Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  IB: Fix RCU lockdep splats
  IB/ipoib: Prevent hung task or softlockup processing multicast response
  IB/qib: Fix over-scheduling of QSFP work
  RDMA/cxgb4: Fix retry with MPAv1 logic for MPAv2
  RDMA/cxgb4: Fix iw_cxgb4 count_rcqes() logic
  IB/qib: Don't use schedule_work()

drivers/infiniband/core/addr.c

@@ -216,7 +216,9 @@ static int addr4_resolve(struct sockaddr_in *src_in,
 
 	neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, rt->dst.dev);
 	if (!neigh || !(neigh->nud_state & NUD_VALID)) {
+		rcu_read_lock();
 		neigh_event_send(dst_get_neighbour(&rt->dst), NULL);
+		rcu_read_unlock();
 		ret = -ENODATA;
 		if (neigh)
 			goto release;
@@ -274,15 +276,16 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 		goto put;
 	}
 
+	rcu_read_lock();
 	neigh = dst_get_neighbour(dst);
 	if (!neigh || !(neigh->nud_state & NUD_VALID)) {
 		if (neigh)
 			neigh_event_send(neigh, NULL);
 		ret = -ENODATA;
-		goto put;
-	}
-
+	} else {
 		ret = rdma_copy_addr(addr, dst->dev, neigh->ha);
+	}
+	rcu_read_unlock();
 put:
 	dst_release(dst);
 	return ret;

drivers/infiniband/hw/cxgb3/iwch_cm.c

@@ -1375,8 +1375,10 @@ static int pass_accept_req(struct t3cdev *tdev, struct sk_buff *skb, void *ctx)
 		goto reject;
 	}
 	dst = &rt->dst;
+	rcu_read_lock();
 	neigh = dst_get_neighbour(dst);
 	l2t = t3_l2t_get(tdev, neigh, neigh->dev);
+	rcu_read_unlock();
 	if (!l2t) {
 		printk(KERN_ERR MOD "%s - failed to allocate l2t entry!\n",
 		       __func__);
@@ -1946,10 +1948,12 @@ int iwch_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	}
 	ep->dst = &rt->dst;
 
+	rcu_read_lock();
 	neigh = dst_get_neighbour(ep->dst);
 
 	/* get a l2t entry */
 	ep->l2t = t3_l2t_get(ep->com.tdev, neigh, neigh->dev);
+	rcu_read_unlock();
 	if (!ep->l2t) {
 		printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
 		err = -ENOMEM;

drivers/infiniband/hw/cxgb4/cm.c

@@ -542,8 +542,10 @@ static void send_mpa_req(struct c4iw_ep *ep, struct sk_buff *skb,
 		     (mpa_rev_to_use == 2 ? MPA_ENHANCED_RDMA_CONN : 0);
 	mpa->private_data_size = htons(ep->plen);
 	mpa->revision = mpa_rev_to_use;
-	if (mpa_rev_to_use == 1)
+	if (mpa_rev_to_use == 1) {
 		ep->tried_with_mpa_v1 = 1;
+		ep->retry_with_mpa_v1 = 0;
+	}
 
 	if (mpa_rev_to_use == 2) {
 		mpa->private_data_size +=
@@ -1594,6 +1596,7 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 		goto reject;
 	}
 	dst = &rt->dst;
+	rcu_read_lock();
 	neigh = dst_get_neighbour(dst);
 	if (neigh->dev->flags & IFF_LOOPBACK) {
 		pdev = ip_dev_find(&init_net, peer_ip);
@@ -1620,6 +1623,7 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 		rss_qid = dev->rdev.lldi.rxq_ids[
 			  cxgb4_port_idx(neigh->dev) * step];
 	}
+	rcu_read_unlock();
 	if (!l2t) {
 		printk(KERN_ERR MOD "%s - failed to allocate l2t entry!\n",
 		       __func__);
@@ -1820,6 +1824,7 @@ static int c4iw_reconnect(struct c4iw_ep *ep)
 	}
 	ep->dst = &rt->dst;
 
