diff options
Diffstat (limited to 'drivers/infiniband/ulp')
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_cm.c | 21 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_ib.c | 12 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_main.c | 123 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 5 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_verbs.c | 6 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/iser/iser_initiator.c | 16 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/isert/ib_isert.c | 8 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/isert/ib_isert.h | 1 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c | 2 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/srp/ib_srp.c | 795 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/srp/ib_srp.h | 43 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/srpt/ib_srpt.c | 965 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/srpt/ib_srpt.h | 100 |
13 files changed, 1436 insertions, 661 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 2c13123bfd69..962fbcb57dc7 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -766,12 +766,14 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ skb_orphan(skb); skb_dst_drop(skb); - if (netif_queue_stopped(dev)) - if (ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP | - IB_CQ_REPORT_MISSED_EVENTS)) { + if (netif_queue_stopped(dev)) { + rc = ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP | + IB_CQ_REPORT_MISSED_EVENTS); + if (unlikely(rc < 0)) ipoib_warn(priv, "IPoIB/CM:request notify on send CQ failed\n"); + else if (rc) napi_schedule(&priv->send_napi); - } + } rc = post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1), tx_req); if (unlikely(rc)) { @@ -876,7 +878,7 @@ int ipoib_cm_dev_open(struct net_device *dev) priv->cm.id = ib_create_cm_id(priv->ca, ipoib_cm_rx_handler, dev); if (IS_ERR(priv->cm.id)) { - printk(KERN_WARNING "%s: failed to create CM ID\n", priv->ca->name); + pr_warn("%s: failed to create CM ID\n", priv->ca->name); ret = PTR_ERR(priv->cm.id); goto err_cm; } @@ -884,8 +886,8 @@ int ipoib_cm_dev_open(struct net_device *dev) ret = ib_cm_listen(priv->cm.id, cpu_to_be64(IPOIB_CM_IETF_ID | priv->qp->qp_num), 0); if (ret) { - printk(KERN_WARNING "%s: failed to listen on ID 0x%llx\n", priv->ca->name, - IPOIB_CM_IETF_ID | priv->qp->qp_num); + pr_warn("%s: failed to listen on ID 0x%llx\n", priv->ca->name, + IPOIB_CM_IETF_ID | priv->qp->qp_num); goto err_listen; } @@ -1456,8 +1458,7 @@ void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb, struct ipoib_dev_priv *priv = ipoib_priv(dev); int e = skb_queue_empty(&priv->cm.skb_queue); - if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); + skb_dst_update_pmtu(skb, mtu); skb_queue_tail(&priv->cm.skb_queue, skb); if (e) @@ -1563,7 +1564,7 @@ static void ipoib_cm_create_srq(struct net_device *dev, int max_sge) priv->cm.srq = ib_create_srq(priv->pd, &srq_init_attr); if (IS_ERR(priv->cm.srq)) { if (PTR_ERR(priv->cm.srq) != -ENOSYS) - printk(KERN_WARNING "%s: failed to allocate SRQ, error %ld\n", + pr_warn("%s: failed to allocate SRQ, error %ld\n", priv->ca->name, PTR_ERR(priv->cm.srq)); priv->cm.srq = NULL; return; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 3b96cdaf9a83..10384ea50bed 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -644,7 +644,7 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb, if (netif_queue_stopped(dev)) if (ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP | - IB_CQ_REPORT_MISSED_EVENTS)) + IB_CQ_REPORT_MISSED_EVENTS) < 0) ipoib_warn(priv, "request notify on send CQ failed\n"); rc = post_send(priv, priv->tx_head & (ipoib_sendq_size - 1), @@ -1085,8 +1085,7 @@ static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv) netif_addr_unlock_bh(priv->dev); - err = ib_find_gid(priv->ca, &search_gid, IB_GID_TYPE_IB, - priv->dev, &port, &index); + err = ib_find_gid(priv->ca, &search_gid, priv->dev, &port, &index); netif_addr_lock_bh(priv->dev); @@ -1236,13 +1235,10 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, ipoib_ib_dev_down(dev); if (level == IPOIB_FLUSH_HEAVY) { - rtnl_lock(); if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) ipoib_ib_dev_stop(dev); - result = ipoib_ib_dev_open(dev); - rtnl_unlock(); - if (result) + if (ipoib_ib_dev_open(dev)) return; if (netif_queue_stopped(dev)) @@ -1282,7 +1278,9 @@ void ipoib_ib_dev_flush_heavy(struct work_struct *work) struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, flush_heavy); + rtnl_lock(); __ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY, 0); + rtnl_unlock(); } void ipoib_ib_dev_cleanup(struct net_device *dev) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 12b7f911f0e5..5930c7d9a8fb 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -768,13 +768,30 @@ static void path_rec_completion(int status, if (!status) { struct rdma_ah_attr av; - if (!ib_init_ah_from_path(priv->ca, priv->port, pathrec, &av)) + if (!ib_init_ah_attr_from_path(priv->ca, priv->port, + pathrec, &av)) ah = ipoib_create_ah(dev, priv->pd, &av); } spin_lock_irqsave(&priv->lock, flags); if (!IS_ERR_OR_NULL(ah)) { + /* + * pathrec.dgid is used as the database key from the LLADDR, + * it must remain unchanged even if the SA returns a different + * GID to use in the AH. + */ + if (memcmp(pathrec->dgid.raw, path->pathrec.dgid.raw, + sizeof(union ib_gid))) { + ipoib_dbg( + priv, + "%s got PathRec for gid %pI6 while asked for %pI6\n", + dev->name, pathrec->dgid.raw, + path->pathrec.dgid.raw); + memcpy(pathrec->dgid.raw, path->pathrec.dgid.raw, + sizeof(union ib_gid)); + } + path->pathrec = *pathrec; old_ah = path->ah; @@ -840,6 +857,23 @@ static void path_rec_completion(int status, } } +static void init_path_rec(struct ipoib_dev_priv *priv, struct ipoib_path *path, + void *gid) +{ + path->dev = priv->dev; + + if (rdma_cap_opa_ah(priv->ca, priv->port)) + path->pathrec.rec_type = SA_PATH_REC_TYPE_OPA; + else + path->pathrec.rec_type = SA_PATH_REC_TYPE_IB; + + memcpy(path->pathrec.dgid.raw, gid, sizeof(union ib_gid)); + path->pathrec.sgid = priv->local_gid; + path->pathrec.pkey = cpu_to_be16(priv->pkey); + path->pathrec.numb_path = 1; + path->pathrec.traffic_class = priv->broadcast->mcmember.traffic_class; +} + static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -852,21 +886,11 @@ static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid) if (!path) return NULL; - path->dev = dev; - skb_queue_head_init(&path->queue); INIT_LIST_HEAD(&path->neigh_list); - if (rdma_cap_opa_ah(priv->ca, priv->port)) - path->pathrec.rec_type = SA_PATH_REC_TYPE_OPA; - else - path->pathrec.rec_type = SA_PATH_REC_TYPE_IB; - memcpy(path->pathrec.dgid.raw, gid, sizeof (union ib_gid)); - path->pathrec.sgid = priv->local_gid; - path->pathrec.pkey = cpu_to_be16(priv->pkey); - path->pathrec.numb_path = 1; - path->pathrec.traffic_class = priv->broadcast->mcmember.traffic_class; + init_path_rec(priv, path, gid); return path; } @@ -902,8 +926,8 @@ static int path_rec_start(struct net_device *dev, return 0; } -static void neigh_add_path(struct sk_buff *skb, u8 *daddr, - struct net_device *dev) +static struct ipoib_neigh *neigh_add_path(struct sk_buff *skb, u8 *daddr, + struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); @@ -917,7 +941,15 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr, spin_unlock_irqrestore(&priv->lock, flags); ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); - return; + return NULL; + } + + /* To avoid race condition, make sure that the + * neigh will be added only once. + */ + if (unlikely(!list_empty(&neigh->list))) { + spin_unlock_irqrestore(&priv->lock, flags); + return neigh; } path = __path_find(dev, daddr + 4); @@ -956,7 +988,7 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr, path->ah->last_send = rn->send(dev, skb, path->ah->ah, IPOIB_QPN(daddr)); ipoib_neigh_put(neigh); - return; + return NULL; } } else { neigh->ah = NULL; @@ -973,7 +1005,7 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr, spin_unlock_irqrestore(&priv->lock, flags); ipoib_neigh_put(neigh); - return; + return NULL; err_path: ipoib_neigh_free(neigh); @@ -983,6 +1015,8 @@ err_drop: spin_unlock_irqrestore(&priv->lock, flags); ipoib_neigh_put(neigh); + + return NULL; } static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, @@ -995,6 +1029,10 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, spin_lock_irqsave(&priv->lock, flags); + /* no broadcast means that all paths are (going to be) not valid */ + if (!priv->broadcast) + goto drop_and_unlock; + path = __path_find(dev, phdr->hwaddr + 4); if (!path || !path->valid) { int new_path = 0; @@ -1004,6 +1042,10 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, new_path = 1; } if (path) { + if (!new_path) + /* make sure there is no changes in the existing path record */ + init_path_rec(priv, path, phdr->hwaddr + 4); + if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, phdr->hwaddr); __skb_queue_tail(&path->queue, skb); @@ -1020,8 +1062,7 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, } else __path_add(dev, path); } else { - ++dev->stats.tx_dropped; - dev_kfree_skb_any(skb); + goto drop_and_unlock; } spin_unlock_irqrestore(&priv->lock, flags); @@ -1041,11 +1082,16 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, push_pseudo_header(skb, phdr->hwaddr); __skb_queue_tail(&path->queue, skb); } else { - ++dev->stats.tx_dropped; - dev_kfree_skb_any(skb); + goto drop_and_unlock; } spin_unlock_irqrestore(&priv->lock, flags); + return; + +drop_and_unlock: + ++dev->stats.tx_dropped; + dev_kfree_skb_any(skb); + spin_unlock_irqrestore(&priv->lock, flags); } static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) @@ -1091,8 +1137,9 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) case htons(ETH_P_TIPC): neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (unlikely(!neigh)) { - neigh_add_path(skb, phdr->hwaddr, dev); - return NETDEV_TX_OK; + neigh = neigh_add_path(skb, phdr->hwaddr, dev); + if (likely(!neigh)) + return NETDEV_TX_OK; } break; case htons(ETH_P_ARP): @@ -1663,8 +1710,8 @@ static int ipoib_dev_init_default(struct net_device *dev) priv->tx_ring = vzalloc(ipoib_sendq_size * sizeof *priv->tx_ring); if (!priv->tx_ring) { - printk(KERN_WARNING "%s: failed to allocate TX ring (%d entries)\n", - priv->ca->name, ipoib_sendq_size); + pr_warn("%s: failed to allocate TX ring (%d entries)\n", + priv->ca->name, ipoib_sendq_size); goto out_rx_ring_cleanup; } @@ -2196,16 +2243,17 @@ static struct net_device *ipoib_add_port(const char *format, int result = -ENOMEM; priv = ipoib_intf_alloc(hca, port, format); - if (!priv) + if (!priv) { + pr_warn("%s, %d: ipoib_intf_alloc failed\n", hca->name, port); goto alloc_mem_failed; + } SET_NETDEV_DEV(priv->dev, hca->dev.parent); priv->dev->dev_id = port - 1; result = ib_query_port(hca, port, &attr); if (result) { - printk(KERN_WARNING "%s: ib_query_port %d failed\n", - hca->name, port); + pr_warn("%s: ib_query_port %d failed\n", hca->name, port); goto device_init_failed; } @@ -2220,8 +2268,8 @@ static struct net_device *ipoib_add_port(const char *format, result = ib_query_pkey(hca, port, 0, &priv->pkey); if (result) { - printk(KERN_WARNING "%s: ib_query_pkey port %d failed (ret = %d)\n", - hca->name, port, result); + pr_warn("%s: ib_query_pkey port %d failed (ret = %d)\n", + hca->name, port, result); goto device_init_failed; } @@ -2238,8 +2286,8 @@ static struct net_device *ipoib_add_port(const char *format, result = ib_query_gid(hca, port, 0, &priv->local_gid, NULL); if (result) { - printk(KERN_WARNING "%s: ib_query_gid port %d failed (ret = %d)\n", - hca->name, port, result); + pr_warn("%s: ib_query_gid port %d failed (ret = %d)\n", + hca->name, port, result); goto device_init_failed; } @@ -2249,8 +2297,8 @@ static struct net_device *ipoib_add_port(const char *format, result = ipoib_dev_init(priv->dev, hca, port); if (result) { - printk(KERN_WARNING "%s: failed to initialize port %d (ret = %d)\n", - hca->name, port, result); + pr_warn("%s: failed to initialize port %d (ret = %d)\n", + hca->name, port, result); goto device_init_failed; } @@ -2260,8 +2308,8 @@ static struct net_device *ipoib_add_port(const char *format, result = register_netdev(priv->dev); if (result) { - printk(KERN_WARNING "%s: couldn't register ipoib port %d; error %d\n", - hca->name, port, result); + pr_warn("%s: couldn't register ipoib port %d; error %d\n", + hca->name, port, result); goto register_failed; } @@ -2326,8 +2374,7 @@ static void ipoib_add_one(struct ib_device *device) } if (!count) { - pr_err("Failed to init port, removing it\n"); - ipoib_remove_one(device, dev_list); + kfree(dev_list); return; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 93e149efc1f5..9b3f47ae2016 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -816,7 +816,10 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb) spin_lock_irqsave(&priv->lock, flags); if (!neigh) { neigh = ipoib_neigh_alloc(daddr, dev); - if (neigh) { + /* Make sure that the neigh will be added only + * once to mcast list. + */ + if (neigh && list_empty(&neigh->list)) { kref_get(&mcast->ah->ref); neigh->ah = mcast->ah; list_add_tail(&neigh->list, &mcast->neigh_list); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c index a1ed25422b72..984a88096f39 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c @@ -178,7 +178,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_rx_completion, NULL, priv, &cq_attr); if (IS_ERR(priv->recv_cq)) { - printk(KERN_WARNING "%s: failed to create receive CQ\n", ca->name); + pr_warn("%s: failed to create receive CQ\n", ca->name); goto out_cm_dev_cleanup; } @@ -187,7 +187,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) priv->send_cq = ib_create_cq(priv->ca, ipoib_ib_tx_completion, NULL, priv, &cq_attr); if (IS_ERR(priv->send_cq)) { - printk(KERN_WARNING "%s: failed to create send CQ\n", ca->name); + pr_warn("%s: failed to create send CQ\n", ca->name); goto out_free_recv_cq; } @@ -208,7 +208,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) priv->qp = ib_create_qp(priv->pd, &init_attr); if (IS_ERR(priv->qp)) { - printk(KERN_WARNING "%s: failed to create QP\n", ca->name); + pr_warn("%s: failed to create QP\n", ca->name); goto out_free_send_cq; } diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c index 2a07692007bd..df49c4eb67f7 100644 --- a/drivers/infiniband/ulp/iser/iser_initiator.c +++ b/drivers/infiniband/ulp/iser/iser_initiator.c @@ -142,8 +142,7 @@ iser_prepare_write_cmd(struct iscsi_task *task, hdr->write_va = cpu_to_be64(mem_reg->sge.addr + unsol_sz); } - iser_dbg("Cmd itt:%d, WRITE tags, RKEY:%#.4X " - "VA:%#llX + unsol:%d\n", + iser_dbg("Cmd itt:%d, WRITE tags, RKEY:%#.4X VA:%#llX + unsol:%d\n", task->itt, mem_reg->rkey, (unsigned long long)mem_reg->sge.addr, unsol_sz); } @@ -436,7 +435,7 @@ int iser_send_data_out(struct iscsi_conn *conn, { struct iser_conn *iser_conn = conn->dd_data; struct iscsi_iser_task *iser_task = task->dd_data; - struct iser_tx_desc *tx_desc = NULL; + struct iser_tx_desc *tx_desc; struct iser_mem_reg *mem_reg; unsigned long buf_offset; unsigned long data_seg_len; @@ -452,10 +451,8 @@ int iser_send_data_out(struct iscsi_conn *conn, __func__,(int)itt,(int)data_seg_len,(int)buf_offset); tx_desc = kmem_cache_zalloc(ig.desc_cache, GFP_ATOMIC); - if (tx_desc == NULL) { - iser_err("Failed to alloc desc for post dataout\n"); + if (!tx_desc) return -ENOMEM; - } tx_desc->type = ISCSI_TX_DATAOUT; tx_desc->cqe.done = iser_dataout_comp; @@ -475,8 +472,7 @@ int iser_send_data_out(struct iscsi_conn *conn, tx_desc->num_sge = 2; if (buf_offset + data_seg_len > iser_task->data[ISER_DIR_OUT].data_len) { - iser_err("Offset:%ld & DSL:%ld in Data-Out " - "inconsistent with total len:%ld, itt:%d\n", + iser_err("Offset:%ld & DSL:%ld in Data-Out inconsistent with total len:%ld, itt:%d\n", buf_offset, data_seg_len, iser_task->data[ISER_DIR_OUT].data_len, itt); err = -EINVAL; @@ -614,8 +610,8 @@ iser_check_remote_inv(struct iser_conn *iser_conn, iser_conn, rkey); if (unlikely(!iser_conn->snd_w_inv)) { - iser_err("conn %p: unexpected remote invalidation, " - "terminating connection\n", iser_conn); + iser_err("conn %p: unexpected remote invalidation, terminating connection\n", + iser_conn); return -EPROTO; } diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 720dfb3a1ac2..fff40b097947 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -741,6 +741,7 @@ isert_connect_error(struct rdma_cm_id *cma_id) { struct isert_conn *isert_conn = cma_id->qp->qp_context; + ib_drain_qp(isert_conn->qp); list_del_init(&isert_conn->node); isert_conn->cm_id = NULL; isert_put_conn(isert_conn); @@ -2123,6 +2124,9 @@ isert_rdma_rw_ctx_post(struct isert_cmd *cmd, struct isert_conn *conn, u32 rkey, offset; int ret; + if (cmd->ctx_init_done) + goto rdma_ctx_post; + if (dir == DMA_FROM_DEVICE) { addr = cmd->write_va; rkey = cmd->write_stag; @@ -2150,11 +2154,15 @@ isert_rdma_rw_ctx_post(struct isert_cmd *cmd, struct isert_conn *conn, se_cmd->t_data_sg, se_cmd->t_data_nents, offset, addr, rkey, dir); } + if (ret < 0) { isert_err("Cmd: %p failed to prepare RDMA res\n", cmd); return ret; } + cmd->ctx_init_done = true; + +rdma_ctx_post: ret = rdma_rw_ctx_post(&cmd->rw, conn->qp, port_num, cqe, chain_wr); if (ret < 0) isert_err("Cmd: %p failed to post RDMA res\n", cmd); diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index d6fd248320ae..3b296bac4f60 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -126,6 +126,7 @@ struct isert_cmd { struct rdma_rw_ctx rw; struct work_struct comp_work; struct scatterlist sg; + bool ctx_init_done; }; static inline struct isert_cmd *tx_desc_to_cmd(struct iser_tx_desc *desc) diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c index 4b615c1451e7..15711dcc6f58 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c @@ -710,7 +710,7 @@ vema_get_port(struct opa_vnic_ctrl_port *cport, u8 port_num) /** * opa_vnic_vema_send_trap -- This function sends a trap to the EM - * @cport: pointer to vnic control port + * @adapter: pointer to vnic adapter * @data: pointer to trap data filled by calling function * @lid: issuers lid (encap_slid from vesw_port_info) * diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 972d4b3c5223..b48843833d69 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -41,6 +41,7 @@ #include <linux/random.h> #include <linux/jiffies.h> #include <linux/lockdep.h> +#include <linux/inet.h> #include <rdma/ib_cache.h> #include <linux/atomic.h> @@ -144,7 +145,9 @@ static void srp_remove_one(struct ib_device *device, void *client_data); static void srp_recv_done(struct ib_cq *cq, struct ib_wc *wc); static void srp_handle_qp_err(struct ib_cq *cq, struct ib_wc *wc, const char *opname); -static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event); +static int srp_ib_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event); +static int srp_rdma_cm_handler(struct rdma_cm_id *cm_id, + struct rdma_cm_event *event); static struct scsi_transport_template *ib_srp_transport_template; static struct workqueue_struct *srp_remove_wq; @@ -265,8 +268,8 @@ static void srp_qp_event(struct ib_event *event, void *context) ib_event_msg(event->event), event->event); } -static int srp_init_qp(struct srp_target_port *target, - struct ib_qp *qp) +static int srp_init_ib_qp(struct srp_target_port *target, + struct ib_qp *qp) { struct ib_qp_attr *attr; int ret; @@ -277,7 +280,7 @@ static int srp_init_qp(struct srp_target_port *target, ret = ib_find_cached_pkey(target->srp_host->srp_dev->dev, target->srp_host->port, - be16_to_cpu(target->pkey), + be16_to_cpu(target->ib_cm.pkey), &attr->pkey_index); if (ret) goto out; @@ -298,32 +301,110 @@ out: return ret; } -static int srp_new_cm_id(struct srp_rdma_ch *ch) +static int srp_new_ib_cm_id(struct srp_rdma_ch *ch) { struct srp_target_port *target = ch->target; struct ib_cm_id *new_cm_id; new_cm_id = ib_create_cm_id(target->srp_host->srp_dev->dev, - srp_cm_handler, ch); + srp_ib_cm_handler, ch); if (IS_ERR(new_cm_id)) return PTR_ERR(new_cm_id); - if (ch->cm_id) - ib_destroy_cm_id(ch->cm_id); - ch->cm_id = new_cm_id; + if (ch->ib_cm.cm_id) + ib_destroy_cm_id(ch->ib_cm.cm_id); + ch->ib_cm.cm_id = new_cm_id; if (rdma_cap_opa_ah(target->srp_host->srp_dev->dev, target->srp_host->port)) - ch->path.rec_type = SA_PATH_REC_TYPE_OPA; + ch->ib_cm.path.rec_type = SA_PATH_REC_TYPE_OPA; else - ch->path.rec_type = SA_PATH_REC_TYPE_IB; - ch->path.sgid = target->sgid; - ch->path.dgid = target->orig_dgid; - ch->path.pkey = target->pkey; - ch->path.service_id = target->service_id; + ch->ib_cm.path.rec_type = SA_PATH_REC_TYPE_IB; + ch->ib_cm.path.sgid = target->sgid; + ch->ib_cm.path.dgid = target->ib_cm.orig_dgid; + ch->ib_cm.path.pkey = target->ib_cm.pkey; + ch->ib_cm.path.service_id = target->ib_cm.service_id; return 0; } +static const char *inet_ntop(const void *sa, char *dst, unsigned int size) +{ + switch (((struct sockaddr *)sa)->sa_family) { + case AF_INET: + snprintf(dst, size, "%pI4", + &((struct sockaddr_in *)sa)->sin_addr); + break; + case AF_INET6: + snprintf(dst, size, "%pI6", + &((struct sockaddr_in6 *)sa)->sin6_addr); + break; + default: + snprintf(dst, size, "???"); + break; + } + return dst; +} + +static int srp_new_rdma_cm_id(struct srp_rdma_ch *ch) +{ + struct srp_target_port *target = ch->target; + struct rdma_cm_id *new_cm_id; + char src_addr[64], dst_addr[64]; + int ret; + + new_cm_id = rdma_create_id(target->net, srp_rdma_cm_handler, ch, + RDMA_PS_TCP, IB_QPT_RC); + if (IS_ERR(new_cm_id)) { + ret = PTR_ERR(new_cm_id); + new_cm_id = NULL; + goto out; + } + + init_completion(&ch->done); + ret = rdma_resolve_addr(new_cm_id, target->rdma_cm.src_specified ? + (struct sockaddr *)&target->rdma_cm.src : NULL, + (struct sockaddr *)&target->rdma_cm.dst, + SRP_PATH_REC_TIMEOUT_MS); + if (ret) { + pr_err("No route available from %s to %s (%d)\n", + target->rdma_cm.src_specified ? + inet_ntop(&target->rdma_cm.src, src_addr, + sizeof(src_addr)) : "(any)", + inet_ntop(&target->rdma_cm.dst, dst_addr, + sizeof(dst_addr)), + ret); + goto out; + } + ret = wait_for_completion_interruptible(&ch->done); + if (ret < 0) + goto out; + + ret = ch->status; + if (ret) { + pr_err("Resolving address %s failed (%d)\n", + inet_ntop(&target->rdma_cm.dst, dst_addr, + sizeof(dst_addr)), + ret); + goto out; + } + + swap(ch->rdma_cm.cm_id, new_cm_id); + +out: + if (new_cm_id) + rdma_destroy_id(new_cm_id); + + return ret; +} + +static int srp_new_cm_id(struct srp_rdma_ch *ch) +{ + struct srp_target_port *target = ch->target; + + return target->using_rdma_cm ? srp_new_rdma_cm_id(ch) : + srp_new_ib_cm_id(ch); +} + static struct ib_fmr_pool *srp_alloc_fmr_pool(struct srp_target_port *target) { struct srp_device *dev = target->srp_host->srp_dev; @@ -521,16 +602,25 @@ static int srp_create_ch_ib(struct srp_rdma_ch *ch) init_attr->send_cq = send_cq; init_attr->recv_cq = recv_cq; - qp = ib_create_qp(dev->pd, init_attr); - if (IS_ERR(qp)) { - ret = PTR_ERR(qp); + if (target->using_rdma_cm) { + ret = rdma_create_qp(ch->rdma_cm.cm_id, dev->pd, init_attr); + qp = ch->rdma_cm.cm_id->qp; + } else { + qp = ib_create_qp(dev->pd, init_attr); + if (!IS_ERR(qp)) { + ret = srp_init_ib_qp(target, qp); + if (ret) + ib_destroy_qp(qp); + } else { + ret = PTR_ERR(qp); + } + } + if (ret) { + pr_err("QP creation failed for dev %s: %d\n", + dev_name(&dev->dev->dev), ret); goto err_send_cq; } - ret = srp_init_qp(target, qp); - if (ret) - goto err_qp; - if (dev->use_fast_reg) { fr_pool = srp_alloc_fr_pool(target); if (IS_ERR(fr_pool)) { @@ -574,7 +664,10 @@ static int srp_create_ch_ib(struct srp_rdma_ch *ch) return 0; err_qp: - ib_destroy_qp(qp); + if (target->using_rdma_cm) + rdma_destroy_qp(ch->rdma_cm.cm_id); + else + ib_destroy_qp(qp); err_send_cq: ib_free_cq(send_cq); @@ -600,9 +693,16 @@ static void srp_free_ch_ib(struct srp_target_port *target, if (!ch->target) return; - if (ch->cm_id) { - ib_destroy_cm_id(ch->cm_id); - ch->cm_id = NULL; + if (target->using_rdma_cm) { + if (ch->rdma_cm.cm_id) { + rdma_destroy_id(ch->rdma_cm.cm_id); + ch->rdma_cm.cm_id = NULL; + } + } else { + if (ch->ib_cm.cm_id) { + ib_destroy_cm_id(ch->ib_cm.cm_id); + ch->ib_cm.cm_id = NULL; + } } /* If srp_new_cm_id() succeeded but srp_create_ch_ib() not, return. */ @@ -658,16 +758,16 @@ static void srp_path_rec_completion(int status, shost_printk(KERN_ERR, target->scsi_host, PFX "Got failed path rec status %d\n", status); else - ch->path = *pathrec; + ch->ib_cm.path = *pathrec; complete(&ch->done); } -static int srp_lookup_path(struct srp_rdma_ch *ch) +static int srp_ib_lookup_path(struct srp_rdma_ch *ch) { struct srp_target_port *target = ch->target; int ret = -ENODEV; - ch->path.numb_path = 1; + ch->ib_cm.path.numb_path = 1; init_completion(&ch->done); @@ -678,10 +778,10 @@ static int srp_lookup_path(struct srp_rdma_ch *ch) if (!scsi_host_get(target->scsi_host)) goto out; - ch->path_query_id = ib_sa_path_rec_get(&srp_sa_client, + ch->ib_cm.path_query_id = ib_sa_path_rec_get(&srp_sa_client, target->srp_host->srp_dev->dev, target->srp_host->port, - &ch->path, + &ch->ib_cm.path, IB_SA_PATH_REC_SERVICE_ID | IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID | @@ -690,8 +790,8 @@ static int srp_lookup_path(struct srp_rdma_ch *ch) SRP_PATH_REC_TIMEOUT_MS, GFP_KERNEL, srp_path_rec_completion, - ch, &ch->path_query); - ret = ch->path_query_id; + ch, &ch->ib_cm.path_query); + ret = ch->ib_cm.path_query_id; if (ret < 0) goto put; @@ -702,7 +802,10 @@ static int srp_lookup_path(struct srp_rdma_ch *ch) ret = ch->status; if (ret < 0) shost_printk(KERN_WARNING, target->scsi_host, - PFX "Path record query failed\n"); + PFX "Path record query failed: sgid %pI6, dgid %pI6, pkey %#04x, service_id %#16llx\n", + ch->ib_cm.path.sgid.raw, ch->ib_cm.path.dgid.raw, + be16_to_cpu(target->ib_cm.pkey), + be64_to_cpu(target->ib_cm.service_id)); put: scsi_host_put(target->scsi_host); @@ -711,6 +814,34 @@ out: return ret; } +static int srp_rdma_lookup_path(struct srp_rdma_ch *ch) +{ + struct srp_target_port *target = ch->target; + int ret; + + init_completion(&ch->done); + + ret = rdma_resolve_route(ch->rdma_cm.cm_id, SRP_PATH_REC_TIMEOUT_MS); + if (ret) + return ret; + + wait_for_completion_interruptible(&ch->done); + + if (ch->status != 0) + shost_printk(KERN_WARNING, target->scsi_host, + PFX "Path resolution failed\n"); + + return ch->status; +} + +static int srp_lookup_path(struct srp_rdma_ch *ch) +{ + struct srp_target_port *target = ch->target; + + return target->using_rdma_cm ? srp_rdma_lookup_path(ch) : + srp_ib_lookup_path(ch); +} + static u8 srp_get_subnet_timeout(struct srp_host *host) { struct ib_port_attr attr; @@ -732,48 +863,76 @@ static int srp_send_req(struct srp_rdma_ch *ch, bool multich) { struct srp_target_port *target = ch->target; struct { - struct ib_cm_req_param param; - struct srp_login_req priv; + struct rdma_conn_param rdma_param; + struct srp_login_req_rdma rdma_req; + struct ib_cm_req_param ib_param; + struct srp_login_req ib_req; } *req = NULL; + char *ipi, *tpi; int status; - u8 subnet_timeout; - - subnet_timeout = srp_get_subnet_timeout(target->srp_host); req = kzalloc(sizeof *req, GFP_KERNEL); if (!req) return -ENOMEM; - req->param.primary_path = &ch->path; - req->param.alternate_path = NULL; - req->param.service_id = target->service_id; - req->param.qp_num = ch->qp->qp_num; - req->param.qp_type = ch->qp->qp_type; - req->param.private_data = &req->priv; - req->param.private_data_len = sizeof req->priv; - req->param.flow_control = 1; - - get_random_bytes(&req->param.starting_psn, 4); - req->param.starting_psn &= 0xffffff; + req->ib_param.flow_control = 1; + req->ib_param.retry_count = target->tl_retry_count; /* * Pick some arbitrary defaults here; we could make these * module parameters if anyone cared about setting them. */ - req->param.responder_resources = 4; - req->param.remote_cm_response_timeout = subnet_timeout + 2; - req->param.local_cm_response_timeout = subnet_timeout + 2; - req->param.retry_count = target->tl_retry_count; - req->param.rnr_retry_count = 7; - req->param.max_cm_retries = 15; - - req->priv.opcode = SRP_LOGIN_REQ; - req->priv.tag = 0; - req->priv.req_it_iu_len = cpu_to_be32(target->max_iu_len); - req->priv.req_buf_fmt = cpu_to_be16(SRP_BUF_FORMAT_DIRECT | + req->ib_param.responder_resources = 4; + req->ib_param.rnr_retry_count = 7; + req->ib_param.max_cm_retries = 15; + + req->ib_req.opcode = SRP_LOGIN_REQ; + req->ib_req.tag = 0; + req->ib_req.req_it_iu_len = cpu_to_be32(target->max_iu_len); + req->ib_req.req_buf_fmt = cpu_to_be16(SRP_BUF_FORMAT_DIRECT | SRP_BUF_FORMAT_INDIRECT); - req->priv.req_flags = (multich ? SRP_MULTICHAN_MULTI : - SRP_MULTICHAN_SINGLE); + req->ib_req.req_flags = (multich ? SRP_MULTICHAN_MULTI : + SRP_MULTICHAN_SINGLE); + + if (target->using_rdma_cm) { + req->rdma_param.flow_control = req->ib_param.flow_control; + req->rdma_param.responder_resources = + req->ib_param.responder_resources; + req->rdma_param.initiator_depth = req->ib_param.initiator_depth; + req->rdma_param.retry_count = req->ib_param.retry_count; + req->rdma_param.rnr_retry_count = req->ib_param.rnr_retry_count; + req->rdma_param.private_data = &req->rdma_req; + req->rdma_param.private_data_len = sizeof(req->rdma_req); + + req->rdma_req.opcode = req->ib_req.opcode; + req->rdma_req.tag = req->ib_req.tag; + req->rdma_req.req_it_iu_len = req->ib_req.req_it_iu_len; + req->rdma_req.req_buf_fmt = req->ib_req.req_buf_fmt; + req->rdma_req.req_flags = req->ib_req.req_flags; + + ipi = req->rdma_req.initiator_port_id; + tpi = req->rdma_req.target_port_id; + } else { + u8 subnet_timeout; + + subnet_timeout = srp_get_subnet_timeout(target->srp_host); + + req->ib_param.primary_path = &ch->ib_cm.path; + req->ib_param.alternate_path = NULL; + req->ib_param.service_id = target->ib_cm.service_id; + get_random_bytes(&req->ib_param.starting_psn, 4); + req->ib_param.starting_psn &= 0xffffff; + req->ib_param.qp_num = ch->qp->qp_num; + req->ib_param.qp_type = ch->qp->qp_type; + req->ib_param.local_cm_response_timeout = subnet_timeout + 2; + req->ib_param.remote_cm_response_timeout = subnet_timeout + 2; + req->ib_param.private_data = &req->ib_req; + req->ib_param.private_data_len = sizeof(req->ib_req); + + ipi = req->ib_req.initiator_port_id; + tpi = req->ib_req.target_port_id; + } + /* * In the published SRP specification (draft rev. 16a), the * port identifier format is 8 bytes of ID extension followed @@ -784,19 +943,15 @@ static int srp_send_req(struct srp_rdma_ch *ch, bool multich) * recognized by the I/O Class they report. */ if (target->io_class == SRP_REV10_IB_IO_CLASS) { - memcpy(req->priv.initiator_port_id, - &target->sgid.global.interface_id, 8); - memcpy(req->priv.initiator_port_id + 8, - &target->initiator_ext, 8); - memcpy(req->priv.target_port_id, &target->ioc_guid, 8); - memcpy(req->priv.target_port_id + 8, &target->id_ext, 8); + memcpy(ipi, &target->sgid.global.interface_id, 8); + memcpy(ipi + 8, &target->initiator_ext, 