diff options
40 files changed, 937 insertions, 511 deletions
diff --git a/drivers/infiniband/core/agent.c b/drivers/infiniband/core/agent.c index f6d29614cb01..a6fc4d6dc7d7 100644 --- a/drivers/infiniband/core/agent.c +++ b/drivers/infiniband/core/agent.c @@ -156,7 +156,7 @@ int ib_agent_port_open(struct ib_device *device, int port_num) goto error1; } - if (rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_INFINIBAND) { + if (rdma_cap_ib_smi(device, port_num)) { /* Obtain send only MAD agent for SMI QP */ port_priv->agent[0] = ib_register_mad_agent(device, port_num, IB_QPT_SMI, NULL, 0, diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index 80f6cf2449fb..08921b34182c 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -58,17 +58,6 @@ struct ib_update_work { u8 port_num; }; -static inline int start_port(struct ib_device *device) -{ - return (device->node_type == RDMA_NODE_IB_SWITCH) ? 0 : 1; -} - -static inline int end_port(struct ib_device *device) -{ - return (device->node_type == RDMA_NODE_IB_SWITCH) ? - 0 : device->phys_port_cnt; -} - int ib_get_cached_gid(struct ib_device *device, u8 port_num, int index, @@ -78,12 +67,12 @@ int ib_get_cached_gid(struct ib_device *device, unsigned long flags; int ret = 0; - if (port_num < start_port(device) || port_num > end_port(device)) + if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device)) return -EINVAL; read_lock_irqsave(&device->cache.lock, flags); - cache = device->cache.gid_cache[port_num - start_port(device)]; + cache = device->cache.gid_cache[port_num - rdma_start_port(device)]; if (index < 0 || index >= cache->table_len) ret = -EINVAL; @@ -112,11 +101,11 @@ int ib_find_cached_gid(struct ib_device *device, read_lock_irqsave(&device->cache.lock, flags); - for (p = 0; p <= end_port(device) - start_port(device); ++p) { + for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p) { cache = device->cache.gid_cache[p]; for (i = 0; i < cache->table_len; ++i) { if (!memcmp(gid, &cache->table[i], sizeof *gid)) { - *port_num = p + start_port(device); + *port_num = p + rdma_start_port(device); if (index) *index = i; ret = 0; @@ -140,12 +129,12 @@ int ib_get_cached_pkey(struct ib_device *device, unsigned long flags; int ret = 0; - if (port_num < start_port(device) || port_num > end_port(device)) + if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device)) return -EINVAL; read_lock_irqsave(&device->cache.lock, flags); - cache = device->cache.pkey_cache[port_num - start_port(device)]; + cache = device->cache.pkey_cache[port_num - rdma_start_port(device)]; if (index < 0 || index >= cache->table_len) ret = -EINVAL; @@ -169,12 +158,12 @@ int ib_find_cached_pkey(struct ib_device *device, int ret = -ENOENT; int partial_ix = -1; - if (port_num < start_port(device) || port_num > end_port(device)) + if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device)) return -EINVAL; read_lock_irqsave(&device->cache.lock, flags); - cache = device->cache.pkey_cache[port_num - start_port(device)]; + cache = device->cache.pkey_cache[port_num - rdma_start_port(device)]; *index = -1; @@ -209,12 +198,12 @@ int ib_find_exact_cached_pkey(struct ib_device *device, int i; int ret = -ENOENT; - if (port_num < start_port(device) || port_num > end_port(device)) + if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device)) return -EINVAL; read_lock_irqsave(&device->cache.lock, flags); - cache = device->cache.pkey_cache[port_num - start_port(device)]; + cache = device->cache.pkey_cache[port_num - rdma_start_port(device)]; *index = -1; @@ -238,11 +227,11 @@ int ib_get_cached_lmc(struct ib_device *device, unsigned long flags; int ret = 0; - if (port_num < start_port(device) || port_num > end_port(device)) + if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device)) return -EINVAL; read_lock_irqsave(&device->cache.lock, flags); - *lmc = device->cache.lmc_cache[port_num - start_port(device)]; + *lmc = device->cache.lmc_cache[port_num - rdma_start_port(device)]; read_unlock_irqrestore(&device->cache.lock, flags); return ret; @@ -303,13 +292,13 @@ static void ib_cache_update(struct ib_device *device, write_lock_irq(&device->cache.lock); - old_pkey_cache = device->cache.pkey_cache[port - start_port(device)]; - old_gid_cache = device->cache.gid_cache [port - start_port(device)]; + old_pkey_cache = device->cache.pkey_cache[port - rdma_start_port(device)]; + old_gid_cache = device->cache.gid_cache [port - rdma_start_port(device)]; - device->cache.pkey_cache[port - start_port(device)] = pkey_cache; - device->cache.gid_cache [port - start_port(device)] = gid_cache; + device->cache.pkey_cache[port - rdma_start_port(device)] = pkey_cache; + device->cache.gid_cache [port - rdma_start_port(device)] = gid_cache; - device->cache.lmc_cache[port - start_port(device)] = tprops->lmc; + device->cache.lmc_cache[port - rdma_start_port(device)] = tprops->lmc; write_unlock_irq(&device->cache.lock); @@ -363,14 +352,14 @@ static void ib_cache_setup_one(struct ib_device *device) device->cache.pkey_cache = kmalloc(sizeof *device->cache.pkey_cache * - (end_port(device) - start_port(device) + 1), GFP_KERNEL); + (rdma_end_port(device) - rdma_start_port(device) + 1), GFP_KERNEL); device->cache.gid_cache = kmalloc(sizeof *device->cache.gid_cache * - (end_port(device) - start_port(device) + 1), GFP_KERNEL); + (rdma_end_port(device) - rdma_start_port(device) + 1), GFP_KERNEL); device->cache.lmc_cache = kmalloc(sizeof *device->cache.lmc_cache * - (end_port(device) - - start_port(device) + 1), + (rdma_end_port(device) - + rdma_start_port(device) + 1), GFP_KERNEL); if (!device->cache.pkey_cache || !device->cache.gid_cache || @@ -380,10 +369,10 @@ static void ib_cache_setup_one(struct ib_device *device) goto err; } - for (p = 0; p <= end_port(device) - start_port(device); ++p) { + for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p) { device->cache.pkey_cache[p] = NULL; device->cache.gid_cache [p] = NULL; - ib_cache_update(device, p + start_port(device)); + ib_cache_update(device, p + rdma_start_port(device)); } INIT_IB_EVENT_HANDLER(&device->cache.event_handler, @@ -394,7 +383,7 @@ static void ib_cache_setup_one(struct ib_device *device) return; err_cache: - for (p = 0; p <= end_port(device) - start_port(device); ++p) { + for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p) { kfree(device->cache.pkey_cache[p]); kfree(device->cache.gid_cache[p]); } @@ -412,7 +401,7 @@ static void ib_cache_cleanup_one(struct ib_device *device) ib_unregister_event_handler(&device->cache.event_handler); flush_workqueue(ib_wq); - for (p = 0; p <= end_port(device) - start_port(device); ++p) { + for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p) { kfree(device->cache.pkey_cache[p]); kfree(device->cache.gid_cache[p]); } diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 0c1419105ff0..14423c20c55b 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -3759,11 +3759,9 @@ static void cm_add_one(struct ib_device *ib_device) }; unsigned long flags; int ret; + int count = 0; u8 i; - if (rdma_node_get_transport(ib_device->node_type) != RDMA_TRANSPORT_IB) - return; - cm_dev = kzalloc(sizeof(*cm_dev) + sizeof(*port) * ib_device->phys_port_cnt, GFP_KERNEL); if (!cm_dev) @@ -3782,6 +3780,9 @@ static void cm_add_one(struct ib_device *ib_device) set_bit(IB_MGMT_METHOD_SEND, reg_req.method_mask); for (i = 1; i <= ib_device->phys_port_cnt; i++) { + if (!rdma_cap_ib_cm(ib_device, i)) + continue; + port = kzalloc(sizeof *port, GFP_KERNEL); if (!port) goto error1; @@ -3808,7 +3809,13 @@ static void cm_add_one(struct ib_device *ib_device) ret = ib_modify_port(ib_device, i, 0, &port_modify); if (ret) goto error3; + + count++; } + + if (!count) + goto free; + ib_set_client_data(ib_device, &cm_client, cm_dev); write_lock_irqsave(&cm.device_lock, flags); @@ -3824,11 +3831,15 @@ error1: port_modify.set_port_cap_mask = 0; port_modify.clr_port_cap_mask = IB_PORT_CM_SUP; while (--i) { + if (!rdma_cap_ib_cm(ib_device, i)) + continue; + port = cm_dev->port[i-1]; ib_modify_port(ib_device, port->port_num, 0, &port_modify); ib_unregister_mad_agent(port->mad_agent); cm_remove_port_fs(port); } +free: device_unregister(cm_dev->device); kfree(cm_dev); } @@ -3852,6 +3863,9 @@ static void cm_remove_one(struct ib_device *ib_device) write_unlock_irqrestore(&cm.device_lock, flags); for (i = 1; i <= ib_device->phys_port_cnt; i++) { + if (!rdma_cap_ib_cm(ib_device, i)) + continue; + port = cm_dev->port[i-1]; ib_modify_port(ib_device, port->port_num, 0, &port_modify); ib_unregister_mad_agent(port->mad_agent); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index b2114efcb89e..c34d650463bd 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -377,18 +377,35 @@ static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_a return ret; } +static inline int cma_validate_port(struct ib_device *device, u8 port, + union ib_gid *gid, int dev_type) +{ + u8 found_port; + int ret = -ENODEV; + + if ((dev_type == ARPHRD_INFINIBAND) && !rdma_protocol_ib(device, port)) + return ret; + + if ((dev_type != ARPHRD_INFINIBAND) && rdma_protocol_ib(device, port)) + return ret; + + ret = ib_find_cached_gid(device, gid, &found_port, NULL); + if (port != found_port) + return -ENODEV; + + return ret; +} + static int cma_acquire_dev(struct rdma_id_private *id_priv, struct rdma_id_private *listen_id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct cma_device *cma_dev; - union ib_gid gid, iboe_gid; + union ib_gid gid, iboe_gid, *gidp; int ret = -ENODEV; - u8 port, found_port; - enum rdma_link_layer dev_ll = dev_addr->dev_type == ARPHRD_INFINIBAND ? - IB_LINK_LAYER_INFINIBAND : IB_LINK_LAYER_ETHERNET; + u8 port; - if (dev_ll != IB_LINK_LAYER_INFINIBAND && + if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; @@ -398,41 +415,36 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv, memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof gid); - if (listen_id_priv && - rdma_port_get_link_layer(listen_id_priv->id.device, - listen_id_priv->id.port_num) == dev_ll) { + + if (listen_id_priv) { cma_dev = listen_id_priv->cma_dev; port = listen_id_priv->id.port_num; - if (rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB && - rdma_port_get_link_layer(cma_dev->device, port) == IB_LINK_LAYER_ETHERNET) - ret = ib_find_cached_gid(cma_dev->device, &iboe_gid, - &found_port, NULL); - else - ret = ib_find_cached_gid(cma_dev->device, &gid, - &found_port, NULL); + gidp = rdma_protocol_roce(cma_dev->device, port) ? + &iboe_gid : &gid; - if (!ret && (port == found_port)) { - id_priv->id.port_num = found_port; + ret = cma_validate_port(cma_dev->device, port, gidp, + dev_addr->dev_type); + if (!ret) { + id_priv->id.port_num = port; goto out; } } + list_for_each_entry(cma_dev, &dev_list, list) { for (port = 1; port <= cma_dev->device->phys_port_cnt; ++port) { if (listen_id_priv && listen_id_priv->cma_dev == cma_dev && listen_id_priv->id.port_num == port) continue; - if (rdma_port_get_link_layer(cma_dev->device, port) == dev_ll) { - if (rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB && - rdma_port_get_link_layer(cma_dev->device, port) == IB_LINK_LAYER_ETHERNET) - ret = ib_find_cached_gid(cma_dev->device, &iboe_gid, &found_port, NULL); - else - ret = ib_find_cached_gid(cma_dev->device, &gid, &found_port, NULL); - - if (!ret && (port == found_port)) { - id_priv->id.port_num = found_port; - goto out; - } + + gidp = rdma_protocol_roce(cma_dev->device, port) ? + &iboe_gid : &gid; + + ret = cma_validate_port(cma_dev->device, port, gidp, + dev_addr->dev_type); + if (!ret) { + id_priv->id.port_num = port; + goto out; } } } @@ -463,10 +475,10 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) pkey = ntohs(addr->sib_pkey); list_for_each_entry(cur_dev, &dev_list, list) { - if (rdma_node_get_transport(cur_dev->device->node_type) != RDMA_TRANSPORT_IB) - continue; - for (p = 1; p <= cur_dev->device->phys_port_cnt; ++p) { + if (!rdma_cap_af_ib(cur_dev->device, p)) + continue; + if (ib_find_cached_pkey(cur_dev->device, p, pkey, &index)) continue; @@ -661,10 +673,9 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv, if (ret) goto out; - if (rdma_node_get_transport(id_priv->cma_dev->device->node_type) - == RDMA_TRANSPORT_IB && - rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num) - == IB_LINK_LAYER_ETHERNET) { + BUG_ON(id_priv->cma_dev->device != id_priv->id.device); + + if (rdma_protocol_roce(id_priv->id.device, id_priv->id.port_num)) { ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr.smac, NULL); if (ret) @@ -728,11 +739,10 @@ static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv, int ret; u16 pkey; - if (rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num) == - IB_LINK_LAYER_INFINIBAND) - pkey = ib_addr_get_pkey(dev_addr); - else + if (rdma_cap_eth_ah(id_priv->id.device, id_priv->id.port_num)) pkey = 0xffff; + else + pkey = ib_addr_get_pkey(dev_addr); ret = ib_find_cached_pkey(id_priv->id.device, id_priv->id.port_num, pkey, &qp_attr->pkey_index); @@ -763,8 +773,7 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr, int ret = 0; id_priv = container_of(id, struct rdma_id_private, id); - switch (rdma_node_get_transport(id_priv->id.device->node_type)) { - case RDMA_TRANSPORT_IB: + if (rdma_cap_ib_cm(id->device, id->port_num)) { if (!id_priv->cm_id.ib || (id_priv->id.qp_type == IB_QPT_UD)) ret = cma_ib_init_qp_attr(id_priv, qp_attr, qp_attr_mask); else @@ -773,19 +782,15 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr, if (qp_attr->qp_state == IB_QPS_RTR) qp_attr->rq_psn = id_priv->seq_num; - break; - case RDMA_TRANSPORT_IWARP: + } else if (rdma_cap_iw_cm(id->device, id->port_num)) { if (!id_priv->cm_id.iw) { qp_attr->qp_access_flags = 0; *qp_attr_mask = IB_QP_STATE | IB_QP_ACCESS_FLAGS; } else ret = iw_cm_init_qp_attr(id_priv->cm_id.iw, qp_attr, qp_attr_mask); - break; - default: + } else ret = -ENOSYS; - break; - } return ret; } @@ -963,13 +968,9 @@ static inline int cma_user_data_offset(struct rdma_id_private *id_priv) static void cma_cancel_route(struct rdma_id_private *id_priv) { - switch (rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num)) { - case IB_LINK_LAYER_INFINIBAND: + if (rdma_cap_ib_sa(id_priv->id.device, id_priv->id.port_num)) { if (id_priv->query) ib_sa_cancel_query(id_priv->query_id, id_priv->query); - break; - default: - break; } } @@ -1041,17 +1042,12 @@ static void cma_leave_mc_groups(struct rdma_id_private *id_priv) mc = container_of(id_priv->mc_list.next, struct cma_multicast, list); list_del(&mc->list); - switch (rdma_port_get_link_layer(id_priv->cma_dev->device, id_priv->id.port_num)) { - case IB_LINK_LAYER_INFINIBAND: + if (rdma_cap_ib_mcast(id_priv->cma_dev->device, + id_priv->id.port_num)) { ib_sa_free_multicast(mc->multicast.ib); kfree(mc); - break; - case IB_LINK_LAYER_ETHERNET: + } else kref_put(&mc->mcref, release_mc); - break; - default: - break; - } } } @@ -1072,17 +1068,12 @@ void rdma_destroy_id(struct rdma_cm_id *id) mutex_unlock(&id_priv->handler_mutex); if (id_priv->cma_dev) { - switch (rdma_node_get_transport(id_priv->id.device->node_type)) { - case RDMA_TRANSPORT_IB: + if (rdma_cap_ib_cm(id_priv->id.device, 1)) { if (id_priv->cm_id.ib) ib_destroy_cm_id(id_priv->cm_id.ib); - break; - case RDMA_TRANSPORT_IWARP: + } else if (rdma_cap_iw_cm(id_priv->id.device, 1)) { if (id_priv->cm_id.iw) iw_destroy_cm_id(id_priv->cm_id.iw); - break; - default: - break; } cma_leave_mc_groups(id_priv); cma_release_dev(id_priv); @@ -1660,8 +1651,7 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv, struct rdma_cm_id *id; int ret; - if (cma_family(id_priv) == AF_IB && - rdma_node_get_transport(cma_dev->device->node_type) != RDMA_TRANSPORT_IB) + if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1)) return; id = rdma_create_id(cma_listen_handler, id_priv, id_priv->id.ps, @@ -2002,26 +1992,15 @@ int rdma_resolve_route(struct rdma_cm_id *id, int timeout_ms) return -EINVAL; atomic_inc(&id_priv->refcount); - switch (rdma_node_get_transport(id->device->node_type)) { - case RDMA_TRANSPORT_IB: - switch (rdma_port_get_link_layer(id->device, id->port_num)) { - case IB_LINK_LAYER_INFINIBAND: - ret = cma_resolve_ib_route(id_priv, timeout_ms); - break; - case IB_LINK_LAYER_ETHERNET: - ret = cma_resolve_iboe_route(id_priv); - break; - default: - ret = -ENOSYS; - } - break; - case RDMA_TRANSPORT_IWARP: + if (rdma_cap_ib_sa(id->device, id->port_num)) + ret = cma_resolve_ib_route(id_priv, timeout_ms); + else if (rdma_protocol_roce(id->device, id->port_num)) + ret = cma_resolve_iboe_route(id_priv); + else if (rdma_protocol_iwarp(id->device, id->port_num)) ret = cma_resolve_iw_route(id_priv, timeout_ms); - break; - default: + else ret = -ENOSYS; - break; - } + if (ret) goto err; @@ -2063,7 +2042,7 @@ static int cma_bind_loopback(struct rdma_id_private *id_priv) mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { if (cma_family(id_priv) == AF_IB && - rdma_node_get_transport(cur_dev->device->node_type) != RDMA_TRANSPORT_IB) + !rdma_cap_ib_cm(cur_dev->device, 1)) continue; if (!cma_dev) @@ -2095,7 +2074,7 @@ port_found: goto out; id_priv->id.route.addr.dev_addr.dev_type = - (rdma_port_get_link_layer(cma_dev->device, p) == IB_LINK_LAYER_INFINIBAND) ? + (rdma_protocol_ib(cma_dev->device, p)) ? ARPHRD_INFINIBAND : ARPHRD_ETHER; rdma_addr_set_sgid(&id_priv->id.route.addr.dev_addr, &gid); @@ -2572,18 +2551,15 @@ int rdma_listen(struct rdma_cm_id *id, int backlog) id_priv->backlog = backlog; if (id->device) { - switch (rdma_node_get_transport(id->device->node_type)) { - case RDMA_TRANSPORT_IB: + if (rdma_cap_ib_cm(id->device, 1)) { ret = cma_ib_listen(id_priv); if (ret) goto err; - break; - case RDMA_TRANSPORT_IWARP: + } else if (rdma_cap_iw_cm(id->device, 1)) { ret = cma_iw_listen(id_priv, backlog); if (ret) goto err; - break; - default: + } else { ret = -ENOSYS; goto err; } @@ -2919,20 +2895,15 @@ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) id_priv->srq = conn_param->srq; } - switch (rdma_node_get_transport(id->device->node_type)) { - case RDMA_TRANSPORT_IB: + if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) ret = cma_resolve_ib_udp(id_priv, conn_param); else ret = cma_connect_ib(id_priv, conn_param); - break; - case RDMA_TRANSPORT_IWARP: + } else if (rdma_cap_iw_cm(id->device, id->port_num)) ret = cma_connect_iw(id_priv, conn_param); - break; - default: + else ret = -ENOSYS; - break; - } if (ret) goto err; @@ -3035,8 +3006,7 @@ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) id_priv->srq = conn_param->srq; } - switch (rdma_node_get_transport(id->device->node_type)) { - case RDMA_TRANSPORT_IB: + if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) { if (conn_param) ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, @@ -3052,14 +3022,10 @@ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) else ret = cma_rep_recv(id_priv); } - break; - case RDMA_TRANSPORT_IWARP: + } else if (rdma_cap_iw_cm(id->device, id->port_num)) ret = cma_accept_iw(id_priv, conn_param); - break; - default: + else ret = -ENOSYS; - break; - } if (ret) goto reject; @@ -3103,8 +3069,7 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data, if (!id_priv->cm_id.ib) return -EINVAL; - switch (rdma_node_get_transport(id->device->node_type)) { - case RDMA_TRANSPORT_IB: + if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT, 0, private_data, private_data_len); @@ -3112,15 +3077,12 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data, ret = ib_send_cm_rej(id_priv->cm_id.ib, IB_CM_REJ_CONSUMER_DEFINED, NULL, 0, private_data, private_data_len); - break; - case RDMA_TRANSPORT_IWARP: + } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = iw_cm_reject(id_priv->cm_id.iw, private_data, private_data_len); - break; - default: + } else ret = -ENOSYS; - break; - } + return ret; } EXPORT_SYMBOL(rdma_reject); @@ -3134,22 +3096,18 @@ int rdma_disconnect(struct rdma_cm_id *id) if (!id_priv->cm_id.ib) return -EINVAL; - switch (rdma_node_get_transport(id->device->node_type)) { - case RDMA_TRANSPORT_IB: + if (rdma_cap_ib_cm(id->device, id->port_num)) { ret = cma_modify_qp_err(id_priv); if (ret) goto out; /* Initiate or respond to a disconnect. */ if (ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0)) ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0); - break; - case RDMA_TRANSPORT_IWARP: + } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = iw_cm_disconnect(id_priv->cm_id.iw, 0); - break; - default: + } else ret = -EINVAL; - break; - } + out: return ret; } @@ -3395,24 +3353,13 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, list_add(&mc->list, &id_priv->mc_list); spin_unlock(&id_priv->lock); - switch (rdma_node_get_transport(id->device->node_type)) { - case RDMA_TRANSPORT_IB: - switch (rdma_port_get_link_layer(id->device, id->port_num)) { - case IB_LINK_LAYER_INFINIBAND: - ret = cma_join_ib_multicast(id_priv, mc); - break; - case IB_LINK_LAYER_ETHERNET: - kref_init(&mc->mcref); - ret = cma_iboe_join_multicast(id_priv, mc); - break; - default: - ret = -EINVAL; - } - break; - default: + if (rdma_protocol_roce(id->device, id->port_num)) { + kref_init(&mc->mcref); + ret = cma_iboe_join_multicast(id_priv, mc); + } else if (rdma_cap_ib_mcast(id->device, id->port_num)) + ret = cma_join_ib_multicast(id_priv, mc); + else ret = -ENOSYS; - break; - } if (ret) { spin_lock_irq(&id_priv->lock); @@ -3440,19 +3387,15 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr) ib_detach_mcast(id->qp, &mc->multicast.ib->rec.mgid, be16_to_cpu(mc->multicast.ib->rec.mlid)); - if (rdma_node_get_transport(id_priv->cma_dev->device->node_type) == RDMA_TRANSPORT_IB) { - switch (rdma_port_get_link_layer(id->device, id->port_num)) { - case IB_LINK_LAYER_INFINIBAND: - ib_sa_free_multicast(mc->multicast.ib); - kfree(mc); - break; - case IB_LINK_LAYER_ETHERNET: - kref_put(&mc->mcref, release_mc); - break; - default: - break; - } - } + + BUG_ON(id_priv->cma_dev->device != id->device); + + 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)) + kref_put(&mc->mcref, release_mc); + return; } } diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 18c1ece765f2..8d07c12ab718 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -92,7 +92,8 @@ static int ib_device_check_mandatory(struct ib_device *device) IB_MANDATORY_FUNC(poll_cq), IB_MANDATORY_FUNC(req_notify_cq), IB_MANDATORY_FUNC(get_dma_mr), - IB_MANDATORY_FUNC(dereg_mr) + IB_MANDATORY_FUNC(dereg_mr), + IB_MANDATORY_FUNC(get_port_immutable) }; int i; @@ -151,18 +152,6 @@ static int alloc_name(char *name) return 0; } -static int start_port(struct ib_device *device) -{ - return (device->node_type == RDMA_NODE_IB_SWITCH) ? 