diff options
Diffstat (limited to 'drivers/infiniband/ulp/ipoib/ipoib_ib.c')
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_ib.c | 364 |
1 files changed, 197 insertions, 167 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 12c4f84a6639..0060b2f9f659 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -52,7 +52,7 @@ MODULE_PARM_DESC(data_debug_level, #endif struct ipoib_ah *ipoib_create_ah(struct net_device *dev, - struct ib_pd *pd, struct ib_ah_attr *attr) + struct ib_pd *pd, struct rdma_ah_attr *attr) { struct ipoib_ah *ah; struct ib_ah *vah; @@ -65,13 +65,13 @@ struct ipoib_ah *ipoib_create_ah(struct net_device *dev, ah->last_send = 0; kref_init(&ah->ref); - vah = ib_create_ah(pd, attr); + vah = rdma_create_ah(pd, attr); if (IS_ERR(vah)) { kfree(ah); ah = (struct ipoib_ah *)vah; } else { ah->ah = vah; - ipoib_dbg(netdev_priv(dev), "Created ah %p\n", ah->ah); + ipoib_dbg(ipoib_priv(dev), "Created ah %p\n", ah->ah); } return ah; @@ -80,7 +80,7 @@ struct ipoib_ah *ipoib_create_ah(struct net_device *dev, void ipoib_free_ah(struct kref *kref) { struct ipoib_ah *ah = container_of(kref, struct ipoib_ah, ref); - struct ipoib_dev_priv *priv = netdev_priv(ah->dev); + struct ipoib_dev_priv *priv = ipoib_priv(ah->dev); unsigned long flags; @@ -99,7 +99,7 @@ static void ipoib_ud_dma_unmap_rx(struct ipoib_dev_priv *priv, static int ipoib_ib_post_receive(struct net_device *dev, int id) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ib_recv_wr *bad_wr; int ret; @@ -121,7 +121,7 @@ static int ipoib_ib_post_receive(struct net_device *dev, int id) static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sk_buff *skb; int buf_size; u64 *mapping; @@ -153,7 +153,7 @@ error: static int ipoib_ib_post_receives(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); int i; for (i = 0; i < ipoib_recvq_size; ++i) { @@ -172,7 +172,7 @@ static int ipoib_ib_post_receives(struct net_device *dev) static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); unsigned int wr_id = wc->wr_id & ~IPOIB_OP_RECV; struct sk_buff *skb; u64 mapping[IPOIB_UD_RX_SG]; @@ -381,7 +381,7 @@ free_res: static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); unsigned int wr_id = wc->wr_id; struct ipoib_tx_buf *tx_req; @@ -485,14 +485,14 @@ poll_more: void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr) { struct net_device *dev = dev_ptr; - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); napi_schedule(&priv->napi); } static void drain_tx_cq(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); netif_tx_lock(dev); while (poll_tx(priv)) @@ -506,14 +506,14 @@ static void drain_tx_cq(struct net_device *dev) void ipoib_send_comp_handler(struct ib_cq *cq, void *dev_ptr) { - struct ipoib_dev_priv *priv = netdev_priv(dev_ptr); + struct ipoib_dev_priv *priv = ipoib_priv(dev_ptr); mod_timer(&priv->poll_timer, jiffies); } static inline int post_send(struct ipoib_dev_priv *priv, unsigned int wr_id, - struct ib_ah *address, u32 qpn, + struct ib_ah *address, u32 dqpn, struct ipoib_tx_buf *tx_req, void *head, int hlen) { @@ -523,7 +523,7 @@ static inline int post_send(struct ipoib_dev_priv *priv, ipoib_build_sge(priv, tx_req); priv->tx_wr.wr.wr_id = wr_id; - priv->tx_wr.remote_qpn = qpn; + priv->tx_wr.remote_qpn = dqpn; priv->tx_wr.ah = address; if (head) { @@ -537,10 +537,10 @@ static inline int post_send(struct ipoib_dev_priv *priv, return ib_post_send(priv->qp, &priv->tx_wr.wr, &bad_wr); } -void ipoib_send(struct net_device *dev, struct sk_buff *skb, - struct ipoib_ah *address, u32 qpn) +int ipoib_send(struct net_device *dev, struct sk_buff *skb, + struct ib_ah *address, u32 dqpn) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_tx_buf *tx_req; int hlen, rc; void *phead; @@ -554,7 +554,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, ++dev->stats.tx_dropped; ++dev->stats.tx_errors; dev_kfree_skb_any(skb); - return; + return -1; } } else { if (unlikely(skb->len > priv->mcast_mtu + IPOIB_ENCAP_LEN)) { @@ -563,7 +563,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, ++dev->stats.tx_dropped; ++dev->stats.tx_errors; ipoib_cm_skb_too_long(dev, skb, priv->mcast_mtu); - return; + return -1; } phead = NULL; hlen = 0; @@ -574,7 +574,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, ++dev->stats.tx_dropped; ++dev->stats.tx_errors; dev_kfree_skb_any(skb); - return; + return -1; } /* Does skb_linearize return ok without reducing nr_frags? */ if (skb_shinfo(skb)->nr_frags > usable_sge) { @@ -582,12 +582,13 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, ++dev->stats.tx_dropped; ++dev->stats.tx_errors; dev_kfree_skb_any(skb); - return; + return -1; } } - ipoib_dbg_data(priv, "sending packet, length=%d address=%p qpn=0x%06x\n", - skb->len, address, qpn); + ipoib_dbg_data(priv, + "sending packet, length=%d address=%p dqpn=0x%06x\n", + skb->len, address, dqpn); /* * We put the skb into the tx_ring _before_ we call post_send() @@ -601,7 +602,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, if (unlikely(ipoib_dma_map_tx(priv->ca, tx_req))) { ++dev->stats.tx_errors; dev_kfree_skb_any(skb); - return; + return -1; } if (skb->ip_summed == CHECKSUM_PARTIAL) @@ -620,7 +621,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, skb_dst_drop(skb); rc = post_send(priv, priv->tx_head & (ipoib_sendq_size - 1), - address->ah, qpn, tx_req, phead, hlen); + address, dqpn, tx_req, phead, hlen); if (unlikely(rc)) { ipoib_warn(priv, "post_send failed, error %d\n", rc); ++dev->stats.tx_errors; @@ -629,21 +630,24 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, dev_kfree_skb_any(skb); if (netif_queue_stopped(dev)) netif_wake_queue(dev); + rc = 0; } else { netif_trans_update(dev); - address->last_send = priv->tx_head; + rc = priv->tx_head; ++priv->tx_head; } if (unlikely(priv->tx_outstanding > MAX_SEND_CQE)) while (poll_tx(priv)) ; /* nothing */ + + return rc; } static void __ipoib_reap_ah(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_ah *ah, *tah; LIST_HEAD(remove_list); unsigned long flags; @@ -654,7 +658,7 @@ static void __ipoib_reap_ah(struct net_device *dev) list_for_each_entry_safe(ah, tah, &priv->dead_ahs, list) if ((int) priv->tx_tail - (int) ah->last_send >= 0) { list_del(&ah->list); - ib_destroy_ah(ah->ah); + rdma_destroy_ah(ah->ah); kfree(ah); } @@ -677,7 +681,7 @@ void ipoib_reap_ah(struct work_struct *work) static void ipoib_flush_ah(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); cancel_delayed_work(&priv->ah_reap_task); flush_workqueue(priv->wq); @@ -686,30 +690,124 @@ static void ipoib_flush_ah(struct net_device *dev) static void ipoib_stop_ah(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); set_bit(IPOIB_STOP_REAPER, &priv->flags); ipoib_flush_ah(dev); } -static void ipoib_ib_tx_timer_func(unsigned long ctx) +static int recvs_pending(struct net_device *dev) { - drain_tx_cq((struct net_device *)ctx); + struct ipoib_dev_priv *priv = ipoib_priv(dev); + int pending = 0; + int i; + + for (i = 0; i < ipoib_recvq_size; ++i) + if (priv->rx_ring[i].skb) + ++pending; + + return pending; } -int ipoib_ib_dev_open(struct net_device *dev) +int ipoib_ib_dev_stop_default(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); - int ret; + struct ipoib_dev_priv *priv = ipoib_priv(dev); + struct ib_qp_attr qp_attr; + unsigned long begin; + struct ipoib_tx_buf *tx_req; + int i; - ipoib_pkey_dev_check_presence(dev); + if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) + napi_disable(&priv->napi); - if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) { - ipoib_warn(priv, "P_Key 0x%04x is %s\n", priv->pkey, - (!