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

Pull final RDMA changes from Roland Dreier:
 - Fix IPoIB to stop using unsafe linkage between networking neighbour
   layer and private path database.
 - Small fixes for bugs found by Fengguang Wu's automated builds.

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  IPoIB: Use a private hash table for path lookup in xmit path
  IB/qib: Fix size of cc_supported_table_entries
  RDMA/ucma: Convert open-coded equivalent to memdup_user()
  RDMA/ocrdma: Fix check of GSI CQs
  RDMA/cma: Use PTR_RET rather than if (IS_ERR(...)) + PTR_ERR

drivers/infiniband/core/cma.c

@@ -3064,10 +3064,7 @@ static int cma_join_ib_multicast(struct rdma_id_private *id_priv,
 						id_priv->id.port_num, &rec,
 						comp_mask, GFP_KERNEL,
 						cma_ib_mc_handler, mc);
-	if (IS_ERR(mc->multicast.ib))
-		return PTR_ERR(mc->multicast.ib);
-
-	return 0;
+	return PTR_RET(mc->multicast.ib);
 }
 
 static void iboe_mcast_work_handler(struct work_struct *work)

drivers/infiniband/core/ucma.c

@@ -1002,23 +1002,18 @@ static ssize_t ucma_set_option(struct ucma_file *file, const char __user *inbuf,
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
-	optval = kmalloc(cmd.optlen, GFP_KERNEL);
-	if (!optval) {
-		ret = -ENOMEM;
-		goto out1;
-	}
-
-	if (copy_from_user(optval, (void __user *) (unsigned long) cmd.optval,
-			   cmd.optlen)) {
-		ret = -EFAULT;
-		goto out2;
+	optval = memdup_user((void __user *) (unsigned long) cmd.optval,
+			     cmd.optlen);
+	if (IS_ERR(optval)) {
+		ret = PTR_ERR(optval);
+		goto out;
 	}
 
 	ret = ucma_set_option_level(ctx, cmd.level, cmd.optname, optval,
 				    cmd.optlen);
-out2:
 	kfree(optval);
-out1:
+
+out:
 	ucma_put_ctx(ctx);
 	return ret;
 }

drivers/infiniband/hw/ocrdma/ocrdma_verbs.c

@@ -893,7 +893,9 @@ static int ocrdma_check_qp_params(struct ib_pd *ibpd, struct ocrdma_dev *dev,
 	/* verify consumer QPs are not trying to use GSI QP's CQ */
 	if ((attrs->qp_type != IB_QPT_GSI) && (dev->gsi_qp_created)) {
 		if ((dev->gsi_sqcq == get_ocrdma_cq(attrs->send_cq)) ||
-		    (dev->gsi_sqcq == get_ocrdma_cq(attrs->send_cq))) {
+		    (dev->gsi_sqcq == get_ocrdma_cq(attrs->recv_cq)) ||
+		    (dev->gsi_rqcq == get_ocrdma_cq(attrs->send_cq)) ||
+		    (dev->gsi_rqcq == get_ocrdma_cq(attrs->recv_cq))) {
 			ocrdma_err("%s(%d) Consumer QP cannot use GSI CQs.\n",
 				   __func__, dev->id);
 			return -EINVAL;

drivers/infiniband/hw/qib/qib.h

@@ -656,6 +656,11 @@ struct qib_pportdata {
 	/* 16 congestion entries with each entry corresponding to a SL */
 	struct ib_cc_congestion_entry_shadow *congestion_entries;
 
+	/* Maximum number of congestion control entries that the agent expects
+	 * the manager to send.
+	 */
+	u16 cc_supported_table_entries;
+
 	/* Total number of congestion control table entries */
 	u16 total_cct_entry;
 
@@ -667,11 +672,6 @@ struct qib_pportdata {
 
 	/* CA's max number of 64 entry units in the congestion control table */
 	u8 cc_max_table_entries;
-
-	/* Maximum number of congestion control entries that the agent expects
-	 * the manager to send.
-	 */
-	u8 cc_supported_table_entries;
 };
 
 /* Observers. Not to be taken lightly, possibly not to ship. */

drivers/infiniband/ulp/ipoib/ipoib.h

@@ -92,6 +92,8 @@ enum {
 	IPOIB_STOP_REAPER	  = 7,
 	IPOIB_FLAG_ADMIN_CM	  = 9,
 	IPOIB_FLAG_UMCAST	  = 10,
+	IPOIB_STOP_NEIGH_GC	  = 11,
+	IPOIB_NEIGH_TBL_FLUSH	  = 12,
 
 	IPOIB_MAX_BACKOFF_SECONDS = 16,
 
@@ -260,6 +262,20 @@ struct ipoib_ethtool_st {
 	u16     max_coalesced_frames;
 };
 
+struct ipoib_neigh_hash {
+	struct ipoib_neigh __rcu      **buckets;
+	struct rcu_head			rcu;
+	u32				mask;
+	u32				size;
+};
+
+struct ipoib_neigh_table {
+	struct ipoib_neigh_hash __rcu  *htbl;
+	rwlock_t			rwlock;
+	atomic_t			entries;
+	struct completion		flushed;
+};
+
 /*
  * Device private locking: network stack tx_lock protects members used
  * in TX fast path, lock protects everything else.  lock nests inside
@@ -279,6 +295,8 @@ struct ipoib_dev_priv {
 	struct rb_root  path_tree;
 	struct list_head path_list;
 
