diff options
Diffstat (limited to 'drivers/infiniband/ulp')
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib.h | 4 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_ib.c | 67 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_main.c | 13 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 4 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/iser/iscsi_iser.h | 25 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/iser/iser_verbs.c | 112 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/isert/ib_isert.c | 175 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/isert/ib_isert.h | 21 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h | 23 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/rtrs/rtrs-clt.c | 16 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/rtrs/rtrs-srv.c | 2 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/srpt/ib_srpt.c | 20 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/srpt/ib_srpt.h | 1 |
13 files changed, 161 insertions, 322 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 9a3379c49541..3440dc48d02c 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -515,7 +515,7 @@ void ipoib_ib_dev_cleanup(struct net_device *dev); int ipoib_ib_dev_open_default(struct net_device *dev); int ipoib_ib_dev_open(struct net_device *dev); -int ipoib_ib_dev_stop(struct net_device *dev); +void ipoib_ib_dev_stop(struct net_device *dev); void ipoib_ib_dev_up(struct net_device *dev); void ipoib_ib_dev_down(struct net_device *dev); int ipoib_ib_dev_stop_default(struct net_device *dev); @@ -527,7 +527,7 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb); void ipoib_mcast_restart_task(struct work_struct *work); void ipoib_mcast_start_thread(struct net_device *dev); -int ipoib_mcast_stop_thread(struct net_device *dev); +void ipoib_mcast_stop_thread(struct net_device *dev); void ipoib_mcast_dev_down(struct net_device *dev); void ipoib_mcast_dev_flush(struct net_device *dev); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index da3c5315bbb5..494f413dc3c6 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -670,13 +670,12 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb, return rc; } -static void __ipoib_reap_ah(struct net_device *dev) +static void ipoib_reap_dead_ahs(struct ipoib_dev_priv *priv) { - struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_ah *ah, *tah; unsigned long flags; - netif_tx_lock_bh(dev); + netif_tx_lock_bh(priv->dev); spin_lock_irqsave(&priv->lock, flags); list_for_each_entry_safe(ah, tah, &priv->dead_ahs, list) @@ -687,37 +686,37 @@ static void __ipoib_reap_ah(struct net_device *dev) } spin_unlock_irqrestore(&priv->lock, flags); - netif_tx_unlock_bh(dev); + netif_tx_unlock_bh(priv->dev); } void ipoib_reap_ah(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, ah_reap_task.work); - struct net_device *dev = priv->dev; - __ipoib_reap_ah(dev); + ipoib_reap_dead_ahs(priv); if (!test_bit(IPOIB_STOP_REAPER, &priv->flags)) queue_delayed_work(priv->wq, &priv->ah_reap_task, round_jiffies_relative(HZ)); } -static void ipoib_flush_ah(struct net_device *dev) +static void ipoib_start_ah_reaper(struct ipoib_dev_priv *priv) { - struct ipoib_dev_priv *priv = ipoib_priv(dev); - - cancel_delayed_work(&priv->ah_reap_task); - flush_workqueue(priv->wq); - ipoib_reap_ah(&priv->ah_reap_task.work); + clear_bit(IPOIB_STOP_REAPER, &priv->flags); + queue_delayed_work(priv->wq, &priv->ah_reap_task, + round_jiffies_relative(HZ)); } -static void ipoib_stop_ah(struct net_device *dev) +static void ipoib_stop_ah_reaper(struct ipoib_dev_priv *priv) { - struct ipoib_dev_priv *priv = ipoib_priv(dev); - set_bit(IPOIB_STOP_REAPER, &priv->flags); - ipoib_flush_ah(dev); + cancel_delayed_work(&priv->ah_reap_task); + /* + * After ipoib_stop_ah_reaper() we always go through + * ipoib_reap_dead_ahs() which ensures the work is really stopped and + * does a final flush out of the dead_ah's list + */ } static int recvs_pending(struct net_device *dev) @@ -846,18 +845,6 @@ timeout: return 0; } -int ipoib_ib_dev_stop(struct net_device *dev) -{ - struct ipoib_dev_priv *priv = ipoib_priv(dev); - - priv->rn_ops->ndo_stop(dev); - - clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); - ipoib_flush_ah(dev); - - return 0; -} - int ipoib_ib_dev_open_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -901,10 +888,7 @@ int ipoib_ib_dev_open(struct net_device *dev) return -1; } - clear_bit(IPOIB_STOP_REAPER, &priv->flags); - queue_delayed_work(priv->wq, &priv->ah_reap_task, - round_jiffies_relative(HZ)); - + ipoib_start_ah_reaper(priv); if (priv->rn_ops->ndo_open(dev)) { pr_warn("%s: Failed to open dev\n", dev->name); goto dev_stop; @@ -915,13 +899,20 @@ int ipoib_ib_dev_open(struct net_device *dev) return 0; dev_stop: - set_bit(IPOIB_STOP_REAPER, &priv->flags); - cancel_delayed_work(&priv->ah_reap_task); - set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); - ipoib_ib_dev_stop(dev); + ipoib_stop_ah_reaper(priv); return -1; } +void ipoib_ib_dev_stop(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + priv->rn_ops->ndo_stop(dev); + + clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); + ipoib_stop_ah_reaper(priv); +} + void ipoib_pkey_dev_check_presence(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -1232,7 +1223,7 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, ipoib_mcast_dev_flush(dev); if (oper_up) set_bit(IPOIB_FLAG_OPER_UP, &priv->flags); - ipoib_flush_ah(dev); + ipoib_reap_dead_ahs(priv); } if (level >= IPOIB_FLUSH_NORMAL) @@ -1307,7 +1298,7 @@ void ipoib_ib_dev_cleanup(struct net_device *dev) * the neighbor garbage collection is stopped and reaped. * That should all be done now, so make a final ah flush. */ - ipoib_stop_ah(dev); + ipoib_reap_dead_ahs(priv); clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 3cfb682b91b0..752581a8627b 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1892,8 +1892,15 @@ static void ipoib_child_init(struct net_device *ndev) priv->max_ib_mtu = ppriv->max_ib_mtu; set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags); - memcpy(priv->dev->dev_addr, ppriv->dev->dev_addr, INFINIBAND_ALEN); - memcpy(&priv->local_gid, &ppriv->local_gid, sizeof(priv->local_gid)); + if (memchr_inv(priv->dev->dev_addr, 0, INFINIBAND_ALEN)) + memcpy(&priv->local_gid, priv->dev->dev_addr + 4, + sizeof(priv->local_gid)); + else { + memcpy(priv->dev->dev_addr, ppriv->dev->dev_addr, + INFINIBAND_ALEN); + memcpy(&priv->local_gid, &ppriv->local_gid, + sizeof(priv->local_gid)); + } } static int ipoib_ndo_init(struct net_device *ndev) @@ -1976,6 +1983,8 @@ static void ipoib_ndo_uninit(struct net_device *dev) /* no more works over the priv->wq */ if (priv->wq) { + /* See ipoib_mcast_carrier_on_task() */ + WARN_ON(test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)); flush_workqueue(priv->wq); destroy_workqueue(priv->wq); priv->wq = NULL; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 9bfa514473d5..86e4ed64e4e2 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -680,15 +680,13 @@ void ipoib_mcast_start_thread(struct net_device *dev) spin_unlock_irqrestore(&priv->lock, flags); } -int ipoib_mcast_stop_thread(struct net_device *dev) +void ipoib_mcast_stop_thread(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg_mcast(priv, "stopping multicast thread\n"); cancel_delayed_work_sync(&priv->mcast_task); - - return 0; } static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast) diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h index 1d77c7f42e38..78ee9445f801 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.h +++ b/drivers/infiniband/ulp/iser/iscsi_iser.h @@ -300,18 +300,6 @@ struct ib_conn; struct iscsi_iser_task; /** - * struct iser_comp - iSER completion context - * - * @cq: completion queue - * @active_qps: Number of active QPs attached - * to completion context - */ -struct iser_comp { - struct ib_cq *cq; - int active_qps; -}; - -/** * struct iser_device - iSER device handle * * @ib_device: RDMA device @@ -320,9 +308,6 @@ struct iser_comp { * @event_handler: IB events handle routine * @ig_list: entry in devices list * @refcount: Reference counter, dominated by open iser connections - * @comps_used: Number of completion contexts used, Min between online - * cpus and device max completion vectors - * @comps: Dinamically allocated array of completion handlers */ struct iser_device { struct ib_device *ib_device; @@ -330,8 +315,6 @@ struct iser_device { struct ib_event_handler event_handler; struct list_head ig_list; int refcount; - int comps_used; - struct iser_comp *comps; }; /** @@ -353,6 +336,7 @@ struct iser_reg_resources { * @list: entry in connection fastreg pool * @rsc: data buffer registration resources * @sig_protected: is region protected indicator + * @all_list: first and last list members */ struct iser_fr_desc { struct list_head list; @@ -367,6 +351,7 @@ struct iser_fr_desc { * @list: list of fastreg descriptors * @lock: protects fastreg pool * @size: size of the pool + * @all_list: first and last list members */ struct iser_fr_pool { struct list_head list; @@ -380,11 +365,12 @@ struct iser_fr_pool { * * @cma_id: rdma_cm connection maneger handle * @qp: Connection Queue-pair + * @cq: Connection completion queue + * @cq_size: The number of max outstanding completions * @post_recv_buf_count: post receive counter * @sig_count: send work request signal count * @rx_wr: receive work request for batch posts * @device: reference to iser device - * @comp: iser completion context * @fr_pool: connection fast registration poool * @pi_support: Indicate device T10-PI support * @reg_cqe: completion handler @@ -392,11 +378,12 @@ struct iser_fr_pool { struct ib_conn { struct rdma_cm_id *cma_id; struct ib_qp *qp; + struct ib_cq *cq; + u32 cq_size; int post_recv_buf_count; u8 sig_count; struct ib_recv_wr rx_wr[ISER_MIN_POSTED_RX]; struct iser_device *device; - struct iser_comp *comp; struct iser_fr_pool fr_pool; bool pi_support; struct ib_cqe reg_cqe; diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c index c1f44c41f501..699e075ae1b3 100644 --- a/drivers/infiniband/ulp/iser/iser_verbs.c +++ b/drivers/infiniband/ulp/iser/iser_verbs.c @@ -68,59 +68,23 @@ static void iser_event_handler(struct ib_event_handler *handler, static int iser_create_device_ib_res(struct iser_device *device) { struct ib_device *ib_dev = device->ib_device; - int i, max_cqe; if (!(ib_dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS)) { iser_err("IB device does not support memory registrations\n"); return -1; } - device->comps_used = min_t(int, num_online_cpus(), - ib_dev->num_comp_vectors); - - device->comps = kcalloc(device->comps_used, sizeof(*device->comps), - GFP_KERNEL); - if (!device->comps) - goto comps_err; - - max_cqe = min(ISER_MAX_CQ_LEN, ib_dev->attrs.max_cqe); - - iser_info("using %d CQs, device %s supports %d vectors max_cqe %d\n", - device->comps_used, dev_name(&ib_dev->dev), - ib_dev->num_comp_vectors, max_cqe); - device->pd = ib_alloc_pd(ib_dev, iser_always_reg ? 0 : IB_PD_UNSAFE_GLOBAL_RKEY); if (IS_ERR(device->pd)) goto pd_err; - for (i = 0; i < device->comps_used; i++) { - struct iser_comp *comp = &device->comps[i]; - - comp->cq = ib_alloc_cq(ib_dev, comp, max_cqe, i, - IB_POLL_SOFTIRQ); - if (IS_ERR(comp->cq)) { - comp->cq = NULL; - goto cq_err; - } - } - INIT_IB_EVENT_HANDLER(&device->event_handler, ib_dev, iser_event_handler); ib_register_event_handler(&device->event_handler); return 0; -cq_err: - for (i = 0; i < device->comps_used; i++) { - struct iser_comp *comp = &device->comps[i]; - - if (comp->cq) - ib_free_cq(comp->cq); - } - ib_dealloc_pd(device->pd); pd_err: - kfree(device->comps); -comps_err: iser_err("failed to allocate an IB resource\n"); return -1; } @@ -131,20 +95,9 @@ comps_err: */ static void iser_free_device_ib_res(struct iser_device *device) { - int i; - - for (i = 0; i < device->comps_used; i++) { - struct iser_comp *comp = &device->comps[i]; - - ib_free_cq(comp->cq); - comp->cq = NULL; - } - ib_unregister_event_handler(&device->event_handler); ib_dealloc_pd(device->pd); - kfree(device->comps); - device->comps = NULL; device->pd = NULL; } @@ -287,70 +240,57 @@ static int iser_create_ib_conn_res(struct ib_conn *ib_conn) struct ib_device *ib_dev; struct ib_qp_init_attr init_attr; int ret = -ENOMEM; - int index, min_index = 0; + unsigned int max_send_wr, cq_size; BUG_ON(ib_conn->device == NULL); device = ib_conn->device; ib_dev = device->ib_device; - memset(&init_attr, 0, sizeof init_attr); + if (ib_conn->pi_support) + max_send_wr = ISER_QP_SIG_MAX_REQ_DTOS + 1; + else + max_send_wr = ISER_QP_MAX_REQ_DTOS + 1; + max_send_wr = min_t(unsigned int, max_send_wr, + (unsigned int)ib_dev->attrs.max_qp_wr); - mutex_lock(&ig.connlist_mutex); - /* select the CQ with the minimal number of usages */ - for (index = 0; index < device->comps_used; index++) { - if (device->comps[index].active_qps < - device->comps[min_index].active_qps) - min_index = index; + cq_size = max_send_wr + ISER_QP_MAX_RECV_DTOS; + ib_conn->cq = ib_cq_pool_get(ib_dev, cq_size, -1, IB_POLL_SOFTIRQ); + if (IS_ERR(ib_conn->cq)) { + ret = PTR_ERR(ib_conn->cq); + goto cq_err; } - ib_conn->comp = &device->comps[min_index]; - ib_conn->comp->active_qps++; - mutex_unlock(&ig.connlist_mutex); - iser_info("cq index %d used for ib_conn %p\n", min_index, ib_conn); + ib_conn->cq_size = cq_size; + + memset(&init_attr, 0, sizeof(init_attr)); init_attr.event_handler = iser_qp_event_callback; init_attr.qp_context = (void *)ib_conn; - init_attr.send_cq = ib_conn->comp->cq; - init_attr.recv_cq = ib_conn->comp->cq; + init_attr.send_cq = ib_conn->cq; + init_attr.recv_cq = ib_conn->cq; init_attr.cap.max_recv_wr = ISER_QP_MAX_RECV_DTOS; init_attr.cap.max_send_sge = 2; init_attr.cap.max_recv_sge = 1; init_attr.sq_sig_type = IB_SIGNAL_REQ_WR; init_attr.qp_type = IB_QPT_RC; - if (ib_conn->pi_support) { - init_attr.cap.max_send_wr = ISER_QP_SIG_MAX_REQ_DTOS + 1; + init_attr.cap.max_send_wr = max_send_wr; + if (ib_conn->pi_support) init_attr.create_flags |= IB_QP_CREATE_INTEGRITY_EN; - iser_conn->max_cmds = - ISER_GET_MAX_XMIT_CMDS(ISER_QP_SIG_MAX_REQ_DTOS); - } else { - if (ib_dev->attrs.max_qp_wr > ISER_QP_MAX_REQ_DTOS) { - init_attr.cap.max_send_wr = ISER_QP_MAX_REQ_DTOS + 1; - iser_conn->max_cmds = - ISER_GET_MAX_XMIT_CMDS(ISER_QP_MAX_REQ_DTOS); - } else { - init_attr.cap.max_send_wr = ib_dev->attrs.max_qp_wr; - iser_conn->max_cmds = - ISER_GET_MAX_XMIT_CMDS(ib_dev->attrs.max_qp_wr); - iser_dbg("device %s supports max_send_wr %d\n", - dev_name(&device->ib_device->dev), - ib_dev->attrs.max_qp_wr); - } - } + iser_conn->max_cmds = ISER_GET_MAX_XMIT_CMDS(max_send_wr - 1); ret = rdma_create_qp(ib_conn->cma_id, device->pd, &init_attr); if (ret) goto out_err; ib_conn->qp = ib_conn->cma_id->qp; - iser_info("setting conn %p cma_id %p qp %p\n", + iser_info("setting conn %p cma_id %p qp %p max_send_wr %d\n", ib_conn, ib_conn->cma_id, - ib_conn->cma_id->qp); + ib_conn->cma_id->qp, max_send_wr); return ret; out_err: - mutex_lock(&ig.connlist_mutex); - ib_conn->comp->active_qps--; - mutex_unlock(&ig.connlist_mutex); + ib_cq_pool_put(ib_conn->cq, ib_conn->cq_size); +cq_err: iser_err("unable to alloc mem or create resource, err %d\n", ret); return ret; @@ -462,10 +402,8 @@ static void iser_free_ib_conn_res(struct iser_conn *iser_conn, iser_conn, ib_conn->cma_id, ib_conn->qp); if (ib_conn->qp != NULL) { - mutex_lock(&ig.connlist_mutex); - ib_conn->comp->active_qps--; - mutex_unlock(&ig.connlist_mutex); rdma_destroy_qp(ib_conn->cma_id); + ib_cq_pool_put(ib_conn->cq, ib_conn->cq_size); ib_conn->qp = NULL; } diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index b7df38ee8ae0..61e2f7fc513d 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -24,13 +24,6 @@ #include "ib_isert.h" -#define ISERT_MAX_CONN 8 -#define ISER_MAX_RX_CQ_LEN (ISERT_QP_MAX_RECV_DTOS * ISERT_MAX_CONN) -#define ISER_MAX_TX_CQ_LEN \ - ((ISERT_QP_MAX_REQ_DTOS + ISCSI_DEF_XMIT_CMDS_MAX) * ISERT_MAX_CONN) -#define ISER_MAX_CQ_LEN (ISER_MAX_RX_CQ_LEN + ISER_MAX_TX_CQ_LEN + \ - ISERT_MAX_CONN) - static int isert_debug_level; module_param_named(debug_level, isert_debug_level, int, 0644); MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0 (default:0)"); @@ -82,53 +75,34 @@ isert_qp_event_callback(struct ib_event *e, void *context) } } -static struct isert_comp * -isert_comp_get(struct isert_conn *isert_conn) -{ - struct isert_device *device = isert_conn->device; - struct isert_comp *comp; - int i, min = 0; - - mutex_lock(&device_list_mutex); - for (i = 0; i < device->comps_used; i++) - if (device->comps[i].active_qps < - device->comps[min].active_qps) - min = i; - comp = &device->comps[min]; - comp->active_qps++; - mutex_unlock(&device_list_mutex); - - isert_info("conn %p, using comp %p min_index: %d\n", - isert_conn, comp, min); - - return comp; -} - -static void -isert_comp_put(struct isert_comp *comp) -{ - mutex_lock(&device_list_mutex); - comp->active_qps--; - mutex_unlock(&device_list_mutex); -} - static struct ib_qp * isert_create_qp(struct isert_conn *isert_conn, - struct isert_comp *comp, struct rdma_cm_id *cma_id) { + u32 cq_size = ISERT_QP_MAX_REQ_DTOS + ISERT_QP_MAX_RECV_DTOS + 2; struct isert_device *device = isert_conn->device; + struct ib_device *ib_dev = device->ib_device; struct ib_qp_init_attr attr; - int ret; + int ret, factor; + + isert_conn->cq = ib_cq_pool_get(ib_dev, cq_size, -1, IB_POLL_WORKQUEUE); + if (IS_ERR(isert_conn->cq)) { + isert_err("Unable to allocate cq\n"); + ret = PTR_ERR(isert_conn->cq); + return ERR_PTR(ret); + } + isert_conn->cq_size = cq_size; memset(&attr, 0, sizeof(struct ib_qp_init_attr)); attr.event_handler = isert_qp_event_callback; attr.qp_context = isert_conn; - attr.send_cq = comp->cq; - attr.recv_cq = comp->cq; + attr.send_cq = isert_conn->cq; + attr.recv_cq = isert_conn->cq; attr.cap.max_send_wr = ISERT_QP_MAX_REQ_DTOS + 1; attr.cap.max_recv_wr = ISERT_QP_MAX_RECV_DTOS + 1; - attr.cap.max_rdma_ctxs = ISCSI_DEF_XMIT_CMDS_MAX; + factor = rdma_rw_mr_factor(device->ib_device, cma_id->port_num, + ISCSI_ISER_MAX_SG_TABLESIZE); + attr.cap.max_rdma_ctxs = ISCSI_DEF_XMIT_CMDS_MAX * factor; attr.cap.max_send_sge = device->ib_device->attrs.max_send_sge; attr.cap.max_recv_sge = 1; attr.sq_sig_type = IB_SIGNAL_REQ_WR; @@ -139,6 +113,8 @@ isert_create_qp(struct isert_conn *isert_conn, ret = rdma_create_qp(cma_id, device->pd, &attr); if (ret) { isert_err("rdma_create_qp failed for cma_id %d\n", ret); + ib_cq_pool_put(isert_conn->cq, isert_conn->cq_size); + return ERR_PTR(ret); } @@ -146,25 +122,6 @@ isert_create_qp(struct isert_conn *isert_conn, } static int -isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id) -{ - struct isert_comp *comp; - int ret; - - comp = isert_comp_get(isert_conn); - isert_conn->qp = isert_create_qp(isert_conn, comp, cma_id); - if (IS_ERR(isert_conn->qp)) { - ret = PTR_ERR(isert_conn->qp); - goto err; - } - - return 0; -err: - isert_comp_put(comp); - return ret; -} - -static int isert_alloc_rx_descriptors(struct isert_conn *isert_conn) { struct isert_device *device = isert_conn->device; @@ -231,61 +188,6 @@ isert_free_rx_descriptors(struct isert_conn *isert_conn) isert_conn->rx_descs = NULL; } -static void -isert_free_comps(struct isert_device *device) -{ - int i; - - for (i = 0; i < device->comps_used; i++) { - struct isert_comp *comp = &device->comps[i]; - - if (comp->cq) - ib_free_cq(comp->cq); - } - kfree(device->comps); -} - -static int -isert_alloc_comps(struct isert_device *device) -{ - int i, max_cqe, ret = 0; - - device->comps_used = min(ISERT_MAX_CQ, min_t(int, num_online_cpus(), - device->ib_device->num_comp_vectors)); - - isert_info("Using %d CQs, %s supports %d vectors support " - "pi_capable %d\n", - device->comps_used, dev_name(&device->ib_device->dev), - device->ib_device->num_comp_vectors, - device->pi_capable); - - device->comps = kcalloc(device->comps_used, sizeof(struct isert_comp), - GFP_KERNEL); - if (!device->comps) - return -ENOMEM; - - max_cqe = min(ISER_MAX_CQ_LEN, device->ib_device->attrs.max_cqe); - - for (i = 0; i < device->comps_used; i++) { - struct isert_comp *comp = &device->comps[i]; - - comp->device = device; - comp->cq = ib_alloc_cq(device->ib_device, comp, max_cqe, i, - IB_POLL_WORKQUEUE); - if (IS_ERR(comp->cq)) { - isert_err("Unable to allocate cq\n"); - ret = PTR_ERR(comp->cq); - comp->cq = NULL; - goto out_cq; - } - } - - return 0; -out_cq: - isert_free_comps(device); - return ret; -} - static int isert_create_device_ib_res(struct isert_device *device) { @@ -296,16 +198,12 @@ isert_create_device_ib_res(struct isert_device *device) ib_dev->attrs.max_send_sge, ib_dev->attrs.max_recv_sge); isert_dbg("devattr->max_sge_rd: %d\n", ib_dev->attrs.max_sge_rd); - ret = isert_alloc_comps(device); - if (ret) - goto out; - device->pd = ib_alloc_pd(ib_dev, 0); if (IS_ERR(device->pd)) { ret = PTR_ERR(device->pd); isert_err("failed to allocate pd, device %p, ret=%d\n", device, ret); - goto out_cq; + return ret; } /* Check signature cap */ @@ -313,13 +211,6 @@ isert_create_device_ib_res(struct isert_device *device) IB_DEVICE_INTEGRITY_HANDOVER ? true : false; return 0; - -out_cq: - isert_free_comps(device); -out: - if (ret > 0) - ret = -EINVAL; - return ret; } static void @@ -328,7 +219,6 @@ isert_free_device_ib_res(struct isert_device *device) isert_info("device %p\n", device); ib_dealloc_pd(device->pd); - isert_free_comps(device); } static void @@ -490,6 +380,13 @@ isert_set_nego_params(struct isert_conn *isert_conn, } } +static void +isert_destroy_qp(struct isert_conn *isert_conn) +{ + ib_destroy_qp(isert_conn->qp); + ib_cq_pool_put(isert_conn->cq, isert_conn->cq_size); +} + static int isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) { @@ -530,17 +427,19 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) isert_set_nego_params(isert_conn, &event->param.conn); - ret = isert_conn_setup_qp(isert_conn, cma_id); - if (ret) + isert_conn->qp = isert_create_qp(isert_conn, cma_id); + if (IS_ERR(isert_conn->qp)) { + ret = PTR_ERR(isert_conn->qp); goto out_conn_dev; + } ret = isert_login_post_recv(isert_conn); if (ret) - goto out_conn_dev; + goto out_destroy_qp; ret = isert_rdma_accept(isert_conn); if (ret) - goto out_conn_dev; + goto out_destroy_qp; mutex_lock(&isert_np->mutex); list_add_tail(&isert_conn->node, &isert_np->accepted); @@ -548,6 +447,8 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) return 0; +out_destroy_qp: + isert_destroy_qp(isert_conn); out_conn_dev: isert_device_put(device); out_rsp_dma_map: @@ -572,12 +473,8 @@ isert_connect_release(struct isert_conn *isert_conn) !isert_conn->dev_removed) rdma_destroy_id(isert_conn->cm_id); - if (isert_conn->qp) { - struct isert_comp *comp = isert_conn->qp->recv_cq->cq_context; - - isert_comp_put(comp); - ib_destroy_qp(isert_conn->qp); - } + if (isert_conn->qp) + isert_destroy_qp(isert_conn); if (isert_conn->login_req_buf) isert_free_login_buf(isert_conn); diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index 3b296bac4f60..c55f7d9bfced 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -63,7 +63,8 @@ (ISER_RX_PAYLOAD_SIZE + sizeof(u64) + sizeof(struct ib_sge) + \ sizeof(struct ib_cqe) + sizeof(bool))) -#define ISCSI_ISER_SG_TABLESIZE 256 +/* Maximum support is 16MB I/O size */ +#define ISCSI_ISER_MAX_SG_TABLESIZE 4096 enum isert_desc_type { ISCSI_TX_CONTROL, @@ -155,6 +156,8 @@ struct isert_conn { struct iser_tx_desc login_tx_desc; struct rdma_cm_id *cm_id; struct ib_qp *qp; + struct ib_cq *cq; + u32 cq_size; struct isert_device *device; struct mutex mutex; struct kref kref; @@ -165,22 +168,6 @@ struct isert_conn { bool dev_removed; }; -#define ISERT_MAX_CQ 64 - -/** - * struct isert_comp - iSER completion context - * - * @device: pointer to device handle - * @cq: completion queue - * @active_qps: Number of active QPs attached - * to completion context - */ -struct isert_comp { - struct isert_device *device; - struct ib_cq *cq; - int active_qps; -}; - struct isert_device { bool pi_capable; int refcount; diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h index d324312a373c..f64519872297 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h @@ -118,12 +118,17 @@ * struct opa_vesw_info - OPA vnic switch information * @fabric_id: 10-bit fabric id * @vesw_id: 12-bit virtual ethernet switch id + * @rsvd0: reserved bytes * @def_port_mask: bitmask of default ports + * @rsvd1: reserved bytes * @pkey: partition key + * @rsvd2: reserved bytes * @u_mcast_dlid: unknown multicast dlid * @u_ucast_dlid: array of unknown unicast dlids + * @rsvd3: reserved bytes * @rc: routing control * @eth_mtu: Ethernet MTU + * @rsvd4: reserved bytes */ struct opa_vesw_info { __be16 fabric_id; @@ -150,12 +155,14 @@ struct opa_vesw_info { * struct opa_per_veswport_info - OPA vnic per port information * @port_num: port number * @eth_link_status: current ethernet link state + * @rsvd0: reserved bytes * @base_mac_addr: base mac address * @config_state: configured port state * @oper_state: operational port state * @max_mac_tbl_ent: max number of mac table entries * @max_smac_ent: max smac entries in mac table * @mac_tbl_digest: mac table digest + * @rsvd1: reserved bytes * @encap_slid: base slid for the port * @pcp_to_sc_uc: sc by pcp index for unicast ethernet packets * @pcp_to_vl_uc: vl by pcp index for unicast ethernet packets @@ -165,8 +172,10 @@ struct opa_vesw_info { * @non_vlan_vl_uc: vl for non-vlan unicast ethernet packets * @non_vlan_sc_mc: sc for non-vlan multicast ethernet packets * @non_vlan_vl_mc: vl for non-vlan multicast ethernet packets + * @rsvd2: reserved bytes * @uc_macs_gen_count: generation count for unicast macs list * @mc_macs_gen_count: generation count for multicast macs list + * @rsvd3: reserved bytes */ struct opa_per_veswport_info { __be32 port_num; @@ -294,6 +303,7 @@ struct opa_veswport_mactable { * @rx_512_1023: received packet length is >=512 and < 1023 bytes * @rx_1024_1518: received packet length is >=1024 and < 1518 bytes * @rx_1519_max: received packet length >= 1519 bytes + * @reserved: reserved bytes * * All the above are counters of corresponding conditions. */ @@ -347,16 +357,26 @@ struct opa_veswport_summary_counters { * @veswport_num: virtual ethernet switch port number * @tx_errors: transmit errors * @rx_errors: receive errors + * @rsvd0: reserved bytes * @tx_smac_filt: smac filter errors + * @rsvd1: reserved bytes + * @rsvd2: reserved bytes + * @rsvd3: reserved bytes * @tx_dlid_zero: transmit packets with invalid dlid + * @rsvd4: reserved bytes * @tx_logic: other transmit errors + * @rsvd5: reserved bytes * @tx_drop_state: packet tansmission in non-forward port state * @rx_bad_veswid: received packet with invalid vesw id + * @rsvd6: reserved bytes * @rx_runt: received ethernet packet with length < 64 bytes * @rx_oversize: received ethernet packet with length > MTU size + * @rsvd7: reserved bytes * @rx_eth_down: received packets when interface is down * @rx_drop_state: received packets in non-forwarding port state * @rx_logic: other receive errors + * @rsvd8: reserved bytes + * @rsvd9: reserved bytes * * All the above are counters of corresponding error conditions. */ @@ -447,6 +467,7 @@ struct opa_veswport_iface_macs { * struct opa_vnic_vema_mad - Generic VEMA MAD * @mad_hdr: Generic MAD header * @rmpp_hdr: RMPP header for vendor specific MADs + * @reserved: reserved bytes * @oui: Unique org identifier * @data: MAD data */ @@ -467,6 +488,7 @@ struct opa_vnic_vema_mad { * @trap_num: Trap number * @toggle_count: Notice toggle bit and count value * @issuer_lid: Trap issuer's lid + * @reserved: reserved bytes * @issuer_gid: Issuer GID (only if Report method) * @raw_data: Trap message body */ @@ -487,6 +509,7 @@ struct opa_vnic_notice_attr { * struct opa_vnic_vema_mad_trap - Generic VEMA MAD Trap * @mad_hdr: Generic MAD header * @rmpp_hdr: RMPP header for vendor specific MADs + * @reserved: reserved bytes * @oui: Unique org identifier * @notice: Notice structure */ diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index 564388a85603..776e89231c52 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -12,6 +12,7 @@ #include <linux/module.h> #include <linux/rculist.h> +#include <linux/random.h> #include "rtrs-clt.h" #include "rtrs-log.h" @@ -23,6 +24,12 @@ * leads to "false positives" failed reconnect attempts */ #define RTRS_RECONNECT_BACKOFF 1000 +/* + * Wait for additional random time between 0 and 8 seconds + * before starting to reconnect to avoid clients reconnecting + * all at once in case of a major network outage + */ +#define RTRS_RECONNECT_SEED 8 MODULE_DESCRIPTION("RDMA Transport Client"); MODULE_LICENSE("GPL"); @@ -306,7 +313,8 @@ static void rtrs_rdma_error_recovery(struct rtrs_clt_con *con) */ delay_ms = clt->reconnect_delay_sec * 1000; queue_delayed_work(rtrs_wq, &sess->reconnect_dwork, - msecs_to_jiffies(delay_ms)); + msecs_to_jiffies(delay_ms + + prandom_u32() % RTRS_RECONNECT_SEED)); } else { /* * Error can happen just on establishing new connection, @@ -2503,7 +2511,9 @@ reconnect_again: sess->stats->reconnects.fail_cnt++; delay_ms = clt->reconnect_delay_sec * 1000; queue_delayed_work(rtrs_wq, &sess->reconnect_dwork, - msecs_to_jiffies(delay_ms)); + msecs_to_jiffies(delay_ms + + prandom_u32() % + RTRS_RECONNECT_SEED)); } } @@ -2972,7 +2982,7 @@ static int __init rtrs_client_init(void) pr_err("Failed to create rtrs-client dev class\n"); return PTR_ERR(rtrs_clt_dev_class); } - rtrs_wq = alloc_workqueue("rtrs_client_wq", WQ_MEM_RECLAIM, 0); + rtrs_wq = alloc_workqueue("rtrs_client_wq", 0, 0); if (!rtrs_wq) { class_destroy(rtrs_clt_dev_class); return -ENOMEM; diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c index 0d9241f5d9e6..a219bd1bdbc2 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c @@ -2150,7 +2150,7 @@ static int __init rtrs_server_init(void) err = PTR_ERR(rtrs_dev_class); goto out_chunk_pool; } - rtrs_wq = alloc_workqueue("rtrs_server_wq", WQ_MEM_RECLAIM, 0); + rtrs_wq = alloc_workqueue("rtrs_server_wq", 0, 0); if (!rtrs_wq) { err = -ENOMEM; goto out_dev_class; diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index ef7fcd3e8e15..0065eb17ae36 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -869,7 +869,7 @@ static int srpt_zerolength_write(struct srpt_rdma_ch *ch) static void srpt_zerolength_write_done(struct ib_cq *cq, struct ib_wc *wc) { - struct srpt_rdma_ch *ch = cq->cq_context; + struct srpt_rdma_ch *ch = wc->qp->qp_context; pr_debug("%s-%d wc->status %d\n", ch->sess_name, ch->qp->qp_num, wc->status); @@ -1322,7 +1322,7 @@ static int srpt_abort_cmd(struct srpt_send_ioctx *ioctx) */ static void srpt_rdma_read_done(struct ib_cq *cq, struct ib_wc *wc) { - struct srpt_rdma_ch *ch = cq->cq_context; + struct srpt_rdma_ch *ch = wc->qp->qp_context; struct srpt_send_ioctx *ioctx = container_of(wc->wr_cqe, struct srpt_send_ioctx, rdma_cqe); @@ -1683,7 +1683,7 @@ push: static void srpt_recv_done(struct ib_cq *cq, struct ib_wc *wc) { - struct srpt_rdma_ch *ch = cq->cq_context; + struct srpt_rdma_ch *ch = wc->qp->qp_context; struct srpt_recv_ioctx *ioctx = container_of(wc->wr_cqe, struct srpt_recv_ioctx, ioctx.cqe); @@ -1744,7 +1744,7 @@ static void srpt_process_wait_list(struct srpt_rdma_ch *ch) */ static void srpt_send_done(struct ib_cq *cq, struct ib_wc *wc) { - struct srpt_rdma_ch *ch = cq->cq_context; + struct srpt_rdma_ch *ch = wc->qp->qp_context; struct srpt_send_ioctx *ioctx = container_of(wc->wr_cqe, struct srpt_send_ioctx, ioctx.cqe); enum srpt_command_state state; @@ -1791,7 +1791,7 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch) goto out; retry: - ch->cq = ib_alloc_cq_any(sdev->device, ch, ch->rq_size + sq_size, + ch->cq = ib_cq_pool_get(sdev->device, ch->rq_size + sq_size, -1, IB_POLL_WORKQUEUE); if (IS_ERR(ch->cq)) { ret = PTR_ERR(ch->cq); @@ -1799,6 +1799,7 @@ retry: ch->rq_size + sq_size, ret); goto out; } + ch->cq_size = ch->rq_size + sq_size; qp_init->qp_context = (void *)ch; qp_init->event_handler @@ -1843,7 +1844,7 @@ retry: if (retry) { pr_debug("failed to create queue pair with sq_size = %d (%d) - retrying\n", sq_size, ret); - ib_free_cq(ch->cq); + ib_cq_pool_put(ch->cq, ch->cq_size); sq_size = max(sq_size / 2, MIN_SRPT_SQ_SIZE); goto retry; } else { @@ -1869,14 +1870,14 @@ out: err_destroy_cq: ch->qp = NULL; - ib_free_cq(ch->cq); + ib_cq_pool_put(ch->cq, ch->cq_size); goto out; } static void srpt_destroy_ch_ib(struct srpt_rdma_ch *ch) { ib_destroy_qp(ch->qp); - ib_free_cq(ch->cq); + ib_cq_pool_put(ch->cq, ch->cq_size); } /** @@ -2156,9 +2157,6 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev, WARN_ON_ONCE(irqs_disabled()); - if (WARN_ON(!sdev || !req)) - return -EINVAL; - it_iu_len = be32_to_cpu(req->req_it_iu_len); pr_info("Received SRP_LOGIN_REQ with i_port_id %pI6, t_port_id %pI6 and it_iu_len %d on port %d (guid=%pI6); pkey %#04x\n", diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h index f31c349d07a1..41435a699b53 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.h +++ b/drivers/infiniband/ulp/srpt/ib_srpt.h @@ -300,6 +300,7 @@ struct srpt_rdma_ch { } rdma_cm; }; struct ib_cq *cq; + u32 cq_size; struct ib_cqe zw_cqe; struct rcu_head rcu; struct kref kref; |