8); + memcpy(tpi, &target->ioc_guid, 8); + memcpy(tpi + 8, &target->id_ext, 8); } else { - memcpy(req->priv.initiator_port_id, - &target->initiator_ext, 8); - memcpy(req->priv.initiator_port_id + 8, - &target->sgid.global.interface_id, 8); - memcpy(req->priv.target_port_id, &target->id_ext, 8); - memcpy(req->priv.target_port_id + 8, &target->ioc_guid, 8); + memcpy(ipi, &target->initiator_ext, 8); + memcpy(ipi + 8, &target->sgid.global.interface_id, 8); + memcpy(tpi, &target->id_ext, 8); + memcpy(tpi + 8, &target->ioc_guid, 8); } /* @@ -809,12 +964,14 @@ static int srp_send_req(struct srp_rdma_ch *ch, bool multich) PFX "Topspin/Cisco initiator port ID workaround " "activated for target GUID %016llx\n", 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); + memset(ipi, 0, 8); + memcpy(ipi + 8, &target->srp_host->srp_dev->dev->node_guid, 8); } - status = ib_send_cm_req(ch->cm_id, &req->param); + if (target->using_rdma_cm) + status = rdma_connect(ch->rdma_cm.cm_id, &req->rdma_param); + else + status = ib_send_cm_req(ch->ib_cm.cm_id, &req->ib_param); kfree(req); @@ -841,14 +998,23 @@ static bool srp_queue_remove_work(struct srp_target_port *target) static void srp_disconnect_target(struct srp_target_port *target) { struct srp_rdma_ch *ch; - int i; + int i, ret; /* XXX should send SRP_I_LOGOUT request */ 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)) { + ret = 0; + if (target->using_rdma_cm) { + if (ch->rdma_cm.cm_id) + rdma_disconnect(ch->rdma_cm.cm_id); + } else { + if (ch->ib_cm.cm_id) + ret = ib_send_cm_dreq(ch->ib_cm.cm_id, + NULL, 0); + } + if (ret < 0) { shost_printk(KERN_DEBUG, target->scsi_host, PFX "Sending CM DREQ failed\n"); } @@ -962,6 +1128,7 @@ static void srp_remove_target(struct srp_target_port *target) scsi_remove_host(target->scsi_host); srp_stop_rport_timers(target->rport); srp_disconnect_target(target); + kobj_ns_drop(KOBJ_NS_TYPE_NET, target->net); for (i = 0; i < target->ch_count; i++) { ch = &target->ch[i]; srp_free_ch_ib(target, ch); @@ -2349,7 +2516,7 @@ static void srp_cm_rep_handler(struct ib_cm_id *cm_id, struct srp_target_port *target = ch->target; struct ib_qp_attr *qp_attr = NULL; int attr_mask = 0; - int ret; + int ret = 0; int i; if (lrsp->opcode == SRP_LOGIN_RSP) { @@ -2379,40 +2546,42 @@ static void srp_cm_rep_handler(struct ib_cm_id *cm_id, goto error; } - ret = -ENOMEM; - qp_attr = kmalloc(sizeof *qp_attr, GFP_KERNEL); - if (!qp_attr) - goto error; - - qp_attr->qp_state = IB_QPS_RTR; - ret = ib_cm_init_qp_attr(cm_id, qp_attr, &attr_mask); - if (ret) - goto error_free; - - ret = ib_modify_qp(ch->qp, qp_attr, attr_mask); - if (ret) - goto error_free; - for (i = 0; i < target->queue_size; i++) { struct srp_iu *iu = ch->rx_ring[i]; ret = srp_post_recv(ch, iu); if (ret) - goto error_free; + goto error; } - qp_attr->qp_state = IB_QPS_RTS; - ret = ib_cm_init_qp_attr(cm_id, qp_attr, &attr_mask); - if (ret) - goto error_free; + if (!target->using_rdma_cm) { + ret = -ENOMEM; + qp_attr = kmalloc(sizeof(*qp_attr), GFP_KERNEL); + if (!qp_attr) + goto error; - target->rq_tmo_jiffies = srp_compute_rq_tmo(qp_attr, attr_mask); + qp_attr->qp_state = IB_QPS_RTR; + ret = ib_cm_init_qp_attr(cm_id, qp_attr, &attr_mask); + if (ret) + goto error_free; - ret = ib_modify_qp(ch->qp, qp_attr, attr_mask); - if (ret) - goto error_free; + ret = ib_modify_qp(ch->qp, qp_attr, attr_mask); + if (ret) + goto error_free; - ret = ib_send_cm_rtu(cm_id, NULL, 0); + qp_attr->qp_state = IB_QPS_RTS; + ret = ib_cm_init_qp_attr(cm_id, qp_attr, &attr_mask); + if (ret) + goto error_free; + + target->rq_tmo_jiffies = srp_compute_rq_tmo(qp_attr, attr_mask); + + ret = ib_modify_qp(ch->qp, qp_attr, attr_mask); + if (ret) + goto error_free; + + ret = ib_send_cm_rtu(cm_id, NULL, 0); + } error_free: kfree(qp_attr); @@ -2421,41 +2590,43 @@ error: ch->status = ret; } -static void srp_cm_rej_handler(struct ib_cm_id *cm_id, - struct ib_cm_event *event, - struct srp_rdma_ch *ch) +static void srp_ib_cm_rej_handler(struct ib_cm_id *cm_id, + struct ib_cm_event *event, + struct srp_rdma_ch *ch) { struct srp_target_port *target = ch->target; struct Scsi_Host *shost = target->scsi_host; struct ib_class_port_info *cpi; int opcode; + u16 dlid; switch (event->param.rej_rcvd.reason) { case IB_CM_REJ_PORT_CM_REDIRECT: cpi = event->param.rej_rcvd.ari; - sa_path_set_dlid(&ch->path, ntohs(cpi->redirect_lid)); - ch->path.pkey = cpi->redirect_pkey; + dlid = be16_to_cpu(cpi->redirect_lid); + sa_path_set_dlid(&ch->ib_cm.path, dlid); + ch->ib_cm.path.pkey = cpi->redirect_pkey; cm_id->remote_cm_qpn = be32_to_cpu(cpi->redirect_qp) & 0x00ffffff; - memcpy(ch->path.dgid.raw, cpi->redirect_gid, 16); + memcpy(ch->ib_cm.path.dgid.raw, cpi->redirect_gid, 16); - ch->status = sa_path_get_dlid(&ch->path) ? - SRP_DLID_REDIRECT : SRP_PORT_REDIRECT; + ch->status = dlid ? SRP_DLID_REDIRECT : SRP_PORT_REDIRECT; break; case IB_CM_REJ_PORT_REDIRECT: if (srp_target_is_topspin(target)) { + union ib_gid *dgid = &ch->ib_cm.path.dgid; + /* * Topspin/Cisco SRP gateways incorrectly send * reject reason code 25 when they mean 24 * (port redirect). */ - memcpy(ch->path.dgid.raw, - event->param.rej_rcvd.ari, 16); + memcpy(dgid->raw, event->param.rej_rcvd.ari, 16); shost_printk(KERN_DEBUG, shost, PFX "Topspin/Cisco redirect to target port GID %016llx%016llx\n", - be64_to_cpu(ch->path.dgid.global.subnet_prefix), - be64_to_cpu(ch->path.dgid.global.interface_id)); + be64_to_cpu(dgid->global.subnet_prefix), + be64_to_cpu(dgid->global.interface_id)); ch->status = SRP_PORT_REDIRECT; } else { @@ -2484,7 +2655,8 @@ static void srp_cm_rej_handler(struct ib_cm_id *cm_id, shost_printk(KERN_WARNING, shost, PFX "SRP LOGIN from %pI6 to %pI6 REJECTED, reason 0x%08x\n", target->sgid.raw, - target->orig_dgid.raw, reason); + target->ib_cm.orig_dgid.raw, + reason); } else shost_printk(KERN_WARNING, shost, " REJ reason: IB_CM_REJ_CONSUMER_DEFINED," @@ -2504,7 +2676,7 @@ static void srp_cm_rej_handler(struct ib_cm_id *cm_id, } } -static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event) +static int srp_ib_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event) { struct srp_rdma_ch *ch = cm_id->context; struct srp_target_port *target = ch->target; @@ -2527,7 +2699,7 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event) shost_printk(KERN_DEBUG, target->scsi_host, PFX "REJ received\n"); comp = 1; - srp_cm_rej_handler(cm_id, event, ch); + srp_ib_cm_rej_handler(cm_id, event, ch); break; case IB_CM_DREQ_RECEIVED: @@ -2565,6 +2737,135 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event) return 0; } +static void srp_rdma_cm_rej_handler(struct srp_rdma_ch *ch, + struct rdma_cm_event *event) +{ + struct srp_target_port *target = ch->target; + struct Scsi_Host *shost = target->scsi_host; + int opcode; + + switch (event->status) { + case IB_CM_REJ_DUPLICATE_LOCAL_COMM_ID: + shost_printk(KERN_WARNING, shost, + " REJ reason: IB_CM_REJ_DUPLICATE_LOCAL_COMM_ID\n"); + ch->status = -ECONNRESET; + break; + + case IB_CM_REJ_CONSUMER_DEFINED: + opcode = *(u8 *) event->param.conn.private_data; + if (opcode == SRP_LOGIN_REJ) { + struct srp_login_rej *rej = + (struct srp_login_rej *) + event->param.conn.private_data; + u32 reason = be32_to_cpu(rej->reason); + + if (reason == SRP_LOGIN_REJ_REQ_IT_IU_LENGTH_TOO_LARGE) + shost_printk(KERN_WARNING, shost, + PFX "SRP_LOGIN_REJ: requested max_it_iu_len too large\n"); + else + shost_printk(KERN_WARNING, shost, + PFX "SRP LOGIN REJECTED, reason 0x%08x\n", reason); + } else { + shost_printk(KERN_WARNING, shost, + " REJ reason: IB_CM_REJ_CONSUMER_DEFINED, opcode 0x%02x\n", + opcode); + } + ch->status = -ECONNRESET; + break; + + case IB_CM_REJ_STALE_CONN: + shost_printk(KERN_WARNING, shost, + " REJ reason: stale connection\n"); + ch->status = SRP_STALE_CONN; + break; + + default: + shost_printk(KERN_WARNING, shost, " REJ reason 0x%x\n", + event->status); + ch->status = -ECONNRESET; + break; + } +} + +static int srp_rdma_cm_handler(struct rdma_cm_id *cm_id, + struct rdma_cm_event *event) +{ + struct srp_rdma_ch *ch = cm_id->context; + struct srp_target_port *target = ch->target; + int comp = 0; + + switch (event->event) { + case RDMA_CM_EVENT_ADDR_RESOLVED: + ch->status = 0; + comp = 1; + break; + + case RDMA_CM_EVENT_ADDR_ERROR: + ch->status = -ENXIO; + comp = 1; + break; + + case RDMA_CM_EVENT_ROUTE_RESOLVED: + ch->status = 0; + comp = 1; + break; + + case RDMA_CM_EVENT_ROUTE_ERROR: + case RDMA_CM_EVENT_UNREACHABLE: + ch->status = -EHOSTUNREACH; + comp = 1; + break; + + case RDMA_CM_EVENT_CONNECT_ERROR: + shost_printk(KERN_DEBUG, target->scsi_host, + PFX "Sending CM REQ failed\n"); + comp = 1; + ch->status = -ECONNRESET; + break; + + case RDMA_CM_EVENT_ESTABLISHED: + comp = 1; + srp_cm_rep_handler(NULL, event->param.conn.private_data, ch); + break; + + case RDMA_CM_EVENT_REJECTED: + shost_printk(KERN_DEBUG, target->scsi_host, PFX "REJ received\n"); + comp = 1; + + srp_rdma_cm_rej_handler(ch, event); + break; + + case RDMA_CM_EVENT_DISCONNECTED: + if (ch->connected) { + shost_printk(KERN_WARNING, target->scsi_host, + PFX "received DREQ\n"); + rdma_disconnect(ch->rdma_cm.cm_id); + comp = 1; + ch->status = 0; + queue_work(system_long_wq, &target->tl_err_work); + } + break; + + case RDMA_CM_EVENT_TIMEWAIT_EXIT: + shost_printk(KERN_ERR, target->scsi_host, + PFX "connection closed\n"); + + comp = 1; + ch->status = 0; + break; + + default: + shost_printk(KERN_WARNING, target->scsi_host, + PFX "Unhandled CM event %d\n", event->event); + break; + } + + if (comp) + complete(&ch->done); + + return 0; +} + /** * srp_change_queue_depth - setting device queue depth * @sdev: scsi device struct @@ -2717,6 +3018,16 @@ static int srp_reset_host(struct scsi_cmnd *scmnd) return srp_reconnect_rport(target->rport) == 0 ? SUCCESS : FAILED; } +static int srp_target_alloc(struct scsi_target *starget) +{ + struct Scsi_Host *shost = dev_to_shost(starget->dev.parent); + struct srp_target_port *target = host_to_target(shost); + + if (target->target_can_queue) + starget->can_queue = target->target_can_queue; + return 0; +} + static int srp_slave_alloc(struct scsi_device *sdev) { struct Scsi_Host *shost = sdev->host; @@ -2766,7 +3077,10 @@ 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", be64_to_cpu(target->service_id)); + if (target->using_rdma_cm) + return -ENOENT; + return sprintf(buf, "0x%016llx\n", + be64_to_cpu(target->ib_cm.service_id)); } static ssize_t show_pkey(struct device *dev, struct device_attribute *attr, @@ -2774,7 +3088,9 @@ static ssize_t show_pkey(struct device *dev, struct device_attribute *attr, { struct srp_target_port *target = host_to_target(class_to_shost(dev)); - return sprintf(buf, "0x%04x\n", be16_to_cpu(target->pkey)); + if (target->using_rdma_cm) + return -ENOENT; + return sprintf(buf, "0x%04x\n", be16_to_cpu(target->ib_cm.pkey)); } static ssize_t show_sgid(struct device *dev, struct device_attribute *attr, @@ -2791,7 +3107,9 @@ static ssize_t show_dgid(struct device *dev, struct device_attribute *attr, struct srp_target_port *target = host_to_target(class_to_shost(dev)); struct srp_rdma_ch *ch = &target->ch[0]; - return sprintf(buf, "%pI6\n", ch->path.dgid.raw); + if (target->using_rdma_cm) + return -ENOENT; + return sprintf(buf, "%pI6\n", ch->ib_cm.path.dgid.raw); } static ssize_t show_orig_dgid(struct device *dev, @@ -2799,7 +3117,9 @@ static ssize_t show_orig_dgid(struct device *dev, { struct srp_target_port *target = host_to_target(class_to_shost(dev)); - return sprintf(buf, "%pI6\n", target->orig_dgid.raw); + if (target->using_rdma_cm) + return -ENOENT; + return sprintf(buf, "%pI6\n", target->ib_cm.orig_dgid.raw); } static ssize_t show_req_lim(struct device *dev, @@ -2921,6 +3241,7 @@ static struct scsi_host_template srp_template = { .module = THIS_MODULE, .name = "InfiniBand SRP initiator", .proc_name = DRV_NAME, + .target_alloc = srp_target_alloc, .slave_alloc = srp_slave_alloc, .slave_configure = srp_slave_configure, .info = srp_target_info, @@ -3044,6 +3365,9 @@ static bool srp_conn_unique(struct srp_host *host, if (t != target && target->id_ext == t->id_ext && target->ioc_guid == t->ioc_guid && + (!target->using_rdma_cm || + memcmp(&target->rdma_cm.dst, &t->rdma_cm.dst, + sizeof(target->rdma_cm.dst)) == 0) && target->initiator_ext == t->initiator_ext) { ret = false; break; @@ -3060,6 +3384,9 @@ out: * * id_ext=<SRP ID ext>,ioc_guid=<SRP IOC GUID>,dgid=<dest GID>, * pkey=<P_Key>,service_id=<service ID> + * or + * id_ext=<SRP ID ext>,ioc_guid=<SRP IOC GUID>, + * [src=<IPv4 address>,]dest=<IPv4 address>:<port number> * * to the add_target sysfs attribute. */ @@ -3080,11 +3407,20 @@ enum { SRP_OPT_COMP_VECTOR = 1 << 12, SRP_OPT_TL_RETRY_COUNT = 1 << 13, SRP_OPT_QUEUE_SIZE = 1 << 14, - SRP_OPT_ALL = (SRP_OPT_ID_EXT | - SRP_OPT_IOC_GUID | - SRP_OPT_DGID | - SRP_OPT_PKEY | - SRP_OPT_SERVICE_ID), + SRP_OPT_IP_SRC = 1 << 15, + SRP_OPT_IP_DEST = 1 << 16, + SRP_OPT_TARGET_CAN_QUEUE= 1 << 17, +}; + +static unsigned int srp_opt_mandatory[] = { + SRP_OPT_ID_EXT | + SRP_OPT_IOC_GUID | + SRP_OPT_DGID | + SRP_OPT_PKEY | + SRP_OPT_SERVICE_ID, + SRP_OPT_ID_EXT | + SRP_OPT_IOC_GUID | + SRP_OPT_IP_DEST, }; static const match_table_t srp_opt_tokens = { @@ -3095,6 +3431,7 @@ static const match_table_t srp_opt_tokens = { { SRP_OPT_SERVICE_ID, "service_id=%s" }, { SRP_OPT_MAX_SECT, "max_sect=%d" }, { SRP_OPT_MAX_CMD_PER_LUN, "max_cmd_per_lun=%d" }, + { SRP_OPT_TARGET_CAN_QUEUE, "target_can_queue=%d" }, { SRP_OPT_IO_CLASS, "io_class=%x" }, { SRP_OPT_INITIATOR_EXT, "initiator_ext=%s" }, { SRP_OPT_CMD_SG_ENTRIES, "cmd_sg_entries=%u" }, @@ -3103,15 +3440,33 @@ static const match_table_t srp_opt_tokens = { { SRP_OPT_COMP_VECTOR, "comp_vector=%u" }, { SRP_OPT_TL_RETRY_COUNT, "tl_retry_count=%u" }, { SRP_OPT_QUEUE_SIZE, "queue_size=%d" }, + { SRP_OPT_IP_SRC, "src=%s" }, + { SRP_OPT_IP_DEST, "dest=%s" }, { SRP_OPT_ERR, NULL } }; -static int srp_parse_options(const char *buf, struct srp_target_port *target) +static int srp_parse_in(struct net *net, struct sockaddr_storage *sa, + const char *addr_port_str) +{ + char *addr = kstrdup(addr_port_str, GFP_KERNEL); + char *port_str = addr; + int ret; + + if (!addr) + return -ENOMEM; + strsep(&port_str, ":"); + ret = inet_pton_with_scope(net, AF_UNSPEC, addr, port_str, sa); + kfree(addr); + return ret; +} + +static int srp_parse_options(struct net *net, const char *buf, + struct srp_target_port *target) { char *options, *sep_opt; char *p; - char dgid[3]; substring_t args[MAX_OPT_ARGS]; + unsigned long long ull; int opt_mask = 0; int token; int ret = -EINVAL; @@ -3136,7 +3491,13 @@ static int srp_parse_options(const char *buf, struct srp_target_port *target) ret = -ENOMEM; goto out; } - target->id_ext = cpu_to_be64(simple_strtoull(p, NULL, 16)); + ret = kstrtoull(p, 16, &ull); + if (ret) { + pr_warn("invalid id_ext parameter '%s'\n", p); + kfree(p); + goto out; + } + target->id_ext = cpu_to_be64(ull); kfree(p); break; @@ -3146,7 +3507,13 @@ static int srp_parse_options(const char *buf, struct srp_target_port *target) ret = -ENOMEM; goto out; } - target->ioc_guid = cpu_to_be64(simple_strtoull(p, NULL, 16)); + ret = kstrtoull(p, 16, &ull); + if (ret) { + pr_warn("invalid ioc_guid parameter '%s'\n", p); + kfree(p); + goto out; + } + target->ioc_guid = cpu_to_be64(ull); kfree(p); break; @@ -3162,16 +3529,10 @@ static int srp_parse_options(const char *buf, struct srp_target_port *target) goto out; } - for (i = 0; i < 16; ++i) { - strlcpy(dgid, p + i * 2, sizeof(dgid)); - if (sscanf(dgid, "%hhx", - &target->orig_dgid.raw[i]) < 1) { - ret = -EINVAL; - kfree(p); - goto out; - } - } + ret = hex2bin(target->ib_cm.orig_dgid.raw, p, 16); kfree(p); + if (ret < 0) + goto out; break; case SRP_OPT_PKEY: @@ -3179,7 +3540,7 @@ static int srp_parse_options(const char *buf, struct srp_target_port *target) pr_warn("bad P_Key parameter '%s'\n", p); goto out; } - target->pkey = cpu_to_be16(token); + target->ib_cm.pkey = cpu_to_be16(token); break; case SRP_OPT_SERVICE_ID: @@ -3188,7 +3549,45 @@ static int srp_parse_options(const char *buf, struct srp_target_port *target) ret = -ENOMEM; goto out; } - target->service_id = cpu_to_be64(simple_strtoull(p, NULL, 16)); + ret = kstrtoull(p, 16, &ull); + if (ret) { + pr_warn("bad service_id parameter '%s'\n", p); + kfree(p); + goto out; + } + target->ib_cm.service_id = cpu_to_be64(ull); + kfree(p); + break; + + case SRP_OPT_IP_SRC: + p = match_strdup(args); + if (!p) { + ret = -ENOMEM; + goto out; + } + ret = srp_parse_in(net, &target->rdma_cm.src.ss, p); + if (ret < 0) { + pr_warn("bad source parameter '%s'\n", p); + kfree(p); + goto out; + } + target->rdma_cm.src_specified = true; + kfree(p); + break; + + case SRP_OPT_IP_DEST: + p = match_strdup(args); + if (!p) { + ret = -ENOMEM; + goto out; + } + ret = srp_parse_in(net, &target->rdma_cm.dst.ss, p); + if (ret < 0) { + pr_warn("bad dest parameter '%s'\n", p); + kfree(p); + goto out; + } + target->using_rdma_cm = true; kfree(p); break; @@ -3221,6 +3620,15 @@ static int srp_parse_options(const char *buf, struct srp_target_port *target) target->scsi_host->cmd_per_lun = token; break; + case SRP_OPT_TARGET_CAN_QUEUE: + if (match_int(args, &token) || token < 1) { + pr_warn("bad max target_can_queue parameter '%s'\n", + p); + goto out; + } + target->target_can_queue = token; + break; + case SRP_OPT_IO_CLASS: if (match_hex(args, &token)) { pr_warn("bad IO class parameter '%s'\n", p); @@ -3242,7 +3650,13 @@ static int srp_parse_options(const char *buf, struct srp_target_port *target) ret = -ENOMEM; goto out; } - target->initiator_ext = cpu_to_be64(simple_strtoull(p, NULL, 16)); + ret = kstrtoull(p, 16, &ull); + if (ret) { + pr_warn("bad initiator_ext value '%s'\n", p); + kfree(p); + goto out; + } + target->initiator_ext = cpu_to_be64(ull); kfree(p); break; @@ -3297,14 +3711,14 @@ static int srp_parse_options(const char *buf, struct srp_target_port *target) } } - if ((opt_mask & SRP_OPT_ALL) == SRP_OPT_ALL) - ret = 0; - else - for (i = 0; i < ARRAY_SIZE(srp_opt_tokens); ++i) - if ((srp_opt_tokens[i].token & SRP_OPT_ALL) && - !(srp_opt_tokens[i].token & opt_mask)) - pr_warn("target creation request is missing parameter '%s'\n", - srp_opt_tokens[i].pattern); + for (i = 0; i < ARRAY_SIZE(srp_opt_mandatory); i++) { + if ((opt_mask & srp_opt_mandatory[i]) == srp_opt_mandatory[i]) { + ret = 0; + break; + } + } + if (ret) + pr_warn("target creation request is missing one or more parameters\n"); if (target->scsi_host->cmd_per_lun > target->scsi_host->can_queue && (opt_mask & SRP_OPT_MAX_CMD_PER_LUN)) @@ -3345,6 +3759,7 @@ static ssize_t srp_create_target(struct device *dev, target = host_to_target(target_host); + target->net = kobj_ns_grab_current(KOBJ_NS_TYPE_NET); target->io_class = SRP_REV16A_IB_IO_CLASS; target->scsi_host = target_host; target->srp_host = host; @@ -3366,18 +3781,29 @@ static ssize_t srp_create_target(struct device *dev, if (ret < 0) goto put; - ret = srp_parse_options(buf, target); + ret = srp_parse_options(target->net, buf, target); if (ret) goto out; target->req_ring_size = target->queue_size - SRP_TSK_MGMT_SQ_SIZE; if (!srp_conn_unique(target->srp_host, target)) { - shost_printk(KERN_INFO, target->scsi_host, - PFX "Already connected to target port with id_ext=%016llx;ioc_guid=%016llx;initiator_ext=%016llx\n", - be64_to_cpu(target->id_ext), - be64_to_cpu(target->ioc_guid), - be64_to_cpu(target->initiator_ext)); + if (target->using_rdma_cm) { + char dst_addr[64]; + + shost_printk(KERN_INFO, target->scsi_host, + PFX "Already connected to target port with id_ext=%016llx;ioc_guid=%016llx;dest=%s\n", + be64_to_cpu(target->id_ext), + be64_to_cpu(target->ioc_guid), + inet_ntop(&target->rdma_cm.dst, dst_addr, + sizeof(dst_addr))); + } else { + shost_printk(KERN_INFO, target->scsi_host, + PFX "Already connected to target port with id_ext=%016llx;ioc_guid=%016llx;initiator_ext=%016llx\n", + be64_to_cpu(target->id_ext), + be64_to_cpu(target->ioc_guid), + be64_to_cpu(target->initiator_ext)); + } ret = -EEXIST; goto out; } @@ -3478,11 +3904,18 @@ static ssize_t srp_create_target(struct device *dev, ret = srp_connect_ch(ch, multich); if (ret) { + char dst[64]; + + if (target->using_rdma_cm) + inet_ntop(&target->rdma_cm.dst, dst, + sizeof(dst)); + else + snprintf(dst, sizeof(dst), "%pI6", + target->ib_cm.orig_dgid.raw); shost_printk(KERN_ERR, target->scsi_host, - PFX "Connection %d/%d to %pI6 failed\n", + PFX "Connection %d/%d to %s failed\n", ch_start + cpu_idx, - target->ch_count, - ch->target->orig_dgid.raw); + target->ch_count, dst); if (node_idx == 0 && cpu_idx == 0) { goto free_ch; } else { @@ -3507,13 +3940,25 @@ connected: goto err_disconnect; if (target->state != SRP_TARGET_REMOVED) { - shost_printk(KERN_DEBUG, target->scsi_host, PFX - "new target: id_ext %016llx ioc_guid %016llx pkey %04x service_id %016llx sgid %pI6 dgid %pI6\n", - be64_to_cpu(target->id_ext), - be64_to_cpu(target->ioc_guid), - be16_to_cpu(target->pkey), - be64_to_cpu(target->service_id), - target->sgid.raw, target->orig_dgid.raw); + if (target->using_rdma_cm) { + char dst[64]; + + inet_ntop(&target->rdma_cm.dst, dst, sizeof(dst)); + shost_printk(KERN_DEBUG, target->scsi_host, PFX + "new target: id_ext %016llx ioc_guid %016llx sgid %pI6 dest %s\n", + be64_to_cpu(target->id_ext), + be64_to_cpu(target->ioc_guid), + target->sgid.raw, dst); + } else { + shost_printk(KERN_DEBUG, target->scsi_host, PFX + "new target: id_ext %016llx ioc_guid %016llx pkey %04x service_id %016llx sgid %pI6 dgid %pI6\n", + be64_to_cpu(target->id_ext), + be64_to_cpu(target->ioc_guid), + be16_to_cpu(target->ib_cm.pkey), + be64_to_cpu(target->ib_cm.service_id), + target->sgid.raw, + target->ib_cm.orig_dgid.raw); + } } ret = count; @@ -3523,8 +3968,16 @@ out: put: scsi_host_put(target->scsi_host); - if (ret < 0) + if (ret < 0) { + /* + * If a call to srp_remove_target() has not been scheduled, + * drop the network namespace reference now that was obtained + * earlier in this function. + */ + if (target->state != SRP_TARGET_REMOVED) + kobj_ns_drop(KOBJ_NS_TYPE_NET, target->net); scsi_host_put(target->scsi_host); + } return ret; diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h index a814f5ef16f9..a2706086b9c7 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.h +++ b/drivers/infiniband/ulp/srp/ib_srp.h @@ -45,6 +45,7 @@ #include <rdma/ib_sa.h> #include <rdma/ib_cm.h> #include <rdma/ib_fmr_pool.h> +#include <rdma/rdma_cm.h> enum { SRP_PATH_REC_TIMEOUT_MS = 1000, @@ -153,11 +154,18 @@ struct srp_rdma_ch { struct completion done; int status; - struct sa_path_rec path; - struct ib_sa_query *path_query; - int path_query_id; + union { + struct ib_cm { + struct sa_path_rec path; + struct ib_sa_query *path_query; + int path_query_id; + struct ib_cm_id *cm_id; + } ib_cm; + struct rdma_cm { + struct rdma_cm_id *cm_id; + } rdma_cm; + }; - struct ib_cm_id *cm_id; struct srp_iu **tx_ring; struct srp_iu **rx_ring; struct srp_request *req_ring; @@ -182,6 +190,7 @@ struct srp_target_port { /* read only in the hot path */ u32 global_rkey; struct srp_rdma_ch *ch; + struct net *net; u32 ch_count; u32 lkey; enum srp_target_state state; @@ -194,7 +203,6 @@ struct srp_target_port { union ib_gid sgid; __be64 id_ext; __be64 ioc_guid; - __be64 service_id; __be64 initiator_ext; u16 io_class; struct srp_host *srp_host; @@ -203,6 +211,7 @@ struct srp_target_port { char target_name[32]; unsigned int scsi_id; unsigned int sg_tablesize; + unsigned int target_can_queue; int mr_pool_size; int mr_per_cmd; int queue_size; @@ -210,8 +219,28 @@ struct srp_target_port { int comp_vector; int tl_retry_count; - union ib_gid orig_dgid; - __be16 pkey; + bool using_rdma_cm; + + union { + struct { + __be64 service_id; + union ib_gid orig_dgid; + __be16 pkey; + } ib_cm; + struct { + union { + struct sockaddr_in ip4; + struct sockaddr_in6 ip6; + struct sockaddr_storage ss; + } src; + union { + struct sockaddr_in ip4; + struct sockaddr_in6 ip6; + struct sockaddr_storage ss; + } dst; + bool src_specified; + } rdma_cm; + }; u32 rq_tmo_jiffies; diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 8a1bd354b1cc..0373b7c40902 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -41,6 +41,7 @@ #include <linux/string.h> #include <linux/delay.h> #include <linux/atomic.h> +#include <rdma/ib_cache.h> #include <scsi/scsi_proto.h> #include <scsi/scsi_tcq.h> #include <target/target_core_base.h> @@ -120,7 +121,9 @@ static bool srpt_set_ch_state(struct srpt_rdma_ch *ch, enum rdma_ch_state new) } /** - * srpt_event_handler() - Asynchronous IB event callback function. + * srpt_event_handler - asynchronous IB event callback function + * @handler: IB event handler registered by ib_register_event_handler(). + * @event: Description of the event that occurred. * * Callback function called by the InfiniBand core when an asynchronous IB * event occurs. This callback may occur in interrupt context. See also @@ -132,6 +135,7 @@ static void srpt_event_handler(struct ib_event_handler *handler, { struct srpt_device *sdev; struct srpt_port *sport; + u8 port_num; sdev = ib_get_client_data(event->device, &srpt_client); if (!sdev || sdev->device != event->device) @@ -142,10 +146,15 @@ static void srpt_event_handler(struct ib_event_handler *handler, switch (event->event) { case IB_EVENT_PORT_ERR: - if (event->element.port_num <= sdev->device->phys_port_cnt) { - sport = &sdev->port[event->element.port_num - 1]; + port_num = event->element.port_num - 1; + if (port_num < sdev->device->phys_port_cnt) { + sport = &sdev->port[port_num]; sport->lid = 0; sport->sm_lid = 0; + } else { + WARN(true, "event %d: port_num %d out of range 1..%d\n", + event->event, port_num + 1, + sdev->device->phys_port_cnt); } break; case IB_EVENT_PORT_ACTIVE: @@ -155,25 +164,31 @@ static void srpt_event_handler(struct ib_event_handler *handler, case IB_EVENT_CLIENT_REREGISTER: case IB_EVENT_GID_CHANGE: /* Refresh port data asynchronously. */ - if (event->element.port_num <= sdev->device->phys_port_cnt) { - sport = &sdev->port[event->element.port_num - 1]; + port_num = event->element.port_num - 1; + if (port_num < sdev->device->phys_port_cnt) { + sport = &sdev->port[port_num]; if (!sport->lid && !sport->sm_lid) schedule_work(&sport->work); + } else { + WARN(true, "event %d: port_num %d out of range 1..%d\n", + event->event, port_num + 1, + sdev->device->phys_port_cnt); } break; default: - pr_err("received unrecognized IB event %d\n", - event->event); + pr_err("received unrecognized IB event %d\n", event->event); break; } } /** - * srpt_srq_event() - SRQ event callback function. + * srpt_srq_event - SRQ event callback function + * @event: Description of the event that occurred. + * @ctx: Context pointer specified at SRQ creation time. */ static void srpt_srq_event(struct ib_event *event, void *ctx) { - pr_info("SRQ event %d\n", event->event); + pr_debug("SRQ event %d\n", event->event); } static const char *get_ch_state_name(enum rdma_ch_state s) @@ -194,16 +209,18 @@ static const char *get_ch_state_name(enum rdma_ch_state s) } /** - * srpt_qp_event() - QP event callback function. + * srpt_qp_event - QP event callback function + * @event: Description of the event that occurred. + * @ch: SRPT RDMA channel. */ static void srpt_qp_event(struct ib_event *event, struct srpt_rdma_ch *ch) { - pr_debug("QP event %d on cm_id=%p sess_name=%s state=%d\n", - event->event, ch->cm_id, ch->sess_name, ch->state); + pr_debug("QP event %d on ch=%p sess_name=%s state=%d\n", + event->event, ch, ch->sess_name, ch->state); switch (event->event) { case IB_EVENT_COMM_EST: - ib_cm_notify(ch->cm_id, event->event); + ib_cm_notify(ch->ib_cm.cm_id, event->event); break; case IB_EVENT_QP_LAST_WQE_REACHED: pr_debug("%s-%d, state %s: received Last WQE event.\n", @@ -217,8 +234,8 @@ static void srpt_qp_event(struct ib_event *event, struct srpt_rdma_ch *ch) } /** - * srpt_set_ioc() - Helper function for initializing an IOUnitInfo structure. - * + * srpt_set_ioc - initialize a IOUnitInfo structure + * @c_list: controller list. * @slot: one-based slot number. * @value: four-bit value. * @@ -241,7 +258,8 @@ static void srpt_set_ioc(u8 *c_list, u32 slot, u8 value) } /** - * srpt_get_class_port_info() - Copy ClassPortInfo to a management datagram. + * srpt_get_class_port_info - copy ClassPortInfo to a management datagram + * @mad: Datagram that will be sent as response to DM_ATTR_CLASS_PORT_INFO. * * See also section 16.3.3.1 ClassPortInfo in the InfiniBand Architecture * Specification. @@ -260,7 +278,8 @@ static void srpt_get_class_port_info(struct ib_dm_mad *mad) } /** - * srpt_get_iou() - Write IOUnitInfo to a management datagram. + * srpt_get_iou - write IOUnitInfo to a management datagram + * @mad: Datagram that will be sent as response to DM_ATTR_IOU_INFO. * * See also section 16.3.3.3 IOUnitInfo in the InfiniBand Architecture * Specification. See also section B.7, table B.6 in the SRP r16a document. @@ -284,7 +303,10 @@ static void srpt_get_iou(struct ib_dm_mad *mad) } /** - * srpt_get_ioc() - Write IOControllerprofile to a management datagram. + * srpt_get_ioc - write IOControllerprofile to a management datagram + * @sport: HCA port through which the MAD has been received. + * @slot: Slot number specified in DM_ATTR_IOC_PROFILE query. + * @mad: Datagram that will be sent as response to DM_ATTR_IOC_PROFILE. * * See also section 16.3.3.4 IOControllerProfile in the InfiniBand * Architecture Specification. See also section B.7, table B.7 in the SRP @@ -314,7 +336,7 @@ static void srpt_get_ioc(struct srpt_port *sport, u32 slot, if (sdev->use_srq) send_queue_depth = sdev->srq_size; else - send_queue_depth = min(SRPT_RQ_SIZE, + send_queue_depth = min(MAX_SRPT_RQ_SIZE, sdev->device->attrs.max_qp_wr); memset(iocp, 0, sizeof(*iocp)); @@ -342,7 +364,12 @@ static void srpt_get_ioc(struct srpt_port *sport, u32 slot, } /** - * srpt_get_svc_entries() - Write ServiceEntries to a management datagram. + * srpt_get_svc_entries - write ServiceEntries to a management datagram + * @ioc_guid: I/O controller GUID to use in reply. + * @slot: I/O controller number. + * @hi: End of the range of service entries to be specified in the reply. + * @lo: Start of the range of service entries to be specified in the reply.. + * @mad: Datagram that will be sent as response to DM_ATTR_SVC_ENTRIES. * * See also section 16.3.3.5 ServiceEntries in the InfiniBand Architecture * Specification. See also section B.7, table B.8 in the SRP r16a document. @@ -379,8 +406,8 @@ static void srpt_get_svc_entries(u64 ioc_guid, } /** - * srpt_mgmt_method_get() - Process a received management datagram. - * @sp: source port through which the MAD has been received. + * srpt_mgmt_method_get - process a received management datagram + * @sp: HCA port through which the MAD has been received. * @rq_mad: received MAD. * @rsp_mad: response MAD. */ @@ -419,7 +446,9 @@ static void srpt_mgmt_method_get(struct srpt_port *sp, struct ib_mad *rq_mad, } /** - * srpt_mad_send_handler() - Post MAD-send callback function. + * srpt_mad_send_handler - MAD send completion callback + * @mad_agent: Return value of ib_register_mad_agent(). + * @mad_wc: Work completion reporting that the MAD has been sent. */ static void srpt_mad_send_handler(struct ib_mad_agent *mad_agent, struct ib_mad_send_wc *mad_wc) @@ -429,7 +458,10 @@ static void srpt_mad_send_handler(struct ib_mad_agent *mad_agent, } /** - * srpt_mad_recv_handler() - MAD reception callback function. + * srpt_mad_recv_handler - MAD reception callback function + * @mad_agent: Return value of ib_register_mad_agent(). + * @send_buf: Not used. + * @mad_wc: Work completion reporting that a MAD has been received. */ static void srpt_mad_recv_handler(struct ib_mad_agent *mad_agent, struct ib_mad_send_buf *send_buf, @@ -493,8 +525,18 @@ err: ib_free_recv_mad(mad_wc); } +static int srpt_format_guid(char *buf, unsigned int size, const __be64 *guid) +{ + const __be16 *g = (const __be16 *)guid; + + return snprintf(buf, size, "%04x:%04x:%04x:%04x", + be16_to_cpu(g[0]), be16_to_cpu(g[1]), + be16_to_cpu(g[2]), be16_to_cpu(g[3])); +} + /** - * srpt_refresh_port() - Configure a HCA port. + * srpt_refresh_port - configure a HCA port + * @sport: SRPT HCA port. * * Enable InfiniBand management datagram processing, update the cached sm_lid, * lid and gid values, and register a callback function for processing MADs @@ -507,7 +549,6 @@ static int srpt_refresh_port(struct srpt_port *sport) struct ib_mad_reg_req reg_req; struct ib_port_modify port_modify; struct ib_port_attr port_attr; - __be16 *guid; int ret; memset(&port_modify, 0, sizeof(port_modify)); @@ -531,11 +572,8 @@ static int srpt_refresh_port(struct srpt_port *sport) goto err_query_port; sport->port_guid_wwn.priv = sport; - guid = (__be16 *)&sport->gid.global.interface_id; - snprintf(sport->port_guid, sizeof(sport->port_guid), - "%04x:%04x:%04x:%04x", - be16_to_cpu(guid[0]), be16_to_cpu(guid[1]), - be16_to_cpu(guid[2]), be16_to_cpu(guid[3])); + srpt_format_guid(sport->port_guid, sizeof(sport->port_guid), + &sport->gid.global.interface_id); sport->port_gid_wwn.priv = sport; snprintf(sport->port_gid, sizeof(sport->port_gid), "0x%016llx%016llx", @@ -577,7 +615,8 @@ err_mod_port: } /** - * srpt_unregister_mad_agent() - Unregister MAD callback functions. + * srpt_unregister_mad_agent - unregister MAD callback functions + * @sdev: SRPT HCA pointer. * * Note: It is safe to call this function more than once for the same device. */ @@ -602,7 +641,11 @@ static void srpt_unregister_mad_agent(struct srpt_device *sdev) } /** - * srpt_alloc_ioctx() - Allocate an SRPT I/O context structure. + * srpt_alloc_ioctx - allocate a SRPT I/O context structure + * @sdev: SRPT HCA pointer. + * @ioctx_size: I/O context size. + * @dma_size: Size of I/O context DMA buffer. + * @dir: DMA data direction. */ static struct srpt_ioctx *srpt_alloc_ioctx(struct srpt_device *sdev, int ioctx_size, int dma_size, @@ -633,7 +676,11 @@ err: } /** - * srpt_free_ioctx() - Free an SRPT I/O context structure. + * srpt_free_ioctx - free a SRPT I/O context structure + * @sdev: SRPT HCA pointer. + * @ioctx: I/O context pointer. + * @dma_size: Size of I/O context DMA buffer. + * @dir: DMA data direction. */ static void srpt_free_ioctx(struct srpt_device *sdev, struct srpt_ioctx *ioctx, int dma_size, enum dma_data_direction dir) @@ -647,7 +694,7 @@ static void srpt_free_ioctx(struct srpt_device *sdev, struct srpt_ioctx *ioctx, } /** - * srpt_alloc_ioctx_ring() - Allocate a ring of SRPT I/O context structures. + * srpt_alloc_ioctx_ring - allocate a ring of SRPT I/O context structures * @sdev: Device to allocate the I/O context ring for. * @ring_size: Number of elements in the I/O context ring. * @ioctx_size: I/O context size. @@ -685,7 +732,12 @@ out: } /** - * srpt_free_ioctx_ring() - Free the ring of SRPT I/O context structures. + * srpt_free_ioctx_ring - free the ring of SRPT I/O context structures + * @ioctx_ring: I/O context ring to be freed. + * @sdev: SRPT HCA pointer. + * @ring_size: Number of ring elements. + * @dma_size: Size of I/O context DMA buffer. + * @dir: DMA data direction. */ static void srpt_free_ioctx_ring(struct srpt_ioctx **ioctx_ring, struct srpt_device *sdev, int ring_size, @@ -702,23 +754,9 @@ static void srpt_free_ioctx_ring(struct srpt_ioctx **ioctx_ring, } /** - * srpt_get_cmd_state() - Get the state of a SCSI command. - */ -static enum srpt_command_state srpt_get_cmd_state(struct srpt_send_ioctx *ioctx) -{ - enum srpt_command_state state; - unsigned long flags; - - BUG_ON(!ioctx); - - spin_lock_irqsave(&ioctx->spinlock, flags); - state = ioctx->state; - spin_unlock_irqrestore(&ioctx->spinlock, flags); - return state; -} - -/** - * srpt_set_cmd_state() - Set the state of a SCSI command. + * srpt_set_cmd_state - set the state of a SCSI command + * @ioctx: Send I/O context. + * @new: New I/O context state. * * Does not modify the state of aborted commands. Returns the previous command * state. @@ -727,21 +765,19 @@ static enum srpt_command_state srpt_set_cmd_state(struct srpt_send_ioctx *ioctx, enum srpt_command_state new) { enum srpt_command_state previous; - unsigned long flags; - BUG_ON(!ioctx); - - spin_lock_irqsave(&ioctx->spinlock, flags); previous = ioctx->state; if (previous != SRPT_STATE_DONE) ioctx->state = new; - spin_unlock_irqrestore(&ioctx->spinlock, flags); return previous; } /** - * srpt_test_and_set_cmd_state() - Test and set the state of a command. + * srpt_test_and_set_cmd_state - test and set the state of a command + * @ioctx: Send I/O context. + * @old: Current I/O context state. + * @new: New I/O context state. * * Returns true if and only if the previous command state was equal to 'old'. */ @@ -750,22 +786,23 @@ static bool srpt_test_and_set_cmd_state(struct srpt_send_ioctx *ioctx, enum srpt_command_state new) { enum srpt_command_state previous; - unsigned long flags; WARN_ON(!ioctx); WARN_ON(old == SRPT_STATE_DONE); WARN_ON(new == SRPT_STATE_NEW); - spin_lock_irqsave(&ioctx->spinlock, flags); previous = ioctx->state; if (previous == old) ioctx->state = new; - spin_unlock_irqrestore(&ioctx->spinlock, flags); + return previous == old; } /** - * srpt_post_recv() - Post an IB receive request. + * srpt_post_recv - post an IB receive request + * @sdev: SRPT HCA pointer. + * @ch: SRPT RDMA channel. + * @ioctx: Receive I/O context pointer. */ static int srpt_post_recv(struct srpt_device *sdev, struct srpt_rdma_ch *ch, struct srpt_recv_ioctx *ioctx) @@ -791,7 +828,8 @@ static int srpt_post_recv(struct srpt_device *sdev, struct srpt_rdma_ch *ch, } /** - * srpt_zerolength_write() - Perform a zero-length RDMA write. + * srpt_zerolength_write - perform a zero-length RDMA write + * @ch: SRPT RDMA channel. * * A quote from the InfiniBand specification: C9-88: For an HCA responder * using Reliable Connection service, for each zero-length RDMA READ or WRITE @@ -802,6 +840,9 @@ static int srpt_zerolength_write(struct srpt_rdma_ch *ch) { struct ib_send_wr wr, *bad_wr; + pr_debug("%s-%d: queued zerolength write\n", ch->sess_name, + ch->qp->qp_num); + memset(&wr, 0, sizeof(wr)); wr.opcode = IB_WR_RDMA_WRITE; wr.wr_cqe = &ch->zw_cqe; @@ -813,13 +854,17 @@ static void srpt_zerolength_write_done(struct ib_cq *cq, struct ib_wc *wc) { struct srpt_rdma_ch *ch = cq->cq_context; + pr_debug("%s-%d wc->status %d\n", ch->sess_name, ch->qp->qp_num, + wc->status); + if (wc->status == IB_WC_SUCCESS) { srpt_process_wait_list(ch); } else { if (srpt_set_ch_state(ch, CH_DISCONNECTED)) schedule_work(&ch->release_work); else - WARN_ONCE(1, "%s-%d\n", ch->sess_name, ch->qp->qp_num); + pr_debug("%s-%d: already disconnected.\n", + ch->sess_name, ch->qp->qp_num); } } @@ -928,11 +973,13 @@ static inline void *srpt_get_desc_buf(struct srp_cmd *srp_cmd) } /** - * srpt_get_desc_tbl() - Parse the data descriptors of an SRP_CMD request. + * srpt_get_desc_tbl - parse the data descriptors of a SRP_CMD request * @ioctx: Pointer to the I/O context associated with the request. * @srp_cmd: Pointer to the SRP_CMD request data. * @dir: Pointer to the variable to which the transfer direction will be * written. + * @sg: [out] scatterlist allocated for the parsed SRP_CMD. + * @sg_cnt: [out] length of @sg. * @data_len: Pointer to the variable to which the total data length of all * descriptors in the SRP_CMD request will be written. * @@ -998,7 +1045,9 @@ static int srpt_get_desc_tbl(struct srpt_send_ioctx *ioctx, } /** - * srpt_init_ch_qp() - Initialize queue pair attributes. + * srpt_init_ch_qp - initialize queue pair attributes + * @ch: SRPT RDMA channel. + * @qp: Queue pair pointer. * * Initialized the attributes of queue pair 'qp' by allowing local write, * remote read and remote write. Also transitions 'qp' to state IB_QPS_INIT. @@ -1013,10 +1062,14 @@ static int srpt_init_ch_qp(struct srpt_rdma_ch *ch, struct ib_qp *qp) return -ENOMEM; attr->qp_state = IB_QPS_INIT; - attr->qp_access_flags = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_READ | - IB_ACCESS_REMOTE_WRITE; + attr->qp_access_flags = IB_ACCESS_LOCAL_WRITE; attr->port_num = ch->sport->port; - attr->pkey_index = 0; + + ret = ib_find_cached_pkey(ch->sport->sdev->device, ch->sport->port, + ch->pkey, &attr->pkey_index); + if (ret < 0) + pr_err("Translating pkey %#x failed (%d) - using index 0\n", + ch->pkey, ret); ret = ib_modify_qp(qp, attr, IB_QP_STATE | IB_QP_ACCESS_FLAGS | IB_QP_PORT | @@ -1027,7 +1080,7 @@ static int srpt_init_ch_qp(struct srpt_rdma_ch *ch, struct ib_qp *qp) } /** - * srpt_ch_qp_rtr() - Change the state of a channel to 'ready to receive' (RTR). + * srpt_ch_qp_rtr - change the state of a channel to 'ready to receive' (RTR) * @ch: channel of the queue pair. * @qp: queue pair to change the state of. * @@ -1044,7 +1097,7 @@ static int srpt_ch_qp_rtr(struct srpt_rdma_ch *ch, struct ib_qp *qp) int ret; qp_attr.qp_state = IB_QPS_RTR; - ret = ib_cm_init_qp_attr(ch->cm_id, &qp_attr, &attr_mask); + ret = ib_cm_init_qp_attr(ch->ib_cm.cm_id, &qp_attr, &attr_mask); if (ret) goto out; @@ -1057,7 +1110,7 @@ out: } /** - * srpt_ch_qp_rts() - Change the state of a channel to 'ready to send' (RTS). + * srpt_ch_qp_rts - change the state of a channel to 'ready to send' (RTS) * @ch: channel of the queue pair. * @qp: queue pair to change the state of. * @@ -1074,7 +1127,7 @@ static int srpt_ch_qp_rts(struct srpt_rdma_ch *ch, struct ib_qp *qp) int ret; qp_attr.qp_state = IB_QPS_RTS; - ret = ib_cm_init_qp_attr(ch->cm_id, &qp_attr, &attr_mask); + ret = ib_cm_init_qp_attr(ch->ib_cm.cm_id, &qp_attr, &attr_mask); if (ret) goto out; @@ -1087,7 +1140,8 @@ out: } /** - * srpt_ch_qp_err() - Set the channel queue pair state to 'error'. + * srpt_ch_qp_err - set the channel queue pair state to 'error' + * @ch: SRPT RDMA channel. */ static int srpt_ch_qp_err(struct srpt_rdma_ch *ch) { @@ -1098,7 +1152,8 @@ static int srpt_ch_qp_err(struct srpt_rdma_ch *ch) } /** - * srpt_get_send_ioctx() - Obtain an I/O context for sending to the initiator. + * srpt_get_send_ioctx - obtain an I/O context for sending to the initiator + * @ch: SRPT RDMA channel. */ static struct srpt_send_ioctx *srpt_get_send_ioctx(struct srpt_rdma_ch *ch) { @@ -1120,11 +1175,9 @@ static struct srpt_send_ioctx *srpt_get_send_ioctx(struct srpt_rdma_ch *ch) return ioctx; BUG_ON(ioctx->ch != ch); - spin_lock_init(&ioctx->spinlock); ioctx->state = SRPT_STATE_NEW; ioctx->n_rdma = 0; ioctx->n_rw_ctx = 0; - init_completion(&ioctx->tx_done); ioctx->queue_status_only = false; /* * transport_init_se_cmd() does not initialize all fields, so do it @@ -1137,14 +1190,12 @@ static struct srpt_send_ioctx *srpt_get_send_ioctx(struct srpt_rdma_ch *ch) } /** - * srpt_abort_cmd() - Abort a SCSI command. + * srpt_abort_cmd - abort a SCSI command * @ioctx: I/O context associated with the SCSI command. - * @context: Preferred execution context. */ static int srpt_abort_cmd(struct srpt_send_ioctx *ioctx) { enum srpt_command_state state; - unsigned long flags; BUG_ON(!ioctx); @@ -1153,7 +1204,6 @@ static int srpt_abort_cmd(struct srpt_send_ioctx *ioctx) * the ib_srpt driver, change the state to the next state. */ - spin_lock_irqsave(&ioctx->spinlock, flags); state = ioctx->state; switch (state) { case SRPT_STATE_NEED_DATA: @@ -1168,7 +1218,6 @@ static int srpt_abort_cmd(struct srpt_send_ioctx *ioctx) __func__, state); break; } - spin_unlock_irqrestore(&ioctx->spinlock, flags); pr_debug("Aborting cmd with state %d -> %d and tag %lld\n", state, ioctx->state, ioctx->cmd.tag); @@ -1207,6 +1256,10 @@ static int srpt_abort_cmd(struct srpt_send_ioctx *ioctx) } /** + * srpt_rdma_read_done - RDMA read completion callback + * @cq: Completion queue. + * @wc: Work completion. + * * XXX: what is now target_execute_cmd used to be asynchronous, and unmapping * the data that has been transferred via IB RDMA had to be postponed until the * check_stop_free() callback. None of this is necessary anymore and needs to @@ -1234,11 +1287,11 @@ static void srpt_rdma_read_done(struct ib_cq *cq, struct ib_wc *wc) target_execute_cmd(&ioctx->cmd); else pr_err("%s[%d]: wrong state = %d\n", __func__, - __LINE__, srpt_get_cmd_state(ioctx)); + __LINE__, ioctx->state); } /** - * srpt_build_cmd_rsp() - Build an SRP_RSP response. + * srpt_build_cmd_rsp - build a SRP_RSP response * @ch: RDMA channel through which the request has been received. * @ioctx: I/O context associated with the SRP_CMD request. The response will * be built in the buffer ioctx->buf points at and hence this function will @@ -1298,7 +1351,7 @@ static int srpt_build_cmd_rsp(struct srpt_rdma_ch *ch, } /** - * srpt_build_tskmgmt_rsp() - Build a task management response. + * srpt_build_tskmgmt_rsp - build a task management response * @ch: RDMA channel through which the request has been received. * @ioctx: I/O context in which the SRP_RSP response will be built. * @rsp_code: RSP_CODE that will be stored in the response. @@ -1346,7 +1399,10 @@ static int srpt_check_stop_free(struct se_cmd *cmd) } /** - * srpt_handle_cmd() - Process SRP_CMD. + * srpt_handle_cmd - process a SRP_CMD information unit + * @ch: SRPT RDMA channel. + * @recv_ioctx: Receive I/O context. + * @send_ioctx: Send I/O context. */ static void srpt_handle_cmd(struct srpt_rdma_ch *ch, struct srpt_recv_ioctx *recv_ioctx, @@ -1428,7 +1484,10 @@ static int srp_tmr_to_tcm(int fn) } /** - * srpt_handle_tsk_mgmt() - Process an SRP_TSK_MGMT information unit. + * srpt_handle_tsk_mgmt - process a SRP_TSK_MGMT information unit + * @ch: SRPT RDMA channel. + * @recv_ioctx: Receive I/O context. + * @send_ioctx: Send I/O context. * * Returns 0 if and only if the request will be processed by the target core. * @@ -1450,9 +1509,9 @@ static void srpt_handle_tsk_mgmt(struct srpt_rdma_ch *ch, srp_tsk = recv_ioctx->ioctx.buf; cmd = &send_ioctx->cmd; - pr_debug("recv tsk_mgmt fn %d for task_tag %lld and cmd tag %lld" - " cm_id %p sess %p\n", srp_tsk->tsk_mgmt_func, - srp_tsk->task_tag, srp_tsk->tag, ch->cm_id, ch->sess); + pr_debug("recv tsk_mgmt fn %d for task_tag %lld and cmd tag %lld ch %p sess %p\n", + srp_tsk->tsk_mgmt_func, srp_tsk->task_tag, srp_tsk->tag, ch, + ch->sess); srpt_set_cmd_state(send_ioctx, SRPT_STATE_MGMT); send_ioctx->cmd.tag = srp_tsk->tag; @@ -1471,41 +1530,42 @@ fail: } /** - * srpt_handle_new_iu() - Process a newly received information unit. + * srpt_handle_new_iu - process a newly received information unit * @ch: RDMA channel through which the information unit has been received. - * @ioctx: SRPT I/O context associated with the information unit. + * @recv_ioctx: Receive I/O context