0 : 1; -} - - -static int end_port(struct ib_device *device) -{ - return (device->node_type == RDMA_NODE_IB_SWITCH) ? - 0 : device->phys_port_cnt; -} - /** * ib_alloc_device - allocate an IB device struct * @size:size of structure to allocate @@ -222,42 +211,38 @@ static int add_client_context(struct ib_device *device, struct ib_client *client return 0; } -static int read_port_table_lengths(struct ib_device *device) +static int read_port_immutable(struct ib_device *device) { - struct ib_port_attr *tprops = NULL; - int num_ports, ret = -ENOMEM; - u8 port_index; - - tprops = kmalloc(sizeof *tprops, GFP_KERNEL); - if (!tprops) - goto out; - - num_ports = end_port(device) - start_port(device) + 1; - - device->pkey_tbl_len = kmalloc(sizeof *device->pkey_tbl_len * num_ports, - GFP_KERNEL); - device->gid_tbl_len = kmalloc(sizeof *device->gid_tbl_len * num_ports, - GFP_KERNEL); - if (!device->pkey_tbl_len || !device->gid_tbl_len) + int ret = -ENOMEM; + u8 start_port = rdma_start_port(device); + u8 end_port = rdma_end_port(device); + u8 port; + + /** + * device->port_immutable is indexed directly by the port number to make + * access to this data as efficient as possible. + * + * Therefore port_immutable is declared as a 1 based array with + * potential empty slots at the beginning. + */ + device->port_immutable = kzalloc(sizeof(*device->port_immutable) + * (end_port + 1), + GFP_KERNEL); + if (!device->port_immutable) goto err; - for (port_index = 0; port_index < num_ports; ++port_index) { - ret = ib_query_port(device, port_index + start_port(device), - tprops); + for (port = start_port; port <= end_port; ++port) { + ret = device->get_port_immutable(device, port, + &device->port_immutable[port]); if (ret) goto err; - device->pkey_tbl_len[port_index] = tprops->pkey_tbl_len; - device->gid_tbl_len[port_index] = tprops->gid_tbl_len; } ret = 0; goto out; - err: - kfree(device->gid_tbl_len); - kfree(device->pkey_tbl_len); + kfree(device->port_immutable); out: - kfree(tprops); return ret; } @@ -294,9 +279,9 @@ int ib_register_device(struct ib_device *device, spin_lock_init(&device->event_handler_lock); spin_lock_init(&device->client_data_lock); - ret = read_port_table_lengths(device); + ret = read_port_immutable(device); if (ret) { - printk(KERN_WARNING "Couldn't create table lengths cache for device %s\n", + printk(KERN_WARNING "Couldn't create per port immutable data %s\n", device->name); goto out; } @@ -305,8 +290,7 @@ int ib_register_device(struct ib_device *device, if (ret) { printk(KERN_WARNING "Couldn't register device %s with driver model\n", device->name); - kfree(device->gid_tbl_len); - kfree(device->pkey_tbl_len); + kfree(device->port_immutable); goto out; } @@ -348,9 +332,6 @@ void ib_unregister_device(struct ib_device *device) list_del(&device->core_list); - kfree(device->gid_tbl_len); - kfree(device->pkey_tbl_len); - mutex_unlock(&device_mutex); ib_device_unregister_sysfs(device); @@ -575,7 +556,7 @@ int ib_query_port(struct ib_device *device, u8 port_num, struct ib_port_attr *port_attr) { - if (port_num < start_port(device) || port_num > end_port(device)) + if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device)) return -EINVAL; return device->query_port(device, port_num, port_attr); @@ -653,7 +634,7 @@ int ib_modify_port(struct ib_device *device, if (!device->modify_port) return -ENOSYS; - if (port_num < start_port(device) || port_num > end_port(device)) + if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device)) return -EINVAL; return device->modify_port(device, port_num, port_modify_mask, @@ -676,8 +657,8 @@ int ib_find_gid(struct ib_device *device, union ib_gid *gid, union ib_gid tmp_gid; int ret, port, i; - for (port = start_port(device); port <= end_port(device); ++port) { - for (i = 0; i < device->gid_tbl_len[port - start_port(device)]; ++i) { + for (port = rdma_start_port(device); port <= rdma_end_port(device); ++port) { + for (i = 0; i < device->port_immutable[port].gid_tbl_len; ++i) { ret = ib_query_gid(device, port, i, &tmp_gid); if (ret) return ret; @@ -709,7 +690,7 @@ int ib_find_pkey(struct ib_device *device, u16 tmp_pkey; int partial_ix = -1; - for (i = 0; i < device->pkey_tbl_len[port_num - start_port(device)]; ++i) { + for (i = 0; i < device->port_immutable[port_num].pkey_tbl_len; ++i) { ret = ib_query_pkey(device, port_num, i, &tmp_pkey); if (ret) return ret; diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index 74c30f4c557e..600af266838c 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -179,12 +179,12 @@ static int is_vendor_method_in_use( return 0; } -int ib_response_mad(struct ib_mad *mad) +int ib_response_mad(const struct ib_mad_hdr *hdr) { - return ((mad->mad_hdr.method & IB_MGMT_METHOD_RESP) || - (mad->mad_hdr.method == IB_MGMT_METHOD_TRAP_REPRESS) || - ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_BM) && - (mad->mad_hdr.attr_mod & IB_BM_ATTR_MOD_RESP))); + return ((hdr->method & IB_MGMT_METHOD_RESP) || + (hdr->method == IB_MGMT_METHOD_TRAP_REPRESS) || + ((hdr->mgmt_class == IB_MGMT_CLASS_BM) && + (hdr->attr_mod & IB_BM_ATTR_MOD_RESP))); } EXPORT_SYMBOL(ib_response_mad); @@ -791,7 +791,7 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv, switch (ret) { case IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY: - if (ib_response_mad(&mad_priv->mad.mad) && + if (ib_response_mad(&mad_priv->mad.mad.mad_hdr) && mad_agent_priv->agent.recv_handler) { local->mad_priv = mad_priv; local->recv_mad_agent = mad_agent_priv; @@ -910,7 +910,7 @@ static int alloc_send_rmpp_list(struct ib_mad_send_wr_private *send_wr, return 0; } -int ib_mad_kernel_rmpp_agent(struct ib_mad_agent *agent) +int ib_mad_kernel_rmpp_agent(const struct ib_mad_agent *agent) { return agent->rmpp_version && !(agent->flags & IB_MAD_USER_RMPP); } @@ -1628,7 +1628,7 @@ find_mad_agent(struct ib_mad_port_private *port_priv, unsigned long flags; spin_lock_irqsave(&port_priv->reg_lock, flags); - if (ib_response_mad(mad)) { + if (ib_response_mad(&mad->mad_hdr)) { u32 hi_tid; struct ib_mad_agent_private *entry; @@ -1708,20 +1708,20 @@ out: return mad_agent; } -static int validate_mad(struct ib_mad *mad, u32 qp_num) +static int validate_mad(const struct ib_mad_hdr *mad_hdr, u32 qp_num) { int valid = 0; /* Make sure MAD base version is understood */ - if (mad->mad_hdr.base_version != IB_MGMT_BASE_VERSION) { + if (mad_hdr->base_version != IB_MGMT_BASE_VERSION) { pr_err("MAD received with unsupported base version %d\n", - mad->mad_hdr.base_version); + mad_hdr->base_version); goto out; } /* Filter SMI packets sent to other than QP0 */ - if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED) || - (mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)) { + if ((mad_hdr->mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED) || + (mad_hdr->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)) { if (qp_num == 0) valid = 1; } else { @@ -1734,8 +1734,8 @@ out: return valid; } -static int is_data_mad(struct ib_mad_agent_private *mad_agent_priv, - struct ib_mad_hdr *mad_hdr) +static int is_rmpp_data_mad(const struct ib_mad_agent_private *mad_agent_priv, + const struct ib_mad_hdr *mad_hdr) { struct ib_rmpp_mad *rmpp_mad; @@ -1747,16 +1747,16 @@ static int is_data_mad(struct ib_mad_agent_private *mad_agent_priv, (rmpp_mad->rmpp_hdr.rmpp_type == IB_MGMT_RMPP_TYPE_DATA); } -static inline int rcv_has_same_class(struct ib_mad_send_wr_private *wr, - struct ib_mad_recv_wc *rwc) +static inline int rcv_has_same_class(const struct ib_mad_send_wr_private *wr, + const struct ib_mad_recv_wc *rwc) { - return ((struct ib_mad *)(wr->send_buf.mad))->mad_hdr.mgmt_class == + return ((struct ib_mad_hdr *)(wr->send_buf.mad))->mgmt_class == rwc->recv_buf.mad->mad_hdr.mgmt_class; } -static inline int rcv_has_same_gid(struct ib_mad_agent_private *mad_agent_priv, - struct ib_mad_send_wr_private *wr, - struct ib_mad_recv_wc *rwc ) +static inline int rcv_has_same_gid(const struct ib_mad_agent_private *mad_agent_priv, + const struct ib_mad_send_wr_private *wr, + const struct ib_mad_recv_wc *rwc ) { struct ib_ah_attr attr; u8 send_resp, rcv_resp; @@ -1765,8 +1765,8 @@ static inline int rcv_has_same_gid(struct ib_mad_agent_private *mad_agent_priv, u8 port_num = mad_agent_priv->agent.port_num; u8 lmc; - send_resp = ib_response_mad((struct ib_mad *)wr->send_buf.mad); - rcv_resp = ib_response_mad(rwc->recv_buf.mad); + send_resp = ib_response_mad((struct ib_mad_hdr *)wr->send_buf.mad); + rcv_resp = ib_response_mad(&rwc->recv_buf.mad->mad_hdr); if (send_resp == rcv_resp) /* both requests, or both responses. GIDs different */ @@ -1811,8 +1811,8 @@ static inline int is_direct(u8 class) } struct ib_mad_send_wr_private* -ib_find_send_mad(struct ib_mad_agent_private *mad_agent_priv, - struct ib_mad_recv_wc *wc) +ib_find_send_mad(const struct ib_mad_agent_private *mad_agent_priv, + const struct ib_mad_recv_wc *wc) { struct ib_mad_send_wr_private *wr; struct ib_mad *mad; @@ -1836,7 +1836,7 @@ ib_find_send_mad(struct ib_mad_agent_private *mad_agent_priv, * been notified that the send has completed */ list_for_each_entry(wr, &mad_agent_priv->send_list, agent_list) { - if (is_data_mad(mad_agent_priv, wr->send_buf.mad) && + if (is_rmpp_data_mad(mad_agent_priv, wr->send_buf.mad) && wr->tid == mad->mad_hdr.tid && wr->timeout && rcv_has_same_class(wr, wc) && @@ -1879,7 +1879,7 @@ static void ib_mad_complete_recv(struct ib_mad_agent_private *mad_agent_priv, } /* Complete corresponding request */ - if (ib_response_mad(mad_recv_wc->recv_buf.mad)) { + if (ib_response_mad(&mad_recv_wc->recv_buf.mad->mad_hdr)) { spin_lock_irqsave(&mad_agent_priv->lock, flags); mad_send_wr = ib_find_send_mad(mad_agent_priv, mad_recv_wc); if (!mad_send_wr) { @@ -1979,7 +1979,7 @@ static void ib_mad_recv_done_handler(struct ib_mad_port_private *port_priv, snoop_recv(qp_info, &recv->header.recv_wc, IB_MAD_SNOOP_RECVS); /* Validate MAD */ - if (!validate_mad(&recv->mad.mad, qp_info->qp->qp_num)) + if (!validate_mad(&recv->mad.mad.mad_hdr, qp_info->qp->qp_num)) goto out; response = kmem_cache_alloc(ib_mad_cache, GFP_KERNEL); @@ -2411,7 +2411,8 @@ find_send_wr(struct ib_mad_agent_private *mad_agent_priv, list_for_each_entry(mad_send_wr, &mad_agent_priv->send_list, agent_list) { - if (is_data_mad(mad_agent_priv, mad_send_wr->send_buf.mad) && + if (is_rmpp_data_mad(mad_agent_priv, + mad_send_wr->send_buf.mad) && &mad_send_wr->send_buf == send_buf) return mad_send_wr; } @@ -2938,7 +2939,7 @@ static int ib_mad_port_open(struct ib_device *device, init_mad_qp(port_priv, &port_priv->qp_info[1]); cq_size = mad_sendq_size + mad_recvq_size; - has_smi = rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_INFINIBAND; + has_smi = rdma_cap_ib_smi(device, port_num); if (has_smi) cq_size *= 2; @@ -3057,9 +3058,6 @@ static void ib_mad_init_device(struct ib_device *device) { int start, end, i; - if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB) - return; - if (device->node_type == RDMA_NODE_IB_SWITCH) { start = 0; end = 0; @@ -3069,6 +3067,9 @@ static void ib_mad_init_device(struct ib_device *device) } for (i = start; i <= end; i++) { + if (!rdma_cap_ib_mad(device, i)) + continue; + if (ib_mad_port_open(device, i)) { dev_err(&device->dev, "Couldn't open port %d\n", i); goto error; @@ -3086,40 +3087,39 @@ error_agent: dev_err(&device->dev, "Couldn't close port %d\n", i); error: - i--; + while (--i >= start) { + if (!rdma_cap_ib_mad(device, i)) + continue; - while (i >= start) { if (ib_agent_port_close(device, i)) dev_err(&device->dev, "Couldn't close port %d for agents\n", i); if (ib_mad_port_close(device, i)) dev_err(&device->dev, "Couldn't close port %d\n", i); - i--; } } static void ib_mad_remove_device(struct ib_device *device) { - int i, num_ports, cur_port; - - if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB) - return; + int