11 files changed, 184 insertions, 126 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 285c143115c..6545fa798b1 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -86,6 +86,7 @@ enum {
 	IPOIB_MCAST_STARTED       = 8,
 	IPOIB_FLAG_NETIF_STOPPED  = 9,
 	IPOIB_FLAG_ADMIN_CM 	  = 10,
+	IPOIB_FLAG_UMCAST	  = 11,
 
 	IPOIB_MAX_BACKOFF_SECONDS = 16,
 
@@ -113,7 +114,27 @@ struct ipoib_pseudoheader {
 	u8  hwaddr[INFINIBAND_ALEN];
 };
 
-struct ipoib_mcast;
+/* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
+struct ipoib_mcast {
+	struct ib_sa_mcmember_rec mcmember;
+	struct ib_sa_multicast	 *mc;
+	struct ipoib_ah          *ah;
+
+	struct rb_node    rb_node;
+	struct list_head  list;
+
+	unsigned long created;
+	unsigned long backoff;
+
+	unsigned long flags;
+	unsigned char logcount;
+
+	struct list_head  neigh_list;
+
+	struct sk_buff_head pkt_queue;
+
+	struct net_device *dev;
+};
 
 struct ipoib_rx_buf {
 	struct sk_buff *skb;
@@ -228,6 +249,8 @@ struct ipoib_dev_priv {
 
 	struct net_device *dev;
 
+	struct napi_struct napi;
+
 	unsigned long flags;
 
 	struct mutex mcast_mutex;
@@ -278,8 +301,6 @@ struct ipoib_dev_priv {
 
 	struct ib_event_handler event_handler;
 
-	struct net_device_stats stats;
-
 	struct net_device *parent;
 	struct list_head child_intfs;
 	struct list_head list;
@@ -351,7 +372,7 @@ extern struct workqueue_struct *ipoib_workqueue;
 
 /* functions */
 
-int ipoib_poll(struct net_device *dev, int *budget);
+int ipoib_poll(struct napi_struct *napi, int budget);
 void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr);
 
 struct ipoib_ah *ipoib_create_ah(struct net_device *dev,
@@ -364,6 +385,7 @@ static inline void ipoib_put_ah(struct ipoib_ah *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);
 
 void ipoib_send(struct net_device *dev, struct sk_buff *skb,
 		struct ipoib_ah *address, u32 qpn);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 08b4676a382..0a0dcb8fdfd 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -430,7 +430,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 		ipoib_dbg(priv, "cm recv error "
 			   "(status=%d, wrid=%d vend_err %x)\n",
 			   wc->status, wr_id, wc->vendor_err);
-		++priv->stats.rx_dropped;
+		++dev->stats.rx_dropped;
 		goto repost;
 	}
 
@@ -457,7 +457,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 		 * this packet and reuse the old buffer.
 		 */
 		ipoib_dbg(priv, "failed to allocate receive buffer %d\n", wr_id);
-		++priv->stats.rx_dropped;
+		++dev->stats.rx_dropped;
 		goto repost;
 	}
 
@@ -474,8 +474,8 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	skb_pull(skb, IPOIB_ENCAP_LEN);
 
 	dev->last_rx = jiffies;
-	++priv->stats.rx_packets;
-	priv->stats.rx_bytes += skb->len;
+	++dev->stats.rx_packets;
+	dev->stats.rx_bytes += skb->len;
 
