1 files changed, 231 insertions, 146 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 57a9655e844d..10b0dbda6cd5 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -40,6 +40,8 @@
 
 #include <linux/ip.h>
 #include <linux/tcp.h>
+#include <net/netdev_lock.h>
+#include <rdma/ib_cache.h>
 
 #include "ipoib.h"
 
@@ -57,7 +59,7 @@ struct ipoib_ah *ipoib_create_ah(struct net_device *dev,
 	struct ipoib_ah *ah;
 	struct ib_ah *vah;
 
-	ah = kmalloc(sizeof *ah, GFP_KERNEL);
+	ah = kmalloc(sizeof(*ah), GFP_KERNEL);
 	if (!ah)
 		return ERR_PTR(-ENOMEM);
 
@@ -65,7 +67,7 @@ struct ipoib_ah *ipoib_create_ah(struct net_device *dev,
 	ah->last_send = 0;
 	kref_init(&ah->ref);
 
-	vah = rdma_create_ah(pd, attr);
+	vah = rdma_create_ah(pd, attr, RDMA_CREATE_AH_SLEEPABLE);
 	if (IS_ERR(vah)) {
 		kfree(ah);
 		ah = (struct ipoib_ah *)vah;
@@ -100,7 +102,6 @@ static void ipoib_ud_dma_unmap_rx(struct ipoib_dev_priv *priv,
 static int ipoib_ib_post_receive(struct net_device *dev, int id)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
-	struct ib_recv_wr *bad_wr;
 	int ret;
 
 	priv->rx_wr.wr_id   = id | IPOIB_OP_RECV;
@@ -108,7 +109,7 @@ static int ipoib_ib_post_receive(struct net_device *dev, int id)
 	priv->rx_sge[1].addr = priv->rx_ring[id].mapping[1];
 
 
-	ret = ib_post_recv(priv->qp, &priv->rx_wr, &bad_wr);
+	ret = ib_post_recv(priv->qp, &priv->rx_wr, NULL);
 	if (unlikely(ret)) {
 		ipoib_warn(priv, "receive failed for buf %d (%d)\n", id, ret);
 		ipoib_ud_dma_unmap_rx(priv, priv->rx_ring[id].mapping);
@@ -192,8 +193,8 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 
 	if (unlikely(wc->status != IB_WC_SUCCESS)) {
 		if (wc->status != IB_WC_WR_FLUSH_ERR)
-			ipoib_warn(priv, "failed recv event "
-				   "(status=%d, wrid=%d vend_err %x)\n",
+			ipoib_warn(priv,
+				   "failed recv event (status=%d, wrid=%d vend_err %#x)\n",
 				   wc->status, wr_id, wc->vendor_err);
 		ipoib_ud_dma_unmap_rx(priv, priv->rx_ring[wr_id].mapping);
 		dev_kfree_skb_any(skb);
@@ -202,7 +203,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	}
 
 	memcpy(mapping, priv->rx_ring[wr_id].mapping,
-	       IPOIB_UD_RX_SG * sizeof *mapping);
+	       IPOIB_UD_RX_SG * sizeof(*mapping));
 
 	/*
 	 * If we can't allocate a new RX buffer, dump
@@ -256,13 +257,15 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 
 	++dev->stats.rx_packets;
 	dev->stats.rx_bytes += skb->len;
+	if (skb->pkt_type == PACKET_MULTICAST)
+		dev->stats.multicast++;
 
 	skb->dev = dev;
 	if ((dev->features & NETIF_F_RXCSUM) &&
 			likely(wc->wc_flags & IB_WC_IP_CSUM_OK))
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
-	napi_gro_receive(&priv->napi, skb);
+	napi_gro_receive(&priv->recv_napi, skb);
 
 repost:
 	if (unlikely(ipoib_ib_post_receive(dev, wr_id)))
@@ -291,7 +294,8 @@ int ipoib_dma_map_tx(struct ib_device *ca, struct ipoib_tx_buf *tx_req)
 		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 		mapping[i + off] = ib_dma_map_page(ca,
 						 skb_frag_page(frag),
-						 frag->page_offset, skb_frag_size(frag),
+						 skb_frag_off(frag),
+						 skb_frag_size(frag),
 						 DMA_TO_DEVICE);
 		if (unlikely(ib_dma_mapping_error(ca, mapping[i + off])))
 			goto partial_error;
@@ -404,16 +408,19 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 	dev_kfree_skb_any(tx_req->skb);
 