start, end, i; if (device->node_type == RDMA_NODE_IB_SWITCH) { - num_ports = 1; - cur_port = 0; + start = 0; + end = 0; } else { - num_ports = device->phys_port_cnt; - cur_port = 1; + start = 1; + end = device->phys_port_cnt; } - for (i = 0; i < num_ports; i++, cur_port++) { - if (ib_agent_port_close(device, cur_port)) + + for (i = start; i <= end; i++) { + if (!rdma_cap_ib_mad(device, i)) + continue; + + if (ib_agent_port_close(device, i)) dev_err(&device->dev, - "Couldn't close port %d for agents\n", - cur_port); - if (ib_mad_port_close(device, cur_port)) - dev_err(&device->dev, "Couldn't close port %d\n", - cur_port); + "Couldn't close port %d for agents\n", i); + if (ib_mad_port_close(device, i)) + dev_err(&device->dev, "Couldn't close port %d\n", i); } } diff --git a/drivers/infiniband/core/mad_priv.h b/drivers/infiniband/core/mad_priv.h index d1a0b0ee9444..7b19cba2adf0 100644 --- a/drivers/infiniband/core/mad_priv.h +++ b/drivers/infiniband/core/mad_priv.h @@ -213,8 +213,8 @@ struct ib_mad_port_private { int ib_send_mad(struct ib_mad_send_wr_private *mad_send_wr); struct ib_mad_send_wr_private * -ib_find_send_mad(struct ib_mad_agent_private *mad_agent_priv, - struct ib_mad_recv_wc *mad_recv_wc); +ib_find_send_mad(const struct ib_mad_agent_private *mad_agent_priv, + const struct ib_mad_recv_wc *mad_recv_wc); void ib_mad_complete_send_wr(struct ib_mad_send_wr_private *mad_send_wr, struct ib_mad_send_wc *mad_send_wc); diff --git a/drivers/infiniband/core/multicast.c b/drivers/infiniband/core/multicast.c index fa17b552ff78..605f20a9af85 100644 --- a/drivers/infiniband/core/multicast.c +++ b/drivers/infiniband/core/multicast.c @@ -780,8 +780,7 @@ static void mcast_event_handler(struct ib_event_handler *handler, int index; dev = container_of(handler, struct mcast_device, event_handler); - if (rdma_port_get_link_layer(dev->device, event->element.port_num) != - IB_LINK_LAYER_INFINIBAND) + if (WARN_ON(!rdma_cap_ib_mcast(dev->device, event->element.port_num))) return; index = event->element.port_num - dev->start_port; @@ -808,9 +807,6 @@ static void mcast_add_one(struct ib_device *device) int i; int count = 0; - if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB) - return; - dev = kmalloc(sizeof *dev + device->phys_port_cnt * sizeof *port, GFP_KERNEL); if (!dev) @@ -824,8 +820,7 @@ static void mcast_add_one(struct ib_device *device) } for (i = 0; i <= dev->end_port - dev->start_port; i++) { - if (rdma_port_get_link_layer(device, dev->start_port + i) != - IB_LINK_LAYER_INFINIBAND) + if (!rdma_cap_ib_mcast(device, dev->start_port + i)) continue; port = &dev->port[i]; port->dev = dev; @@ -863,8 +858,7 @@ static void mcast_remove_one(struct ib_device *device) flush_workqueue(mcast_wq); for (i = 0; i <= dev->end_port - dev->start_port; i++) { - if (rdma_port_get_link_layer(device, dev->start_port + i) == - IB_LINK_LAYER_INFINIBAND) { + if (rdma_cap_ib_mcast(device, dev->start_port + i)) { port = &dev->port[i]; deref_port(port); wait_for_completion(&port->comp); diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index c38f030f0dc9..7f7c8c9fa92c 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -450,7 +450,7 @@ static void ib_sa_event(struct ib_event_handler *handler, struct ib_event *event struct ib_sa_port *port = &sa_dev->port[event->element.port_num - sa_dev->start_port]; - if (rdma_port_get_link_layer(handler->device, port->port_num) != IB_LINK_LAYER_INFINIBAND) + if (WARN_ON(!rdma_cap_ib_sa(handler->device, port->port_num))) return; spin_lock_irqsave(&port->ah_lock, flags); @@ -540,7 +540,7 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num, ah_attr->port_num = port_num; ah_attr->static_rate = rec->rate; - force_grh = rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_ETHERNET; + force_grh = rdma_cap_eth_ah(device, port_num); if (rec->hop_limit > 1 || force_grh) { ah_attr->ah_flags = IB_AH_GRH; @@ -1153,9 +1153,7 @@ static void ib_sa_add_one(struct ib_device *device) { struct ib_sa_device *sa_dev; int s, e, i; - - if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB) - return; + int count = 0; if (device->node_type == RDMA_NODE_IB_SWITCH) s = e = 0; @@ -1175,7 +1173,7 @@ static void ib_sa_add_one(struct ib_device *device) for (i = 0; i <= e - s; ++i) { spin_lock_init(&sa_dev->port[i].ah_lock); - if (rdma_port_get_link_layer(device, i + 1) != IB_LINK_LAYER_INFINIBAND) + if (!rdma_cap_ib_sa(device, i + 1)) continue; sa_dev->port[i].sm_ah = NULL; @@ -1189,8 +1187,13 @@ static void ib_sa_add_one(struct ib_device *device) goto err; INIT_WORK(&sa_dev->port[i].update_task, update_sm_ah); + + count++; } + if (!count) + goto free; + ib_set_client_data(device, &sa_client, sa_dev); /* @@ -1204,19 +1207,20 @@ static void ib_sa_add_one(struct ib_device *device) if (ib_register_event_handler(&sa_dev->event_handler)) goto err; - for (i = 0; i <= e - s; ++i) - if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND) + for (i = 0; i <= e - s; ++i) { + if (rdma_cap_ib_sa(device, i + 1)) update_sm_ah(&sa_dev->port[i].update_task); + } return; err: - while (--i >= 0) - if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND) + while (--i >= 0) { + if (rdma_cap_ib_sa(device, i + 1)) ib_unregister_mad_agent(sa_dev->port[i].agent); - + } +free: kfree(sa_dev); - return; } @@ -1233,7 +1237,7 @@ static void ib_sa_remove_one(struct ib_device *device) flush_workqueue(ib_wq); for (i = 0; i <= sa_dev->end_port - sa_dev->start_port; ++i) { - if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND) { + if (rdma_cap_ib_sa(device, i + 1)) { ib_unregister_mad_agent(sa_dev->port[i].agent); if (sa_dev->port[i].sm_ah) kref_put(&sa_dev->port[i].sm_ah->ref, free_sm_ah); diff --git a/drivers/infiniband/core/smi.c b/drivers/infiniband/core/smi.c index 5855e4405d9b..e6c6810c8c41 100644 --- a/drivers/infiniband/core/smi.c +++ b/drivers/infiniband/core/smi.c @@ -41,7 +41,7 @@ /* * Fixup a directed route SMP for sending - * Return 0 if the SMP should be discarded + * Return IB_SMI_DISCARD if the SMP should be discarded */ enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp, u8 node_type, int port_num) @@ -126,7 +126,7 @@ enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp, /* * Adjust information for a received SMP - * Return 0 if the SMP should be dropped + * Return IB_SMI_DISCARD if the SMP should be dropped */ enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, u8 node_type, int port_num, int phys_port_cnt) diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index cbd0383f622e..d0334c101ecb 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -456,6 +456,7 @@ static void ib_device_release(struct device *device) { struct ib_device *dev = container_of(device, struct ib_device, dev); + kfree(dev->port_immutable); kfree(dev); } diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c index f2f63933e8a9..62c24b1452b8 100644 --- a/drivers/infiniband/core/ucm.c +++ b/drivers/infiniband/core/ucm.c @@ -1253,8 +1253,7 @@ static void ib_ucm_add_one(struct ib_device *device) dev_t base; struct ib_ucm_device *ucm_dev; - if (!device->alloc_ucontext || - rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB) + if (!device->alloc_ucontext || !rdma_cap_ib_cm(device, 1)) return; ucm_dev = kzalloc(sizeof *ucm_dev, GFP_KERNEL); diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 45d67e9228d7..ad45469f7582 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -722,26 +722,13 @@ static ssize_t ucma_query_route(struct ucma_file *file, resp.node_guid = (__force __u64) ctx->cm_id->device->node_guid; resp.port_num = ctx->cm_id->port_num; - switch (rdma_node_get_transport(ctx->cm_id->device->node_type)) { - case RDMA_TRANSPORT_IB: - switch (rdma_port_get_link_layer(ctx->cm_id->device, - ctx->cm_id->port_num)) { - case IB_LINK_LAYER_INFINIBAND: - ucma_copy_ib_route(&resp, &ctx->cm_id->route); - break; - case IB_LINK_LAYER_ETHERNET: - ucma_copy_iboe_route(&resp, &ctx->cm_id->route); - break; - default: - break; - } - break; - case RDMA_TRANSPORT_IWARP: + + if (rdma_cap_ib_sa(ctx->cm_id->device, ctx->cm_id->port_num)) + ucma_copy_ib_route(&resp, &ctx->cm_id->route); + else if (rdma_protocol_roce(ctx->cm_id->device, ctx->cm_id->port_num)) + ucma_copy_iboe_route(&resp, &ctx->cm_id->route); + else if (rdma_protocol_iwarp(ctx->cm_id->device, ctx->cm_id->port_num)) ucma_copy_iw_route(&resp, &ctx->cm_id->route); - break; - default: - break; - } out: if (copy_to_user((void __user *)(unsigned long)cmd.response, diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index 928cdd20e2d1..e58d701b7791 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -99,7 +99,6 @@ struct ib_umad_port { }; struct ib_umad_device { - int start_port, end_port; struct kobject kobj; struct ib_umad_port port[0]; }; @@ -426,11 +425,11 @@ static int is_duplicate(struct ib_umad_file *file, * the same TID, reject the second as a duplicate. This is more * restrictive than required by the spec. */ - if (!ib_response_mad((struct ib_mad *) hdr)) { - if (!ib_response_mad((struct ib_mad *) sent_hdr)) + if (!ib_response_mad(hdr)) { + if (!ib_response_mad(sent_hdr)) return 1; continue; - } else if (!ib_response_mad((struct ib_mad *) sent_hdr)) + } else if (!ib_response_mad(sent_hdr)) continue; if (same_destination(&packet->mad.hdr, &sent_packet->mad.hdr)) @@ -1273,16 +1272,10 @@ static void ib_umad_add_one(struct ib_device *device) { struct ib_umad_device *umad_dev; int s, e, i; + int count = 0; - if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB) - return; - - if (device->node_type == RDMA_NODE_IB_SWITCH) - s = e = 0; - else { - s = 1; - e = device->phys_port_cnt; - } + s = rdma_start_port(device); + e = rdma_end_port(device); umad_dev = kzalloc(sizeof *umad_dev + (e - s + 1) * sizeof (struct ib_umad_port), @@ -1292,25 +1285,34 @@ static void ib_umad_add_one(struct ib_device *device) kobject_init(&umad_dev->kobj, &ib_umad_dev_ktype); - umad_dev->start_port = s; - umad_dev->end_port = e; - for (i = s; i <= e; ++i) { + if (!rdma_cap_ib_mad(device, i)) + continue; + umad_dev->port[i - s].umad_dev = umad_dev; if (ib_umad_init_port(device, i, umad_dev, &umad_dev->port[i - s])) goto err; + + count++; } + if (!count) + goto free; + ib_set_client_data(device, &umad_client, umad_dev); return; err: - while (--i >= s) - ib_umad_kill_port(&umad_dev->port[i - s]); + while (--i >= s) { + if (!rdma_cap_ib_mad(device, i)) + continue; + ib_umad_kill_port(&umad_dev->port[i - s]); + } +free: kobject_put(&umad_dev->kobj); } @@ -1322,8 +1324,10 @@ static void ib_umad_remove_one(struct ib_device *device) if (!umad_dev) return; - for (i = 0; i <= umad_dev->end_port - umad_dev->start_port; ++i) - ib_umad_kill_port(&umad_dev->port[i]); + for (i = 0; i <= rdma_end_port(device) - rdma_start_port(device); ++i) { + if (rdma_cap_ib_mad(device, i + rdma_start_port(device))) + ib_umad_kill_port(&umad_dev->port[i]); + } kobject_put(&umad_dev->kobj); } diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 4c01a34512da..685a362f6ed6 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -263,11 +263,9 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc, u32 flow_class; u16 gid_index; int ret; - int is_eth = (rdma_port_get_link_layer(device, port_num) == - IB_LINK_LAYER_ETHERNET); memset(ah_attr, 0, sizeof *ah_attr); - if (is_eth) { + if (rdma_cap_eth_ah(device, port_num)) { if (!