 	skb->dev = dev;
 	/* XXX get correct PACKET_ type here */
@@ -512,8 +512,8 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
 	if (unlikely(skb->len > tx->mtu)) {
 		ipoib_warn(priv, "packet len %d (> %d) too long to send, dropping\n",
 			   skb->len, tx->mtu);
-		++priv->stats.tx_dropped;
-		++priv->stats.tx_errors;
+		++dev->stats.tx_dropped;
+		++dev->stats.tx_errors;
 		ipoib_cm_skb_too_long(dev, skb, tx->mtu - IPOIB_ENCAP_LEN);
 		return;
 	}
@@ -532,7 +532,7 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
 	tx_req->skb = skb;
 	addr = ib_dma_map_single(priv->ca, skb->data, skb->len, DMA_TO_DEVICE);
 	if (unlikely(ib_dma_mapping_error(priv->ca, addr))) {
-		++priv->stats.tx_errors;
+		++dev->stats.tx_errors;
 		dev_kfree_skb_any(skb);
 		return;
 	}
@@ -542,7 +542,7 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
 	if (unlikely(post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1),
 			        addr, skb->len))) {
 		ipoib_warn(priv, "post_send failed\n");
-		++priv->stats.tx_errors;
+		++dev->stats.tx_errors;
 		ib_dma_unmap_single(priv->ca, addr, skb->len, DMA_TO_DEVICE);
 		dev_kfree_skb_any(skb);
 	} else {
@@ -580,8 +580,8 @@ static void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ipoib_cm_tx *tx
 	ib_dma_unmap_single(priv->ca, tx_req->mapping, tx_req->skb->len, DMA_TO_DEVICE);
 
 	/* FIXME: is this right? Shouldn't we only increment on success? */
-	++priv->stats.tx_packets;
-	priv->stats.tx_bytes += tx_req->skb->len;
+	++dev->stats.tx_packets;
+	dev->stats.tx_bytes += tx_req->skb->len;
 
 	dev_kfree_skb_any(tx_req->skb);
 
@@ -810,14 +810,16 @@ static int ipoib_cm_rep_handler(struct ib_cm_id *cm_id, struct ib_cm_event *even
 static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ib_cq *cq)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
-	struct ib_qp_init_attr attr = {};
-	attr.recv_cq = priv->cq;
-	attr.srq = priv->cm.srq;
-	attr.cap.max_send_wr = ipoib_sendq_size;
-	attr.cap.max_send_sge = 1;
-	attr.sq_sig_type = IB_SIGNAL_ALL_WR;
-	attr.qp_type = IB_QPT_RC;
-	attr.send_cq = cq;
+	struct ib_qp_init_attr attr = {
+		.send_cq		= cq,
+		.recv_cq		= priv->cq,
+		.srq			= priv->cm.srq,
+		.cap.max_send_wr	= ipoib_sendq_size,
+		.cap.max_send_sge	= 1,
+		.sq_sig_type		= IB_SIGNAL_ALL_WR,
+		.qp_type		= IB_QPT_RC,
+        };
+
 	return ib_create_qp(priv->pd, &attr);
 }
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 10944888cff..1a77e79f6b4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -208,7 +208,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	 * this packet and reuse the old buffer.
 	 */
 	if (unlikely(ipoib_alloc_rx_skb(dev, wr_id))) {
-		++priv->stats.rx_dropped;
+		++dev->stats.rx_dropped;
 		goto repost;
 	}
 
@@ -225,8 +225,8 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	skb_pull(skb, IPOIB_ENCAP_LEN);
 
 	dev->last_rx = jiffies;
-	++priv->stats.rx_packets;
-	priv->stats.rx_bytes += skb->len;
+	++dev->stats.rx_packets;
+	dev->stats.rx_bytes += skb->len;
 
 	skb->dev = dev;
 	/* XXX get correct PACKET_ type here */
@@ -260,8 +260,8 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 	ib_dma_unmap_single(priv->ca, tx_req->mapping,
 			    tx_req->skb->len, DMA_TO_DEVICE);
 
-	++priv->stats.tx_packets;
-	priv->stats.tx_bytes += tx_req->skb->len;
+	++dev->stats.tx_packets;
+	dev->stats.tx_bytes += tx_req->skb->len;
 
 	dev_kfree_skb_any(tx_req->skb);
 
@@ -281,63 +281,58 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 			   wc->status, wr_id, wc->vendor_err);
 }
 
-int ipoib_poll(struct net_device *dev, int *budget)
+int ipoib_poll(struct napi_struct *napi, int budget)
 {
-	struct ipoib_dev_priv *priv = netdev_priv(dev);
-	int max = min(*budget, dev->quota);
+	struct ipoib_dev_priv *priv = container_of(napi, struct ipoib_dev_priv, napi);
+	struct net_device *dev = priv->dev;
 	int done;
 	int t;
-	int empty;
 	int n, i;
 
 	done  = 0;
-	empty = 0;
 
