5 files changed, 303 insertions, 43 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 79859c4d4..edc5b8565 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -80,7 +80,7 @@ enum {
 	IPOIB_NUM_WC		  = 4,
 
 	IPOIB_MAX_PATH_REC_QUEUE  = 3,
-	IPOIB_MAX_MCAST_QUEUE	  = 3,
+	IPOIB_MAX_MCAST_QUEUE	  = 64,
 
 	IPOIB_FLAG_OPER_UP	  = 0,
 	IPOIB_FLAG_INITIALIZED	  = 1,
@@ -342,7 +342,6 @@ struct ipoib_dev_priv {
 	u16		  pkey;
 	u16		  pkey_index;
 	struct ib_pd	 *pd;
-	struct ib_mr	 *mr;
 	struct ib_cq	 *recv_cq;
 	struct ib_cq	 *send_cq;
 	struct ib_qp	 *qp;
@@ -496,6 +495,7 @@ 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, u8 *daddr, struct sk_buff *skb);
+void ipoib_mcast_free(struct ipoib_mcast *mc);
 
 void ipoib_mcast_restart_task(struct work_struct *work);
 int ipoib_mcast_start_thread(struct net_device *dev);
@@ -549,6 +549,8 @@ void ipoib_path_iter_read(struct ipoib_path_iter *iter,
 
 int ipoib_mcast_attach(struct net_device *dev, u16 mlid,
 		       union ib_gid *mgid, int set_qkey);
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast);
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid);
 
 int ipoib_init_qp(struct net_device *dev);
 int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index ee39be6cc..c78dc1638 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -332,7 +332,7 @@ static void ipoib_cm_init_rx_wr(struct net_device *dev,
 	int i;
 
 	for (i = 0; i < priv->cm.num_frags; ++i)
-		sge[i].lkey = priv->mr->lkey;
+		sge[i].lkey = priv->pd->local_dma_lkey;
 
 	sge[0].length = IPOIB_CM_HEAD_SIZE;
 	for (i = 1; i < priv->cm.num_frags; ++i)
@@ -848,7 +848,7 @@ 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, NULL);
+			   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);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index b2943c84a..babba05d7 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -48,6 +48,9 @@
 
 #include <linux/jhash.h>
 #include <net/arp.h>
+#include <net/addrconf.h>
+#include <linux/inetdevice.h>
+#include <rdma/ib_cache.h>
 
 #define DRV_VERSION "1.0.0"
 
@@ -89,13 +92,18 @@ struct workqueue_struct *ipoib_workqueue;
 struct ib_sa_client ipoib_sa_client;
 
 static void ipoib_add_one(struct ib_device *device);
-static void ipoib_remove_one(struct ib_device *device);
+static void ipoib_remove_one(struct ib_device *device, void *client_data);
 static void ipoib_neigh_reclaim(struct rcu_head *rp);
+static struct net_device *ipoib_get_net_dev_by_params(
+		struct ib_device *dev, u8 port, u16 pkey,
+		const union ib_gid *gid, const struct sockaddr *addr,
+		void *client_data);
 
 static struct ib_client ipoib_client = {
 	.name   = "ipoib",
 	.add    = ipoib_add_one,
-	.remove = ipoib_remove_one
+	.remove = ipoib_remove_one,
+	.get_net_dev_by_params = ipoib_get_net_dev_by_params,
 };
 