+	struct ipoib_neigh_table ntbl;
+
 	struct ipoib_mcast *broadcast;
 	struct list_head multicast_list;
 	struct rb_root multicast_tree;
@@ -291,7 +309,7 @@ struct ipoib_dev_priv {
 	struct work_struct flush_heavy;
 	struct work_struct restart_task;
 	struct delayed_work ah_reap_task;
-
+	struct delayed_work neigh_reap_task;
 	struct ib_device *ca;
 	u8		  port;
 	u16		  pkey;
@@ -377,13 +395,16 @@ struct ipoib_neigh {
 #ifdef CONFIG_INFINIBAND_IPOIB_CM
 	struct ipoib_cm_tx *cm;
 #endif
-	union ib_gid	    dgid;
+	u8     daddr[INFINIBAND_ALEN];
 	struct sk_buff_head queue;
 
-	struct neighbour   *neighbour;
 	struct net_device *dev;
 
 	struct list_head    list;
+	struct ipoib_neigh __rcu *hnext;
+	struct rcu_head     rcu;
+	atomic_t	    refcnt;
+	unsigned long       alive;
 };
 
 #define IPOIB_UD_MTU(ib_mtu)		(ib_mtu - IPOIB_ENCAP_LEN)
@@ -394,21 +415,17 @@ static inline int ipoib_ud_need_sg(unsigned int ib_mtu)
 	return IPOIB_UD_BUF_SIZE(ib_mtu) > PAGE_SIZE;
 }
 
-/*
- * We stash a pointer to our private neighbour information after our
- * hardware address in neigh->ha.  The ALIGN() expression here makes
- * sure that this pointer is stored aligned so that an unaligned
- * load is not needed to dereference it.
- */
-static inline struct ipoib_neigh **to_ipoib_neigh(struct neighbour *neigh)
+void ipoib_neigh_dtor(struct ipoib_neigh *neigh);
+static inline void ipoib_neigh_put(struct ipoib_neigh *neigh)
 {
-	return (void*) neigh + ALIGN(offsetof(struct neighbour, ha) +
-				     INFINIBAND_ALEN, sizeof(void *));
+	if (atomic_dec_and_test(&neigh->refcnt))
+		ipoib_neigh_dtor(neigh);
 }
-
-struct ipoib_neigh *ipoib_neigh_alloc(struct neighbour *neigh,
+struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr);
+struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr,
 				      struct net_device *dev);
-void ipoib_neigh_free(struct net_device *dev, struct ipoib_neigh *neigh);
+void ipoib_neigh_free(struct ipoib_neigh *neigh);
+void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid);
 
 extern struct workqueue_struct *ipoib_workqueue;
 
@@ -425,7 +442,6 @@ static inline void ipoib_put_ah(struct ipoib_ah *ah)
 {
 	kref_put(&ah->ref, ipoib_free_ah);
 }
-
 int ipoib_open(struct net_device *dev);
 int ipoib_add_pkey_attr(struct net_device *dev);
 int ipoib_add_umcast_attr(struct net_device *dev);
@@ -455,7 +471,7 @@ void ipoib_dev_cleanup(struct net_device *dev);
 
 void ipoib_mcast_join_task(struct work_struct *work);
 void ipoib_mcast_carrier_on_task(struct work_struct *work);
-void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb);
+void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb);
 
 void ipoib_mcast_restart_task(struct work_struct *work);
 int ipoib_mcast_start_thread(struct net_device *dev);
@@ -517,10 +533,10 @@ static inline int ipoib_cm_admin_enabled(struct net_device *dev)
 		test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
 }
 
-static inline int ipoib_cm_enabled(struct net_device *dev, struct neighbour *n)
+static inline int ipoib_cm_enabled(struct net_device *dev, u8 *hwaddr)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
-	return IPOIB_CM_SUPPORTED(n->ha) &&
+	return IPOIB_CM_SUPPORTED(hwaddr) &&
 		test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
 }
 
@@ -575,7 +591,7 @@ static inline int ipoib_cm_admin_enabled(struct net_device *dev)
 {
 	return 0;
 }
-static inline int ipoib_cm_enabled(struct net_device *dev, struct neighbour *n)
+static inline int ipoib_cm_enabled(struct net_device *dev, u8 *hwaddr)
 