-	while (max) {
+poll_more:
+	while (done < budget) {
+		int max = (budget - done);
+
 		t = min(IPOIB_NUM_WC, max);
 		n = ib_poll_cq(priv->cq, t, priv->ibwc);
 
-		for (i = 0; i < n; ++i) {
+		for (i = 0; i < n; i++) {
 			struct ib_wc *wc = priv->ibwc + i;
 
 			if (wc->wr_id & IPOIB_CM_OP_SRQ) {
 				++done;
-				--max;
 				ipoib_cm_handle_rx_wc(dev, wc);
 			} else if (wc->wr_id & IPOIB_OP_RECV) {
 				++done;
-				--max;
 				ipoib_ib_handle_rx_wc(dev, wc);
 			} else
 				ipoib_ib_handle_tx_wc(dev, wc);
 		}
 
-		if (n != t) {
-			empty = 1;
+		if (n != t)
 			break;
-		}
 	}
 
-	dev->quota -= done;
-	*budget    -= done;
-
-	if (empty) {
-		netif_rx_complete(dev);
+	if (done < budget) {
+		netif_rx_complete(dev, napi);
 		if (unlikely(ib_req_notify_cq(priv->cq,
 					      IB_CQ_NEXT_COMP |
 					      IB_CQ_REPORT_MISSED_EVENTS)) &&
-		    netif_rx_reschedule(dev, 0))
-			return 1;
-
-		return 0;
+		    netif_rx_reschedule(dev, napi))
+			goto poll_more;
 	}
 
-	return 1;
+	return done;
 }
 
 void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr)
 {
-	netif_rx_schedule(dev_ptr);
+	struct net_device *dev = dev_ptr;
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+
+	netif_rx_schedule(dev, &priv->napi);
 }
 
 static inline int post_send(struct ipoib_dev_priv *priv,
@@ -367,8 +362,8 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
 	if (unlikely(skb->len > priv->mcast_mtu + IPOIB_ENCAP_LEN)) {
 		ipoib_warn(priv, "packet len %d (> %d) too long to send, dropping\n",
 			   skb->len, priv->mcast_mtu + IPOIB_ENCAP_LEN);
-		++priv->stats.tx_dropped;
-		++priv->stats.tx_errors;
+		++dev->stats.tx_dropped;
+		++dev->stats.tx_errors;
 		ipoib_cm_skb_too_long(dev, skb, priv->mcast_mtu);
 		return;
 	}
@@ -388,7 +383,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
 	addr = ib_dma_map_single(priv->ca, skb->data, skb->len,
 				 DMA_TO_DEVICE);
 	if (unlikely(ib_dma_mapping_error(priv->ca, addr))) {
-		++priv->stats.tx_errors;
+		++dev->stats.tx_errors;
 		dev_kfree_skb_any(skb);
 		return;
 	}
@@ -397,7 +392,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
 	if (unlikely(post_send(priv, priv->tx_head & (ipoib_sendq_size - 1),
 			       address->ah, qpn, addr, skb->len))) {
 		ipoib_warn(priv, "post_send failed\n");
-		++priv->stats.tx_errors;
+		++dev->stats.tx_errors;
 		ib_dma_unmap_single(priv->ca, addr, skb->len, DMA_TO_DEVICE);
 		dev_kfree_skb_any(skb);
 	} else {
@@ -558,6 +553,14 @@ void ipoib_drain_cq(struct net_device *dev)
 	do {
 		n = ib_poll_cq(priv->cq, IPOIB_NUM_WC, priv->ibwc);
 		for (i = 0; i < n; ++i) {
+			/*
+			 * Convert any successful completions to flush
+			 * errors to avoid passing packets up the
+			 * stack after bringing the device down.
+			 */
+			if (priv->ibwc[i].status == IB_WC_SUCCESS)
+				priv->ibwc[i].status = IB_WC_WR_FLUSH_ERR;
+
 			if (priv->ibwc[i].wr_id & IPOIB_CM_OP_SRQ)
 				ipoib_cm_handle_rx_wc(dev, priv->ibwc + i);
 			else if (priv->ibwc[i].wr_id & IPOIB_OP_RECV)
@@ -577,7 +580,6 @@ int ipoib_ib_dev_stop(struct net_device *dev, int flush)
 	int i;
 
 	clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
-	netif_poll_disable(dev);
 
 	ipoib_cm_dev_stop(dev);
 