 int ipoib_open(struct net_device *dev)
@@ -222,6 +230,225 @@ static int ipoib_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
+/* Called with an RCU read lock taken */
+static bool ipoib_is_dev_match_addr_rcu(const struct sockaddr *addr,
+					struct net_device *dev)
+{
+	struct net *net = dev_net(dev);
+	struct in_device *in_dev;
+	struct sockaddr_in *addr_in = (struct sockaddr_in *)addr;
+	struct sockaddr_in6 *addr_in6 = (struct sockaddr_in6 *)addr;
+	__be32 ret_addr;
+
+	switch (addr->sa_family) {
+	case AF_INET:
+		in_dev = in_dev_get(dev);
+		if (!in_dev)
+			return false;
+
+		ret_addr = inet_confirm_addr(net, in_dev, 0,
+					     addr_in->sin_addr.s_addr,
+					     RT_SCOPE_HOST);
+		in_dev_put(in_dev);
+		if (ret_addr)
+			return true;
+
+		break;
+	case AF_INET6:
+		if (IS_ENABLED(CONFIG_IPV6) &&
+		    ipv6_chk_addr(net, &addr_in6->sin6_addr, dev, 1))
+			return true;
+
+		break;
+	}
+	return false;
+}
+
+/**
+ * Find the master net_device on top of the given net_device.
+ * @dev: base IPoIB net_device
+ *
+ * Returns the master net_device with a reference held, or the same net_device
+ * if no master exists.
+ */
+static struct net_device *ipoib_get_master_net_dev(struct net_device *dev)
+{
+	struct net_device *master;
+
+	rcu_read_lock();
+	master = netdev_master_upper_dev_get_rcu(dev);
+	if (master)
+		dev_hold(master);
+	rcu_read_unlock();
+
+	if (master)
+		return master;
+
+	dev_hold(dev);
+	return dev;
+}
+
+/**
+ * Find a net_device matching the given address, which is an upper device of
+ * the given net_device.
+ * @addr: IP address to look for.
+ * @dev: base IPoIB net_device
+ *
+ * If found, returns the net_device with a reference held. Otherwise return
+ * NULL.
+ */
+static struct net_device *ipoib_get_net_dev_match_addr(
+		const struct sockaddr *addr, struct net_device *dev)
+{
+	struct net_device *upper,
+			  *result = NULL;
+	struct list_head *iter;
+
+	rcu_read_lock();
+	if (ipoib_is_dev_match_addr_rcu(addr, dev)) {
+		dev_hold(dev);
+		result = dev;
+		goto out;
+	}
+
+	netdev_for_each_all_upper_dev_rcu(dev, upper, iter) {
+		if (ipoib_is_dev_match_addr_rcu(addr, upper)) {
+			dev_hold(upper);
+			result = upper;
+			break;
+		}
+	}
+out:
+	rcu_read_unlock();
+	return result;
+}
+
+/* returns the number of IPoIB netdevs on top a given ipoib device matching a
+ * pkey_index and address, if one exists.
+ *
+ * @found_net_dev: contains a matching net_device if the return value >= 1,
+ * with a reference held. */
+static int ipoib_match_gid_pkey_addr(struct ipoib_dev_priv *priv,
+				     const union ib_gid *gid,
+				     u16 pkey_index,
+				     const struct sockaddr *addr,
+				     int nesting,
+				     struct net_device **found_net_dev)
+{
+	struct ipoib_dev_priv *child_priv;
+	struct net_device *net_dev = NULL;
+	int matches = 0;
+
+	if (priv->pkey_index == pkey_index &&
+	    (!gid || !memcmp(gid, &priv->local_gid, sizeof(*gid)))) {
+		if (!addr) {
+			net_dev = ipoib_get_master_net_dev(priv->dev);
+		} else {
+			/* Verify the net_device matches the IP address, as
+			 * IPoIB child devices currently share a GID. */
+			net_dev = ipoib_get_net_dev_match_addr(addr, priv->dev);
+		}
+		if (net_dev) {
+			if (!*found_net_dev)
+				*found_net_dev = net_dev;
+			else
+				dev_put(net_dev);
+			++matches;
+		}
+	}
+
+	/* Check child interfaces */
+	down_read_nested(&priv->vlan_rwsem, nesting);
+	list_for_each_entry(child_priv, &priv->child_intfs, list) {
+		matches += ipoib_match_gid_pkey_addr(child_priv, gid,
+						    pkey_index, addr,
+						    nesting + 1,
+						    found_net_dev);
+		if (matches > 1)
+			break;
+	}
+	up_read(&priv->vlan_rwsem);
+
+	return matches;
+}
+
+/* Returns the number of matching net_devs found (between 0 and 2). Also
+ * return the matching net_device in the @net_dev parameter, holding a
+ * reference to the net_device, if the number of matches >= 1 */
+static int __ipoib_get_net_dev_by_params(struct list_head *dev_list, u8 port,
+					 u16 pkey_index,
+					 const union ib_gid *gid,
+					 const struct sockaddr *addr,
+					 struct net_device **net_dev)
+{
+	struct ipoib_dev_priv *priv;
+	int matches = 0;
+
+	*net_dev = NULL;
+
+	list_for_each_entry(priv, dev_list, list) {
+		if (priv->port != port)
+			continue;
+
+		matches += ipoib_match_gid_pkey_addr(priv, gid, pkey_index,
+						     addr, 0, net_dev);
+		if (matches > 1)
+			break;
+	}
+
+	return matches;
+}
+
+static struct net_device *ipoib_get_net_dev_by_params(
+		struct ib_device *dev, u8 port, u16 pkey,
+		const union ib_gid *gid, const struct sockaddr *addr,
+		void *client_data)
+{
+	struct net_device *net_dev;
+	struct list_head *dev_list = client_data;
+	u16 pkey_index;
+	int matches;
+	int ret;
+
+	if (!rdma_protocol_ib(dev, port))
+		return NULL;
+
+	ret = ib_find_cached_pkey(dev, port, pkey, &pkey_index);
+	if (ret)
+		return NULL;
+
+	if (!dev_list)
+		return NULL;
+
+	/* See if we can find a unique device matching the L2 parameters */
+	matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index,
+						gid, NULL, &net_dev);
+
+	switch (matches) {
+	case 0:
+		return NULL;
+	case 1:
+		return net_dev;
+	}
+
+	dev_put(net_dev);
+
+	/* Couldn't find a unique device with L2 parameters only. Use L3
+	 * address to uniquely match the net device */
+	matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index,
+						gid, addr, &net_dev);
+	switch (matches) {
+	case 0:
+		return NULL;
+	default:
+		dev_warn_ratelimited(&dev->dev,
+				     "duplicate IP address detected\n");
+		/* Fall through */
+	case 1:
+		return net_dev;
+	}
+}
+
 int ipoib_set_mode(struct net_device *dev, const char *buf)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -922,6 +1149,9 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 	unsigned long dt;
 	unsigned long flags;
 	int i;
+	LIST_HEAD(remove_list);
+	struct ipoib_mcast *mcast, *tmcast;
+	struct net_device *dev = priv->dev;
 