associated with the information unit. */ -static void srpt_handle_new_iu(struct srpt_rdma_ch *ch, - struct srpt_recv_ioctx *recv_ioctx, - struct srpt_send_ioctx *send_ioctx) +static bool +srpt_handle_new_iu(struct srpt_rdma_ch *ch, struct srpt_recv_ioctx *recv_ioctx) { + struct srpt_send_ioctx *send_ioctx = NULL; struct srp_cmd *srp_cmd; + bool res = false; + u8 opcode; BUG_ON(!ch); BUG_ON(!recv_ioctx); + if (unlikely(ch->state == CH_CONNECTING)) + goto push; + ib_dma_sync_single_for_cpu(ch->sport->sdev->device, recv_ioctx->ioctx.dma, srp_max_req_size, DMA_FROM_DEVICE); - if (unlikely(ch->state == CH_CONNECTING)) - goto out_wait; - - if (unlikely(ch->state != CH_LIVE)) - return; - srp_cmd = recv_ioctx->ioctx.buf; - if (srp_cmd->opcode == SRP_CMD || srp_cmd->opcode == SRP_TSK_MGMT) { - if (!send_ioctx) { - if (!list_empty(&ch->cmd_wait_list)) - goto out_wait; - send_ioctx = srpt_get_send_ioctx(ch); - } + opcode = srp_cmd->opcode; + if (opcode == SRP_CMD || opcode == SRP_TSK_MGMT) { + send_ioctx = srpt_get_send_ioctx(ch); if (unlikely(!send_ioctx)) - goto out_wait; + goto push; } - switch (srp_cmd->opcode) { + if (!list_empty(&recv_ioctx->wait_list)) { + WARN_ON_ONCE(!ch->processing_wait_list); + list_del_init(&recv_ioctx->wait_list); + } + + switch (opcode) { case SRP_CMD: srpt_handle_cmd(ch, recv_ioctx, send_ioctx); break; @@ -1525,16 +1585,22 @@ static void srpt_handle_new_iu(struct srpt_rdma_ch *ch, pr_err("Received SRP_RSP\n"); break; default: - pr_err("received IU with unknown opcode 0x%x\n", - srp_cmd->opcode); + pr_err("received IU with unknown opcode 0x%x\n", opcode); break; } srpt_post_recv(ch->sport->sdev, ch, recv_ioctx); - return; + res = true; + +out: + return res; -out_wait: - list_add_tail(&recv_ioctx->wait_list, &ch->cmd_wait_list); +push: + if (list_empty(&recv_ioctx->wait_list)) { + WARN_ON_ONCE(ch->processing_wait_list); + list_add_tail(&recv_ioctx->wait_list, &ch->cmd_wait_list); + } + goto out; } static void srpt_recv_done(struct ib_cq *cq, struct ib_wc *wc) @@ -1549,10 +1615,10 @@ static void srpt_recv_done(struct ib_cq *cq, struct ib_wc *wc) req_lim = atomic_dec_return(&ch->req_lim); if (unlikely(req_lim < 0)) pr_err("req_lim = %d < 0\n", req_lim); - srpt_handle_new_iu(ch, ioctx, NULL); + srpt_handle_new_iu(ch, ioctx); } else { - pr_info("receiving failed for ioctx %p with status %d\n", - ioctx, wc->status); + pr_info_ratelimited("receiving failed for ioctx %p with status %d\n", + ioctx, wc->status); } } @@ -1563,22 +1629,28 @@ static void srpt_recv_done(struct ib_cq *cq, struct ib_wc *wc) */ static void srpt_process_wait_list(struct srpt_rdma_ch *ch) { - struct srpt_send_ioctx *ioctx; + struct srpt_recv_ioctx *recv_ioctx, *tmp; + + WARN_ON_ONCE(ch->state == CH_CONNECTING); - while (!list_empty(&ch->cmd_wait_list) && - ch->state >= CH_LIVE && - (ioctx = srpt_get_send_ioctx(ch)) != NULL) { - struct srpt_recv_ioctx *recv_ioctx; + if (list_empty(&ch->cmd_wait_list)) + return; - recv_ioctx = list_first_entry(&ch->cmd_wait_list, - struct srpt_recv_ioctx, - wait_list); - list_del(&recv_ioctx->wait_list); - srpt_handle_new_iu(ch, recv_ioctx, ioctx); + WARN_ON_ONCE(ch->processing_wait_list); + ch->processing_wait_list = true; + list_for_each_entry_safe(recv_ioctx, tmp, &ch->cmd_wait_list, + wait_list) { + if (!srpt_handle_new_iu(ch, recv_ioctx)) + break; } + ch->processing_wait_list = false; } /** + * srpt_send_done - send completion callback + * @cq: Completion queue. + * @wc: Work completion. + * * Note: Although this has not yet been observed during tests, at least in * theory it is possible that the srpt_get_send_ioctx() call invoked by * srpt_handle_new_iu() fails. This is possible because the req_lim_delta @@ -1620,7 +1692,8 @@ static void srpt_send_done(struct ib_cq *cq, struct ib_wc *wc) } /** - * srpt_create_ch_ib() - Create receive and send completion queues. + * srpt_create_ch_ib - create receive and send completion queues + * @ch: SRPT RDMA channel. */ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch) { @@ -1628,7 +1701,7 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch) struct srpt_port *sport = ch->sport; struct srpt_device *sdev = sport->sdev; const struct ib_device_attr *attrs = &sdev->device->attrs; - u32 srp_sq_size = sport->port_attrib.srp_sq_size; + int sq_size = sport->port_attrib.srp_sq_size; int i, ret; WARN_ON(ch->rq_size < 1); @@ -1639,12 +1712,12 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch) goto out; retry: - ch->cq = ib_alloc_cq(sdev->device, ch, ch->rq_size + srp_sq_size, + ch->cq = ib_alloc_cq(sdev->device, ch, ch->rq_size + sq_size, 0 /* XXX: spread CQs */, IB_POLL_WORKQUEUE); if (IS_ERR(ch->cq)) { ret = PTR_ERR(ch->cq); pr_err("failed to create CQ cqe= %d ret= %d\n", - ch->rq_size + srp_sq_size, ret); + ch->rq_size + sq_size, ret); goto out; } @@ -1662,8 +1735,8 @@ retry: * both both, as RDMA contexts will also post completions for the * RDMA READ case. */ - qp_init->cap.max_send_wr = min(srp_sq_size / 2, attrs->max_qp_wr + 0U); - qp_init->cap.max_rdma_ctxs = srp_sq_size / 2; + qp_init->cap.max_send_wr = min(sq_size / 2, attrs->max_qp_wr); + qp_init->cap.max_rdma_ctxs = sq_size / 2; qp_init->cap.max_send_sge = min(attrs->max_sge, SRPT_MAX_SG_PER_WQE); qp_init->port_num = ch->sport->port; if (sdev->use_srq) { @@ -1677,8 +1750,8 @@ retry: if (IS_ERR(ch->qp)) { ret = PTR_ERR(ch->qp); if (ret == -ENOMEM) { - srp_sq_size /= 2; - if (srp_sq_size >= MIN_SRPT_SQ_SIZE) { + sq_size /= 2; + if (sq_size >= MIN_SRPT_SQ_SIZE) { ib_destroy_cq(ch->cq); goto retry; } @@ -1689,9 +1762,9 @@ retry: atomic_set(&ch->sq_wr_avail, qp_init->cap.max_send_wr); - pr_debug("%s: max_cqe= %d max_sge= %d sq_size = %d cm_id= %p\n", + pr_debug("%s: max_cqe= %d max_sge= %d sq_size = %d ch= %p\n", __func__, ch->cq->cqe, qp_init->cap.max_send_sge, - qp_init->cap.max_send_wr, ch->cm_id); + qp_init->cap.max_send_wr, ch); ret = srpt_init_ch_qp(ch, ch->qp); if (ret) @@ -1719,7 +1792,8 @@ static void srpt_destroy_ch_ib(struct srpt_rdma_ch *ch) } /** - * srpt_close_ch() - Close an RDMA channel. + * srpt_close_ch - close a RDMA channel + * @ch: SRPT RDMA channel. * * Make sure all resources associated with the channel will be deallocated at * an appropriate time. @@ -1744,8 +1818,6 @@ static bool srpt_close_ch(struct srpt_rdma_ch *ch) pr_err("%s-%d: changing queue pair into error state failed: %d\n", ch->sess_name, ch->qp->qp_num, ret); - pr_debug("%s-%d: queued zerolength write\n", ch->sess_name, - ch->qp->qp_num); ret = srpt_zerolength_write(ch); if (ret < 0) { pr_err("%s-%d: queuing zero-length write failed: %d\n", @@ -1777,9 +1849,9 @@ static int srpt_disconnect_ch(struct srpt_rdma_ch *ch) if (!srpt_set_ch_state(ch, CH_DISCONNECTING)) return -ENOTCONN; - ret = ib_send_cm_dreq(ch->cm_id, NULL, 0); + ret = ib_send_cm_dreq(ch->ib_cm.cm_id, NULL, 0); if (ret < 0) - ret = ib_send_cm_drep(ch->cm_id, NULL, 0); + ret = ib_send_cm_drep(ch->ib_cm.cm_id, NULL, 0); if (ret < 0 && srpt_close_ch(ch)) ret = 0; @@ -1787,83 +1859,135 @@ static int srpt_disconnect_ch(struct srpt_rdma_ch *ch) return ret; } -/* - * Send DREQ and wait for DREP. Return true if and only if this function - * changed the state of @ch. - */ -static bool srpt_disconnect_ch_sync(struct srpt_rdma_ch *ch) - __must_hold(&sdev->mutex) +static bool srpt_ch_closed(struct srpt_port *sport, struct srpt_rdma_ch *ch) { - DECLARE_COMPLETION_ONSTACK(release_done); - struct srpt_device *sdev = ch->sport->sdev; - bool wait; + struct srpt_nexus *nexus; + struct srpt_rdma_ch *ch2; + bool res = true; + + rcu_read_lock(); + list_for_each_entry(nexus, &sport->nexus_list, entry) { + list_for_each_entry(ch2, &nexus->ch_list, list) { + if (ch2 == ch) { + res = false; + goto done; + } + } + } +done: + rcu_read_unlock(); - lockdep_assert_held(&sdev->mutex); + return res; +} + +/* Send DREQ and wait for DREP. */ +static void srpt_disconnect_ch_sync(struct srpt_rdma_ch *ch) +{ + struct srpt_port *sport = ch->sport; pr_debug("ch %s-%d state %d\n", ch->sess_name, ch->qp->qp_num, ch->state); - WARN_ON(ch->release_done); - ch->release_done = &release_done; - wait = !list_empty(&ch->list); + mutex_lock(&sport->mutex); srpt_disconnect_ch(ch); - mutex_unlock(&sdev->mutex); + mutex_unlock(&sport->mutex); - if (!wait) - goto out; - - while (wait_for_completion_timeout(&release_done, 180 * HZ) == 0) + while (wait_event_timeout(sport->ch_releaseQ, srpt_ch_closed(sport, ch), + 5 * HZ) == 0) pr_info("%s(%s-%d state %d): still waiting ...\n", __func__, ch->sess_name, ch->qp->qp_num, ch->state); -out: - mutex_lock(&sdev->mutex); - return wait; } -static void srpt_set_enabled(struct srpt_port *sport, bool enabled) - __must_hold(&sdev->mutex) +static void __srpt_close_all_ch(struct srpt_port *sport) { - struct srpt_device *sdev = sport->sdev; + struct srpt_nexus *nexus; struct srpt_rdma_ch *ch; - lockdep_assert_held(&sdev->mutex); + lockdep_assert_held(&sport->mutex); - if (sport->enabled == enabled) - return; - sport->enabled = enabled; - if (sport->enabled) - return; + list_for_each_entry(nexus, &sport->nexus_list, entry) { + list_for_each_entry(ch, &nexus->ch_list, list) { + if (srpt_disconnect_ch(ch) >= 0) + pr_info("Closing channel %s-%d because target %s_%d has been disabled\n", + ch->sess_name, ch->qp->qp_num, + sport->sdev->device->name, sport->port); + srpt_close_ch(ch); + } + } +} -again: - list_for_each_entry(ch, &sdev->rch_list, list) { - if (ch->sport == sport) { - pr_info("%s: closing channel %s-%d\n", - sdev->device->name, ch->sess_name, - ch->qp->qp_num); - if (srpt_disconnect_ch_sync(ch)) - goto again; +/* + * Look up (i_port_id, t_port_id) in sport->nexus_list. Create an entry if + * it does not yet exist. + */ +static struct srpt_nexus *srpt_get_nexus(struct srpt_port *sport, + const u8 i_port_id[16], + const u8 t_port_id[16]) +{ + struct srpt_nexus *nexus = NULL, *tmp_nexus = NULL, *n; + + for (;;) { + mutex_lock(&sport->mutex); + list_for_each_entry(n, &sport->nexus_list, entry) { + if (memcmp(n->i_port_id, i_port_id, 16) == 0 && + memcmp(n->t_port_id, t_port_id, 16) == 0) { + nexus = n; + break; + } } + if (!nexus && tmp_nexus) { + list_add_tail_rcu(&tmp_nexus->entry, + &sport->nexus_list); + swap(nexus, tmp_nexus); + } + mutex_unlock(&sport->mutex); + + if (nexus) + break; + tmp_nexus = kzalloc(sizeof(*nexus), GFP_KERNEL); + if (!tmp_nexus) { + nexus = ERR_PTR(-ENOMEM); + break; + } + INIT_LIST_HEAD(&tmp_nexus->ch_list); + memcpy(tmp_nexus->i_port_id, i_port_id, 16); + memcpy(tmp_nexus->t_port_id, t_port_id, 16); } + kfree(tmp_nexus); + + return nexus; +} + +static void srpt_set_enabled(struct srpt_port *sport, bool enabled) + __must_hold(&sport->mutex) +{ + lockdep_assert_held(&sport->mutex); + + if (sport->enabled == enabled) + return; + sport->enabled = enabled; + if (!enabled) + __srpt_close_all_ch(sport); } static void srpt_free_ch(struct kref *kref) { struct srpt_rdma_ch *ch = container_of(kref, struct srpt_rdma_ch, kref); - kfree(ch); + kfree_rcu(ch, rcu); } static void srpt_release_channel_work(struct work_struct *w) { struct srpt_rdma_ch *ch; struct srpt_device *sdev; + struct srpt_port *sport; struct se_session *se_sess; ch = container_of(w, struct srpt_rdma_ch, release_work); - pr_debug("%s: %s-%d; release_done = %p\n", __func__, ch->sess_name, - ch->qp->qp_num, ch->release_done); + pr_debug("%s-%d\n", ch->sess_name, ch->qp->qp_num); sdev = ch->sport->sdev; BUG_ON(!sdev); @@ -1878,169 +2002,141 @@ static void srpt_release_channel_work(struct work_struct *w) transport_deregister_session(se_sess); ch->sess = NULL; - ib_destroy_cm_id(ch->cm_id); + ib_destroy_cm_id(ch->ib_cm.cm_id); srpt_destroy_ch_ib(ch); srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_ring, ch->sport->sdev, ch->rq_size, - ch->rsp_size, DMA_TO_DEVICE); + ch->max_rsp_size, DMA_TO_DEVICE); srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_recv_ring, sdev, ch->rq_size, srp_max_req_size, DMA_FROM_DEVICE); - mutex_lock(&sdev->mutex); - list_del_init(&ch->list); - if (ch->release_done) - complete(ch->release_done); - mutex_unlock(&sdev->mutex); + sport = ch->sport; + mutex_lock(&sport->mutex); + list_del_rcu(&ch->list); + mutex_unlock(&sport->mutex); - wake_up(&sdev->ch_releaseQ); + wake_up(&sport->ch_releaseQ); kref_put(&ch->kref, srpt_free_ch); } /** - * srpt_cm_req_recv() - Process the event IB_CM_REQ_RECEIVED. + * srpt_cm_req_recv - process the event IB_CM_REQ_RECEIVED + * @cm_id: IB/CM connection identifier. + * @port_num: Port through which the IB/CM REQ message was received. + * @pkey: P_Key of the incoming connection. + * @req: SRP login request. + * @src_addr: GID of the port that submitted the login request. * * Ownership of the cm_id is transferred to the target session if this * functions returns zero. Otherwise the caller remains the owner of cm_id. */ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, - struct ib_cm_req_event_param *param, - void *private_data) + u8 port_num, __be16 pkey, + const struct srp_login_req *req, + const char *src_addr) { struct srpt_device *sdev = cm_id->context; - struct srpt_port *sport = &sdev->port[param->port - 1]; - struct srp_login_req *req; - struct srp_login_rsp *rsp; - struct srp_login_rej *rej; - struct ib_cm_rep_param *rep_param; - struct srpt_rdma_ch *ch, *tmp_ch; - __be16 *guid; + struct srpt_port *sport = &sdev->port[port_num - 1]; + struct srpt_nexus *nexus; + struct srp_login_rsp *rsp = NULL; + struct srp_login_rej *rej = NULL; + struct ib_cm_rep_param *rep_param = NULL; + struct srpt_rdma_ch *ch; + char i_port_id[36]; u32 it_iu_len; - int i, ret = 0; + int i, ret; WARN_ON_ONCE(irqs_disabled()); - if (WARN_ON(!sdev || !private_data)) + if (WARN_ON(!sdev || !req)) return -EINVAL; - req = (struct srp_login_req *)private_data; - it_iu_len = be32_to_cpu(req->req_it_iu_len); - pr_info("Received SRP_LOGIN_REQ with i_port_id 0x%llx:0x%llx," - " t_port_id 0x%llx:0x%llx and it_iu_len %d on port %d" - " (guid=0x%llx:0x%llx)\n", - be64_to_cpu(*(__be64 *)&req->initiator_port_id[0]), - be64_to_cpu(*(__be64 *)&req->initiator_port_id[8]), - be64_to_cpu(*(__be64 *)&req->target_port_id[0]), - be64_to_cpu(*(__be64 *)&req->target_port_id[8]), - it_iu_len, - param->port, - be64_to_cpu(*(__be64 *)&sdev->port[param->port - 1].gid.raw[0]), - be64_to_cpu(*(__be64 *)&sdev->port[param->port - 1].gid.raw[8])); + 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", + req->initiator_port_id, req->target_port_id, it_iu_len, + port_num, &sport->gid, be16_to_cpu(pkey)); + nexus = srpt_get_nexus(sport, req->initiator_port_id, + req->target_port_id); + if (IS_ERR(nexus)) { + ret = PTR_ERR(nexus); + goto out; + } + + ret = -ENOMEM; rsp = kzalloc(sizeof(*rsp), GFP_KERNEL); rej = kzalloc(sizeof(*rej), GFP_KERNEL); rep_param = kzalloc(sizeof(*rep_param), GFP_KERNEL); - - if (!rsp || !rej || !rep_param) { - ret = -ENOMEM; + if (!rsp || !rej || !rep_param) goto out; - } + ret = -EINVAL; if (it_iu_len > srp_max_req_size || it_iu_len < 64) { rej->reason = cpu_to_be32( - SRP_LOGIN_REJ_REQ_IT_IU_LENGTH_TOO_LARGE); - ret = -EINVAL; - pr_err("rejected SRP_LOGIN_REQ because its" - " length (%d bytes) is out of range (%d .. %d)\n", + SRP_LOGIN_REJ_REQ_IT_IU_LENGTH_TOO_LARGE); + pr_err("rejected SRP_LOGIN_REQ because its length (%d bytes) is out of range (%d .. %d)\n", it_iu_len, 64, srp_max_req_size); goto reject; } if (!sport->enabled) { - rej->reason = cpu_to_be32( - SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); - ret = -EINVAL; - pr_err("rejected SRP_LOGIN_REQ because the target port" - " has not yet been enabled\n"); + rej->reason = cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); + pr_info("rejected SRP_LOGIN_REQ because target port %s_%d has not yet been enabled\n", + sport->sdev->device->name, port_num); goto reject; } - if ((req->req_flags & SRP_MTCH_ACTION) == SRP_MULTICHAN_SINGLE) { - rsp->rsp_flags = SRP_LOGIN_RSP_MULTICHAN_NO_CHAN; - - mutex_lock(&sdev->mutex); - - list_for_each_entry_safe(ch, tmp_ch, &sdev->rch_list, list) { - if (!memcmp(ch->i_port_id, req->initiator_port_id, 16) - && !memcmp(ch->t_port_id, req->target_port_id, 16) - && param->port == ch->sport->port - && param->listen_id == ch->sport->sdev->cm_id - && ch->cm_id) { - if (srpt_disconnect_ch(ch) < 0) - continue; - pr_info("Relogin - closed existing channel %s\n", - ch->sess_name); - rsp->rsp_flags = - SRP_LOGIN_RSP_MULTICHAN_TERMINATED; - } - } - - mutex_unlock(&sdev->mutex); - - } else - rsp->rsp_flags = SRP_LOGIN_RSP_MULTICHAN_MAINTAINED; - if (*(__be64 *)req->target_port_id != cpu_to_be64(srpt_service_guid) || *(__be64 *)(req->target_port_id + 8) != cpu_to_be64(srpt_service_guid)) { rej->reason = cpu_to_be32( - SRP_LOGIN_REJ_UNABLE_ASSOCIATE_CHANNEL); - ret = -ENOMEM; - pr_err("rejected SRP_LOGIN_REQ because it" - " has an invalid target port identifier.