@@ -660,7 +662,6 @@ timeout:
 		msleep(1);
 	}
 
-	netif_poll_enable(dev);
 	ib_req_notify_cq(priv->cq, IB_CQ_NEXT_COMP);
 
 	return 0;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 894b1dcdf3e..e072f3c32ce 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -98,16 +98,20 @@ int ipoib_open(struct net_device *dev)
 
 	ipoib_dbg(priv, "bringing up interface\n");
 
+	napi_enable(&priv->napi);
 	set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
 
 	if (ipoib_pkey_dev_delay_open(dev))
 		return 0;
 
-	if (ipoib_ib_dev_open(dev))
+	if (ipoib_ib_dev_open(dev)) {
+		napi_disable(&priv->napi);
 		return -EINVAL;
+	}
 
 	if (ipoib_ib_dev_up(dev)) {
 		ipoib_ib_dev_stop(dev, 1);
+		napi_disable(&priv->napi);
 		return -EINVAL;
 	}
 
@@ -140,6 +144,7 @@ static int ipoib_stop(struct net_device *dev)
 	ipoib_dbg(priv, "stopping interface\n");
 
 	clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
+	napi_disable(&priv->napi);
 
 	netif_stop_queue(dev);
 
@@ -468,9 +473,10 @@ static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid)
 	INIT_LIST_HEAD(&path->neigh_list);
 
 	memcpy(path->pathrec.dgid.raw, gid, sizeof (union ib_gid));
-	path->pathrec.sgid      = priv->local_gid;
-	path->pathrec.pkey      = cpu_to_be16(priv->pkey);
-	path->pathrec.numb_path = 1;
+	path->pathrec.sgid          = priv->local_gid;
+	path->pathrec.pkey          = cpu_to_be16(priv->pkey);
+	path->pathrec.numb_path     = 1;
+	path->pathrec.traffic_class = priv->broadcast->mcmember.traffic_class;
 
 	return path;
 }
@@ -491,6 +497,7 @@ static int path_rec_start(struct net_device *dev,
 				   IB_SA_PATH_REC_DGID		|
 				   IB_SA_PATH_REC_SGID		|
 				   IB_SA_PATH_REC_NUMB_PATH	|
+				   IB_SA_PATH_REC_TRAFFIC_CLASS |
 				   IB_SA_PATH_REC_PKEY,
 				   1000, GFP_ATOMIC,
 				   path_rec_completion,
@@ -512,7 +519,7 @@ static void neigh_add_path(struct sk_buff *skb, struct net_device *dev)
 
 	neigh = ipoib_neigh_alloc(skb->dst->neighbour);
 	if (!neigh) {
-		++priv->stats.tx_dropped;
+		++dev->stats.tx_dropped;
 		dev_kfree_skb_any(skb);
 		return;
 	}
@@ -577,7 +584,7 @@ err_list:
 err_path:
 	ipoib_neigh_free(dev, neigh);
 err_drop:
-	++priv->stats.tx_dropped;
+	++dev->stats.tx_dropped;
 	dev_kfree_skb_any(skb);
 
 	spin_unlock(&priv->lock);
@@ -626,7 +633,7 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 			} else
 				__path_add(dev, path);
 		} else {
-			++priv->stats.tx_dropped;
+			++dev->stats.tx_dropped;
 			dev_kfree_skb_any(skb);
 		}
 
@@ -645,7 +652,7 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 		skb_push(skb, sizeof *phdr);
 		__skb_queue_tail(&path->queue, skb);
 	} else {
-		++priv->stats.tx_dropped;
+		++dev->stats.tx_dropped;
 		dev_kfree_skb_any(skb);
 	}
 