 	if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
 		return;
@@ -949,6 +1179,19 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 							  lockdep_is_held(&priv->lock))) != NULL) {
 			/* was the neigh idle for two GC periods */
 			if (time_after(neigh_obsolete, neigh->alive)) {
+				u8 *mgid = neigh->daddr + 4;
+
+				/* Is this multicast ? */
+				if (*mgid == 0xff) {
+					mcast = __ipoib_mcast_find(dev, mgid);
+
+					if (mcast && test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
+						list_del(&mcast->list);
+						rb_erase(&mcast->rb_node, &priv->multicast_tree);
+						list_add_tail(&mcast->list, &remove_list);
+					}
+				}
+
 				rcu_assign_pointer(*np,
 						   rcu_dereference_protected(neigh->hnext,
 									     lockdep_is_held(&priv->lock)));
@@ -964,6 +1207,10 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 
 out_unlock:
 	spin_unlock_irqrestore(&priv->lock, flags);
+	list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
+		ipoib_mcast_leave(dev, mcast);
+		ipoib_mcast_free(mcast);
+	}
 }
 
 static void ipoib_reap_neigh(struct work_struct *work)
@@ -1715,12 +1962,11 @@ static void ipoib_add_one(struct ib_device *device)
 	ib_set_client_data(device, &ipoib_client, dev_list);
 }
 
-static void ipoib_remove_one(struct ib_device *device)
+static void ipoib_remove_one(struct ib_device *device, void *client_data)
 {
 	struct ipoib_dev_priv *priv, *tmp;
-	struct list_head *dev_list;
+	struct list_head *dev_list = client_data;
 