\n"); + SRP_LOGIN_REJ_UNABLE_ASSOCIATE_CHANNEL); + pr_err("rejected SRP_LOGIN_REQ because it has an invalid target port identifier.\n"); goto reject; } + ret = -ENOMEM; ch = kzalloc(sizeof(*ch), GFP_KERNEL); if (!ch) { - rej->reason = cpu_to_be32( - SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); - pr_err("rejected SRP_LOGIN_REQ because no memory.\n"); - ret = -ENOMEM; + rej->reason = cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); + pr_err("rejected SRP_LOGIN_REQ because out of memory.\n"); goto reject; } kref_init(&ch->kref); + ch->pkey = be16_to_cpu(pkey); + ch->nexus = nexus; ch->zw_cqe.done = srpt_zerolength_write_done; INIT_WORK(&ch->release_work, srpt_release_channel_work); - memcpy(ch->i_port_id, req->initiator_port_id, 16); - memcpy(ch->t_port_id, req->target_port_id, 16); - ch->sport = &sdev->port[param->port - 1]; - ch->cm_id = cm_id; + ch->sport = sport; + ch->ib_cm.cm_id = cm_id; cm_id->context = ch; /* * ch->rq_size should be at least as large as the initiator queue * depth to avoid that the initiator driver has to report QUEUE_FULL * to the SCSI mid-layer. */ - ch->rq_size = min(SRPT_RQ_SIZE, sdev->device->attrs.max_qp_wr); + ch->rq_size = min(MAX_SRPT_RQ_SIZE, sdev->device->attrs.max_qp_wr); spin_lock_init(&ch->spinlock); ch->state = CH_CONNECTING; INIT_LIST_HEAD(&ch->cmd_wait_list); - ch->rsp_size = ch->sport->port_attrib.srp_max_rsp_size; + ch->max_rsp_size = ch->sport->port_attrib.srp_max_rsp_size; ch->ioctx_ring = (struct srpt_send_ioctx **) srpt_alloc_ioctx_ring(ch->sport->sdev, ch->rq_size, sizeof(*ch->ioctx_ring[0]), - ch->rsp_size, DMA_TO_DEVICE); - if (!ch->ioctx_ring) + ch->max_rsp_size, DMA_TO_DEVICE); + if (!ch->ioctx_ring) { + pr_err("rejected SRP_LOGIN_REQ because creating a new QP SQ ring failed.\n"); + rej->reason = cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); goto free_ch; + } INIT_LIST_HEAD(&ch->free_list); for (i = 0; i < ch->rq_size; i++) { @@ -2059,59 +2155,88 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); goto free_ring; } + for (i = 0; i < ch->rq_size; i++) + INIT_LIST_HEAD(&ch->ioctx_recv_ring[i]->wait_list); } ret = srpt_create_ch_ib(ch); if (ret) { - rej->reason = cpu_to_be32( - SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); - pr_err("rejected SRP_LOGIN_REQ because creating" - " a new RDMA channel failed.\n"); - goto free_recv_ring; - } - - ret = srpt_ch_qp_rtr(ch, ch->qp); - if (ret) { rej->reason = cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); - pr_err("rejected SRP_LOGIN_REQ because enabling" - " RTR failed (error code = %d)\n", ret); - goto destroy_ib; + pr_err("rejected SRP_LOGIN_REQ because creating a new RDMA channel failed.\n"); + goto free_recv_ring; } - guid = (__be16 *)¶m->primary_path->sgid.global.interface_id; - snprintf(ch->ini_guid, sizeof(ch->ini_guid), "%04x:%04x:%04x:%04x", - be16_to_cpu(guid[0]), be16_to_cpu(guid[1]), - be16_to_cpu(guid[2]), be16_to_cpu(guid[3])); - snprintf(ch->sess_name, sizeof(ch->sess_name), "0x%016llx%016llx", - be64_to_cpu(*(__be64 *)ch->i_port_id), - be64_to_cpu(*(__be64 *)(ch->i_port_id + 8))); + strlcpy(ch->sess_name, src_addr, sizeof(ch->sess_name)); + snprintf(i_port_id, sizeof(i_port_id), "0x%016llx%016llx", + be64_to_cpu(*(__be64 *)nexus->i_port_id), + be64_to_cpu(*(__be64 *)(nexus->i_port_id + 8))); pr_debug("registering session %s\n", ch->sess_name); if (sport->port_guid_tpg.se_tpg_wwn) ch->sess = target_alloc_session(&sport->port_guid_tpg, 0, 0, TARGET_PROT_NORMAL, - ch->ini_guid, ch, NULL); + ch->sess_name, ch, NULL); if (sport->port_gid_tpg.se_tpg_wwn && IS_ERR_OR_NULL(ch->sess)) ch->sess = target_alloc_session(&sport->port_gid_tpg, 0, 0, - TARGET_PROT_NORMAL, ch->sess_name, ch, + TARGET_PROT_NORMAL, i_port_id, ch, NULL); /* Retry without leading "0x" */ if (sport->port_gid_tpg.se_tpg_wwn && IS_ERR_OR_NULL(ch->sess)) ch->sess = target_alloc_session(&sport->port_gid_tpg, 0, 0, TARGET_PROT_NORMAL, - ch->sess_name + 2, ch, NULL); + i_port_id + 2, ch, NULL); if (IS_ERR_OR_NULL(ch->sess)) { - pr_info("Rejected login because no ACL has been configured yet for initiator %s.\n", - ch->sess_name); - rej->reason = cpu_to_be32((PTR_ERR(ch->sess) == -ENOMEM) ? + ret = PTR_ERR(ch->sess); + pr_info("Rejected login for initiator %s: ret = %d.\n", + ch->sess_name, ret); + rej->reason = cpu_to_be32(ret == -ENOMEM ? SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES : SRP_LOGIN_REJ_CHANNEL_LIMIT_REACHED); + goto reject; + } + + mutex_lock(&sport->mutex); + + if ((req->req_flags & SRP_MTCH_ACTION) == SRP_MULTICHAN_SINGLE) { + struct srpt_rdma_ch *ch2; + + rsp->rsp_flags = SRP_LOGIN_RSP_MULTICHAN_NO_CHAN; + + list_for_each_entry(ch2, &nexus->ch_list, list) { + if (srpt_disconnect_ch(ch2) < 0) + continue; + pr_info("Relogin - closed existing channel %s\n", + ch2->sess_name); + rsp->rsp_flags = SRP_LOGIN_RSP_MULTICHAN_TERMINATED; + } + } else { + rsp->rsp_flags = SRP_LOGIN_RSP_MULTICHAN_MAINTAINED; + } + + list_add_tail_rcu(&ch->list, &nexus->ch_list); + + if (!sport->enabled) { + rej->reason = cpu_to_be32( + SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); + pr_info("rejected SRP_LOGIN_REQ because target %s_%d is not enabled\n", + sdev->device->name, port_num); + mutex_unlock(&sport->mutex); + goto reject; + } + + mutex_unlock(&sport->mutex); + + ret = srpt_ch_qp_rtr(ch, ch->qp); + if (ret) { + rej->reason = cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); + pr_err("rejected SRP_LOGIN_REQ because enabling RTR failed (error code = %d)\n", + ret); goto destroy_ib; } - pr_debug("Establish connection sess=%p name=%s cm_id=%p\n", ch->sess, - ch->sess_name, ch->cm_id); + pr_debug("Establish connection sess=%p name=%s ch=%p\n", ch->sess, + ch->sess_name, ch); /* create srp_login_response */ rsp->opcode = SRP_LOGIN_RSP; @@ -2119,8 +2244,8 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, rsp->max_it_iu_len = req->req_it_iu_len; rsp->max_ti_iu_len = req->req_it_iu_len; ch->max_ti_iu_len = it_iu_len; - rsp->buf_fmt = cpu_to_be16(SRP_BUF_FORMAT_DIRECT - | SRP_BUF_FORMAT_INDIRECT); + rsp->buf_fmt = cpu_to_be16(SRP_BUF_FORMAT_DIRECT | + SRP_BUF_FORMAT_INDIRECT); rsp->req_lim_delta = cpu_to_be32(ch->rq_size); atomic_set(&ch->req_lim, ch->rq_size); atomic_set(&ch->req_lim_delta, 0); @@ -2136,25 +2261,31 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, rep_param->responder_resources = 4; rep_param->initiator_depth = 4; - ret = ib_send_cm_rep(cm_id, rep_param); - if (ret) { - pr_err("sending SRP_LOGIN_REQ response failed" - " (error code = %d)\n", ret); - goto release_channel; - } + /* + * Hold the sport mutex while accepting a connection to avoid that + * srpt_disconnect_ch() is invoked concurrently with this code. + */ + mutex_lock(&sport->mutex); + if (sport->enabled && ch->state == CH_CONNECTING) + ret = ib_send_cm_rep(cm_id, rep_param); + else + ret = -EINVAL; + mutex_unlock(&sport->mutex); - mutex_lock(&sdev->mutex); - list_add_tail(&ch->list, &sdev->rch_list); - mutex_unlock(&sdev->mutex); + switch (ret) { + case 0: + break; + case -EINVAL: + goto reject; + default: + rej->reason = cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); + pr_err("sending SRP_LOGIN_REQ response failed (error code = %d)\n", + ret); + goto reject; + } goto out; -release_channel: - srpt_disconnect_ch(ch); - transport_deregister_session_configfs(ch->sess); - transport_deregister_session(ch->sess); - ch->sess = NULL; - destroy_ib: srpt_destroy_ch_ib(ch); @@ -2166,15 +2297,20 @@ free_recv_ring: free_ring: srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_ring, ch->sport->sdev, ch->rq_size, - ch->rsp_size, DMA_TO_DEVICE); + ch->max_rsp_size, DMA_TO_DEVICE); free_ch: + cm_id->context = NULL; kfree(ch); + ch = NULL; + + WARN_ON_ONCE(ret == 0); reject: + pr_info("Rejecting login with reason %#x\n", be32_to_cpu(rej->reason)); rej->opcode = SRP_LOGIN_REJ; rej->tag = req->tag; - rej->buf_fmt = cpu_to_be16(SRP_BUF_FORMAT_DIRECT - | SRP_BUF_FORMAT_INDIRECT); + rej->buf_fmt = cpu_to_be16(SRP_BUF_FORMAT_DIRECT | + SRP_BUF_FORMAT_INDIRECT); ib_send_cm_rej(cm_id, IB_CM_REJ_CONSUMER_DEFINED, NULL, 0, (void *)rej, sizeof(*rej)); @@ -2187,6 +2323,19 @@ out: return ret; } +static int srpt_ib_cm_req_recv(struct ib_cm_id *cm_id, + struct ib_cm_req_event_param *param, + void *private_data) +{ + char sguid[40]; + + srpt_format_guid(sguid, sizeof(sguid), + ¶m->primary_path->dgid.global.interface_id); + + return srpt_cm_req_recv(cm_id, param->port, param->primary_path->pkey, + private_data, sguid); +} + static void srpt_cm_rej_recv(struct srpt_rdma_ch *ch, enum ib_cm_rej_reason reason, const u8 *private_data, @@ -2207,7 +2356,8 @@ static void srpt_cm_rej_recv(struct srpt_rdma_ch *ch, } /** - * srpt_cm_rtu_recv() - Process an IB_CM_RTU_RECEIVED or USER_ESTABLISHED event. + * srpt_cm_rtu_recv - process an IB_CM_RTU_RECEIVED or USER_ESTABLISHED event + * @ch: SRPT RDMA channel. * * An IB_CM_RTU_RECEIVED message indicates that the connection is established * and that the recipient may begin transmitting (RTU = ready to use). @@ -2216,21 +2366,34 @@ static void srpt_cm_rtu_recv(struct srpt_rdma_ch *ch) { int ret; - if (srpt_set_ch_state(ch, CH_LIVE)) { - ret = srpt_ch_qp_rts(ch, ch->qp); + ret = srpt_ch_qp_rts(ch, ch->qp); + if (ret < 0) { + pr_err("%s-%d: QP transition to RTS failed\n", ch->sess_name, + ch->qp->qp_num); + srpt_close_ch(ch); + return; + } - if (ret == 0) { - /* Trigger wait list processing. */ - ret = srpt_zerolength_write(ch); - WARN_ONCE(ret < 0, "%d\n", ret); - } else { - srpt_close_ch(ch); - } + /* + * Note: calling srpt_close_ch() if the transition to the LIVE state + * fails is not necessary since that means that that function has + * already been invoked from another thread. + */ + if (!srpt_set_ch_state(ch, CH_LIVE)) { + pr_err("%s-%d: channel transition to LIVE state failed\n", + ch->sess_name, ch->qp->qp_num); + return; } + + /* Trigger wait list processing. */ + ret = srpt_zerolength_write(ch); + WARN_ONCE(ret < 0, "%d\n", ret); } /** - * srpt_cm_handler() - IB connection manager callback function. + * srpt_cm_handler - IB connection manager callback function + * @cm_id: IB/CM connection identifier. + * @event: IB/CM event. * * A non-zero return value will cause the caller destroy the CM ID. * @@ -2247,8 +2410,8 @@ static int srpt_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event) ret = 0; switch (event->event) { case IB_CM_REQ_RECEIVED: - ret = srpt_cm_req_recv(cm_id, &event->param.req_rcvd, - event->private_data); + ret = srpt_ib_cm_req_recv(cm_id, &event->param.req_rcvd, + event->private_data); break; case IB_CM_REJ_RECEIVED: srpt_cm_rej_recv(ch, event->param.rej_rcvd.reason, @@ -2295,11 +2458,11 @@ static int srpt_write_pending_status(struct se_cmd *se_cmd) struct srpt_send_ioctx *ioctx; ioctx = container_of(se_cmd, struct srpt_send_ioctx, cmd); - return srpt_get_cmd_state(ioctx) == SRPT_STATE_NEED_DATA; + return ioctx->state == SRPT_STATE_NEED_DATA; } /* - * srpt_write_pending() - Start data transfer from initiator to target (write). + * srpt_write_pending - Start data transfer from initiator to target (write). */ static int srpt_write_pending(struct se_cmd *se_cmd) { @@ -2356,7 +2519,8 @@ static u8 tcm_to_srp_tsk_mgmt_status(const int tcm_mgmt_status) } /** - * srpt_queue_response() - Transmits the response to a SCSI command. + * srpt_queue_response - transmit the response to a SCSI command + * @cmd: SCSI target command. * * Callback function called by the TCM core. Must not block since it can be * invoked on the context of the IB completion handler. @@ -2370,13 +2534,11 @@ static void srpt_queue_response(struct se_cmd *cmd) struct ib_send_wr send_wr, *first_wr = &send_wr, *bad_wr; struct ib_sge sge; enum srpt_command_state state; - unsigned long flags; int resp_len, ret, i; u8 srp_tm_status; BUG_ON(!ch); - spin_lock_irqsave(&ioctx->spinlock, flags); state = ioctx->state; switch (state) { case SRPT_STATE_NEW: @@ -2391,7 +2553,6 @@ static void srpt_queue_response(struct se_cmd *cmd) ch, ioctx->ioctx.index, ioctx->state); break; } - spin_unlock_irqrestore(&ioctx->spinlock, flags); if (unlikely(WARN_ON_ONCE(state == SRPT_STATE_CMD_RSP_SENT))) return; @@ -2495,26 +2656,56 @@ static void srpt_refresh_port_work(struct work_struct *work) srpt_refresh_port(sport); } +static bool srpt_ch_list_empty(struct srpt_port *sport) +{ + struct srpt_nexus *nexus; + bool res = true; + + rcu_read_lock(); + list_for_each_entry(nexus, &sport->nexus_list, entry) + if (!list_empty(&nexus->ch_list)) + res = false; + rcu_read_unlock(); + + return res; +} + /** - * srpt_release_sdev() - Free the channel resources associated with a target. + * srpt_release_sport - disable login and wait for associated channels + * @sport: SRPT HCA port. */ -static int srpt_release_sdev(struct srpt_device *sdev) +static int srpt_release_sport(struct srpt_port *sport) { - int i, res; + struct srpt_nexus *nexus, *next_n; + struct srpt_rdma_ch *ch; WARN_ON_ONCE(irqs_disabled()); - BUG_ON(!sdev); - - mutex_lock(&sdev->mutex); - for (i = 0; i < ARRAY_SIZE(sdev->port); i++) - srpt_set_enabled(&sdev->port[i], false); - mutex_unlock(&sdev->mutex); + mutex_lock(&sport->mutex); + srpt_set_enabled(sport, false); + mutex_unlock(&sport->mutex); + + while (wait_event_timeout(sport->ch_releaseQ, + srpt_ch_list_empty(sport), 5 * HZ) <= 0) { + pr_info("%s_%d: waiting for session unregistration ...\n", + sport->sdev->device->name, sport->port); + rcu_read_lock(); + list_for_each_entry(nexus, &sport->nexus_list, entry) { + list_for_each_entry(ch, &nexus->ch_list, list) { + pr_info("%s-%d: state %s\n", + ch->sess_name, ch->qp->qp_num, + get_ch_state_name(ch->state)); + } + } + rcu_read_unlock(); + } - res = wait_event_interruptible(sdev->ch_releaseQ, - list_empty_careful(&sdev->rch_list)); - if (res) - pr_err("%s: interrupted.