(priv->pkey & 0x7fff) ? "Invalid" : "not found")); - return -1; + ipoib_cm_dev_stop(dev); + + /* + * Move our QP to the error state and then reinitialize in + * when all work requests have completed or have been flushed. + */ + qp_attr.qp_state = IB_QPS_ERR; + if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE)) + ipoib_warn(priv, "Failed to modify QP to ERROR state\n"); + + /* Wait for all sends and receives to complete */ + begin = jiffies; + + while (priv->tx_head != priv->tx_tail || recvs_pending(dev)) { + if (time_after(jiffies, begin + 5 * HZ)) { + ipoib_warn(priv, + "timing out; %d sends %d receives not completed\n", + priv->tx_head - priv->tx_tail, + recvs_pending(dev)); + + /* + * assume the HW is wedged and just free up + * all our pending work requests. + */ + while ((int)priv->tx_tail - (int)priv->tx_head < 0) { + tx_req = &priv->tx_ring[priv->tx_tail & + (ipoib_sendq_size - 1)]; + ipoib_dma_unmap_tx(priv, tx_req); + dev_kfree_skb_any(tx_req->skb); + ++priv->tx_tail; + --priv->tx_outstanding; + } + + for (i = 0; i < ipoib_recvq_size; ++i) { + struct ipoib_rx_buf *rx_req; + + rx_req = &priv->rx_ring[i]; + if (!rx_req->skb) + continue; + ipoib_ud_dma_unmap_rx(priv, + priv->rx_ring[i].mapping); + dev_kfree_skb_any(rx_req->skb); + rx_req->skb = NULL; + } + + goto timeout; + } + + ipoib_drain_cq(dev); + + msleep(1); } + ipoib_dbg(priv, "All sends and receives done.\n"); + +timeout: + del_timer_sync(&priv->poll_timer); + qp_attr.qp_state = IB_QPS_RESET; + if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE)) + ipoib_warn(priv, "Failed to modify QP to RESET state\n"); + + ib_req_notify_cq(priv->recv_cq, IB_CQ_NEXT_COMP); + + return 0; +} + +int ipoib_ib_dev_stop(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + priv->rn_ops->ndo_stop(dev); + + clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); + ipoib_flush_ah(dev); + + return 0; +} + +void ipoib_ib_tx_timer_func(unsigned long ctx) +{ + drain_tx_cq((struct net_device *)ctx); +} + +int ipoib_ib_dev_open_default(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + int ret; + ret = ipoib_init_qp(dev); if (ret) { ipoib_warn(priv, "ipoib_init_qp returned %d\n", ret); @@ -719,33 +817,60 @@ int ipoib_ib_dev_open(struct net_device *dev) ret = ipoib_ib_post_receives(dev); if (ret) { ipoib_warn(priv, "ipoib_ib_post_receives returned %d\n", ret); - goto dev_stop; + goto out; } ret = ipoib_cm_dev_open(dev); if (ret) { ipoib_warn(priv, "ipoib_cm_dev_open returned %d\n", ret); - goto dev_stop; + goto out; + } + + if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) + napi_enable(&priv->napi); + + return 0; +out: + return -1; +} + +int ipoib_ib_dev_open(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + ipoib_pkey_dev_check_presence(dev); + + if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) { + ipoib_warn(priv, "P_Key 0x%04x is %s\n", priv->pkey, + (!(priv->pkey & 0x7fff) ? "Invalid" : "not found")); + return -1; } clear_bit(IPOIB_STOP_REAPER, &priv->flags); queue_delayed_work(priv->wq, &priv->ah_reap_task, round_jiffies_relative(HZ)); - if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) - napi_enable(&priv->napi); + if (priv->rn_ops->ndo_open(dev)) { + pr_warn("%s: Failed to open dev\n", dev->name); + goto dev_stop; + } + + set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); return 0; + dev_stop: - if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) - napi_enable(&priv->napi); + set_bit(IPOIB_STOP_REAPER, &priv->flags); + cancel_delayed_work(&priv->ah_reap_task); + set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); + napi_enable(&priv->napi); ipoib_ib_dev_stop(dev); return -1; } void ipoib_pkey_dev_check_presence(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!