = cm_init_av_for_response(work->port, work->mad_recv_wc->wc, - work->mad_recv_wc->recv_buf.grh, - &cm_id_priv->av); - if (ret) - goto unlock; ret = cm_init_av_by_path(param->alternate_path, &cm_id_priv->alt_av, cm_id_priv); if (ret) diff --git a/sys/ofed/drivers/infiniband/core/ib_cma.c b/sys/ofed/drivers/infiniband/core/ib_cma.c index 33a4189804e1..09c1d266d6f8 100644 --- a/sys/ofed/drivers/infiniband/core/ib_cma.c +++ b/sys/ofed/drivers/infiniband/core/ib_cma.c @@ -648,10 +648,12 @@ static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_a static inline int cma_validate_port(struct ib_device *device, u8 port, enum ib_gid_type gid_type, union ib_gid *gid, - const struct rdma_dev_addr *dev_addr) + struct rdma_id_private *id_priv) { - const int dev_type = dev_addr->dev_type; - if_t ndev; + struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; + int bound_if_index = dev_addr->bound_dev_if; + int dev_type = dev_addr->dev_type; + if_t ndev = NULL; int ret = -ENODEV; if ((dev_type == ARPHRD_INFINIBAND) && !rdma_protocol_ib(device, port)) @@ -661,9 +663,10 @@ static inline int cma_validate_port(struct ib_device *device, u8 port, return ret; if (dev_type == ARPHRD_ETHER && rdma_protocol_roce(device, port)) { - ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); + ndev = dev_get_by_index(dev_addr->net, bound_if_index); + if (!ndev) + return ret; } else { - ndev = NULL; gid_type = IB_GID_TYPE_IB; } @@ -707,7 +710,7 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv, ret = cma_validate_port(cma_dev->device, port, rdma_protocol_ib(cma_dev->device, port) ? IB_GID_TYPE_IB : - listen_id_priv->gid_type, gidp, dev_addr); + listen_id_priv->gid_type, gidp, id_priv); if (!ret) { id_priv->id.port_num = port; goto out; @@ -729,7 +732,7 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv, rdma_protocol_ib(cma_dev->device, port) ? IB_GID_TYPE_IB : cma_dev->default_gid_type[port - 1], - gidp, dev_addr); + gidp, id_priv); if (!ret) { id_priv->id.port_num = port; goto out; @@ -2333,6 +2336,33 @@ __be64 rdma_get_service_id(struct rdma_cm_id *id, struct sockaddr *addr) } EXPORT_SYMBOL(rdma_get_service_id); +void rdma_read_gids(struct rdma_cm_id *cm_id, union ib_gid *sgid, + union ib_gid *dgid) +{ + struct rdma_addr *addr = &cm_id->route.addr; + + if (!cm_id->device) { + if (sgid) + memset(sgid, 0, sizeof(*sgid)); + if (dgid) + memset(dgid, 0, sizeof(*dgid)); + return; + } + + if (rdma_protocol_roce(cm_id->device, cm_id->port_num)) { + if (sgid) + rdma_ip2gid((struct sockaddr *)&addr->src_addr, sgid); + if (dgid) + rdma_ip2gid((struct sockaddr *)&addr->dst_addr, dgid); + } else { + if (sgid) + rdma_addr_get_sgid(&addr->dev_addr, sgid); + if (dgid) + rdma_addr_get_dgid(&addr->dev_addr, dgid); + } +} +EXPORT_SYMBOL(rdma_read_gids); + static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event) { struct rdma_id_private *id_priv = iw_id->context; @@ -2713,6 +2743,26 @@ out: kfree(work); } +static void cma_init_resolve_route_work(struct cma_work *work, + struct rdma_id_private *id_priv) +{ + work->id = id_priv; + INIT_WORK(&work->work, cma_work_handler); + work->old_state = RDMA_CM_ROUTE_QUERY; + work->new_state = RDMA_CM_ROUTE_RESOLVED; + work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; +} + +static void cma_init_resolve_addr_work(struct cma_work *work, + struct rdma_id_private *id_priv) +{ + work->id = id_priv; + INIT_WORK(&work->work, cma_work_handler); + work->old_state = RDMA_CM_ADDR_QUERY; + work->new_state = RDMA_CM_ADDR_RESOLVED; + work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED; +} + static int cma_resolve_ib_route(struct rdma_id_private *id_priv, int timeout_ms) { struct rdma_route *route = &id_priv->id.route; @@ -2723,11 +2773,7 @@ static int cma_resolve_ib_route(struct rdma_id_private *id_priv, int timeout_ms) if (!work) return -ENOMEM; - work->id = id_priv; - INIT_WORK(&work->work, cma_work_handler); - work->old_state = RDMA_CM_ROUTE_QUERY; - work->new_state = RDMA_CM_ROUTE_RESOLVED; - work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; + cma_init_resolve_route_work(work, id_priv); route->path_rec = kmalloc(sizeof *route->path_rec, GFP_KERNEL); if (!route->path_rec) { @@ -2748,10 +2794,63 @@ err1: return ret; } -int rdma_set_ib_paths(struct rdma_cm_id *id, - struct sa_path_rec *path_rec, int num_paths) +static enum ib_gid_type cma_route_gid_type(enum rdma_network_type network_type, + unsigned long supported_gids, + enum ib_gid_type default_gid) +{ + if ((network_type == RDMA_NETWORK_IPV4 || + network_type == RDMA_NETWORK_IPV6) && + test_bit(IB_GID_TYPE_ROCE_UDP_ENCAP, &supported_gids)) + return IB_GID_TYPE_ROCE_UDP_ENCAP; + + return default_gid; +} + +/* + * cma_iboe_set_path_rec_l2_fields() is helper function which sets + * path record type based on GID type. + * It also sets up other L2 fields which includes destination mac address + * netdev ifindex, of the path record. + * It returns the netdev of the bound interface for this path record entry. + */ +static if_t +cma_iboe_set_path_rec_l2_fields(struct rdma_id_private *id_priv) +{ + struct rdma_route *route = &id_priv->id.route; + enum ib_gid_type gid_type = IB_GID_TYPE_ROCE; + struct rdma_addr *addr = &route->addr; + unsigned long supported_gids; + if_t