@@ -713,7 +720,7 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			__skb_queue_tail(&neigh->queue, skb);
 			spin_unlock(&priv->lock);
 		} else {
-			++priv->stats.tx_dropped;
+			++dev->stats.tx_dropped;
 			dev_kfree_skb_any(skb);
 		}
 	} else {
@@ -739,7 +746,7 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 					   IPOIB_QPN(phdr->hwaddr),
 					   IPOIB_GID_RAW_ARG(phdr->hwaddr + 4));
 				dev_kfree_skb_any(skb);
-				++priv->stats.tx_dropped;
+				++dev->stats.tx_dropped;
 				goto out;
 			}
 
@@ -753,13 +760,6 @@ out:
 	return NETDEV_TX_OK;
 }
 
-static struct net_device_stats *ipoib_get_stats(struct net_device *dev)
-{
-	struct ipoib_dev_priv *priv = netdev_priv(dev);
-
-	return &priv->stats;
-}
-
 static void ipoib_timeout(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -775,7 +775,7 @@ static void ipoib_timeout(struct net_device *dev)
 static int ipoib_hard_header(struct sk_buff *skb,
 			     struct net_device *dev,
 			     unsigned short type,
-			     void *daddr, void *saddr, unsigned len)
+			     const void *daddr, const void *saddr, unsigned len)
 {
 	struct ipoib_header *header;
 
@@ -856,11 +856,10 @@ struct ipoib_neigh *ipoib_neigh_alloc(struct neighbour *neighbour)
 
 void ipoib_neigh_free(struct net_device *dev, struct ipoib_neigh *neigh)
 {
-	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct sk_buff *skb;
 	*to_ipoib_neigh(neigh->neighbour) = NULL;
 	while ((skb = __skb_dequeue(&neigh->queue))) {
-		++priv->stats.tx_dropped;
+		++dev->stats.tx_dropped;
 		dev_kfree_skb_any(skb);
 	}
 	if (ipoib_cm_get(neigh))
@@ -935,6 +934,10 @@ void ipoib_dev_cleanup(struct net_device *dev)
 	priv->tx_ring = NULL;
 }
 
+static const struct header_ops ipoib_header_ops = {
+	.create	= ipoib_hard_header,
+};
+
 static void ipoib_setup(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -943,13 +946,12 @@ static void ipoib_setup(struct net_device *dev)
 	dev->stop 		 = ipoib_stop;
 	dev->change_mtu 	 = ipoib_change_mtu;
 	dev->hard_start_xmit 	 = ipoib_start_xmit;
-	dev->get_stats 		 = ipoib_get_stats;
 	dev->tx_timeout 	 = ipoib_timeout;
-	dev->hard_header 	 = ipoib_hard_header;
+	dev->header_ops 	 = &ipoib_header_ops;
 	dev->set_multicast_list  = ipoib_set_mcast_list;
 	dev->neigh_setup         = ipoib_neigh_setup_dev;
-	dev->poll                = ipoib_poll;
-	dev->weight              = 100;
+
+	netif_napi_add(dev, &priv->napi, ipoib_poll, 100);
 
 	dev->watchdog_timeo 	 = HZ;
 
@@ -973,8 +975,6 @@ static void ipoib_setup(struct net_device *dev)
 
 	netif_carrier_off(dev);
 
-	SET_MODULE_OWNER(dev);
-
 	priv->dev = dev;
 
 	spin_lock_init(&priv->lock);
@@ -1017,6 +1017,37 @@ static ssize_t show_pkey(struct device *dev,
 }
 static DEVICE_ATTR(pkey, S_IRUGO, show_pkey, NULL);
 