(wc->wc_flags & IB_WC_GRH)) return -EPROTOTYPE; @@ -936,7 +934,7 @@ int ib_resolve_eth_l2_attrs(struct ib_qp *qp, union ib_gid sgid; if ((*qp_attr_mask & IB_QP_AV) && - (rdma_port_get_link_layer(qp->device, qp_attr->ah_attr.port_num) == IB_LINK_LAYER_ETHERNET)) { + (rdma_cap_eth_ah(qp->device, qp_attr->ah_attr.port_num))) { ret = ib_query_gid(qp->device, qp_attr->ah_attr.port_num, qp_attr->ah_attr.grh.sgid_index, &sgid); if (ret) diff --git a/drivers/infiniband/hw/amso1100/c2_provider.c b/drivers/infiniband/hw/amso1100/c2_provider.c index bdf3507810cb..d396c39918de 100644 --- a/drivers/infiniband/hw/amso1100/c2_provider.c +++ b/drivers/infiniband/hw/amso1100/c2_provider.c @@ -757,6 +757,23 @@ static struct net_device *c2_pseudo_netdev_init(struct c2_dev *c2dev) return netdev; } +static int c2_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = c2_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + immutable->core_cap_flags = RDMA_CORE_PORT_IWARP; + + return 0; +} + int c2_register_device(struct c2_dev *dev) { int ret = -ENOMEM; @@ -820,6 +837,7 @@ int c2_register_device(struct c2_dev *dev) dev->ibdev.reg_phys_mr = c2_reg_phys_mr; dev->ibdev.reg_user_mr = c2_reg_user_mr; dev->ibdev.dereg_mr = c2_dereg_mr; + dev->ibdev.get_port_immutable = c2_port_immutable; dev->ibdev.alloc_fmr = NULL; dev->ibdev.unmap_fmr = NULL; diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index 811b24a539c0..061ef08c92e2 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -1343,6 +1343,23 @@ static struct device_attribute *iwch_class_attributes[] = { &dev_attr_board_id, }; +static int iwch_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = iwch_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + immutable->core_cap_flags = RDMA_CORE_PORT_IWARP; + + return 0; +} + int iwch_register_device(struct iwch_dev *dev) { int ret; @@ -1420,6 +1437,7 @@ int iwch_register_device(struct iwch_dev *dev) dev->ibdev.post_recv = iwch_post_receive; dev->ibdev.get_protocol_stats = iwch_get_mib; dev->ibdev.uverbs_abi_ver = IWCH_UVERBS_ABI_VERSION; + dev->ibdev.get_port_immutable = iwch_port_immutable; dev->ibdev.iwcm = kmalloc(sizeof(struct iw_cm_verbs), GFP_KERNEL); if (!dev->ibdev.iwcm) diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c index 66bd6a2ad83b..ef08a9f29451 100644 --- a/drivers/infiniband/hw/cxgb4/provider.c +++ b/drivers/infiniband/hw/cxgb4/provider.c @@ -465,6 +465,23 @@ static struct device_attribute *c4iw_class_attributes[] = { &dev_attr_board_id, }; +static int c4iw_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = c4iw_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + immutable->core_cap_flags = RDMA_CORE_PORT_IWARP; + + return 0; +} + int c4iw_register_device(struct c4iw_dev *dev) { int ret; @@ -542,6 +559,7 @@ int c4iw_register_device(struct c4iw_dev *dev) dev->ibdev.post_recv = c4iw_post_receive; dev->ibdev.get_protocol_stats = c4iw_get_mib; dev->ibdev.uverbs_abi_ver = C4IW_UVERBS_ABI_VERSION; + dev->ibdev.get_port_immutable = c4iw_port_immutable; dev->ibdev.iwcm = kmalloc(sizeof(struct iw_cm_verbs), GFP_KERNEL); if (!dev->ibdev.iwcm) diff --git a/drivers/infiniband/hw/ehca/ehca_iverbs.h b/drivers/infiniband/hw/ehca/ehca_iverbs.h index 22f79afa7fc1..077185b3fbd6 100644 --- a/drivers/infiniband/hw/ehca/ehca_iverbs.h +++ b/drivers/infiniband/hw/ehca/ehca_iverbs.h @@ -49,6 +49,9 @@ int ehca_query_device(struct ib_device *ibdev, struct ib_device_attr *props); int ehca_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr *props); +enum rdma_protocol_type +ehca_query_protocol(struct ib_device *device, u8 port_num); + int ehca_query_sma_attr(struct ehca_shca *shca, u8 port, struct ehca_sma_attr *attr); diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c index cd8d290a09fc..5e30b72d3677 100644 --- a/drivers/infiniband/hw/ehca/ehca_main.c +++ b/drivers/infiniband/hw/ehca/ehca_main.c @@ -431,6 +431,23 @@ init_node_guid1: return ret; } +static int ehca_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = ehca_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB; + + return 0; +} + static int ehca_init_device(struct ehca_shca *shca) { int ret; @@ -510,6 +527,7 @@ static int ehca_init_device(struct ehca_shca *shca) shca->ib_device.process_mad = ehca_process_mad; shca->ib_device.mmap = ehca_mmap; shca->ib_device.dma_ops = &ehca_dma_mapping_ops; + shca->ib_device.get_port_immutable = ehca_port_immutable; if (EHCA_BMASK_GET(HCA_CAP_SRQ, shca->hca_cap)) { shca->ib_device.uverbs_cmd_mask |= diff --git a/drivers/infiniband/hw/ipath/ipath_verbs.c b/drivers/infiniband/hw/ipath/ipath_verbs.c index 44ea9390417c..764081d305b6 100644 --- a/drivers/infiniband/hw/ipath/ipath_verbs.c +++ b/drivers/infiniband/hw/ipath/ipath_verbs.c @@ -1980,6 +1980,23 @@ static int disable_timer(struct ipath_devdata *dd) return 0; } +static int ipath_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = ipath_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB; + + return 0; +} + /** * ipath_register_ib_device - register our device with the infiniband core * @dd: the device data structure @@ -2179,6 +2196,7 @@ int ipath_register_ib_device(struct ipath_devdata *dd) dev->process_mad = ipath_process_mad; dev->mmap = ipath_mmap; dev->dma_ops = &ipath_dma_mapping_ops; + dev->get_port_immutable = ipath_port_immutable; snprintf(dev->node_desc, sizeof(dev->node_desc), IPATH_IDSTR " %s", init_utsname()->nodename); diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index cc64400d41ac..c49dd0bb251a 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -2114,6 +2114,27 @@ static void mlx4_ib_free_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev) kfree(ibdev->eq_table); } +static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = mlx4_ib_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + + if (mlx4_ib_port_link_layer(ibdev, port_num) == IB_LINK_LAYER_INFINIBAND) + immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB; + else + immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE; + + return 0; +} + static void *mlx4_ib_add(struct mlx4_dev *dev) { struct mlx4_ib_dev *ibdev; @@ -2241,6 +2262,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) ibdev->ib_dev.attach_mcast = mlx4_ib_mcg_attach; ibdev->ib_dev.detach_mcast = mlx4_ib_mcg_detach; ibdev->ib_dev.process_mad = mlx4_ib_process_mad; + ibdev->ib_dev.get_port_immutable = mlx4_port_immutable; if (!mlx4_is_slave(ibdev->dev)) { ibdev->ib_dev.alloc_fmr = mlx4_ib_fmr_alloc; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 57c9809e8b87..b2fdb9cfa645 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1182,6 +1182,23 @@ static void destroy_dev_resources(struct mlx5_ib_resources *devr) mlx5_ib_dealloc_pd(devr->p0); } +static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = mlx5_ib_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB; + + return 0; +} + static void *mlx5_ib_add(struct mlx5_core_dev *mdev) { struct mlx5_ib_dev *dev; @@ -1285,6 +1302,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) dev->ib_dev.alloc_fast_reg_page_list = mlx5_ib_alloc_fast_reg_page_list; dev->ib_dev.free_fast_reg_page_list = mlx5_ib_free_fast_reg_page_list; dev->ib_dev.check_mr_status = mlx5_ib_check_mr_status; + dev->ib_dev.get_port_immutable = mlx5_port_immutable; mlx5_ib_internal_query_odp_caps(dev); diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c index 415f8e1a54db..509d59e7a15a 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.c +++ b/drivers/infiniband/hw/mthca/mthca_provider.c @@ -1244,6 +1244,23 @@ out: return err; } +static int mthca_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = mthca_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB; + + return 0; +} + int mthca_register_device(struct mthca_dev *dev) { int ret; @@ -1323,6 +1340,7 @@ int mthca_register_device(struct mthca_dev *dev) dev->ib_dev.reg_phys_mr = mthca_reg_phys_mr; dev->ib_dev.reg_user_mr = mthca_reg_user_mr; dev->ib_dev.dereg_mr = mthca_dereg_mr; + dev->ib_dev.get_port_immutable = mthca_port_immutable; if (dev->mthca_flags & MTHCA_FLAG_FMR) { dev->ib_dev.alloc_fmr = mthca_alloc_fmr; diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index c0d0296e7a00..05530e3f6ff0 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -606,7 +606,6 @@ static int nes_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr return 0; } - /** * nes_query_pkey */ @@ -3828,6 +3827,22 @@ static int nes_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags notify_ return 0; } +static int nes_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = nes_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + immutable->core_cap_flags = RDMA_CORE_PORT_IWARP; + + return 0; +} /** * nes_init_ofa_device @@ -3928,6 +3943,7 @@ struct nes_ib_device *nes_init_ofa_device(struct net_device *netdev) nesibdev->ibdev.iwcm->reject = nes_reject; nesibdev->ibdev.iwcm->create_listen = nes_create_listen; nesibdev->ibdev.iwcm->destroy_listen = nes_destroy_listen; + nesibdev->ibdev.get_port_immutable = nes_port_immutable; return nesibdev; } diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index 7a2b59aca004..f55289869357 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -202,6 +202,23 @@ static enum rdma_link_layer ocrdma_link_layer(struct ib_device *device, return IB_LINK_LAYER_ETHERNET; } +static int ocrdma_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = ocrdma_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE; + + return 0; +} + static int ocrdma_register_device(struct ocrdma_dev *dev) { strlcpy(dev->ibdev.name, "ocrdma%d", IB_DEVICE_NAME_MAX); @@ -286,6 +303,7 @@ static int ocrdma_register_device(struct ocrdma_dev *dev) dev->ibdev.dma_device = &dev->nic_info.pdev->dev; dev->ibdev.process_mad = ocrdma_process_mad; + dev->ibdev.get_port_immutable = ocrdma_port_immutable; if (ocrdma_get_asic_type(dev) == OCRDMA_ASIC_GEN_SKH_R) { dev->ibdev.uverbs_cmd_mask |= diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h index b8f7853fd36c..3cdc81e6ae9b 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h @@ -41,6 +41,9 @@ int ocrdma_query_port(struct ib_device *, u8 port, struct ib_port_attr *props); int ocrdma_modify_port(struct ib_device *, u8 port, int mask, struct ib_port_modify *props); +enum rdma_protocol_type +ocrdma_query_protocol(struct ib_device *device, u8 port_num); + void ocrdma_get_guid(struct ocrdma_dev *, u8 *guid); int ocrdma_query_gid(struct ib_device *, u8 port, int index, union ib_gid *gid); diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c index 4a3599890ea5..dba1c92f1a54 100644 --- a/drivers/infiniband/hw/qib/qib_verbs.c +++ b/drivers/infiniband/hw/qib/qib_verbs.c @@ -2040,6 +2040,23 @@ static void init_ibport(struct qib_pportdata *ppd) RCU_INIT_POINTER(ibp->qp1, NULL); } +static int qib_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = qib_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB; + + return 0; +} + /** * qib_register_ib_device - register our device with the infiniband core * @dd: the device data structure @@ -2227,6 +2244,7 @@ int qib_register_ib_device(struct qib_devdata *dd) ibdev->process_mad = qib_process_mad; ibdev->mmap = qib_mmap; ibdev->dma_ops = &qib_dma_mapping_ops; + ibdev->get_port_immutable = qib_port_immutable; snprintf(ibdev->node_desc, sizeof(ibdev->node_desc), "Intel Infiniband HCA %s", init_utsname()->nodename); diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index 0d0f98695d53..34c49b8105fe 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -300,6 +300,22 @@ static struct notifier_block usnic_ib_inetaddr_notifier = { }; /* End of inet section*/ +static int