ndev; + + if (!addr->dev_addr.bound_dev_if) + return NULL; + + ndev = dev_get_by_index(addr->dev_addr.net, + addr->dev_addr.bound_dev_if); + if (!ndev) + return NULL; + + supported_gids = roce_gid_type_mask_support(id_priv->id.device, + id_priv->id.port_num); + gid_type = cma_route_gid_type(addr->dev_addr.network, + supported_gids, + id_priv->gid_type); + /* Use the hint from IP Stack to select GID Type */ + if (gid_type < ib_network_to_gid_type(addr->dev_addr.network)) + gid_type = ib_network_to_gid_type(addr->dev_addr.network); + route->path_rec->rec_type = sa_conv_gid_to_pathrec_type(gid_type); + + sa_path_set_ndev(route->path_rec, addr->dev_addr.net); + sa_path_set_ifindex(route->path_rec, if_getindex(ndev)); + sa_path_set_dmac(route->path_rec, addr->dev_addr.dst_dev_addr); + return ndev; +} + +int rdma_set_ib_path(struct rdma_cm_id *id, + struct sa_path_rec *path_rec) { struct rdma_id_private *id_priv; + if_t ndev; int ret; id_priv = container_of(id, struct rdma_id_private, id); @@ -2759,20 +2858,33 @@ int rdma_set_ib_paths(struct rdma_cm_id *id, RDMA_CM_ROUTE_RESOLVED)) return -EINVAL; - id->route.path_rec = kmemdup(path_rec, sizeof *path_rec * num_paths, + id->route.path_rec = kmemdup(path_rec, sizeof(*path_rec), GFP_KERNEL); if (!id->route.path_rec) { ret = -ENOMEM; goto err; } - id->route.num_paths = num_paths; + if (rdma_protocol_roce(id->device, id->port_num)) { + ndev = cma_iboe_set_path_rec_l2_fields(id_priv); + if (!ndev) { + ret = -ENODEV; + goto err_free; + } + dev_put(ndev); + } + + id->route.num_paths = 1; return 0; + +err_free: + kfree(id->route.path_rec); + id->route.path_rec = NULL; err: cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_ADDR_RESOLVED); return ret; } -EXPORT_SYMBOL(rdma_set_ib_paths); +EXPORT_SYMBOL(rdma_set_ib_path); static int cma_resolve_iw_route(struct rdma_id_private *id_priv, int timeout_ms) { @@ -2782,11 +2894,7 @@ static int cma_resolve_iw_route(struct rdma_id_private *id_priv, int timeout_ms) if (!work) return -ENOMEM; - work->id = id_priv; - INIT_WORK(&work->work, cma_work_handler); - work->old_state = RDMA_CM_ROUTE_QUERY; - work->new_state = RDMA_CM_ROUTE_RESOLVED; - work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; + cma_init_resolve_route_work(work, id_priv); queue_work(cma_wq, &work->work); return 0; } @@ -2800,26 +2908,14 @@ static int iboe_tos_to_sl(if_t ndev, int tos) return sl; } -static enum ib_gid_type cma_route_gid_type(enum rdma_network_type network_type, - unsigned long supported_gids, - enum ib_gid_type default_gid) -{ - if ((network_type == RDMA_NETWORK_IPV4 || - network_type == RDMA_NETWORK_IPV6) && - test_bit(IB_GID_TYPE_ROCE_UDP_ENCAP, &supported_gids)) - return IB_GID_TYPE_ROCE_UDP_ENCAP; - - return default_gid; -} - 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; struct cma_work *work; int ret; - if_t ndev = NULL; - enum ib_gid_type gid_type = IB_GID_TYPE_IB; + if_t ndev; + u8 default_roce_tos = id_priv->cma_dev->default_roce_tos[id_priv->id.port_num - rdma_start_port(id_priv->cma_dev->device)]; u8 tos = id_priv->tos_set ? id_priv->tos : default_roce_tos; @@ -2829,9 +2925,6 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) if (!work) return -ENOMEM; - work->id = id_priv; - INIT_WORK(&work->work, cma_work_handler); - route->path_rec = kzalloc(sizeof *route->path_rec, GFP_KERNEL); if (!route->path_rec) { ret = -ENOMEM; @@ -2840,43 +2933,17 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) route->num_paths = 1; - if (addr->dev_addr.bound_dev_if) { - unsigned long supported_gids; - - ndev = dev_get_by_index(addr->dev_addr.net, - addr->dev_addr.bound_dev_if); - if (!ndev) { - ret = -ENODEV; - goto err2; - } - - supported_gids = roce_gid_type_mask_support(id_priv->id.device, - id_priv->id.port_num); - gid_type = cma_route_gid_type(addr->dev_addr.network, - supported_gids, - id_priv->gid_type); - route->path_rec->rec_type = - sa_conv_gid_to_pathrec_type(gid_type); - sa_path_set_ndev(route->path_rec, if_getvnet(ndev)); - sa_path_set_ifindex(route->path_rec, if_getindex(ndev)); - } + ndev = cma_iboe_set_path_rec_l2_fields(id_priv); if (!ndev) { ret = -ENODEV; goto err2; } - sa_path_set_dmac(route->path_rec, addr->dev_addr.dst_dev_addr); - 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); - /* Use the hint from IP Stack to select GID Type */ - if (gid_type < ib_network_to_gid_type(addr->dev_addr.network)) - gid_type = ib_network_to_gid_type(addr->dev_addr.network); - route->path_rec->rec_type = sa_conv_gid_to_pathrec_type(gid_type); - 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 = addr->dev_addr.hoplimit; @@ -2898,11 +2965,7 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) goto err2; } - work->old_state = RDMA_CM_ROUTE_QUERY; - work->new_state = RDMA_CM_ROUTE_RESOLVED; - work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; - work->event.status = 0; - + cma_init_resolve_route_work(work, id_priv); queue_work(cma_wq, &work->work); return 0; @@ -3076,11 +3139,7 @@ static int cma_resolve_loopback(struct rdma_id_private *id_priv) rdma_addr_get_sgid(&id_priv->id.route.addr.dev_addr, &gid); rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, &gid); - work->id = id_priv; - INIT_WORK(&work->work, cma_work_handler); - work->old_state = RDMA_CM_ADDR_QUERY; - work->new_state = RDMA_CM_ADDR_RESOLVED; - work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED; + cma_init_resolve_addr_work(work, id_priv); queue_work(cma_wq, &work->work); return 0; err: @@ -3106,11 +3165,7 @@ static int cma_resolve_ib_addr(struct rdma_id_private *id_priv) rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *) &(((struct sockaddr_ib *) &id_priv->id.route.addr.dst_addr)->sib_addr)); - work->id = id_priv; - INIT_WORK(&work->work, cma_work_handler); - work->old_state = RDMA_CM_ADDR_QUERY; - work->new_state = RDMA_CM_ADDR_RESOLVED; - work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED; + cma_init_resolve_addr_work(work, id_priv); queue_work(cma_wq, &work->work); return 0; err: @@ -3745,10 +3800,10 @@ static int cma_sidr_rep_handler(struct ib_cm_id *cm_id, event.status = ret; break; } - ret = ib_init_ah_from_path(id_priv->id.device, - id_priv->id.port_num, - id_priv->id.route.path_rec, - &event.param.ud.ah_attr); + ret = ib_init_ah_attr_from_path(id_priv->id.device, + id_priv->id.port_num, + id_priv->id.route.path_rec, + &event.param.ud.ah_attr); if (ret) { event.event = RDMA_CM_EVENT_ADDR_ERROR; event.status = ret; diff --git a/sys/ofed/drivers/infiniband/core/ib_cq.c b/sys/ofed/drivers/infiniband/core/ib_cq.c index 9b100619cde7..d5c498e65509 100644 --- a/sys/ofed/drivers/infiniband/core/ib_cq.c +++ b/sys/ofed/drivers/infiniband/core/ib_cq.c @@ -41,6 +41,7 @@ /* # of WCs to poll for with a single call to ib_poll_cq */ #define IB_POLL_BATCH 16 +#define IB_POLL_BATCH_DIRECT 8 /* # of WCs to iterate over before yielding */ #define IB_POLL_BUDGET_WORKQUEUE 65536 @@ -48,7 +49,8 @@ #define IB_POLL_FLAGS \ (IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS) -static int __ib_process_cq(struct ib_cq *cq, int budget) +static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *wcs, + int batch) { int i, n, completed = 0; @@ -57,10 +59,10 @@ static int __ib_process_cq(struct ib_cq *cq, int budget) * want to bound this call, thus we need unsigned * minimum here. */ - while ((n = ib_poll_cq(cq, min_t(u32, IB_POLL_BATCH, - budget - completed), cq->wc)) > 0) { + while ((n = ib_poll_cq(cq, min_t(u32, batch, + budget - completed), wcs)) > 0) { for (i = 0; i < n; i++) { - struct ib_wc *wc = &cq->wc[i]; + struct ib_wc *wc = &wcs[i]; if (wc->wr_cqe) wc->wr_cqe->done(cq, wc); @@ -70,8 +72,7 @@ static int __ib_process_cq(struct ib_cq *cq, int budget) completed += n; - if (n != IB_POLL_BATCH || - (budget != -1 && completed >= budget)) + if (n != batch || (budget != -1 && completed >= budget)) break; } @@ -83,18 +84,20 @@ static int __ib_process_cq(struct ib_cq *cq, int budget) * @cq: CQ to process * @budget: number of CQEs to poll for * - * This function is used to process all outstanding CQ entries on a - * %IB_POLL_DIRECT CQ. It does not offload CQ processing to a different - * context and does not ask for completion interrupts from the HCA. + * This function is used to process all outstanding CQ entries. + * It does not offload CQ processing to a different context and does + * not ask for completion interrupts from the HCA. + * Using direct processing on CQ with non IB_POLL_DIRECT type may trigger + * concurrent processing. * * Note: do not pass -1 as %budget unless it is guaranteed that the number * of completions that will be processed is small. */ int ib_process_cq_direct(struct ib_cq *cq, int budget) { - WARN_ON_ONCE(cq->poll_ctx != IB_POLL_DIRECT); + struct ib_wc wcs[IB_POLL_BATCH_DIRECT]; - return __ib_process_cq(cq, budget); + return __ib_process_cq(cq, budget, wcs, IB_POLL_BATCH_DIRECT); } EXPORT_SYMBOL(ib_process_cq_direct); @@ -108,7 +111,8 @@ static void ib_cq_poll_work(struct work_struct *work) struct ib_cq *cq = container_of(work, struct ib_cq, work); int completed; - completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE); + completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE, cq->wc, + IB_POLL_BATCH); if (completed >= IB_POLL_BUDGET_WORKQUEUE || ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0) queue_work(ib_comp_wq, &cq->work); diff --git a/sys/ofed/drivers/infiniband/core/ib_device.c b/sys/ofed/drivers/infiniband/core/ib_device.c index 7aae715657fb..9c45149a7877 100644 --- a/sys/ofed/drivers/infiniband/core/ib_device.c +++ b/sys/ofed/drivers/infiniband/core/ib_device.c @@ -857,32 +857,22 @@ EXPORT_SYMBOL(ib_modify_port); /** * ib_find_gid - Returns the port number and GID table index where - * a specified GID value occurs. + * a specified GID value occurs. Its searches only for IB link layer. * @device: The device to query. * @gid: The GID value to search for. - * @gid_type: Type of GID. * @ndev: The ndev related to the GID to search for. * @port_num: The port number of the device where the GID value was found. * @index: The index into the GID table where the GID was found. This * parameter may be NULL. */ int ib_find_gid(struct ib_device *device, union ib_gid *gid, - enum ib_gid_type gid_type, if_t ndev, - u8 *port_num, u16 *index) + if_t ndev, u8 *port_num, u16 *index) { union ib_gid tmp_gid; int ret, port, i; for (port = rdma_start_port(device); port <= rdma_end_port(device); ++port) { - if (rdma_cap_roce_gid_table(device, port)) { - if (!ib_find_cached_gid_by_port(device, gid, gid_type, port, - ndev, index)) { - *port_num = port; - return 0; - } - } - - if (gid_type != IB_GID_TYPE_IB) + if (rdma_cap_roce_gid_table(device, port)) continue; for (i = 0; i < device->port_immutable[port].gid_tbl_len; ++i) { diff --git a/sys/ofed/drivers/infiniband/core/ib_sa_query.c b/sys/ofed/drivers/infiniband/core/ib_sa_query.c index c8e1af4bd2f2..65d132fe7f7a 100644 --- a/sys/ofed/drivers/infiniband/core/ib_sa_query.c +++ b/sys/ofed/drivers/infiniband/core/ib_sa_query.c @@ -790,9 +790,9 @@ static u8 get_src_path_mask(struct ib_device *device, u8 port_num) return src_path_mask; } -int ib_init_ah_from_path(struct ib_device *device, u8 port_num, - struct sa_path_rec *rec, - struct rdma_ah_attr *ah_attr) +int ib_init_ah_attr_from_path(struct ib_device *device, u8 port_num, + struct sa_path_rec *rec, + struct rdma_ah_attr *ah_attr) { int ret; u16 gid_index; @@ -897,10 +897,11 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num, return 0; } -EXPORT_SYMBOL(ib_init_ah_from_path); +EXPORT_SYMBOL(ib_init_ah_attr_from_path); static int alloc_mad(struct ib_sa_query *query, gfp_t gfp_mask) { + struct rdma_ah_attr ah_attr; unsigned long flags; spin_lock_irqsave(&query->port->ah_lock, flags); @@ -912,6 +913,15 @@ static int alloc_mad(struct ib_sa_query *query, gfp_t gfp_mask) query->sm_ah = query->port->sm_ah; spin_unlock_irqrestore(&query->port->ah_lock, flags); + /* + * Always check if sm_ah has valid dlid assigned, + * before querying for class port info + */ + if ((rdma_query_ah(query->sm_ah->ah, &ah_attr) < 0) || + !rdma_is_valid_unicast_lid(&ah_attr)) { + kref_put(&query->sm_ah->ref, free_sm_ah); + return -EAGAIN; + } query->mad_buf = ib_create_send_mad(query->port->agent, 1, query->sm_ah->pkey_index, 0, IB_MGMT_SA_HDR, IB_MGMT_SA_DATA, diff --git a/sys/ofed/drivers/infiniband/core/ib_ucma.c b/sys/ofed/drivers/infiniband/core/ib_ucma.c index 4d17b8285012..66b8875082db 100644 --- a/sys/ofed/drivers/infiniband/core/ib_ucma.c +++ b/sys/ofed/drivers/infiniband/core/ib_ucma.c @@ -922,13 +922,14 @@ static ssize_t ucma_query_path(struct ucma_context *ctx, resp->path_data[i].flags = IB_PATH_GMP | IB_PATH_PRIMARY | IB_PATH_BIDIRECTIONAL; - if (rec->rec_type == SA_PATH_REC_TYPE_IB) { - ib_sa_pack_path(rec, &resp->path_data[i].path_rec); - } else { + if (rec->rec_type == SA_PATH_REC_TYPE_OPA) { struct sa_path_rec ib; sa_convert_path_opa_to_ib(&ib, rec); ib_sa_pack_path(&ib, &resp->path_data[i].path_rec); + + } else { + ib_sa_pack_path(rec, &resp->path_data[i].path_rec); } } @@ -961,8 +962,8 @@ static ssize_t ucma_query_gid(struct ucma_context *ctx, } else { addr->sib_family = AF_IB; addr->sib_pkey = (__force __be16) resp.pkey; - rdma_addr_get_sgid(&ctx->cm_id->route.addr.dev_addr, - (union ib_gid *) &addr->sib_addr); + rdma_read_gids(ctx->cm_id, (union ib_gid *)&addr->sib_addr, + NULL); addr->sib_sid = rdma_get_service_id(ctx->cm_id, (struct sockaddr *) &ctx->cm_id->route.addr.src_addr); } @@ -974,8 +975,8 @@ static ssize_t ucma_query_gid(struct ucma_context *ctx, } else { addr->sib_family = AF_IB; addr->sib_pkey = (__force __be16) resp.pkey; - rdma_addr_get_dgid(&ctx->cm_id->route.addr.dev_addr, - (union ib_gid *) &addr->sib_addr); + rdma_read_gids(ctx->cm_id, NULL, + (union ib_gid *)&addr->sib_addr); addr->sib_sid = rdma_get_service_id(ctx->cm_id, (struct sockaddr *) &ctx->cm_id->route.addr.dst_addr); } @@ -1256,9 +1257,9 @@ static int ucma_set_ib_path(struct ucma_context *ctx, struct sa_path_rec opa; sa_convert_path_ib_to_opa(&opa, &sa_path); - ret = rdma_set_ib_paths(ctx->cm_id, &opa, 1); + ret = rdma_set_ib_path(ctx->cm_id, &opa); } else { - ret = rdma_set_ib_paths(ctx->cm_id, &sa_path, 1); + ret = rdma_set_ib_path(ctx->cm_id, &sa_path); } if (ret) return ret; diff --git a/sys/ofed/drivers/infiniband/core/ib_user_mad.c b/sys/ofed/drivers/infiniband/core/ib_user_mad.c index 3b7f6f67c185..682c05576116 100644 --- a/sys/ofed/drivers/infiniband/core/ib_user_mad.c +++ b/sys/ofed/drivers/infiniband/core/ib_user_mad.c @@ -241,9 +241,10 @@ static void recv_handler(struct ib_mad_agent *agent, const struct ib_global_route *grh; int ret; - ret = ib_init_ah_from_wc(agent->device, agent->port_num, - mad_recv_wc->wc, mad_recv_wc->recv_buf.grh, - &ah_attr); + ret = ib_init_ah_attr_from_wc(agent->device, agent->port_num, + mad_recv_wc->wc, + mad_recv_wc->recv_buf.grh, + &ah_attr); if (ret) goto err2; diff --git a/sys/ofed/drivers/infiniband/core/ib_verbs.c b/sys/ofed/drivers/infiniband/core/ib_verbs.c index b0cdf8a318d9..390f57892441 100644 --- a/sys/ofed/drivers/infiniband/core/ib_verbs.c +++ b/sys/ofed/drivers/infiniband/core/ib_verbs.c @@ -511,8 +511,7 @@ static bool find_gid_index(const union ib_gid *gid, void *context) { u16 vlan_diff; - struct find_gid_index_context *ctx = - (struct find_gid_index_context *)context; + struct find_gid_index_context *ctx = context; if (ctx->gid_type != gid_attr->gid_type) return false; @@ -575,8 +574,53 @@ int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr, } EXPORT_SYMBOL(ib_get_gids_from_rdma_hdr); +/* Resolve destination mac address and hop limit for unicast destination + * GID entry, considering the source GID entry as well. + * ah_attribute must have have valid port_num, sgid_index. + */ +static int ib_resolve_unicast_gid_dmac(struct ib_device *device, + struct rdma_ah_attr *ah_attr) +{ + struct ib_gid_attr sgid_attr; + struct ib_global_route *grh; + int hop_limit = 0xff; + union ib_gid sgid; + int ret; + + grh = rdma_ah_retrieve_grh(ah_attr); + + ret = ib_query_gid(device, + rdma_ah_get_port_num(ah_attr), + grh->sgid_index, + &sgid, &sgid_attr); + if (ret || !sgid_attr.ndev) { + if (!ret) + ret = -ENXIO; + return ret; + } + + /* If destination is link local and source GID is RoCEv1, + * IP stack is not used. + */ + if (rdma_link_local_addr((struct in6_addr *)grh->dgid.raw) && + sgid_attr.gid_type == IB_GID_TYPE_ROCE) { + rdma_get_ll_mac((struct in6_addr *)grh->dgid.raw, + ah_attr->roce.dmac); + goto done; + } + + ret = rdma_addr_find_l2_eth_by_grh(&sgid, &grh->dgid, + ah_attr->roce.dmac, + sgid_attr.ndev, &hop_limit); +done: + dev_put(sgid_attr.ndev); + + grh->hop_limit = hop_limit; + return ret; +} + /* - * This function creates ah from the incoming packet. + * This function initializes address handle attributes from the incoming packet. * Incoming packet has dgid of the receiver node on which this code is * getting executed and, sgid contains the GID of the sender. * @@ -584,13 +628,10 @@ EXPORT_SYMBOL(ib_get_gids_from_rdma_hdr); * as sgid and, sgid is used as dgid because sgid contains destinations * GID whom to respond to. * - * This is why when calling rdma_addr_find_l2_eth_by_grh() function, the - * position of arguments dgid and sgid do not match the order of the - * parameters. */ -int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, - const struct ib_wc *wc, const struct ib_grh *grh, - struct rdma_ah_attr *ah_attr) +int ib_init_ah_attr_from_wc(struct ib_device *device, u8 port_num, + const struct ib_wc *wc, const struct ib_grh *grh, + struct rdma_ah_attr *ah_attr) { u32 flow_class; u16 gid_index = 0; @@ -615,42 +656,33 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, if (ret) return ret; + rdma_ah_set_sl(ah_attr, wc->sl); + rdma_ah_set_port_num(ah_attr, port_num); + if (rdma_protocol_roce(device, port_num)) { - struct ib_gid_attr dgid_attr; const u16 vlan_id = (wc->wc_flags & IB_WC_WITH_VLAN) ? wc->vlan_id : 0xffff; if (!(wc->wc_flags & IB_WC_GRH)) return -EPROTOTYPE; - ret = get_sgid_index_from_eth(device, port_num, vlan_id, - &dgid, gid_type, &gid_index); - if (ret) - return ret; - - ret = ib_get_cached_gid(device, port_num, gid_index, &dgid, &dgid_attr); - if (ret) - return ret; - - if (dgid_attr.ndev == NULL) - return -ENODEV; - - ret = rdma_addr_find_l2_eth_by_grh(&dgid, &sgid, - ah_attr->roce.dmac, - dgid_attr.ndev, &hoplimit); - - dev_put(dgid_attr.ndev); + ret = get_sgid_index_from_eth(device, port_num, + vlan_id, &dgid, + gid_type, &gid_index); if (ret) return ret; - } - rdma_ah_set_dlid(ah_attr, wc->slid); - rdma_ah_set_sl(ah_attr, wc->sl); - rdma_ah_set_path_bits(ah_attr, wc->dlid_path_bits); - rdma_ah_set_port_num(ah_attr, port_num); + flow_class = be32_to_cpu(grh->version_tclass_flow); + rdma_ah_set_grh(ah_attr, &sgid, + flow_class & 0xFFFFF, + (u8)gid_index, hoplimit, + (flow_class >> 20) & 0xFF); + return ib_resolve_unicast_gid_dmac(device, ah_attr); + } else { + rdma_ah_set_dlid(ah_attr, wc->slid); + rdma_ah_set_path_bits(ah_attr, wc->dlid_path_bits); - if (wc->wc_flags & IB_WC_GRH) { - if (!rdma_cap_eth_ah(device, port_num)) { + if (wc->wc_flags & IB_WC_GRH) { if (dgid.global.interface_id != cpu_to_be64(IB_SA_WELL_KNOWN_GUID)) { ret = ib_find_cached_gid_by_port(device, &dgid, IB_GID_TYPE_IB, @@ -659,18 +691,17 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, if (ret) return ret; } - } - - flow_class = be32_to_cpu(grh->version_tclass_flow); - rdma_ah_set_grh(ah_attr, &sgid, - flow_class & 0xFFFFF, - (u8)gid_index, hoplimit, - (flow_class >> 20) & 0xFF); + flow_class = be32_to_cpu(grh->version_tclass_flow); + rdma_ah_set_grh(ah_attr, &sgid, + flow_class & 0xFFFFF, + (u8)gid_index, hoplimit, + (flow_class >> 20) & 0xFF); + } + return 0; } - return 0; } -EXPORT_SYMBOL(ib_init_ah_from_wc); +EXPORT_SYMBOL(ib_init_ah_attr_from_wc); struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc, const struct ib_grh *grh, u8 port_num) @@ -678,7 +709,7 @@ struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc, struct rdma_ah_attr ah_attr; int ret; - ret = ib_init_ah_from_wc(pd->device, port_num, wc, grh, &ah_attr); + ret = ib_init_ah_attr_from_wc(pd->device, port_num, wc, grh, &ah_attr); if (ret) return ERR_PTR(ret); @@ -693,7 +724,7 @@ int rdma_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr) return ah->device->modify_ah ? ah->device->modify_ah(ah, ah_attr) : - -ENOSYS; + -EOPNOTSUPP; } EXPORT_SYMBOL(rdma_modify_ah); @@ -701,7 +732,7 @@ int rdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr) { return ah->device->query_ah ? ah->device->query_ah(ah, ah_attr) : - -ENOSYS; + -EOPNOTSUPP; } EXPORT_SYMBOL(rdma_query_ah); @@ -772,7 +803,7 @@ int ib_modify_srq(struct ib_srq *srq, { return srq->device->modify_srq ? srq->device->modify_srq(srq, srq_attr, srq_attr_mask, NULL) : - -ENOSYS; + -EOPNOTSUPP; } EXPORT_SYMBOL(ib_modify_srq); @@ -780,7 +811,7 @@ int ib_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr) { return srq->device->query_srq ? - srq->device->query_srq(srq, srq_attr) : -ENOSYS; + srq->device->query_srq(srq, srq_attr) : -EOPNOTSUPP; } EXPORT_SYMBOL(ib_query_srq); @@ -1295,18 +1326,12 @@ EXPORT_SYMBOL(ib_modify_qp_is_ok); static int ib_resolve_eth_dmac(struct ib_device *device, struct rdma_ah_attr *ah_attr) { - struct ib_gid_attr sgid_attr; - union ib_gid sgid; - int hop_limit; - int ret; + int ret = 0; struct ib_global_route *grh; if (!rdma_is_port_valid(device, rdma_ah_get_port_num(ah_attr))) return -EINVAL; - if (ah_attr->type != RDMA_AH_ATTR_TYPE_ROCE) - return 0; - grh = rdma_ah_retrieve_grh(ah_attr); if (rdma_is_multicast_addr((struct in6_addr *)ah_attr->grh.dgid.raw)) { @@ -1319,24 +1344,9 @@ static int ib_resolve_eth_dmac(struct ib_device *device, ipv6_eth_mc_map((struct in6_addr *)ah_attr->grh.dgid.raw, (char *)ah_attr->roce.dmac); } - return 0; + } else { + ret = ib_resolve_unicast_gid_dmac(device, ah_attr); } - - ret = ib_query_gid(device, - rdma_ah_get_port_num(ah_attr), - grh->sgid_index, - &sgid, &sgid_attr); - if (ret != 0) - return (ret); - if (!sgid_attr.ndev) - return -ENXIO; - - ret = rdma_addr_find_l2_eth_by_grh(&sgid, &grh->dgid, - ah_attr->roce.dmac, - sgid_attr.ndev, &hop_limit); - dev_put(sgid_attr.ndev); - - grh->hop_limit = hop_limit; return ret; } @@ -1379,7 +1389,7 @@ static int _ib_modify_qp(struct ib_qp *qp, struct ib_qp_attr *attr, * users have to provide already resolved rdma_ah_attr's */ if (udata && (attr_mask & IB_QP_AV) && - rdma_protocol_roce(qp->device, port) && + attr->ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE && is_qp_type_connected(qp)) { ret = ib_resolve_eth_dmac(qp->device, &attr->ah_attr); if (ret) @@ -1445,7 +1455,7 @@ int ib_query_qp(struct ib_qp *qp, { return qp->device->query_qp ? qp->device->query_qp(qp->real_qp, qp_attr, qp_attr_mask, qp_init_attr) : - -ENOSYS; + -EOPNOTSUPP; } EXPORT_SYMBOL(ib_query_qp); @@ -1571,7 +1581,7 @@ EXPORT_SYMBOL(__ib_create_cq); int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period) { return cq->device->modify_cq ? - cq->device->modify_cq(cq, cq_count, cq_period) : -ENOSYS; + cq->device->modify_cq(cq, cq_count, cq_period) : -EOPNOTSUPP; } EXPORT_SYMBOL(rdma_set_cq_moderation); @@ -1589,7 +1599,7 @@ EXPORT_SYMBOL(ib_destroy_cq_user); int ib_resize_cq(struct ib_cq *cq, int cqe) { return cq->device->resize_cq ? - cq->device->resize_cq(cq, cqe, NULL) : -ENOSYS; + cq->device->resize_cq(cq, cqe, NULL) : -EOPNOTSUPP; } EXPORT_SYMBOL(ib_resize_cq); @@ -1669,7 +1679,7 @@ struct ib_fmr *ib_alloc_fmr(struct ib_pd *pd, struct ib_fmr *fmr; if (!pd->device->alloc_fmr) - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); fmr = pd->device->alloc_fmr(pd, mr_access_flags, fmr_attr); if (!IS_ERR(fmr)) { @@ -1753,7 +1763,7 @@ int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid) int ret; if (!qp->device->attach_mcast) - return -ENOSYS; + return -EOPNOTSUPP; if (!rdma_is_multicast_addr((struct in6_addr *)gid->raw) || qp->qp_type != IB_QPT_UD || !is_valid_mcast_lid(qp, lid)) @@ -1771,7 +1781,7 @@ int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid) int ret; if (!qp->device->detach_mcast) - return -ENOSYS; + return -EOPNOTSUPP; if (!rdma_is_multicast_addr((struct in6_addr *)gid->raw) || qp->qp_type != IB_QPT_UD || !is_valid_mcast_lid(qp, lid)) @@ -1844,7 +1854,7 @@ struct ib_wq *ib_create_wq(struct ib_pd *pd, struct ib_wq *wq; if (!pd->device->create_wq) - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); wq = pd->device->create_wq(pd, wq_attr, NULL); if (!IS_ERR(wq)) { @@ -1898,7 +1908,7 @@ int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr, int err; if (!wq->device->modify_wq) - return -ENOSYS; + return -EOPNOTSUPP; err = wq->device->modify_wq(wq, wq_attr, wq_attr_mask, NULL); return err; @@ -1923,7 +1933,7 @@ struct ib_rwq_ind_table *ib_create_rwq_ind_table(struct ib_device *device, u32 table_size; if (!device->create_rwq_ind_table) - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); table_size = (1 << init_attr->log_ind_tbl_size); rwq_ind_table = device->create_rwq_ind_table(device, @@ -1971,7 +1981,7 @@ int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status) { return mr->device->check_mr_status ? - mr->device->check_mr_status(mr, check_mask, mr_status) : -ENOSYS; + mr->device->check_mr_status(mr, check_mask, mr_status) : -EOPNOTSUPP; } EXPORT_SYMBOL(ib_check_mr_status); @@ -1979,7 +1989,7 @@ int ib_set_vf_link_state(struct ib_device *device, int vf, u8 port, int state) { if (!device->set_vf_link_state) - return -ENOSYS; + return -EOPNOTSUPP; return device->set_vf_link_state(device, vf, port, state); } @@ -1989,7 +1999,7 @@ int ib_get_vf_config(struct ib_device *device, int vf, u8 port, struct ifla_vf_info *info) { if (!device->get_vf_config) - return -ENOSYS; + return -EOPNOTSUPP; return device->get_vf_config(device, vf, port, info); } @@ -1999,7 +2009,7 @@ int ib_get_vf_stats(struct ib_device *device, int vf, u8 port, struct ifla_vf_stats *stats) { if (!device->get_vf_stats) - return -ENOSYS; + return -EOPNOTSUPP; return device->get_vf_stats(device, vf, port, stats); } @@ -2009,7 +2019,7 @@ int ib_set_vf_guid(struct ib_device *device, int vf, u8 port, u64 guid, int type) { if (!device->set_vf_guid) - return -ENOSYS; + return -EOPNOTSUPP; return