+	rcu_read_lock();
 	neigh = dst_get_neighbour(ep->dst);
 
 	/* get a l2t entry */
@@ -1856,6 +1861,7 @@ static int c4iw_reconnect(struct c4iw_ep *ep)
 		ep->rss_qid = ep->com.dev->rdev.lldi.rxq_ids[
 			cxgb4_port_idx(neigh->dev) * step];
 	}
+	rcu_read_unlock();
 	if (!ep->l2t) {
 		printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
 		err = -ENOMEM;
@@ -2301,6 +2307,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	}
 	ep->dst = &rt->dst;
 
+	rcu_read_lock();
 	neigh = dst_get_neighbour(ep->dst);
 
 	/* get a l2t entry */
@@ -2339,6 +2346,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		ep->retry_with_mpa_v1 = 0;
 		ep->tried_with_mpa_v1 = 0;
 	}
+	rcu_read_unlock();
 	if (!ep->l2t) {
 		printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
 		err = -ENOMEM;

drivers/infiniband/hw/cxgb4/cq.c

@@ -311,7 +311,7 @@ void c4iw_count_rcqes(struct t4_cq *cq, struct t4_wq *wq, int *count)
 	while (ptr != cq->sw_pidx) {
 		cqe = &cq->sw_queue[ptr];
 		if (RQ_TYPE(cqe) && (CQE_OPCODE(cqe) != FW_RI_READ_RESP) &&
-		    (CQE_QPID(cqe) == wq->rq.qid) && cqe_completes_wr(cqe, wq))
+		    (CQE_QPID(cqe) == wq->sq.qid) && cqe_completes_wr(cqe, wq))
 			(*count)++;
 		if (++ptr == cq->size)
 			ptr = 0;

drivers/infiniband/hw/nes/nes_cm.c

@@ -1377,9 +1377,11 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi
 		neigh_release(neigh);
 	}
 
-	if ((neigh == NULL) || (!(neigh->nud_state & NUD_VALID)))
+	if ((neigh == NULL) || (!(neigh->nud_state & NUD_VALID))) {
+		rcu_read_lock();
 		neigh_event_send(dst_get_neighbour(&rt->dst), NULL);
-
+		rcu_read_unlock();
+	}
 	ip_rt_put(rt);
 	return rc;
 }

drivers/infiniband/hw/qib/qib_iba7322.c

@@ -2307,19 +2307,11 @@ static int qib_7322_bringup_serdes(struct qib_pportdata *ppd)
 		SYM_LSB(IBCCtrlA_0, MaxPktLen);
 	ppd->cpspec->ibcctrl_a = ibc; /* without linkcmd or linkinitcmd! */
 
-	/* initially come up waiting for TS1, without sending anything. */
-	val = ppd->cpspec->ibcctrl_a | (QLOGIC_IB_IBCC_LINKINITCMD_DISABLE <<
-		QLOGIC_IB_IBCC_LINKINITCMD_SHIFT);
-
-	ppd->cpspec->ibcctrl_a = val;
 	/*
 	 * Reset the PCS interface to the serdes (and also ibc, which is still
 	 * in reset from above).  Writes new value of ibcctrl_a as last step.
 	 */
 	qib_7322_mini_pcs_reset(ppd);
-	qib_write_kreg(dd, kr_scratch, 0ULL);
-	/* clear the linkinit cmds */
-	ppd->cpspec->ibcctrl_a &= ~SYM_MASK(IBCCtrlA_0, LinkInitCmd);
 
 	if (!ppd->cpspec->ibcctrl_b) {
 		unsigned lse = ppd->link_speed_enabled;
@@ -2385,6 +2377,14 @@ static int qib_7322_bringup_serdes(struct qib_pportdata *ppd)
 	ppd->cpspec->ibcctrl_a |= SYM_MASK(IBCCtrlA_0, IBLinkEn);
 	set_vls(ppd);
 