usnic_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = usnic_ib_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + + return 0; +} + /* Start of PF discovery section */ static void *usnic_ib_device_add(struct pci_dev *dev) { @@ -383,6 +399,7 @@ static void *usnic_ib_device_add(struct pci_dev *dev) us_ibdev->ib_dev.poll_cq = usnic_ib_poll_cq; us_ibdev->ib_dev.req_notify_cq = usnic_ib_req_notify_cq; us_ibdev->ib_dev.get_dma_mr = usnic_ib_get_dma_mr; + us_ibdev->ib_dev.get_port_immutable = usnic_port_immutable; if (ib_register_device(&us_ibdev->ib_dev, NULL)) diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h index bb864f5aed70..57ddba5035ac 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h +++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h @@ -27,6 +27,8 @@ int usnic_ib_query_device(struct ib_device *ibdev, struct ib_device_attr *props); int usnic_ib_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr *props); +enum rdma_protocol_type +usnic_ib_query_protocol(struct ib_device *device, u8 port_num); int usnic_ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 9e1b203d756d..3421e42870c3 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1685,9 +1685,7 @@ static void ipoib_add_one(struct ib_device *device) struct net_device *dev; struct ipoib_dev_priv *priv; int s, e, p; - - if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB) - return; + int count = 0; dev_list = kmalloc(sizeof *dev_list, GFP_KERNEL); if (!dev_list) @@ -1704,15 +1702,21 @@ static void ipoib_add_one(struct ib_device *device) } for (p = s; p <= e; ++p) { - if (rdma_port_get_link_layer(device, p) != IB_LINK_LAYER_INFINIBAND) + if (!rdma_protocol_ib(device, p)) continue; dev = ipoib_add_port("ib%d", device, p); if (!IS_ERR(dev)) { priv = netdev_priv(dev); list_add_tail(&priv->list, dev_list); + count++; } } + if (!count) { + kfree(dev_list); + return; + } + ib_set_client_data(device, &ipoib_client, dev_list); } @@ -1721,9 +1725,6 @@ static void ipoib_remove_one(struct ib_device *device) struct ipoib_dev_priv *priv, *tmp; struct list_head *dev_list; - if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB) - return; - dev_list = ib_get_client_data(device, &ipoib_client); if (!dev_list) return; diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 667df9d423ef..c3f654d20038 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -59,9 +59,10 @@ #define DRV_RELDATE "July 1, 2013" MODULE_AUTHOR("Roland Dreier"); -MODULE_DESCRIPTION("InfiniBand SCSI RDMA Protocol initiator " - "v" DRV_VERSION " (" DRV_RELDATE ")"); +MODULE_DESCRIPTION("InfiniBand SCSI RDMA Protocol initiator"); MODULE_LICENSE("Dual BSD/GPL"); +MODULE_VERSION(DRV_VERSION); +MODULE_INFO(release_date, DRV_RELDATE); static unsigned int srp_sg_tablesize; static unsigned int cmd_sg_entries; @@ -466,14 +467,13 @@ static struct srp_fr_pool *srp_alloc_fr_pool(struct srp_target_port *target) */ static void srp_destroy_qp(struct srp_rdma_ch *ch) { - struct srp_target_port *target = ch->target; static struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR }; static struct ib_recv_wr wr = { .wr_id = SRP_LAST_WR_ID }; struct ib_recv_wr *bad_wr; int ret; /* Destroying a QP and reusing ch->done is only safe if not connected */ - WARN_ON_ONCE(target->connected); + WARN_ON_ONCE(ch->connected); ret = ib_modify_qp(ch->qp, &attr, IB_QP_STATE); WARN_ONCE(ret, "ib_cm_init_qp_attr() returned %d\n", ret); @@ -782,7 +782,7 @@ static int srp_send_req(struct srp_rdma_ch *ch, bool multich) shost_printk(KERN_DEBUG, target->scsi_host, PFX "Topspin/Cisco initiator port ID workaround " "activated for target GUID %016llx\n", - (unsigned long long) be64_to_cpu(target->ioc_guid)); + be64_to_cpu(target->ioc_guid)); memset(req->priv.initiator_port_id, 0, 8); memcpy(req->priv.initiator_port_id + 8, &target->srp_host->srp_dev->dev->node_guid, 8); @@ -812,35 +812,19 @@ static bool srp_queue_remove_work(struct srp_target_port *target) return changed; } -static bool srp_change_conn_state(struct srp_target_port *target, - bool connected) -{ - bool changed = false; - - spin_lock_irq(&target->lock); - if (target->connected != connected) { - target->connected = connected; - changed = true; - } - spin_unlock_irq(&target->lock); - - return changed; -} - static void srp_disconnect_target(struct srp_target_port *target) { struct srp_rdma_ch *ch; int i; - if (srp_change_conn_state(target, false)) { - /* XXX should send SRP_I_LOGOUT request */ + /* XXX should send SRP_I_LOGOUT request */ - for (i = 0; i < target->ch_count; i++) { - ch = &target->ch[i]; - if (ch->cm_id && ib_send_cm_dreq(ch->cm_id, NULL, 0)) { - shost_printk(KERN_DEBUG, target->scsi_host, - PFX "Sending CM DREQ failed\n"); - } + for (i = 0; i < target->ch_count; i++) { + ch = &target->ch[i]; + ch->connected = false; + if (ch->cm_id && ib_send_cm_dreq(ch->cm_id, NULL, 0)) { + shost_printk(KERN_DEBUG, target->scsi_host, + PFX "Sending CM DREQ failed\n"); } } } @@ -853,7 +837,7 @@ static void srp_free_req_data(struct srp_target_port *target, struct srp_request *req; int i; - if (!ch->target || !ch->req_ring) + if (!ch->req_ring) return; for (i = 0; i < target->req_ring_size; ++i) { @@ -987,14 +971,26 @@ static void srp_rport_delete(struct srp_rport *rport) srp_queue_remove_work(target); } +/** + * srp_connected_ch() - number of connected channels + * @target: SRP target port. + */ +static int srp_connected_ch(struct srp_target_port *target) +{ + int i, c = 0; + + for (i = 0; i < target->ch_count; i++) + c += target->ch[i].connected; + + return c; +} + static int srp_connect_ch(struct srp_rdma_ch *ch, bool multich) { struct srp_target_port *target = ch->target; int ret; - WARN_ON_ONCE(!multich && target->connected); - - target->qp_in_error = false; + WARN_ON_ONCE(!multich && srp_connected_ch(target) > 0); ret = srp_lookup_path(ch); if (ret) @@ -1017,7 +1013,7 @@ static int srp_connect_ch(struct srp_rdma_ch *ch, bool multich) */ switch (ch->status) { case 0: - srp_change_conn_state(target, true); + ch->connected = true; return 0; case SRP_PORT_REDIRECT: @@ -1215,14 +1211,10 @@ static int srp_rport_reconnect(struct srp_rport *rport) */ for (i = 0; i < target->ch_count; i++) { ch = &target->ch[i]; - if (!ch->target) - break; ret += srp_new_cm_id(ch); } for (i = 0; i < target->ch_count; i++) { ch = &target->ch[i]; - if (!ch->target) - break; for (j = 0; j < target->req_ring_size; ++j) { struct srp_request *req = &ch->req_ring[j]; @@ -1231,8 +1223,6 @@ static int srp_rport_reconnect(struct srp_rport *rport) } for (i = 0; i < target->ch_count; i++) { ch = &target->ch[i]; - if (!ch->target) - break; /* * Whether or not creating a new CM ID succeeded, create a new * QP. This guarantees that all completion callback function @@ -1244,13 +1234,13 @@ static int srp_rport_reconnect(struct srp_rport *rport) for (j = 0; j < target->queue_size; ++j) list_add(&ch->tx_ring[j]->list, &ch->free_tx); } + + target->qp_in_error = false; + for (i = 0; i < target->ch_count; i++) { ch = &target->ch[i]; - if (ret || !ch->target) { - if (i > 1) - ret = 0; + if (ret) break; - } ret = srp_connect_ch(ch, multich); multich = true; } @@ -1843,7 +1833,7 @@ static void srp_process_aer_req(struct srp_rdma_ch *ch, s32 delta = be32_to_cpu(req->req_lim_delta); shost_printk(KERN_ERR, target->scsi_host, PFX - "ignoring AER for LUN %llu\n", be64_to_cpu(req->lun)); + "ignoring AER for LUN %llu\n", scsilun_to_int(&req->lun)); if (srp_response_common(ch, delta, &rsp, sizeof(rsp))) shost_printk(KERN_ERR, target->scsi_host, PFX @@ -1930,7 +1920,7 @@ static void srp_handle_qp_err(u64 wr_id, enum ib_wc_status wc_status, return; } - if (target->connected && !target->qp_in_error) { + if (ch->connected && !target->qp_in_error) { if (wr_id & LOCAL_INV_WR_ID_MASK) { shost_printk(KERN_ERR, target->scsi_host, PFX "LOCAL_INV failed with status %s (%d)\n", @@ -2036,7 +2026,7 @@ static int srp_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scmnd) memset(cmd, 0, sizeof *cmd); cmd->opcode = SRP_CMD; - cmd->lun = cpu_to_be64((u64) scmnd->device->lun << 48); + int_to_scsilun(scmnd->device->lun, &cmd->lun); cmd->tag = tag; memcpy(cmd->cdb, scmnd->cmnd, scmnd->cmd_len); @@ -2369,7 +2359,7 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event) case IB_CM_DREQ_RECEIVED: shost_printk(KERN_WARNING, target->scsi_host, PFX "DREQ received - connection closed\n"); - srp_change_conn_state(target, false); + ch->connected = false; if (ib_send_cm_drep(cm_id, NULL, 0)) shost_printk(KERN_ERR, target->scsi_host, PFX "Sending CM DREP failed\n"); @@ -2416,8 +2406,8 @@ srp_change_queue_depth(struct scsi_device *sdev, int qdepth) return scsi_change_queue_depth(sdev, qdepth); } -static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, - unsigned int lun, u8 func) +static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun, + u8 func) { struct srp_target_port *target = ch->target; struct srp_rport *rport = target->rport; @@ -2425,7 +2415,7 @@ static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, struct srp_iu *iu; struct srp_tsk_mgmt *tsk_mgmt; - if (!target->connected || target->qp_in_error) + if (!ch->connected || target->qp_in_error) return -1; init_completion(&ch->tsk_mgmt_done); @@ -2451,7 +2441,7 @@ static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, memset(tsk_mgmt, 0, sizeof *tsk_mgmt); tsk_mgmt->opcode = SRP_TSK_MGMT; - tsk_mgmt->lun = cpu_to_be64((u64) lun << 48); + int_to_scsilun(lun, &tsk_mgmt->lun); tsk_mgmt->tag = req_tag | SRP_TAG_TSK_MGMT; tsk_mgmt->tsk_mgmt_func = func; tsk_mgmt->task_tag = req_tag; @@ -2565,8 +2555,7 @@ static ssize_t show_id_ext(struct device *dev, struct device_attribute *attr, { struct srp_target_port *target = host_to_target(class_to_shost(dev)); - return sprintf(buf, "0x%016llx\n", - (unsigned long long) be64_to_cpu(target->id_ext)); + return sprintf(buf, "0x%016llx\n", be64_to_cpu(target->id_ext)); } static ssize_t show_ioc_guid(struct device *dev, struct device_attribute *attr, @@ -2574,8 +2563,7 @@ static ssize_t show_ioc_guid(struct device *dev, struct device_attribute *attr, { struct srp_target_port *target = host_to_target(class_to_shost(dev)); - return sprintf(buf, "0x%016llx\n", - (unsigned long long) be64_to_cpu(target->ioc_guid)); + return sprintf(buf, "0x%016llx\n", be64_to_cpu(target->ioc_guid)); } static ssize_t show_service_id(struct device *dev, @@ -2583,8 +2571,7 @@ static ssize_t show_service_id(struct device *dev, { struct srp_target_port *target = host_to_target(class_to_shost(dev)); - return sprintf(buf, "0x%016llx\n", - (unsigned long long) be64_to_cpu(target->service_id)); + return sprintf(buf, "0x%016llx\n", be64_to_cpu(target->service_id)); } static ssize_t show_pkey(struct device *dev, struct device_attribute *attr, @@ -2775,7 +2762,7 @@ static int srp_add_target(struct srp_host *host, struct srp_target_port *target) target->state = SRP_TARGET_SCANNING; sprintf(target->target_name, "SRP.T10:%016llX", - (unsigned long long) be64_to_cpu(target->id_ext)); + be64_to_cpu(target->id_ext)); if (scsi_add_host(target->scsi_host, host->srp_dev->dev->dma_device)) return -ENODEV; @@ -2799,7 +2786,8 @@ static int srp_add_target(struct srp_host *host, struct srp_target_port *target) scsi_scan_target(&target->scsi_host->shost_gendev, 0, target->scsi_id, SCAN_WILD_CARD, 0); - if (!target->connected || target->qp_in_error) { + if (srp_connected_ch(target) < target->ch_count || + target->qp_in_error) { shost_printk(KERN_INFO, target->scsi_host, PFX "SCSI scan failed - removing