device->set_vf_guid(device, vf, port, guid, type); } @@ -2044,7 +2054,7 @@ int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size) { if (unlikely(!mr->device->map_mr_sg)) - return -ENOSYS; + return -EOPNOTSUPP; mr->page_size = page_size; @@ -2170,15 +2180,15 @@ static void __ib_drain_sq(struct ib_qp *qp) }; int ret; - sdrain.cqe.done = ib_drain_qp_done; - init_completion(&sdrain.done); - ret = ib_modify_qp(qp, &attr, IB_QP_STATE); if (ret) { WARN_ONCE(ret, "failed to drain send queue: %d\n", ret); return; } + sdrain.cqe.done = ib_drain_qp_done; + init_completion(&sdrain.done); + ret = ib_post_send(qp, &swr.wr, &bad_swr); if (ret) { WARN_ONCE(ret, "failed to drain send queue: %d\n", ret); @@ -2204,16 +2214,16 @@ static void __ib_drain_rq(struct ib_qp *qp) const struct ib_recv_wr *bad_rwr; int ret; - rwr.wr_cqe = &rdrain.cqe; - rdrain.cqe.done = ib_drain_qp_done; - init_completion(&rdrain.done); - ret = ib_modify_qp(qp, &attr, IB_QP_STATE); if (ret) { WARN_ONCE(ret, "failed to drain recv queue: %d\n", ret); return; } + rwr.wr_cqe = &rdrain.cqe; + rdrain.cqe.done = ib_drain_qp_done; + init_completion(&rdrain.done); + ret = ib_post_recv(qp, &rwr, &bad_rwr); if (ret) { WARN_ONCE(ret, "failed to drain recv queue: %d\n", ret); diff --git a/sys/ofed/drivers/infiniband/ulp/ipoib/ipoib_main.c b/sys/ofed/drivers/infiniband/ulp/ipoib/ipoib_main.c index 90243707f692..9cdfa153eb1c 100644 --- a/sys/ofed/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/sys/ofed/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -530,7 +530,8 @@ path_rec_completion(int status, struct sa_path_rec *pathrec, void *path_ptr) if (!status) { struct rdma_ah_attr av; - if (!ib_init_ah_from_path(priv->ca, priv->port, pathrec, &av)) + if (!ib_init_ah_attr_from_path(priv->ca, priv->port, + pathrec, &av)) ah = ipoib_create_ah(priv, priv->pd, &av); } diff --git a/sys/ofed/include/rdma/ib_addr.h b/sys/ofed/include/rdma/ib_addr.h index b59d4a7bd572..bea3315d8deb 100644 --- a/sys/ofed/include/rdma/ib_addr.h +++ b/sys/ofed/include/rdma/ib_addr.h @@ -150,7 +150,7 @@ int rdma_addr_size_kss(struct sockaddr_storage *addr); int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid, const union ib_gid *dgid, - u8 *smac, if_t dev, + u8 *dmac, if_t ndev, int *hoplimit); static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr) @@ -227,40 +227,15 @@ static inline void rdma_gid2ip(struct sockaddr *out, const union ib_gid *gid) } } -static u_int -_iboe_addr_get_sgid_ia_cb(void *arg, struct ifaddr *ifa, u_int count __unused) -{ - ipv6_addr_set_v4mapped(((struct sockaddr_in *) - ifa->ifa_addr)->sin_addr.s_addr, - (struct in6_addr *)arg); - return (0); -} - -static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr, - union ib_gid *gid) -{ - if_t dev; - -#ifdef VIMAGE - if (dev_addr->net == NULL) - return; -#endif - dev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); - if (dev) { - if_foreach_addr_type(dev, AF_INET, - _iboe_addr_get_sgid_ia_cb, gid); - dev_put(dev); - } -} - +/* + * rdma_get/set_sgid/dgid() APIs are applicable to IB, and iWarp. + * They are not applicable to RoCE. + * RoCE GIDs are derived from the IP addresses. + */ static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { - if (dev_addr->transport == RDMA_TRANSPORT_IB && - dev_addr->dev_type != ARPHRD_INFINIBAND) - iboe_addr_get_sgid(dev_addr, gid); - else - memcpy(gid, dev_addr->src_dev_addr + - rdma_addr_gid_offset(dev_addr), sizeof *gid); + memcpy(gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), + sizeof(*gid)); } static inline void rdma_addr_set_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) diff --git a/sys/ofed/include/rdma/ib_sa.h b/sys/ofed/include/rdma/ib_sa.h index d79012d23abf..96fef101cd89 100644 --- a/sys/ofed/include/rdma/ib_sa.h +++ b/sys/ofed/include/rdma/ib_sa.h @@ -550,12 +550,12 @@ int ib_init_ah_from_mcmember(struct ib_device *device, u8 port_num, struct rdma_ah_attr *ah_attr); /** - * ib_init_ah_from_path - Initialize address handle attributes based on an SA - * path record. + * ib_init_ah_attr_from_path - Initialize address handle attributes based on + * an SA path record. */ -int ib_init_ah_from_path(struct ib_device *device, u8 port_num, - struct sa_path_rec *rec, - struct rdma_ah_attr *ah_attr); +int ib_init_ah_attr_from_path(struct ib_device *device, u8 port_num, + struct sa_path_rec *rec, + struct rdma_ah_attr *ah_attr); /** * ib_sa_pack_path - Conert a path record from struct ib_sa_path_rec diff --git a/sys/ofed/include/rdma/ib_verbs.h b/sys/ofed/include/rdma/ib_verbs.h index 45c7d238de68..07446d16283c 100644 --- a/sys/ofed/include/rdma/ib_verbs.h +++ b/sys/ofed/include/rdma/ib_verbs.h @@ -836,6 +836,7 @@ struct ib_mr_status { __attribute_const__ enum ib_rate mult_to_ib_rate(int mult); enum rdma_ah_attr_type { + RDMA_AH_ATTR_TYPE_UNDEFINED, RDMA_AH_ATTR_TYPE_IB, RDMA_AH_ATTR_TYPE_ROCE, RDMA_AH_ATTR_TYPE_OPA, @@ -942,9 +943,9 @@ struct ib_wc { u32 invalidate_rkey; } ex; u32 src_qp; + u32 slid; int wc_flags; u16 pkey_index; - u32 slid; u8 sl; u8 dlid_path_bits; u8 port_num; /* valid only for DR SMPs on switches */ @@ -2959,8 +2960,7 @@ int ib_modify_port(struct ib_device *device, struct ib_port_modify *port_modify); int ib_find_gid(struct ib_device *device, union ib_gid *gid, - enum ib_gid_type