\n", __func__); + mutex_lock(&sport->mutex); + list_for_each_entry_safe(nexus, next_n, &sport->nexus_list, entry) { + list_del(&nexus->entry); + kfree_rcu(nexus, rcu); + } + mutex_unlock(&sport->mutex); return 0; } @@ -2601,8 +2792,10 @@ static int srpt_alloc_srq(struct srpt_device *sdev) sdev->use_srq = true; sdev->srq = srq; - for (i = 0; i < sdev->srq_size; ++i) + for (i = 0; i < sdev->srq_size; ++i) { + INIT_LIST_HEAD(&sdev->ioctx_ring[i]->wait_list); srpt_post_recv(sdev, NULL, sdev->ioctx_ring[i]); + } return 0; } @@ -2624,7 +2817,8 @@ static int srpt_use_srq(struct srpt_device *sdev, bool use_srq) } /** - * srpt_add_one() - Infiniband device addition callback function. + * srpt_add_one - InfiniBand device addition callback function + * @device: Describes a HCA. */ static void srpt_add_one(struct ib_device *device) { @@ -2639,9 +2833,7 @@ static void srpt_add_one(struct ib_device *device) goto err; sdev->device = device; - INIT_LIST_HEAD(&sdev->rch_list); - init_waitqueue_head(&sdev->ch_releaseQ); - mutex_init(&sdev->mutex); + mutex_init(&sdev->sdev_mutex); sdev->pd = ib_alloc_pd(device, 0); if (IS_ERR(sdev->pd)) @@ -2682,6 +2874,9 @@ static void srpt_add_one(struct ib_device *device) for (i = 1; i <= sdev->device->phys_port_cnt; i++) { sport = &sdev->port[i - 1]; + INIT_LIST_HEAD(&sport->nexus_list); + init_waitqueue_head(&sport->ch_releaseQ); + mutex_init(&sport->mutex); sport->sdev = sdev; sport->port = i; sport->port_attrib.srp_max_rdma_size = DEFAULT_MAX_RDMA_SIZE; @@ -2722,7 +2917,9 @@ err: } /** - * srpt_remove_one() - InfiniBand device removal callback function. + * srpt_remove_one - InfiniBand device removal callback function + * @device: Describes a HCA. + * @client_data: The value passed as the third argument to ib_set_client_data(). */ static void srpt_remove_one(struct ib_device *device, void *client_data) { @@ -2752,7 +2949,9 @@ static void srpt_remove_one(struct ib_device *device, void *client_data) spin_lock(&srpt_dev_lock); list_del(&sdev->list); spin_unlock(&srpt_dev_lock); - srpt_release_sdev(sdev); + + for (i = 0; i < sdev->device->phys_port_cnt; i++) + srpt_release_sport(&sdev->port[i]); srpt_free_srq(sdev); @@ -2828,7 +3027,8 @@ static void srpt_release_cmd(struct se_cmd *se_cmd) } /** - * srpt_close_session() - Forcibly close a session. + * srpt_close_session - forcibly close a session + * @se_sess: SCSI target session. * * Callback function invoked by the TCM core to clean up sessions associated * with a node ACL when the user invokes @@ -2837,15 +3037,13 @@ static void srpt_release_cmd(struct se_cmd *se_cmd) static void srpt_close_session(struct se_session *se_sess) { struct srpt_rdma_ch *ch = se_sess->fabric_sess_ptr; - struct srpt_device *sdev = ch->sport->sdev; - mutex_lock(&sdev->mutex); srpt_disconnect_ch_sync(ch); - mutex_unlock(&sdev->mutex); } /** - * srpt_sess_get_index() - Return the value of scsiAttIntrPortIndex (SCSI-MIB). + * srpt_sess_get_index - return the value of scsiAttIntrPortIndex (SCSI-MIB) + * @se_sess: SCSI target session. * * A quote from RFC 4455 (SCSI-MIB) about this MIB object: * This object represents an arbitrary integer used to uniquely identify a @@ -2867,7 +3065,7 @@ static int srpt_get_tcm_cmd_state(struct se_cmd *se_cmd) struct srpt_send_ioctx *ioctx; ioctx = container_of(se_cmd, struct srpt_send_ioctx, cmd); - return srpt_get_cmd_state(ioctx); + return ioctx->state; } static int srpt_parse_guid(u64 *guid, const char *name) @@ -2884,7 +3082,7 @@ out: } /** - * srpt_parse_i_port_id() - Parse an initiator port ID. + * srpt_parse_i_port_id - parse an initiator port ID * @name: ASCII representation of a 128-bit initiator port ID. * @i_port_id: Binary 128-bit port ID. */ @@ -3065,18 +3263,24 @@ static ssize_t srpt_tpg_attrib_use_srq_store(struct config_item *item, if (val != !!val) return -EINVAL; - ret = mutex_lock_interruptible(&sdev->mutex); + ret = mutex_lock_interruptible(&sdev->sdev_mutex); if (ret < 0) return ret; + ret = mutex_lock_interruptible(&sport->mutex); + if (ret < 0) + goto unlock_sdev; enabled = sport->enabled; /* Log out all initiator systems before changing 'use_srq'. */ srpt_set_enabled(sport, false); sport->port_attrib.use_srq = val; srpt_use_srq(sdev, sport->port_attrib.use_srq); srpt_set_enabled(sport, enabled); - mutex_unlock(&sdev->mutex); + ret = count; + mutex_unlock(&sport->mutex); +unlock_sdev: + mutex_unlock(&sdev->sdev_mutex); - return count; + return ret; } CONFIGFS_ATTR(srpt_tpg_attrib_, srp_max_rdma_size); @@ -3105,7 +3309,6 @@ static ssize_t srpt_tpg_enable_store(struct config_item *item, { struct se_portal_group *se_tpg = to_tpg(item); struct srpt_port *sport = srpt_tpg_to_sport(se_tpg); - struct srpt_device *sdev = sport->sdev; unsigned long tmp; int ret; @@ -3120,9 +3323,9 @@ static ssize_t srpt_tpg_enable_store(struct config_item *item, return -EINVAL; } - mutex_lock(&sdev->mutex); + mutex_lock(&sport->mutex); srpt_set_enabled(sport, tmp); - mutex_unlock(&sdev->mutex); + mutex_unlock(&sport->mutex); return count; } @@ -3135,8 +3338,10 @@ static struct configfs_attribute *srpt_tpg_attrs[] = { }; /** - * configfs callback invoked for - * mkdir /sys/kernel/config/target/$driver/$port/$tpg + * srpt_make_tpg - configfs callback invoked for mkdir /sys/kernel/config/target/$driver/$port/$tpg + * @wwn: Corresponds to $driver/$port. + * @group: Not used. + * @name: $tpg. */ static struct se_portal_group *srpt_make_tpg(struct se_wwn *wwn, struct config_group *group, @@ -3158,8 +3363,8 @@ static struct se_portal_group *srpt_make_tpg(struct se_wwn *wwn, } /** - * configfs callback invoked for - * rmdir /sys/kernel/config/target/$driver/$port/$tpg + * srpt_drop_tpg - configfs callback invoked for rmdir /sys/kernel/config/target/$driver/$port/$tpg + * @tpg: Target portal group to deregister. */ static void srpt_drop_tpg(struct se_portal_group *tpg) { @@ -3170,8 +3375,10 @@ static void srpt_drop_tpg(struct se_portal_group *tpg) } /** - * configfs callback invoked for - * mkdir /sys/kernel/config/target/$driver/$port + * srpt_make_tport - configfs callback invoked for mkdir /sys/kernel/config/target/$driver/$port + * @tf: Not used. + * @group: Not used. + * @name: $port. */ static struct se_wwn *srpt_make_tport(struct target_fabric_configfs *tf, struct config_group *group, @@ -3181,8 +3388,8 @@ static struct se_wwn *srpt_make_tport(struct target_fabric_configfs *tf, } /** - * configfs callback invoked for - * rmdir /sys/kernel/config/target/$driver/$port + * srpt_drop_tport - configfs callback invoked for rmdir /sys/kernel/config/target/$driver/$port + * @wwn: $port. */ static void srpt_drop_tport(struct se_wwn *wwn) { @@ -3240,7 +3447,7 @@ static const struct target_core_fabric_ops srpt_template = { }; /** - * srpt_init_module() - Kernel module initialization. + * srpt_init_module - kernel module initialization * * Note: Since ib_register_client() registers callback functions, and since at * least one of these callback functions (srpt_add_one()) calls target core diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h index 673387d365a3..4d9199fd00dc 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.h +++ b/drivers/infiniband/ulp/srpt/ib_srpt.h @@ -54,6 +54,8 @@ */ #define SRP_SERVICE_NAME_PREFIX "SRP.T10:" +struct srpt_nexus; + enum { /* * SRP IOControllerProfile attributes for SRP target ports that have @@ -114,7 +116,7 @@ enum { MIN_SRPT_SQ_SIZE = 16, DEF_SRPT_SQ_SIZE = 4096, - SRPT_RQ_SIZE = 128, + MAX_SRPT_RQ_SIZE = 128, MIN_SRPT_SRQ_SIZE = 4, DEFAULT_SRPT_SRQ_SIZE = 4095, MAX_SRPT_SRQ_SIZE = 65535, @@ -134,7 +136,7 @@ enum { }; /** - * enum srpt_command_state - SCSI command state managed by SRPT. + * enum srpt_command_state - SCSI command state managed by SRPT * @SRPT_STATE_NEW: New command arrived and is being processed. * @SRPT_STATE_NEED_DATA: Processing a write or bidir command and waiting * for data arrival. @@ -158,7 +160,8 @@ enum srpt_command_state { }; /** - * struct srpt_ioctx - Shared SRPT I/O context information. + * struct srpt_ioctx - shared SRPT I/O context information + * @cqe: Completion queue element. * @buf: Pointer to the buffer. * @dma: DMA address of the buffer. * @index: Index of the I/O context in its ioctx_ring array. @@ -171,7 +174,7 @@ struct srpt_ioctx { }; /** - * struct srpt_recv_ioctx - SRPT receive I/O context. + * struct srpt_recv_ioctx - SRPT receive I/O context * @ioctx: See above. * @wait_list: Node for insertion in srpt_rdma_ch.cmd_wait_list. */ @@ -187,13 +190,20 @@ struct srpt_rw_ctx { }; /** - * struct srpt_send_ioctx - SRPT send I/O context. + * struct srpt_send_ioctx - SRPT send I/O context * @ioctx: See above. * @ch: Channel pointer. - * @spinlock: Protects 'state'. + * @s_rw_ctx: @rw_ctxs points here if only a single rw_ctx is needed. + * @rw_ctxs: RDMA read/write contexts. + * @rdma_cqe: RDMA completion queue element. + * @free_list: Node in srpt_rdma_ch.free_list. * @state: I/O context state. * @cmd: Target core command data structure. * @sense_data: SCSI sense data. + * @n_rdma: Number of work requests needed to transfer this ioctx. + * @n_rw_ctx: Size of rw_ctxs array. + * @queue_status_only: Send a SCSI status back to the initiator but no data. + * @sense_data: Sense data to be sent to the initiator. */ struct srpt_send_ioctx { struct srpt_ioctx ioctx; @@ -204,10 +214,8 @@ struct srpt_send_ioctx { struct ib_cqe rdma_cqe; struct list_head free_list; - spinlock_t spinlock; enum srpt_command_state state; struct se_cmd cmd; - struct completion tx_done; u8 n_rdma; u8 n_rw_ctx; bool queue_status_only; @@ -215,7 +223,7 @@ struct srpt_send_ioctx { }; /** - * enum rdma_ch_state - SRP channel state. + * enum rdma_ch_state - SRP channel state * @CH_CONNECTING: QP is in RTR state; waiting for RTU. * @CH_LIVE: QP is in RTS state. * @CH_DISCONNECTING: DREQ has been sent and waiting for DREP or DREQ has @@ -233,17 +241,19 @@ enum rdma_ch_state { }; /** - * struct srpt_rdma_ch - RDMA channel. - * @cm_id: IB CM ID associated with the channel. + * struct srpt_rdma_ch - RDMA channel + * @nexus: I_T nexus this channel is associated with. * @qp: IB queue pair used for communicating over this channel. + * @cm_id: IB CM ID associated with the channel. * @cq: IB completion queue for this channel. + * @zw_cqe: Zero-length write CQE. + * @rcu: RCU head. + * @kref: kref for this channel. * @rq_size: IB receive queue size. - * @rsp_size IB response message size in bytes. + * @max_rsp_size: Maximum size of an RSP response message in bytes. * @sq_wr_avail: number of work requests available in the send queue. * @sport: pointer to the information of the HCA port used by this * channel. - * @i_port_id: 128-bit initiator port identifier copied from SRP_LOGIN_REQ. - * @t_port_id: 128-bit target port identifier copied from SRP_LOGIN_REQ. * @max_ti_iu_len: maximum target-to-initiator information unit length. * @req_lim: request limit: maximum number of requests that may be sent * by the initiator without having received a response. @@ -251,30 +261,34 @@ enum rdma_ch_state { * @spinlock: Protects free_list and state. * @free_list: Head of list with free send I/O contexts. * @state: channel state. See also enum rdma_ch_state. + * @processing_wait_list: Whether or not cmd_wait_list is being processed. * @ioctx_ring: Send ring. * @ioctx_recv_ring: Receive I/O context ring. - * @list: Node for insertion in the srpt_device.rch_list list. + * @list: Node in srpt_nexus.ch_list. * @cmd_wait_list: List of SCSI commands that arrived before the RTU event. This * list contains struct srpt_ioctx elements and is protected * against concurrent modification by the cm_id spinlock. + * @pkey: P_Key of the IB partition for this SRP channel. * @sess: Session information associated with this SRP channel. * @sess_name: Session name. - * @ini_guid: Initiator port GUID. * @release_work: Allows scheduling of srpt_release_channel(). - * @release_done: Enables waiting for srpt_release_channel() completion. */ struct srpt_rdma_ch { - struct ib_cm_id *cm_id; + struct srpt_nexus *nexus; struct ib_qp *qp; + union { + struct { + struct ib_cm_id *cm_id; + } ib_cm; + }; struct ib_cq *cq; struct ib_cqe zw_cqe; + struct rcu_head rcu; struct kref kref; int rq_size; - u32 rsp_size; + u32 max_rsp_size; atomic_t sq_wr_avail; struct srpt_port *sport; - u8 i_port_id[16]; - u8 t_port_id[16]; int max_ti_iu_len; atomic_t req_lim; atomic_t req_lim_delta; @@ -285,15 +299,31 @@ struct srpt_rdma_ch { struct srpt_recv_ioctx **ioctx_recv_ring; struct list_head list; struct list_head cmd_wait_list; + uint16_t pkey; + bool processing_wait_list; struct se_session *sess; - u8 sess_name[36]; - u8 ini_guid[24]; + u8 sess_name[24]; struct work_struct release_work; - struct completion *release_done; }; /** - * struct srpt_port_attib - Attributes for SRPT port + * struct srpt_nexus - I_T nexus + * @rcu: RCU head for this data structure. + * @entry: srpt_port.nexus_list list node. + * @ch_list: struct srpt_rdma_ch list. Protected by srpt_port.mutex. + * @i_port_id: 128-bit initiator port identifier copied from SRP_LOGIN_REQ. + * @t_port_id: 128-bit target port identifier copied from SRP_LOGIN_REQ. + */ +struct srpt_nexus { + struct rcu_head rcu; + struct list_head entry; + struct list_head ch_list; + u8 i_port_id[16]; + u8 t_port_id[16]; +}; + +/** + * struct srpt_port_attib - attributes for SRPT port * @srp_max_rdma_size: Maximum size of SRP RDMA transfers for new connections. * @srp_max_rsp_size: Maximum size of SRP response messages in bytes. * @srp_sq_size: Shared receive queue (SRQ) size. @@ -307,7 +337,7 @@ struct srpt_port_attrib { }; /** - * struct srpt_port - Information associated by SRPT with a single IB port. + * struct srpt_port - information associated by SRPT with a single IB port * @sdev: backpointer to the HCA information. * @mad_agent: per-port management datagram processing information. * @enabled: Whether or not this target port is enabled. @@ -323,7 +353,10 @@ struct srpt_port_attrib { * @port_guid_wwn: WWN associated with target port GUID. * @port_gid_tpg: TPG associated with target port GID. * @port_gid_wwn: WWN associated with target port GID. - * @port_acl_list: Head of the list with all node ACLs for this port. + * @port_attrib: Port attributes that can be accessed through configfs. + * @ch_releaseQ: Enables waiting for removal from nexus_list. + * @mutex: Protects nexus_list. + * @nexus_list: Nexus list. See also srpt_nexus.entry. */ struct srpt_port { struct srpt_device *sdev; @@ -341,21 +374,22 @@ struct srpt_port { struct se_portal_group port_gid_tpg; struct se_wwn port_gid_wwn; struct srpt_port_attrib port_attrib; + wait_queue_head_t ch_releaseQ; + struct mutex mutex; + struct list_head nexus_list; }; /** - * struct srpt_device - Information associated by SRPT with a single HCA. + * struct srpt_device - information associated by SRPT with a single HCA * @device: Backpointer to the struct ib_device managed by the IB core. * @pd: IB protection domain. * @lkey: L_Key (local key) with write access to all local memory. * @srq: Per-HCA SRQ (shared receive queue). * @cm_id: Connection identifier. * @srq_size: SRQ size. + * @sdev_mutex: Serializes use_srq changes. * @use_srq: Whether or not to use SRQ. * @ioctx_ring: Per-HCA SRQ. - * @rch_list: Per-device channel list -- see also srpt_rdma_ch.list. - * @ch_releaseQ: Enables waiting for removal from rch_list. - * @mutex: Protects rch_list. * @port: Information about the ports owned by this HCA. * @event_handler: Per-HCA asynchronous IB event handler. * @list: Node in srpt_dev_list. @@ -367,11 +401,9 @@ struct srpt_device { struct ib_srq *srq; struct ib_cm_id *cm_id; int srq_size; + struct mutex sdev_mutex; bool use_srq; struct srpt_recv_ioctx **ioctx_ring; - struct list_head rch_list; - wait_queue_head_t ch_releaseQ; - struct mutex mutex; struct srpt_port port[2]; struct ib_event_handler event_handler; struct list_head list; |