+	/* initially come up DISABLED, without sending anything. */
+	val = ppd->cpspec->ibcctrl_a | (QLOGIC_IB_IBCC_LINKINITCMD_DISABLE <<
+					QLOGIC_IB_IBCC_LINKINITCMD_SHIFT);
+	qib_write_kreg_port(ppd, krp_ibcctrl_a, val);
+	qib_write_kreg(dd, kr_scratch, 0ULL);
+	/* clear the linkinit cmds */
+	ppd->cpspec->ibcctrl_a = val & ~SYM_MASK(IBCCtrlA_0, LinkInitCmd);
+
 	/* be paranoid against later code motion, etc. */
 	spin_lock_irqsave(&dd->cspec->rcvmod_lock, flags);
 	ppd->p_rcvctrl |= SYM_MASK(RcvCtrl_0, RcvIBPortEnable);
@@ -5241,7 +5241,7 @@ static int qib_7322_ib_updown(struct qib_pportdata *ppd, int ibup, u64 ibcs)
 			   off */
 			if (ppd->dd->flags & QIB_HAS_QSFP) {
 				qd->t_insert = get_jiffies_64();
-				schedule_work(&qd->work);
+				queue_work(ib_wq, &qd->work);
 			}
 			spin_lock_irqsave(&ppd->sdma_lock, flags);
 			if (__qib_sdma_running(ppd))

drivers/infiniband/hw/qib/qib_qsfp.c

@@ -480,18 +480,6 @@ void qib_qsfp_init(struct qib_qsfp_data *qd,
 	udelay(20); /* Generous RST dwell */
 
 	dd->f_gpio_mod(dd, mask, mask, mask);
-	/* Spec says module can take up to two seconds! */
-	mask = QSFP_GPIO_MOD_PRS_N;
-	if (qd->ppd->hw_pidx)
-		mask <<= QSFP_GPIO_PORT2_SHIFT;
-
-	/* Do not try to wait here. Better to let event handle it */
-	if (!qib_qsfp_mod_present(qd->ppd))
-		goto bail;
-	/* We see a module, but it may be unwise to look yet. Just schedule */
-	qd->t_insert = get_jiffies_64();
-	queue_work(ib_wq, &qd->work);
-bail:
 	return;
 }
 

drivers/infiniband/ulp/ipoib/ipoib_ib.c

@@ -57,21 +57,24 @@ struct ipoib_ah *ipoib_create_ah(struct net_device *dev,
 				 struct ib_pd *pd, struct ib_ah_attr *attr)
 {
 	struct ipoib_ah *ah;
+	struct ib_ah *vah;
 
 	ah = kmalloc(sizeof *ah, GFP_KERNEL);
 	if (!ah)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	ah->dev       = dev;
 	ah->last_send = 0;
 	kref_init(&ah->ref);
 
-	ah->ah = ib_create_ah(pd, attr);
-	if (IS_ERR(ah->ah)) {
+	vah = ib_create_ah(pd, attr);
+	if (IS_ERR(vah)) {
 		kfree(ah);
-		ah = NULL;
-	} else
+		ah = (struct ipoib_ah *)vah;
+	} else {
+		ah->ah = vah;
 		ipoib_dbg(netdev_priv(dev), "Created ah %p\n", ah->ah);
+	}
 
 	return ah;
 }

drivers/infiniband/ulp/ipoib/ipoib_main.c

@@ -432,7 +432,7 @@ static void path_rec_completion(int status,
 
 	spin_lock_irqsave(&priv->lock, flags);
 
-	if (ah) {
+	if (!IS_ERR_OR_NULL(ah)) {
 		path->pathrec = *pathrec;
 
 		old_ah   = path->ah;
@@ -555,6 +555,7 @@ static int path_rec_start(struct net_device *dev,
 	return 0;
 }
 