gid_type, if_t ndev, - u8 *port_num, u16 *index); + if_t ndev, u8 *port_num, u16 *index); int ib_find_pkey(struct ib_device *device, u8 port_num, u16 pkey, u16 *index); @@ -3053,7 +3053,7 @@ int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr, int ib_get_rdma_header_version(const union rdma_network_hdr *hdr); /** - * ib_init_ah_from_wc - Initializes address handle attributes from a + * ib_init_ah_attr_from_wc - Initializes address handle attributes from a * work completion. * @device: Device on which the received message arrived. * @port_num: Port on which the received message arrived. @@ -3063,9 +3063,9 @@ int ib_get_rdma_header_version(const union rdma_network_hdr *hdr); * @ah_attr: Returned attributes that can be used when creating an address * handle for replying to the message. */ -int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, - const struct ib_wc *wc, const struct ib_grh *grh, - struct rdma_ah_attr *ah_attr); +int ib_init_ah_attr_from_wc(struct ib_device *device, u8 port_num, + const struct ib_wc *wc, const struct ib_grh *grh, + struct rdma_ah_attr *ah_attr); /** * ib_create_ah_from_wc - Creates an address handle associated with the @@ -4094,18 +4094,24 @@ static inline void rdma_ah_set_grh(struct rdma_ah_attr *attr, grh->traffic_class = traffic_class; } -/*Get AH type */ +/** + * rdma_ah_find_type - Return address handle type. + * + * @dev: Device to be checked + * @port_num: Port number + */ static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev, - u32 port_num) + u8 port_num) { - if ((rdma_protocol_roce(dev, port_num)) || - (rdma_protocol_iwarp(dev, port_num))) + if (rdma_protocol_roce(dev, port_num)) return RDMA_AH_ATTR_TYPE_ROCE; - else if ((rdma_protocol_ib(dev, port_num)) && - (rdma_cap_opa_ah(dev, port_num))) - return RDMA_AH_ATTR_TYPE_OPA; - else + if (rdma_protocol_ib(dev, port_num)) { + if (rdma_cap_opa_ah(dev, port_num)) + return RDMA_AH_ATTR_TYPE_OPA; return RDMA_AH_ATTR_TYPE_IB; + } + + return RDMA_AH_ATTR_TYPE_UNDEFINED; } /** diff --git a/sys/ofed/include/rdma/opa_addr.h b/sys/ofed/include/rdma/opa_addr.h index 9ae126fb8648..364e947314e3 100644 --- a/sys/ofed/include/rdma/opa_addr.h +++ b/sys/ofed/include/rdma/opa_addr.h @@ -113,4 +113,20 @@ static inline u32 opa_get_mcast_base(u32 nr_top_bits) return (be32_to_cpu(OPA_LID_PERMISSIVE) << (32 - nr_top_bits)); } +/* Check for a valid unicast LID for non-SM traffic types */ +static inline bool rdma_is_valid_unicast_lid(struct rdma_ah_attr *attr) +{ + if (attr->type == RDMA_AH_ATTR_TYPE_IB) { + if (!rdma_ah_get_dlid(attr) || + rdma_ah_get_dlid(attr) >= + be32_to_cpu(IB_MULTICAST_LID_BASE)) + return false; + } else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) { + if (!rdma_ah_get_dlid(attr) || + rdma_ah_get_dlid(attr) >= + opa_get_mcast_base(OPA_MCAST_NR)) + return false; + } + return true; +} #endif /* OPA_ADDR_H */ diff --git a/sys/ofed/include/rdma/rdma_cm.h b/sys/ofed/include/rdma/rdma_cm.h index a1262696c097..2f262aa35bae 100644 --- a/sys/ofed/include/rdma/rdma_cm.h +++ b/sys/ofed/include/rdma/rdma_cm.h @@ -416,4 +416,23 @@ bool rdma_is_consumer_reject(struct rdma_cm_id *id, int reason); const void *rdma_consumer_reject_data(struct rdma_cm_id *id, struct rdma_cm_event *ev, u8 *data_len); +/** + * rdma_read_gids - Return the SGID and DGID used for establishing + * connection. This can be used after rdma_resolve_addr() + * on client side. This can be use on new connection + * on server side. This is applicable to IB, RoCE, iWarp. + * If cm_id is not bound yet to the RDMA device, it doesn't + * copy and SGID or DGID to the given pointers. + * @id: Communication identifier whose GIDs are queried. + * @sgid: Pointer to SGID where SGID will be returned. It is optional. + * @dgid: Pointer to DGID where DGID will be returned. It is optional. + * Note: This API should not be used by any new ULPs or new code. + * Instead, users interested in querying GIDs should refer to path record + * of the rdma_cm_id to query the GIDs. + * This API is provided for compatibility for existing users. + */ + +void rdma_read_gids(struct rdma_cm_id *cm_id, union ib_gid *sgid, + union ib_gid *dgid); + #endif /* RDMA_CM_H */ diff --git a/sys/ofed/include/rdma/rdma_cm_ib.h b/sys/ofed/include/rdma/rdma_cm_ib.h index 7da2f7365b24..292498c23f4b 100644 --- a/sys/ofed/include/rdma/rdma_cm_ib.h +++ b/sys/ofed/include/rdma/rdma_cm_ib.h @@ -38,17 +38,17 @@ #include <rdma/rdma_cm.h> /** - * rdma_set_ib_paths - Manually sets the path records used to establish a + * rdma_set_ib_path - Manually sets the path record used to establish a * connection. * @id: Connection identifier associated with the request. * @path_rec: Reference to the path record * * This call permits a user to specify routing information for rdma_cm_id's - * bound to Infiniband devices. It is called on the client side of a + * bound to InfiniBand devices. It is called on the client side of a * connection and replaces the call to rdma_resolve_route. */ -int rdma_set_ib_paths(struct rdma_cm_id *id, - struct sa_path_rec *path_rec, int num_paths); +int rdma_set_ib_path(struct rdma_cm_id *id, + struct sa_path_rec *path_rec); /* Global qkey for UDP QPs and multicast groups. */ #define RDMA_UDP_QKEY 0x01234567 |