+static ssize_t show_umcast(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(to_net_dev(dev));
+
+	return sprintf(buf, "%d\n", test_bit(IPOIB_FLAG_UMCAST, &priv->flags));
+}
+
+static ssize_t set_umcast(struct device *dev,
+			  struct device_attribute *attr,
+			  const char *buf, size_t count)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(to_net_dev(dev));
+	unsigned long umcast_val = simple_strtoul(buf, NULL, 0);
+
+	if (umcast_val > 0) {
+		set_bit(IPOIB_FLAG_UMCAST, &priv->flags);
+		ipoib_warn(priv, "ignoring multicast groups joined directly "
+				"by userspace\n");
+	} else
+		clear_bit(IPOIB_FLAG_UMCAST, &priv->flags);
+
+	return count;
+}
+static DEVICE_ATTR(umcast, S_IWUSR | S_IRUGO, show_umcast, set_umcast);
+
+int ipoib_add_umcast_attr(struct net_device *dev)
+{
+	return device_create_file(&dev->dev, &dev_attr_umcast);
+}
+
 static ssize_t create_child(struct device *dev,
 			    struct device_attribute *attr,
 			    const char *buf, size_t count)
@@ -1083,7 +1114,7 @@ static struct net_device *ipoib_add_port(const char *format,
 	if (result) {
 		printk(KERN_WARNING "%s: ib_query_pkey port %d failed (ret = %d)\n",
 		       hca->name, port, result);
-		goto alloc_mem_failed;
+		goto device_init_failed;
 	}
 
 	/*
@@ -1099,7 +1130,7 @@ static struct net_device *ipoib_add_port(const char *format,
 	if (result) {
 		printk(KERN_WARNING "%s: ib_query_gid port %d failed (ret = %d)\n",
 		       hca->name, port, result);
-		goto alloc_mem_failed;
+		goto device_init_failed;
 	} else
 		memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));
 
@@ -1134,6 +1165,8 @@ static struct net_device *ipoib_add_port(const char *format,
 		goto sysfs_failed;
 	if (ipoib_add_pkey_attr(priv->dev))
 		goto sysfs_failed;
+	if (ipoib_add_umcast_attr(priv->dev))
+		goto sysfs_failed;
 	if (device_create_file(&priv->dev->dev, &dev_attr_create_child))
 		goto sysfs_failed;
 	if (device_create_file(&priv->dev->dev, &dev_attr_delete_child))
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index aae367057a5..827820ec66d 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -57,28 +57,6 @@ MODULE_PARM_DESC(mcast_debug_level,
 
 static DEFINE_MUTEX(mcast_mutex);
 
-/* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
-struct ipoib_mcast {
-	struct ib_sa_mcmember_rec mcmember;
-	struct ib_sa_multicast	 *mc;
-	struct ipoib_ah          *ah;
-
-	struct rb_node    rb_node;
-	struct list_head  list;
-
-	unsigned long created;
-	unsigned long backoff;
-
-	unsigned long flags;
-	unsigned char logcount;
-
-	struct list_head  neigh_list;
-
-	struct sk_buff_head pkt_queue;
-
-	struct net_device *dev;
-};
-
 struct ipoib_mcast_iter {
 	struct net_device *dev;
 	union ib_gid       mgid;
@@ -125,7 +103,7 @@ static void ipoib_mcast_free(struct ipoib_mcast *mcast)
 	}
 
 	spin_lock_irqsave(&priv->tx_lock, flags);
-	priv->stats.tx_dropped += tx_dropped;
+	dev->stats.tx_dropped += tx_dropped;
 	spin_unlock_irqrestore(&priv->tx_lock, flags);
 
 	kfree(mcast);
@@ -320,7 +298,7 @@ ipoib_mcast_sendonly_join_complete(int status,
 		/* Flush out any queued packets */
 		spin_lock_irq(&priv->tx_lock);
 		while (!skb_queue_empty(&mcast->pkt_queue)) {
-			++priv->stats.tx_dropped;
+			++dev->stats.tx_dropped;
 			dev_kfree_skb_any(skb_dequeue(&mcast->pkt_queue));
 		}
 		spin_unlock_irq(&priv->tx_lock);
@@ -675,7 +653,7 @@ void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb)
 	if (!test_bit(IPOIB_MCAST_STARTED, &priv->flags)	||
 	    !priv->broadcast					||
 	    !test_bit(IPOIB_MCAST_FLAG_ATTACHED, &priv->broadcast->flags)) {
-		++priv->stats.tx_dropped;
+		++dev->stats.tx_dropped;
 		dev_kfree_skb_any(skb);
 		goto unlock;
 	}
@@ -690,7 +668,7 @@ void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb)
 		if (!mcast) {
 			ipoib_warn(priv, "unable to allocate memory for "
 				   "multicast structure\n");
-			++priv->stats.tx_dropped;
+			++dev->stats.tx_dropped;
 			dev_kfree_skb_any(skb);
 			goto out;
 		}
@@ -705,7 +683,7 @@ void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb)
 		if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE)
 			skb_queue_tail(&mcast->pkt_queue, skb);
 		else {
-			++priv->stats.tx_dropped;
+			++dev->stats.tx_dropped;
 			dev_kfree_skb_any(skb);
 		}
 