SCSI host\n"); srp_queue_remove_work(target); @@ -3148,7 +3136,7 @@ static ssize_t srp_create_target(struct device *dev, target_host->transportt = ib_srp_transport_template; target_host->max_channel = 0; target_host->max_id = 1; - target_host->max_lun = SRP_MAX_LUN; + target_host->max_lun = -1LL; target_host->max_cmd_len = sizeof ((struct srp_cmd *) (void *) 0L)->cdb; target = host_to_target(target_host); @@ -3174,11 +3162,11 @@ static ssize_t srp_create_target(struct device *dev, ret = srp_parse_options(buf, target); if (ret) - goto err; + goto out; ret = scsi_init_shared_tag_map(target_host, target_host->can_queue); if (ret) - goto err; + goto out; target->req_ring_size = target->queue_size - SRP_TSK_MGMT_SQ_SIZE; @@ -3189,7 +3177,7 @@ static ssize_t srp_create_target(struct device *dev, be64_to_cpu(target->ioc_guid), be64_to_cpu(target->initiator_ext)); ret = -EEXIST; - goto err; + goto out; } if (!srp_dev->has_fmr && !srp_dev->has_fr && !target->allow_ext_sg && @@ -3210,7 +3198,7 @@ static ssize_t srp_create_target(struct device *dev, spin_lock_init(&target->lock); ret = ib_query_gid(ibdev, host->port, 0, &target->sgid); if (ret) - goto err; + goto out; ret = -ENOMEM; target->ch_count = max_t(unsigned, num_online_nodes(), @@ -3221,7 +3209,7 @@ static ssize_t srp_create_target(struct device *dev, target->ch = kcalloc(target->ch_count, sizeof(*target->ch), GFP_KERNEL); if (!target->ch) - goto err; + goto out; node_idx = 0; for_each_online_node(node) { @@ -3317,9 +3305,6 @@ err_disconnect: } kfree(target->ch); - -err: - scsi_host_put(target_host); goto out; } diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h index a611556406ac..17ee3f80ba55 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.h +++ b/drivers/infiniband/ulp/srp/ib_srp.h @@ -54,7 +54,6 @@ enum { SRP_DLID_REDIRECT = 2, SRP_STALE_CONN = 3, - SRP_MAX_LUN = 512, SRP_DEF_SG_TABLESIZE = 12, SRP_DEFAULT_QUEUE_SIZE = 1 << 6, @@ -170,6 +169,7 @@ struct srp_rdma_ch { struct completion tsk_mgmt_done; u8 tsk_mgmt_status; + bool connected; }; /** @@ -214,7 +214,6 @@ struct srp_target_port { __be16 pkey; u32 rq_tmo_jiffies; - bool connected; int zero_req_lim; diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index acea5d6eebd0..6a41c36b16b0 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -1053,7 +1053,7 @@ static int ibmvscsi_queuecommand_lck(struct scsi_cmnd *cmnd, memset(srp_cmd, 0x00, SRP_MAX_IU_LEN); srp_cmd->opcode = SRP_CMD; memcpy(srp_cmd->cdb, cmnd->cmnd, sizeof(srp_cmd->cdb)); - srp_cmd->lun = cpu_to_be64(((u64)lun) << 48); + int_to_scsilun(lun, &srp_cmd->lun); if (!map_data_for_srp_cmd(cmnd, evt_struct, srp_cmd, hostdata->dev)) { if (!firmware_has_feature(FW_FEATURE_CMO)) @@ -1529,7 +1529,7 @@ static int ibmvscsi_eh_abort_handler(struct scsi_cmnd *cmd) /* Set up an abort SRP command */ memset(tsk_mgmt, 0x00, sizeof(*tsk_mgmt)); tsk_mgmt->opcode = SRP_TSK_MGMT; - tsk_mgmt->lun = cpu_to_be64(((u64) lun) << 48); + int_to_scsilun(lun, &tsk_mgmt->lun); tsk_mgmt->tsk_mgmt_func = SRP_TSK_ABORT_TASK; tsk_mgmt->task_tag = (u64) found_evt; @@ -1652,7 +1652,7 @@ static int ibmvscsi_eh_device_reset_handler(struct scsi_cmnd *cmd) /* Set up a lun reset SRP command */ memset(tsk_mgmt, 0x00, sizeof(*tsk_mgmt)); tsk_mgmt->opcode = SRP_TSK_MGMT; - tsk_mgmt->lun = cpu_to_be64(((u64) lun) << 48); + int_to_scsilun(lun, &tsk_mgmt->lun); tsk_mgmt->tsk_mgmt_func = SRP_TSK_LUN_RESET; evt->sync_srp = &srp_rsp; diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c index ae45bd99baed..a85292b1d09d 100644 --- a/drivers/scsi/scsi_transport_srp.c +++ b/drivers/scsi/scsi_transport_srp.c @@ -61,6 +61,11 @@ static inline struct Scsi_Host *rport_to_shost(struct srp_rport *r) return dev_to_shost(r->dev.parent); } +static inline struct srp_rport *shost_to_rport(struct Scsi_Host *shost) +{ + return transport_class_to_srp_rport(&shost->shost_gendev); +} + /** * srp_tmo_valid() - check timeout combination validity * @reconnect_delay: Reconnect delay in seconds. @@ -396,6 +401,36 @@ static void srp_reconnect_work(struct work_struct *work) } } +/** + * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn() + * @shost: SCSI host for which to count the number of scsi_request_fn() callers. + * + * To do: add support for scsi-mq in this function. + */ +static int scsi_request_fn_active(struct Scsi_Host *shost) +{ + struct scsi_device *sdev; + struct request_queue *q; + int request_fn_active = 0; + + shost_for_each_device(sdev, shost) { + q = sdev->request_queue; + + spin_lock_irq(q->queue_lock); + request_fn_active += q->request_fn_active; + spin_unlock_irq(q->queue_lock); + } + + return request_fn_active; +} + +/* Wait until ongoing shost->hostt->queuecommand() calls have finished. */ +static void srp_wait_for_queuecommand(struct Scsi_Host *shost) +{ + while (scsi_request_fn_active(shost)) + msleep(20); +} + static void __rport_fail_io_fast(struct srp_rport *rport) { struct Scsi_Host *shost = rport_to_shost(rport); @@ -409,8 +444,10 @@ static void __rport_fail_io_fast(struct srp_rport *rport) /* Involve the LLD if possible to terminate all I/O on the rport. */ i = to_srp_internal(shost->transportt); - if (i->f->terminate_rport_io) + if (i->f->terminate_rport_io) { + srp_wait_for_queuecommand(shost); i->f->terminate_rport_io(rport); + } } /** @@ -504,27 +541,6 @@ void srp_start_tl_fail_timers(struct srp_rport *rport) EXPORT_SYMBOL(srp_start_tl_fail_timers); /** - * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn() - * @shost: SCSI host for which to count the number of scsi_request_fn() callers. - */ -static int scsi_request_fn_active(struct Scsi_Host *shost) -{ - struct scsi_device *sdev; - struct request_queue *q; - int request_fn_active = 0; - - shost_for_each_device(sdev, shost) { - q = sdev->request_queue; - - spin_lock_irq(q->queue_lock); - request_fn_active += q->request_fn_active; - spin_unlock_irq(q->queue_lock); - } - - return request_fn_active; -} - -/** * srp_reconnect_rport() - reconnect to an SRP target port * @rport: SRP target port. * @@ -559,8 +575,7 @@ int srp_reconnect_rport(struct srp_rport *rport) if (res) goto out; scsi_target_block(&shost->shost_gendev); - while (scsi_request_fn_active(shost)) - msleep(20); + srp_wait_for_queuecommand(shost); res = rport->state != SRP_RPORT_LOST ? i->f->reconnect(rport) : -ENODEV; pr_debug("%s (state %d): transport.reconnect() returned %d\n", dev_name(&shost->shost_gendev), rport->state, res); @@ -618,9 +633,11 @@ static enum blk_eh_timer_return srp_timed_out(struct scsi_cmnd *scmd) struct scsi_device *sdev = scmd->device; struct Scsi_Host *shost = sdev->host; struct srp_internal *i = to_srp_internal(shost->transportt); + struct srp_rport *rport = shost_to_rport(shost); pr_debug("timeout for sdev %s\n", dev_name(&sdev->sdev_gendev)); - return i->f->reset_timer_if_blocked && scsi_device_blocked(sdev) ? + return rport->fast_io_fail_tmo < 0 && rport->dev_loss_tmo < 0 && + i->f->reset_timer_if_blocked && scsi_device_blocked(sdev) ? BLK_EH_RESET_TIMER : BLK_EH_NOT_HANDLED; } diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h index 9bb99e983f58..c0ea51f90a03 100644 --- a/include/rdma/ib_mad.h +++ b/include/rdma/ib_mad.h @@ -263,7 +263,7 @@ struct ib_mad_send_buf { * ib_response_mad - Returns if the specified MAD has been generated in * response to a sent request or trap. */ -int ib_response_mad(struct ib_mad *mad); +int ib_response_mad(const struct ib_mad_hdr *hdr); /** * ib_get_rmpp_resptime - Returns the RMPP response time. @@ -675,6 +675,6 @@ void ib_free_send_mad(struct ib_mad_send_buf *send_buf); * @agent: the agent in question * @return: true if agent is performing rmpp, false otherwise. */ -int ib_mad_kernel_rmpp_agent(struct ib_mad_agent *agent); +int ib_mad_kernel_rmpp_agent(const struct ib_mad_agent *agent); #endif /* IB_MAD_H */ diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 672fc8f20409..ad499bda62a4 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -81,6 +81,13 @@ enum rdma_transport_type { RDMA_TRANSPORT_USNIC_UDP }; +enum rdma_protocol_type { + RDMA_PROTOCOL_IB, + RDMA_PROTOCOL_IBOE, + RDMA_PROTOCOL_IWARP, + RDMA_PROTOCOL_USNIC_UDP +}; + __attribute_const__ enum rdma_transport_type rdma_node_get_transport(enum rdma_node_type node_type); @@ -346,6 +353,40 @@ union rdma_protocol_stats { struct iw_protocol_stats iw; }; +/* Define bits for the various functionality this port needs to be supported by + * the core. + */ +/* Management 0x00000FFF */ +#define RDMA_CORE_CAP_IB_MAD 0x00000001 +#define RDMA_CORE_CAP_IB_SMI 0x00000002 +#define RDMA_CORE_CAP_IB_CM 0x00000004 +#define RDMA_CORE_CAP_IW_CM 0x00000008 +#define RDMA_CORE_CAP_IB_SA 0x00000010 + +/* Address format 0x000FF000 */ +#define RDMA_CORE_CAP_AF_IB 0x00001000 +#define RDMA_CORE_CAP_ETH_AH 0x00002000 + +/* Protocol 0xFFF00000 */ +#define RDMA_CORE_CAP_PROT_IB 0x00100000 +#define RDMA_CORE_CAP_PROT_ROCE 0x00200000 +#define RDMA_CORE_CAP_PROT_IWARP 0x00400000 + +#define RDMA_CORE_PORT_IBA_IB (RDMA_CORE_CAP_PROT_IB \ + | RDMA_CORE_CAP_IB_MAD \ + | RDMA_CORE_CAP_IB_SMI \ + | RDMA_CORE_CAP_IB_CM \ + | RDMA_CORE_CAP_IB_SA \ + | RDMA_CORE_CAP_AF_IB) +#define RDMA_CORE_PORT_IBA_ROCE (RDMA_CORE_CAP_PROT_ROCE \ + | RDMA_CORE_CAP_IB_MAD \ + | RDMA_CORE_CAP_IB_CM \ + | RDMA_CORE_CAP_IB_SA \ + | RDMA_CORE_CAP_AF_IB \ + | RDMA_CORE_CAP_ETH_AH) +#define RDMA_CORE_PORT_IWARP (RDMA_CORE_CAP_PROT_IWARP \ + | RDMA_CORE_CAP_IW_CM) + struct ib_port_attr { enum ib_port_state state; enum ib_mtu max_mtu; @@ -1478,6 +1519,12 @@ struct ib_dma_mapping_ops { struct iw_cm_verbs; +struct ib_port_immutable { + int pkey_tbl_len; + int gid_tbl_len; + u32 core_cap_flags; +}; + struct ib_device { struct device *dma_device; @@ -1491,8 +1538,10 @@ struct ib_device { struct list_head client_data_list; struct ib_cache cache; - int *pkey_tbl_len; - int *gid_tbl_len; + /** + * port_immutable is indexed by port number + */ + struct ib_port_immutable *port_immutable; int num_comp_vectors; @@ -1679,6 +1728,14 @@ struct ib_device { u32 local_dma_lkey; u8 node_type; u8 phys_port_cnt; + + /** + * The following mandatory functions are used only at device + * registration. Keep functions such as these at the end of this + * structure to avoid cache line misses when accessing struct ib_device + * in fast paths. + */ + int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *); }; struct ib_client { @@ -1747,6 +1804,242 @@ int ib_query_port(struct ib_device *device, enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u8 port_num); +/** + * rdma_start_port - Return the first valid port number for the device + * specified + * + * @device: Device to be checked + * + * Return start port number + */ +static inline u8 rdma_start_port(const struct ib_device *device) +{ + return (device->node_type == RDMA_NODE_IB_SWITCH) ? 