(priv->pkey & 0x7fff) || ib_find_pkey(priv->ca, priv->port, priv->pkey, @@ -757,7 +882,7 @@ void ipoib_pkey_dev_check_presence(struct net_device *dev) void ipoib_ib_dev_up(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_pkey_dev_check_presence(dev); @@ -773,7 +898,7 @@ void ipoib_ib_dev_up(struct net_device *dev) void ipoib_ib_dev_down(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "downing ib_dev\n"); @@ -786,22 +911,9 @@ void ipoib_ib_dev_down(struct net_device *dev) ipoib_flush_paths(dev); } -static int recvs_pending(struct net_device *dev) -{ - struct ipoib_dev_priv *priv = netdev_priv(dev); - int pending = 0; - int i; - - for (i = 0; i < ipoib_recvq_size; ++i) - if (priv->rx_ring[i].skb) - ++pending; - - return pending; -} - void ipoib_drain_cq(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); int i, n; /* @@ -838,107 +950,6 @@ void ipoib_drain_cq(struct net_device *dev) local_bh_enable(); } -void ipoib_ib_dev_stop(struct net_device *dev) -{ - struct ipoib_dev_priv *priv = netdev_priv(dev); - struct ib_qp_attr qp_attr; - unsigned long begin; - struct ipoib_tx_buf *tx_req; - int i; - - if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) - napi_disable(&priv->napi); - - ipoib_cm_dev_stop(dev); - - /* - * Move our QP to the error state and then reinitialize in - * when all work requests have completed or have been flushed. - */ - qp_attr.qp_state = IB_QPS_ERR; - if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE)) - ipoib_warn(priv, "Failed to modify QP to ERROR state\n"); - - /* Wait for all sends and receives to complete */ - begin = jiffies; - - while (priv->tx_head != priv->tx_tail || recvs_pending(dev)) { - if (time_after(jiffies, begin + 5 * HZ)) { - ipoib_warn(priv, "timing out; %d sends %d receives not completed\n", - priv->tx_head - priv->tx_tail, recvs_pending(dev)); - - /* - * assume the HW is wedged and just free up - * all our pending work requests. - */ - while ((int) priv->tx_tail - (int) priv->tx_head < 0) { - tx_req = &priv->tx_ring[priv->tx_tail & - (ipoib_sendq_size - 1)]; - ipoib_dma_unmap_tx(priv, tx_req); - dev_kfree_skb_any(tx_req->skb); - ++priv->tx_tail; - --priv->tx_outstanding; - } - - for (i = 0; i < ipoib_recvq_size; ++i) { - struct ipoib_rx_buf *rx_req; - - rx_req = &priv->rx_ring[i]; - if (!rx_req->skb) - continue; - ipoib_ud_dma_unmap_rx(priv, - priv->rx_ring[i].mapping); - dev_kfree_skb_any(rx_req->skb); - rx_req->skb = NULL; - } - - goto timeout; - } - - ipoib_drain_cq(dev); - - msleep(1); - } - - ipoib_dbg(priv, "All sends and receives done.\n"); - -timeout: - del_timer_sync(&priv->poll_timer); - qp_attr.qp_state = IB_QPS_RESET; - if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE)) - ipoib_warn(priv, "Failed to modify QP to RESET state\n"); - - ipoib_flush_ah(dev); - - ib_req_notify_cq(priv->recv_cq, IB_CQ_NEXT_COMP); -} - -int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port) -{ - struct ipoib_dev_priv *priv = netdev_priv(dev); - - priv->ca = ca; - priv->port = port; - priv->qp = NULL; - - if (ipoib_transport_dev_init(dev, ca)) { - printk(KERN_WARNING "%s: ipoib_transport_dev_init failed\n", ca->name); - return -ENODEV; - } - - setup_timer(&priv->poll_timer, ipoib_ib_tx_timer_func, - (unsigned long) dev); - - if (dev->flags & IFF_UP) { - if (ipoib_ib_dev_open(dev)) { - ipoib_transport_dev_cleanup(dev); - return -ENODEV; - } - } - - return 0; -} - /* * Takes whatever value which is in pkey index 0 and updates priv->pkey * returns 0 if the pkey value was changed. @@ -967,6 +978,19 @@ static inline int update_parent_pkey(struct ipoib_dev_priv *priv) */ priv->dev->broadcast[8] = priv->pkey >> 8; priv->dev->broadcast[9] = priv->pkey & 0xff; + + /* + * Update the broadcast address in the priv->broadcast object, + * in case it already exists, otherwise no one will do that. + */ + if (priv->broadcast) { + spin_lock_irq(&priv->lock); + memcpy(priv->broadcast->mcmember.mgid.raw, + priv->dev->broadcast + 4, + sizeof(union ib_gid)); + spin_unlock_irq(&priv->lock); + } + return 0; } @@ -1216,7 +1240,7 @@ void ipoib_ib_dev_flush_heavy(struct work_struct *work) void ipoib_ib_dev_cleanup(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "cleaning up ib_dev\n"); /* @@ -1236,7 +1260,13 @@ void ipoib_ib_dev_cleanup(struct net_device *dev) */ ipoib_stop_ah(dev); - ipoib_transport_dev_cleanup(dev); -} + clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags); + priv->rn_ops->ndo_uninit(dev); + + if (priv->pd) { + ib_dealloc_pd(priv->pd); + priv->pd = NULL; + } +} |