1 files changed, 271 insertions, 29 deletions

diff --git a/kernel/drivers/infiniband/ulp/ipoib/ipoib_main.c b/kernel/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 9e1b203d7..7d3281866 100644
--- a/kernel/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/kernel/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)
@@ -190,7 +198,7 @@ static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_featu
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
 	if (test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags))
-		features &= ~(NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO);
+		features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
 
 	return features;
 }
@@ -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);
@@ -232,8 +459,9 @@ int ipoib_set_mode(struct net_device *dev, const char *buf)
 		ipoib_warn(priv, "enabling connected mode "
 			   "will cause multicast packet drops\n");
 		netdev_update_features(dev);
+		dev_set_mtu(dev, ipoib_cm_max_mtu(dev));
 		rtnl_unlock();
-		priv->tx_wr.send_flags &= ~IB_SEND_IP_CSUM;
+		priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM;
 
 		ipoib_flush_paths(dev);
 		rtnl_lock();
@@ -921,6 +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;
@@ -948,6 +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)));
@@ -963,6 +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)
@@ -1128,7 +1376,7 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv)
 {
 	struct ipoib_neigh_table *ntbl = &priv->ntbl;
 	struct ipoib_neigh_hash *htbl;
-	struct ipoib_neigh **buckets;
+	struct ipoib_neigh __rcu **buckets;
 	u32 size;
 
 	clear_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags);
@@ -1146,7 +1394,7 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv)
 	htbl->size = size;
 	htbl->mask = (size - 1);
 	htbl->buckets = buckets;
-	ntbl->htbl = htbl;
+	RCU_INIT_POINTER(ntbl->htbl, htbl);
 	htbl->ntbl = ntbl;
 	atomic_set(&ntbl->entries, 0);
 
@@ -1577,7 +1825,8 @@ static struct net_device *ipoib_add_port(const char *format,
 	SET_NETDEV_DEV(priv->dev, hca->dma_device);
 	priv->dev->dev_id = port - 1;
 
-	if (!ib_query_port(hca, port, &attr))
+	result = ib_query_port(hca, port, &attr);
+	if (!result)
 		priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
 	else {
 		printk(KERN_WARNING "%s: ib_query_port %d failed\n",
@@ -1598,7 +1847,8 @@ static struct net_device *ipoib_add_port(const char *format,
 		goto device_init_failed;
 	}
 
-	if (ipoib_set_dev_features(priv, hca))
+	result = ipoib_set_dev_features(priv, hca);
+	if (result)
 		goto device_init_failed;
 
 	/*
@@ -1610,7 +1860,7 @@ static struct net_device *ipoib_add_port(const char *format,
 	priv->dev->broadcast[8] = priv->pkey >> 8;
 	priv->dev->broadcast[9] = priv->pkey & 0xff;
 
-	result = ib_query_gid(hca, port, 0, &priv->local_gid);
+	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);
@@ -1684,10 +1934,8 @@ static void ipoib_add_one(struct ib_device *device)
 	struct list_head *dev_list;
 	struct net_device *dev;
 	struct ipoib_dev_priv *priv;
-	int s, e, p;
-
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
+	int p;
+	int count = 0;
 
 	dev_list = kmalloc(sizeof *dev_list, GFP_KERNEL);
 	if (!dev_list)
@@ -1695,36 +1943,30 @@ static void ipoib_add_one(struct ib_device *device)
 
 	INIT_LIST_HEAD(dev_list);
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH) {
-		s = 0;
-		e = 0;
-	} else {
-		s = 1;
-		e = device->phys_port_cnt;
-	}
-
-	for (p = s; p <= e; ++p) {
-		if (rdma_port_get_link_layer(device, p) != IB_LINK_LAYER_INFINIBAND)
+	for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
+		if (!rdma_protocol_ib(device, p))
 			continue;
 		dev = ipoib_add_port("ib%d", device, p);
 		if (!IS_ERR(dev)) {
 			priv = netdev_priv(dev);
 			list_add_tail(&priv->list, dev_list);
+			count++;
 		}
 	}
 
+	if (!count) {
+		kfree(dev_list);
+		return;
+	}
+
 	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;
-
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
+	struct list_head *dev_list = client_data;
 
-	dev_list = ib_get_client_data(device, &ipoib_client);
 	if (!dev_list)
 		return;