0 : 1; +} + +/** + * rdma_end_port - Return the last valid port number for the device + * specified + * + * @device: Device to be checked + * + * Return last port number + */ +static inline u8 rdma_end_port(const struct ib_device *device) +{ + return (device->node_type == RDMA_NODE_IB_SWITCH) ? + 0 : device->phys_port_cnt; +} + +static inline bool rdma_protocol_ib(struct ib_device *device, u8 port_num) +{ + return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_IB; +} + +static inline bool rdma_protocol_roce(struct ib_device *device, u8 port_num) +{ + return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_ROCE; +} + +static inline bool rdma_protocol_iwarp(struct ib_device *device, u8 port_num) +{ + return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_IWARP; +} + +static inline bool rdma_ib_or_roce(struct ib_device *device, u8 port_num) +{ + return device->port_immutable[port_num].core_cap_flags & + (RDMA_CORE_CAP_PROT_IB | RDMA_CORE_CAP_PROT_ROCE); +} + +/** + * rdma_cap_ib_mad - Check if the port of a device supports Infiniband + * Management Datagrams. + * @device: Device to check + * @port_num: Port number to check + * + * Management Datagrams (MAD) are a required part of the InfiniBand + * specification and are supported on all InfiniBand devices. A slightly + * extended version are also supported on OPA interfaces. + * + * Return: true if the port supports sending/receiving of MAD packets. + */ +static inline bool rdma_cap_ib_mad(struct ib_device *device, u8 port_num) +{ + return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_MAD; +} + +/** + * rdma_cap_ib_smi - Check if the port of a device provides an Infiniband + * Subnet Management Agent (SMA) on the Subnet Management Interface (SMI). + * @device: Device to check + * @port_num: Port number to check + * + * Each InfiniBand node is required to provide a Subnet Management Agent + * that the subnet manager can access. Prior to the fabric being fully + * configured by the subnet manager, the SMA is accessed via a well known + * interface called the Subnet Management Interface (SMI). This interface + * uses directed route packets to communicate with the SM to get around the + * chicken and egg problem of the SM needing to know what's on the fabric + * in order to configure the fabric, and needing to configure the fabric in + * order to send packets to the devices on the fabric. These directed + * route packets do not need the fabric fully configured in order to reach + * their destination. The SMI is the only method allowed to send + * directed route packets on an InfiniBand fabric. + * + * Return: true if the port provides an SMI. + */ +static inline bool rdma_cap_ib_smi(struct ib_device *device, u8 port_num) +{ + return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_SMI; +} + +/** + * rdma_cap_ib_cm - Check if the port of device has the capability Infiniband + * Communication Manager. + * @device: Device to check + * @port_num: Port number to check + * + * The InfiniBand Communication Manager is one of many pre-defined General + * Service Agents (GSA) that are accessed via the General Service + * Interface (GSI). It's role is to facilitate establishment of connections + * between nodes as well as other management related tasks for established + * connections. + * + * Return: true if the port supports an IB CM (this does not guarantee that + * a CM is actually running however). + */ +static inline bool rdma_cap_ib_cm(struct ib_device *device, u8 port_num) +{ + return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_CM; +} + +/** + * rdma_cap_iw_cm - Check if the port of device has the capability IWARP + * Communication Manager. + * @device: Device to check + * @port_num: Port number to check + * + * Similar to above, but specific to iWARP connections which have a different + * managment protocol than InfiniBand. + * + * Return: true if the port supports an iWARP CM (this does not guarantee that + * a CM is actually running however). + */ +static inline bool rdma_cap_iw_cm(struct ib_device *device, u8 port_num) +{ + return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IW_CM; +} + +/** + * rdma_cap_ib_sa - Check if the port of device has the capability Infiniband + * Subnet Administration. + * @device: Device to check + * @port_num: Port number to check + * + * An InfiniBand Subnet Administration (SA) service is a pre-defined General + * Service Agent (GSA) provided by the Subnet Manager (SM). On InfiniBand + * fabrics, devices should resolve routes to other hosts by contacting the + * SA to query the proper route. + * + * Return: true if the port should act as a client to the fabric Subnet + * Administration interface. This does not imply that the SA service is + * running locally. + */ +static inline bool rdma_cap_ib_sa(struct ib_device *device, u8 port_num) +{ + return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_SA; +} + +/** + * rdma_cap_ib_mcast - Check if the port of device has the capability Infiniband + * Multicast. + * @device: Device to check + * @port_num: Port number to check + * + * InfiniBand multicast registration is more complex than normal IPv4 or + * IPv6 multicast registration. Each Host Channel Adapter must register + * with the Subnet Manager when it wishes to join a multicast group. It + * should do so only once regardless of how many queue pairs it subscribes + * to this group. And it should leave the group only after all queue pairs + * attached to the group have been detached. + * + * Return: true if the port must undertake the additional adminstrative + * overhead of registering/unregistering with the SM and tracking of the + * total number of queue pairs attached to the multicast group. + */ +static inline bool rdma_cap_ib_mcast(struct ib_device *device, u8 port_num) +{ + return rdma_cap_ib_sa(device, port_num); +} + +/** + * rdma_cap_af_ib - Check if the port of device has the capability + * Native Infiniband Address. + * @device: Device to check + * @port_num: Port number to check + * + * InfiniBand addressing uses a port's GUID + Subnet Prefix to make a default + * GID. RoCE uses a different mechanism, but still generates a GID via + * a prescribed mechanism and port specific data. + * + * Return: true if the port uses a GID address to identify devices on the + * network. + */ +static inline bool rdma_cap_af_ib(struct ib_device *device, u8 port_num) +{ + return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_AF_IB; +} + +/** + * rdma_cap_eth_ah - Check if the port of device has the capability + * Ethernet Address Handle. + * @device: Device to check + * @port_num: Port number to check + * + * RoCE is InfiniBand over Ethernet, and it uses a well defined technique + * to fabricate GIDs over Ethernet/IP specific addresses native to the + * port. Normally, packet headers are generated by the sending host + * adapter, but when sending connectionless datagrams, we must manually + * inject the proper headers for the fabric we are communicating over. + * + * Return: true if we are running as a RoCE port and must force the + * addition of a Global Route Header built from our Ethernet Address + * Handle into our header list for connectionless packets. + */ +static inline bool rdma_cap_eth_ah(struct ib_device *device, u8 port_num) +{ + return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_ETH_AH; +} + +/** + * rdma_cap_read_multi_sge - Check if the port of device has the capability + * RDMA Read Multiple Scatter-Gather Entries. + * @device: Device to check + * @port_num: Port number to check + * + * iWARP has a restriction that RDMA READ requests may only have a single + * Scatter/Gather Entry (SGE) in the work request. + * + * NOTE: although the linux kernel currently assumes all devices are either + * single SGE RDMA READ devices or identical SGE maximums for RDMA READs and + * WRITEs, according to Tom Talpey, this is not accurate. There are some + * devices out there that support more than a single SGE on RDMA READ + * requests, but do not support the same number of SGEs as they do on + * RDMA WRITE requests. The linux kernel would need rearchitecting to + * support these imbalanced READ/WRITE SGEs allowed devices. So, for now, + * suffice with either the device supports the same READ/WRITE SGEs, or + * it only gets one READ sge. + * + * Return: true for any device that allows more than one SGE in RDMA READ + * requests. + */ +static inline bool rdma_cap_read_multi_sge(struct ib_device *device, + u8 port_num) +{ + return !(device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_IWARP); +} + int ib_query_gid(struct ib_device *device, u8 port_num, int index, union ib_gid *gid); diff --git a/include/scsi/srp.h b/include/scsi/srp.h index 1ae84db4c9fb..5be834de491a 100644 --- a/include/scsi/srp.h +++ b/include/scsi/srp.h @@ -42,6 +42,7 @@ */ #include <linux/types.h> +#include <scsi/scsi.h> enum { SRP_LOGIN_REQ = 0x00, @@ -179,7 +180,7 @@ struct srp_tsk_mgmt { u8 reserved1[6]; u64 tag; u8 reserved2[4]; - __be64 lun __attribute__((packed)); + struct scsi_lun lun; u8 reserved3[2]; u8 tsk_mgmt_func; u8 reserved4; @@ -200,7 +201,7 @@ struct srp_cmd { u8 data_in_desc_cnt; u64 tag; u8 reserved2[4]; - __be64 lun __attribute__((packed)); + struct scsi_lun lun; u8 reserved3; u8 task_attr; u8 reserved4; @@ -265,7 +266,7 @@ struct srp_aer_req { __be32 req_lim_delta; u64 tag; u32 reserved2; - __be64 lun; + struct scsi_lun lun; __be32 sense_data_len; u32 reserved3; u8 sense_data[0]; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index f9f13a32ddb8..86b44164172b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -117,8 +117,8 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count) { - if (rdma_node_get_transport(xprt->sc_cm_id->device->node_type) == - RDMA_TRANSPORT_IWARP) + if (!rdma_cap_read_multi_sge(xprt->sc_cm_id->device, + xprt->sc_cm_id->port_num)) return 1; else return min_t(int, sge_count, xprt->sc_max_sge); diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 13ee04f213d7..88eb994edd36 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -858,7 +858,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) struct ib_qp_init_attr qp_attr; struct ib_device_attr devattr; int uninitialized_var(dma_mr_acc); - int need_dma_mr; + int need_dma_mr = 0; int ret; int i; @@ -992,35 +992,26 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) /* * Determine if a DMA MR is required and if so, what privs are required */ - switch (rdma_node_get_transport(newxprt->sc_cm_id->device->node_type)) { - case RDMA_TRANSPORT_IWARP: - newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_READ_W_INV; - if (!(newxprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)) { - need_dma_mr = 1; - dma_mr_acc = - (IB_ACCESS_LOCAL_WRITE | - IB_ACCESS_REMOTE_WRITE); - } else if (!(devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)) { - need_dma_mr = 1; - dma_mr_acc = IB_ACCESS_LOCAL_WRITE; - } else - need_dma_mr = 0; - break; - case RDMA_TRANSPORT_IB: - if (!(newxprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)) { - need_dma_mr = 1; - dma_mr_acc = IB_ACCESS_LOCAL_WRITE; - } else if (!(devattr.device_cap_flags & - IB_DEVICE_LOCAL_DMA_LKEY)) { - need_dma_mr = 1; - dma_mr_acc = IB_ACCESS_LOCAL_WRITE; - } else - need_dma_mr = 0; - break; - default: + if (!rdma_protocol_iwarp(newxprt->sc_cm_id->device, + newxprt->sc_cm_id->port_num) && + !rdma_ib_or_roce(newxprt->sc_cm_id->device, + newxprt->sc_cm_id->port_num)) goto errout; + + if (!(newxprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG) || + !(devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)) { + need_dma_mr = 1; + dma_mr_acc = IB_ACCESS_LOCAL_WRITE; + if (rdma_protocol_iwarp(newxprt->sc_cm_id->device, + newxprt->sc_cm_id->port_num) && + !(newxprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)) + dma_mr_acc |= IB_ACCESS_REMOTE_WRITE; } + if (rdma_protocol_iwarp(newxprt->sc_cm_id->device, + newxprt->sc_cm_id->port_num)) + newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_READ_W_INV; + /* Create the DMA MR if needed, otherwise, use the DMA LKEY */ if (need_dma_mr) { /* Register all of physical memory */ |