-	dev_list = ib_get_client_data(device, &ipoib_client);
 	if (!dev_list)
 		return;
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 0d23e0568..d750a8604 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -106,7 +106,7 @@ static void __ipoib_mcast_schedule_join_thread(struct ipoib_dev_priv *priv,
 		queue_delayed_work(priv->wq, &priv->mcast_task, 0);
 }
 
-static void ipoib_mcast_free(struct ipoib_mcast *mcast)
+void ipoib_mcast_free(struct ipoib_mcast *mcast)
 {
 	struct net_device *dev = mcast->dev;
 	int tx_dropped = 0;
@@ -153,7 +153,7 @@ static struct ipoib_mcast *ipoib_mcast_alloc(struct net_device *dev,
 	return mcast;
 }
 
-static struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct rb_node *n = priv->multicast_tree.rb_node;
@@ -393,8 +393,13 @@ static int ipoib_mcast_join_complete(int status,
 			goto out_locked;
 		}
 	} else {
-		if (mcast->logcount++ < 20) {
-			if (status == -ETIMEDOUT || status == -EAGAIN) {
+		bool silent_fail =
+		    test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) &&
+		    status == -EINVAL;
+
+		if (mcast->logcount < 20) {
+			if (status == -ETIMEDOUT || status == -EAGAIN ||
+			    silent_fail) {
 				ipoib_dbg_mcast(priv, "%smulticast join failed for %pI6, status %d\n",
 						test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) ? "sendonly " : "",
 						mcast->mcmember.mgid.raw, status);
@@ -403,6 +408,9 @@ static int ipoib_mcast_join_complete(int status,
 						test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) ? "sendonly " : "",
 					   mcast->mcmember.mgid.raw, status);
 			}
+
+			if (!silent_fail)
+				mcast->logcount++;
 		}
 
 		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) &&
@@ -448,8 +456,7 @@ out_locked:
 	return status;
 }
 
-static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast,
-			     int create)
+static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ib_sa_multicast *multicast;
@@ -471,7 +478,14 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast,
 		IB_SA_MCMEMBER_REC_PKEY		|
 		IB_SA_MCMEMBER_REC_JOIN_STATE;
 
-	if (create) {
+	if (mcast != priv->broadcast) {
+		/*
+		 * RFC 4391:
+		 *  The MGID MUST use the same P_Key, Q_Key, SL, MTU,
+		 *  and HopLimit as those used in the broadcast-GID.  The rest
+		 *  of attributes SHOULD follow the values used in the
+		 *  broadcast-GID as well.
+		 */
 		comp_mask |=
 			IB_SA_MCMEMBER_REC_QKEY			|
 			IB_SA_MCMEMBER_REC_MTU_SELECTOR		|
@@ -492,6 +506,24 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast,
 		rec.sl		  = priv->broadcast->mcmember.sl;
 		rec.flow_label	  = priv->broadcast->mcmember.flow_label;
 		rec.hop_limit	  = priv->broadcast->mcmember.hop_limit;
+
+		/*
+		 * Send-only IB Multicast joins do not work at the core
+		 * IB layer yet, so we can't use them here.  However,
+		 * we are emulating an Ethernet multicast send, which
+		 * does not require a multicast subscription and will
+		 * still send properly.  The most appropriate thing to
+		 * do is to create the group if it doesn't exist as that
+		 * most closely emulates the behavior, from a user space
+		 * application perspecitive, of Ethernet multicast
+		 * operation.  For now, we do a full join, maybe later
+		 * when the core IB layers support send only joins we
+		 * will use them.
+		 */
+#if 0
+		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
+			rec.join_state = 4;
+#endif
 	}
 
 	multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port,
@@ -517,7 +549,6 @@ void ipoib_mcast_join_task(struct work_struct *work)
 	struct ib_port_attr port_attr;
 	unsigned long delay_until = 0;
 	struct ipoib_mcast *mcast = NULL;
-	int create = 1;
 