@@ -783,6 +761,7 @@ void ipoib_mcast_restart_task(struct work_struct *work)
 	struct ipoib_mcast *mcast, *tmcast;
 	LIST_HEAD(remove_list);
 	unsigned long flags;
+	struct ib_sa_mcmember_rec rec;
 
 	ipoib_dbg_mcast(priv, "restarting multicast task\n");
 
@@ -816,6 +795,14 @@ void ipoib_mcast_restart_task(struct work_struct *work)
 		if (!mcast || test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
 			struct ipoib_mcast *nmcast;
 
+			/* ignore group which is directly joined by userspace */
+			if (test_bit(IPOIB_FLAG_UMCAST, &priv->flags) &&
+			    !ib_sa_get_mcmember_rec(priv->ca, priv->port, &mgid, &rec)) {
+				ipoib_dbg_mcast(priv, "ignoring multicast entry for mgid "
+						IPOIB_GID_FMT "\n", IPOIB_GID_ARG(mgid));
+				continue;
+			}
+
 			/* Not found or send-only group, let's add a new entry */
 			ipoib_dbg_mcast(priv, "adding multicast entry for mgid "
 					IPOIB_GID_FMT "\n", IPOIB_GID_ARG(mgid));
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index 982eb88e27e..3c6e45db0ab 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -185,7 +185,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 		goto out_free_cq;
 
 	init_attr.send_cq = priv->cq;
-	init_attr.recv_cq = priv->cq,
+	init_attr.recv_cq = priv->cq;
 
 	priv->qp = ib_create_qp(priv->pd, &init_attr);
 	if (IS_ERR(priv->qp)) {
@@ -211,6 +211,7 @@ out_free_cq:
 
 out_free_mr:
 	ib_dereg_mr(priv->mr);
+	ipoib_cm_dev_cleanup(dev);
 
 out_free_pd:
 	ib_dealloc_pd(priv->pd);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index 6762988439d..293f5b892e3 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -119,6 +119,8 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 		goto sysfs_failed;
 	if (ipoib_add_pkey_attr(priv->dev))
 		goto sysfs_failed;
+	if (ipoib_add_umcast_attr(priv->dev))
+		goto sysfs_failed;
 
 	if (device_create_file(&priv->dev->dev, &dev_attr_parent))
 		goto sysfs_failed;
diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c
index 9ea5b9aaba7..a6f2303ed14 100644
--- a/drivers/infiniband/ulp/iser/iser_initiator.c
+++ b/drivers/infiniband/ulp/iser/iser_initiator.c
@@ -34,8 +34,6 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
-#include <asm/io.h>
-#include <asm/scatterlist.h>
 #include <linux/scatterlist.h>
 #include <linux/kfifo.h>
 #include <scsi/scsi_cmnd.h>
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index 36cdf77ae92..e05690e3592 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -36,8 +36,6 @@
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
-#include <asm/io.h>
-#include <asm/scatterlist.h>
 #include <linux/scatterlist.h>
 
 #include "iscsi_iser.h"
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index d42ec0156ee..654a4dce023 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -32,7 +32,6 @@
  *
  * $Id: iser_verbs.c 7051 2006-05-10 12:29:11Z ogerlitz $
  */
-#include <asm/io.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/delay.h>
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index e616c4fc6ff..950228fb009 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -76,16 +76,12 @@ module_param(topspin_workarounds, int, 0444);
 MODULE_PARM_DESC(topspin_workarounds,
 		 "Enable workarounds for Topspin/Cisco SRP target bugs if != 0");
 