+/* called with rcu_read_lock */
 static void neigh_add_path(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -636,6 +637,7 @@ static void neigh_add_path(struct sk_buff *skb, struct net_device *dev)
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
+/* called with rcu_read_lock */
 static void ipoib_path_lookup(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(skb->dev);
@@ -720,13 +722,14 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct neighbour *n = NULL;
 	unsigned long flags;
 
+	rcu_read_lock();
 	if (likely(skb_dst(skb)))
 		n = dst_get_neighbour(skb_dst(skb));
 
 	if (likely(n)) {
 		if (unlikely(!*to_ipoib_neigh(n))) {
 			ipoib_path_lookup(skb, dev);
-			return NETDEV_TX_OK;
+			goto unlock;
 		}
 
 		neigh = *to_ipoib_neigh(n);
@@ -749,17 +752,17 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			ipoib_neigh_free(dev, neigh);
 			spin_unlock_irqrestore(&priv->lock, flags);
 			ipoib_path_lookup(skb, dev);
-			return NETDEV_TX_OK;
+			goto unlock;
 		}
 
 		if (ipoib_cm_get(neigh)) {
 			if (ipoib_cm_up(neigh)) {
 				ipoib_cm_send(dev, skb, ipoib_cm_get(neigh));
-				return NETDEV_TX_OK;
+				goto unlock;
 			}
 		} else if (neigh->ah) {
 			ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(n->ha));
-			return NETDEV_TX_OK;
+			goto unlock;
 		}
 
 		if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
@@ -793,13 +796,14 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 					   phdr->hwaddr + 4);
 				dev_kfree_skb_any(skb);
 				++dev->stats.tx_dropped;
-				return NETDEV_TX_OK;
+				goto unlock;
 			}
 
 			unicast_arp_send(skb, dev, phdr);
 		}
 	}
-
+unlock:
+	rcu_read_unlock();
 	return NETDEV_TX_OK;
 }
 
@@ -837,7 +841,7 @@ static int ipoib_hard_header(struct sk_buff *skb,
 	dst = skb_dst(skb);
 	n = NULL;
 	if (dst)
-		n = dst_get_neighbour(dst);
+		n = dst_get_neighbour_raw(dst);
 	if ((!dst || !n) && daddr) {
 		struct ipoib_pseudoheader *phdr =
 			(struct ipoib_pseudoheader *) skb_push(skb, sizeof *phdr);

drivers/infiniband/ulp/ipoib/ipoib_multicast.c

@@ -240,8 +240,11 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
 		av.grh.dgid = mcast->mcmember.mgid;
 
 		ah = ipoib_create_ah(dev, priv->pd, &av);
-		if (!ah) {
-			ipoib_warn(priv, "ib_address_create failed\n");
+		if (IS_ERR(ah)) {
+			ipoib_warn(priv, "ib_address_create failed %ld\n",
+				-PTR_ERR(ah));
+			/* use original error */
+			return PTR_ERR(ah);
 		} else {
 			spin_lock_irq(&priv->lock);
 			mcast->ah = ah;
@@ -266,7 +269,7 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
 
 		skb->dev = dev;
 		if (dst)
-			n = dst_get_neighbour(dst);
+			n = dst_get_neighbour_raw(dst);
 		if (!dst || !n) {
 			/* put pseudoheader back on for next time */
 			skb_push(skb, sizeof (struct ipoib_pseudoheader));
@@ -722,6 +725,8 @@ void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb)
 	if (mcast && mcast->ah) {
 		struct dst_entry *dst = skb_dst(skb);
 		struct neighbour *n = NULL;
+
+		rcu_read_lock();
 		if (dst)
 			n = dst_get_neighbour(dst);
 		if (n && !*to_ipoib_neigh(n)) {
@@ -734,7 +739,7 @@ void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb)
 				list_add_tail(&neigh->list, &mcast->neigh_list);
 			}
 		}
-
+		rcu_read_unlock();
 		spin_unlock_irqrestore(&priv->lock, flags);
 		ipoib_send(dev, skb, mcast->ah, IB_MULTICAST_QPN);
 		return;