 	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
 		return;
@@ -566,7 +597,6 @@ void ipoib_mcast_join_task(struct work_struct *work)
 		if (IS_ERR_OR_NULL(priv->broadcast->mc) &&
 		    !test_bit(IPOIB_MCAST_FLAG_BUSY, &priv->broadcast->flags)) {
 			mcast = priv->broadcast;
-			create = 0;
 			if (mcast->backoff > 1 &&
 			    time_before(jiffies, mcast->delay_until)) {
 				delay_until = mcast->delay_until;
@@ -590,12 +620,8 @@ void ipoib_mcast_join_task(struct work_struct *work)
 				/* Found the next unjoined group */
 				init_completion(&mcast->done);
 				set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
-				if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
-					create = 0;
-				else
-					create = 1;
 				spin_unlock_irq(&priv->lock);
-				ipoib_mcast_join(dev, mcast, create);
+				ipoib_mcast_join(dev, mcast);
 				spin_lock_irq(&priv->lock);
 			} else if (!delay_until ||
 				 time_before(mcast->delay_until, delay_until))
@@ -618,7 +644,7 @@ out:
 	}
 	spin_unlock_irq(&priv->lock);
 	if (mcast)
-		ipoib_mcast_join(dev, mcast, create);
+		ipoib_mcast_join(dev, mcast);
 }
 
 int ipoib_mcast_start_thread(struct net_device *dev)
@@ -651,7 +677,7 @@ int ipoib_mcast_stop_thread(struct net_device *dev)
 	return 0;
 }
 
-static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	int ret = 0;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index 851c8219d..78845b6e8 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -152,12 +152,6 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 		return -ENODEV;
 	}
 
-	priv->mr = ib_get_dma_mr(priv->pd, IB_ACCESS_LOCAL_WRITE);
-	if (IS_ERR(priv->mr)) {
-		printk(KERN_WARNING "%s: ib_get_dma_mr failed\n", ca->name);
-		goto out_free_pd;
-	}
-
 	/*
 	 * the various IPoIB tasks assume they will never race against
 	 * themselves, so always use a single thread workqueue
@@ -165,7 +159,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 	priv->wq = create_singlethread_workqueue("ipoib_wq");
 	if (!priv->wq) {
 		printk(KERN_WARNING "ipoib: failed to allocate device WQ\n");
-		goto out_free_mr;
+		goto out_free_pd;
 	}
 
 	size = ipoib_recvq_size + 1;
@@ -225,13 +219,13 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 	priv->dev->dev_addr[3] = (priv->qp->qp_num      ) & 0xff;
 
 	for (i = 0; i < MAX_SKB_FRAGS + 1; ++i)
-		priv->tx_sge[i].lkey = priv->mr->lkey;
+		priv->tx_sge[i].lkey = priv->pd->local_dma_lkey;
 
 	priv->tx_wr.opcode	= IB_WR_SEND;
 	priv->tx_wr.sg_list	= priv->tx_sge;
 	priv->tx_wr.send_flags	= IB_SEND_SIGNALED;
 
-	priv->rx_sge[0].lkey = priv->mr->lkey;
+	priv->rx_sge[0].lkey = priv->pd->local_dma_lkey;
 
 	priv->rx_sge[0].length = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
 	priv->rx_wr.num_sge = 1;
@@ -254,9 +248,6 @@ out_free_wq:
 	destroy_workqueue(priv->wq);
 	priv->wq = NULL;
 
-out_free_mr:
-	ib_dereg_mr(priv->mr);
-
 out_free_pd:
 	ib_dealloc_pd(priv->pd);
 
@@ -289,12 +280,7 @@ void ipoib_transport_dev_cleanup(struct net_device *dev)
 		priv->wq = NULL;
 	}
 
-	if (ib_dereg_mr(priv->mr))
-		ipoib_warn(priv, "ib_dereg_mr failed\n");
-
-	if (ib_dealloc_pd(priv->pd))
-		ipoib_warn(priv, "ib_dealloc_pd failed\n");
-
+	ib_dealloc_pd(priv->pd);
 }
 
 void ipoib_event(struct ib_event_handler *handler,