-static const u8 topspin_oui[3] = { 0x00, 0x05, 0xad };
-
 static int mellanox_workarounds = 1;
 
 module_param(mellanox_workarounds, int, 0444);
 MODULE_PARM_DESC(mellanox_workarounds,
 		 "Enable workarounds for Mellanox SRP target bugs if != 0");
 
-static const u8 mellanox_oui[3] = { 0x00, 0x02, 0xc9 };
-
 static void srp_add_one(struct ib_device *device);
 static void srp_remove_one(struct ib_device *device);
 static void srp_completion(struct ib_cq *cq, void *target_ptr);
@@ -111,6 +107,24 @@ static const char *srp_target_info(struct Scsi_Host *host)
 	return host_to_target(host)->target_name;
 }
 
+static int srp_target_is_topspin(struct srp_target_port *target)
+{
+	static const u8 topspin_oui[3] = { 0x00, 0x05, 0xad };
+	static const u8 cisco_oui[3]   = { 0x00, 0x1b, 0x0d };
+
+	return topspin_workarounds &&
+		(!memcmp(&target->ioc_guid, topspin_oui, sizeof topspin_oui) ||
+		 !memcmp(&target->ioc_guid, cisco_oui, sizeof cisco_oui));
+}
+
+static int srp_target_is_mellanox(struct srp_target_port *target)
+{
+	static const u8 mellanox_oui[3] = { 0x00, 0x02, 0xc9 };
+
+	return mellanox_workarounds &&
+		!memcmp(&target->ioc_guid, mellanox_oui, sizeof mellanox_oui);
+}
+
 static struct srp_iu *srp_alloc_iu(struct srp_host *host, size_t size,
 				   gfp_t gfp_mask,
 				   enum dma_data_direction direction)
@@ -274,6 +288,7 @@ static int srp_lookup_path(struct srp_target_port *target)
 						   target->srp_host->dev->dev,
 						   target->srp_host->port,
 						   &target->path,
+						   IB_SA_PATH_REC_SERVICE_ID	|
 						   IB_SA_PATH_REC_DGID		|
 						   IB_SA_PATH_REC_SGID		|
 						   IB_SA_PATH_REC_NUMB_PATH	|
@@ -363,7 +378,7 @@ static int srp_send_req(struct srp_target_port *target)
 	 * zero out the first 8 bytes of our initiator port ID and set
 	 * the second 8 bytes to the local node GUID.
 	 */
-	if (topspin_workarounds && !memcmp(&target->ioc_guid, topspin_oui, 3)) {
+	if (srp_target_is_topspin(target)) {
 		printk(KERN_DEBUG PFX "Topspin/Cisco initiator port ID workaround "
 		       "activated for target GUID %016llx\n",
 		       (unsigned long long) be64_to_cpu(target->ioc_guid));
@@ -589,8 +604,8 @@ static int srp_map_fmr(struct srp_target_port *target, struct scatterlist *scat,
 	if (!dev->fmr_pool)
 		return -ENODEV;
 
-	if ((ib_sg_dma_address(ibdev, &scat[0]) & ~dev->fmr_page_mask) &&
-	    mellanox_workarounds && !memcmp(&target->ioc_guid, mellanox_oui, 3))
+	if (srp_target_is_mellanox(target) &&
+	    (ib_sg_dma_address(ibdev, &scat[0]) & ~dev->fmr_page_mask))
 		return -EINVAL;
 
 	len = page_cnt = 0;
@@ -1091,8 +1106,7 @@ static void srp_cm_rej_handler(struct ib_cm_id *cm_id,
 		break;
 
 	case IB_CM_REJ_PORT_REDIRECT:
-		if (topspin_workarounds &&
-		    !memcmp(&target->ioc_guid, topspin_oui, 3)) {
+		if (srp_target_is_topspin(target)) {
 			/*
 			 * Topspin/Cisco SRP gateways incorrectly send
 			 * reject reason code 25 when they mean 24
@@ -1695,6 +1709,7 @@ static int srp_parse_options(const char *buf, struct srp_target_port *target)
 				goto out;
 			}
 			target->service_id = cpu_to_be64(simple_strtoull(p, NULL, 16));
+			target->path.service_id = target->service_id;
 			kfree(p);
 			break;