 {
 	return 0;

drivers/infiniband/ulp/ipoib/ipoib_cm.c

@@ -811,9 +811,7 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 		if (neigh) {
 			neigh->cm = NULL;
 			list_del(&neigh->list);
-			if (neigh->ah)
-				ipoib_put_ah(neigh->ah);
-			ipoib_neigh_free(dev, neigh);
+			ipoib_neigh_free(neigh);
 
 			tx->neigh = NULL;
 		}
@@ -1230,9 +1228,7 @@ static int ipoib_cm_tx_handler(struct ib_cm_id *cm_id,
 		if (neigh) {
 			neigh->cm = NULL;
 			list_del(&neigh->list);
-			if (neigh->ah)
-				ipoib_put_ah(neigh->ah);
-			ipoib_neigh_free(dev, neigh);
+			ipoib_neigh_free(neigh);
 
 			tx->neigh = NULL;
 		}
@@ -1279,7 +1275,7 @@ void ipoib_cm_destroy_tx(struct ipoib_cm_tx *tx)
 		list_move(&tx->list, &priv->cm.reap_list);
 		queue_work(ipoib_workqueue, &priv->cm.reap_task);
 		ipoib_dbg(priv, "Reap connection for gid %pI6\n",
-			  tx->neigh->dgid.raw);
+			  tx->neigh->daddr + 4);
 		tx->neigh = NULL;
 	}
 }
@@ -1304,7 +1300,7 @@ static void ipoib_cm_tx_start(struct work_struct *work)
 		p = list_entry(priv->cm.start_list.next, typeof(*p), list);
 		list_del_init(&p->list);
 		neigh = p->neigh;
-		qpn = IPOIB_QPN(neigh->neighbour->ha);
+		qpn = IPOIB_QPN(neigh->daddr);
 		memcpy(&pathrec, &p->path->pathrec, sizeof pathrec);
 
 		spin_unlock_irqrestore(&priv->lock, flags);
@@ -1320,9 +1316,7 @@ static void ipoib_cm_tx_start(struct work_struct *work)
 			if (neigh) {
 				neigh->cm = NULL;
 				list_del(&neigh->list);
-				if (neigh->ah)
-					ipoib_put_ah(neigh->ah);
-				ipoib_neigh_free(dev, neigh);
+				ipoib_neigh_free(neigh);
 			}
 			list_del(&p->list);
 			kfree(p);

drivers/infiniband/ulp/ipoib/ipoib_multicast.c

@@ -69,28 +69,13 @@ struct ipoib_mcast_iter {
 static void ipoib_mcast_free(struct ipoib_mcast *mcast)
 {
 	struct net_device *dev = mcast->dev;
-	struct ipoib_dev_priv *priv = netdev_priv(dev);
-	struct ipoib_neigh *neigh, *tmp;
 	int tx_dropped = 0;
 
 	ipoib_dbg_mcast(netdev_priv(dev), "deleting multicast group %pI6\n",
 			mcast->mcmember.mgid.raw);
 
-	spin_lock_irq(&priv->lock);
-
-	list_for_each_entry_safe(neigh, tmp, &mcast->neigh_list, list) {
-		/*
-		 * It's safe to call ipoib_put_ah() inside priv->lock
-		 * here, because we know that mcast->ah will always
-		 * hold one more reference, so ipoib_put_ah() will
-		 * never do more than decrement the ref count.
-		 */
-		if (neigh->ah)
-			ipoib_put_ah(neigh->ah);
-		ipoib_neigh_free(dev, neigh);
-	}
-
-	spin_unlock_irq(&priv->lock);
+	/* remove all neigh connected to this mcast */
+	ipoib_del_neighs_by_gid(dev, mcast->mcmember.mgid.raw);
 
 	if (mcast->ah)
 		ipoib_put_ah(mcast->ah);
@@ -655,17 +640,12 @@ static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
 	return 0;
 }
 
-void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb)
+void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
-	struct dst_entry *dst = skb_dst(skb);
 	struct ipoib_mcast *mcast;
-	struct neighbour *n;
 	unsigned long flags;
-
-	n = NULL;
-	if (dst)
-		n = dst_neigh_lookup_skb(dst, skb);
+	void *mgid = daddr + 4;
 
 	spin_lock_irqsave(&priv->lock, flags);
 
@@ -721,28 +701,29 @@ void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb)
 
 out:
 	if (mcast && mcast->ah) {
-		if (n) {
-			if (!*to_ipoib_neigh(n)) {
 		struct ipoib_neigh *neigh;
 
-				neigh = ipoib_neigh_alloc(n, skb->dev);
+		spin_unlock_irqrestore(&priv->lock, flags);
+		neigh = ipoib_neigh_get(dev, daddr);
+		spin_lock_irqsave(&priv->lock, flags);
+		if (!neigh) {
+			spin_unlock_irqrestore(&priv->lock, flags);
+			neigh = ipoib_neigh_alloc(daddr, dev);
+			spin_lock_irqsave(&priv->lock, flags);
 			if (neigh) {
 				kref_get(&mcast->ah->ref);
 				neigh->ah	= mcast->ah;
-					list_add_tail(&neigh->list,
-						      &mcast->neigh_list);
-				}
+				list_add_tail(&neigh->list, &mcast->neigh_list);
 			}
-			neigh_release(n);
 		}
 		spin_unlock_irqrestore(&priv->lock, flags);
 		ipoib_send(dev, skb, mcast->ah, IB_MULTICAST_QPN);
+		if (neigh)
+			ipoib_neigh_put(neigh);
 		return;
 	}
 
 unlock:
-	if (n)
-		neigh_release(n);
 	spin_unlock_irqrestore(&priv->lock, flags);
 }