 	++priv->tx_tail;
-	if (unlikely(--priv->tx_outstanding == ipoib_sendq_size >> 1) &&
-	    netif_queue_stopped(dev) &&
-	    test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
+	++priv->global_tx_tail;
+
+	if (unlikely(netif_queue_stopped(dev) &&
+		     ((priv->global_tx_head - priv->global_tx_tail) <=
+		      ipoib_sendq_size >> 1) &&
+		     test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)))
 		netif_wake_queue(dev);
 
 	if (wc->status != IB_WC_SUCCESS &&
 	    wc->status != IB_WC_WR_FLUSH_ERR) {
 		struct ipoib_qp_state_validate *qp_work;
-		ipoib_warn(priv, "failed send event "
-			   "(status=%d, wrid=%d vend_err %x)\n",
+		ipoib_warn(priv,
+			   "failed send event (status=%d, wrid=%d vend_err %#x)\n",
 			   wc->status, wr_id, wc->vendor_err);
 		qp_work = kzalloc(sizeof(*qp_work), GFP_ATOMIC);
 		if (!qp_work)
@@ -428,17 +435,23 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 static int poll_tx(struct ipoib_dev_priv *priv)
 {
 	int n, i;
+	struct ib_wc *wc;
 
 	n = ib_poll_cq(priv->send_cq, MAX_SEND_CQE, priv->send_wc);
-	for (i = 0; i < n; ++i)
-		ipoib_ib_handle_tx_wc(priv->dev, priv->send_wc + i);
-
+	for (i = 0; i < n; ++i) {
+		wc = priv->send_wc + i;
+		if (wc->wr_id & IPOIB_OP_CM)
+			ipoib_cm_handle_tx_wc(priv->dev, priv->send_wc + i);
+		else
+			ipoib_ib_handle_tx_wc(priv->dev, priv->send_wc + i);
+	}
 	return n == MAX_SEND_CQE;
 }
 
-int ipoib_poll(struct napi_struct *napi, int budget)
+int ipoib_rx_poll(struct napi_struct *napi, int budget)
 {
-	struct ipoib_dev_priv *priv = container_of(napi, struct ipoib_dev_priv, napi);
+	struct ipoib_dev_priv *priv =
+		container_of(napi, struct ipoib_dev_priv, recv_napi);
 	struct net_device *dev = priv->dev;
 	int done;
 	int t;
@@ -462,8 +475,9 @@ poll_more:
 					ipoib_cm_handle_rx_wc(dev, wc);
 				else
 					ipoib_ib_handle_rx_wc(dev, wc);
-			} else
-				ipoib_cm_handle_tx_wc(priv->dev, wc);
+			} else {
+				pr_warn("%s: Got unexpected wqe id\n", __func__);
+			}
 		}
 
 		if (n != t)
@@ -475,40 +489,78 @@ poll_more:
 		if (unlikely(ib_req_notify_cq(priv->recv_cq,
 					      IB_CQ_NEXT_COMP |
 					      IB_CQ_REPORT_MISSED_EVENTS)) &&
-		    napi_reschedule(napi))
+		    napi_schedule(napi))
 			goto poll_more;
 	}
 
 	return done;
 }
 
-void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr)
+int ipoib_tx_poll(struct napi_struct *napi, int budget)
 {
-	struct net_device *dev = dev_ptr;
-	struct ipoib_dev_priv *priv = ipoib_priv(dev);
+	struct ipoib_dev_priv *priv = container_of(napi, struct ipoib_dev_priv,
+						   send_napi);
+	struct net_device *dev = priv->dev;
+	int n, i;
+	struct ib_wc *wc;
+
+poll_more:
+	n = ib_poll_cq(priv->send_cq, MAX_SEND_CQE, priv->send_wc);
 
-	napi_schedule(&priv->napi);
+	for (i = 0; i < n; i++) {
+		wc = priv->send_wc + i;
+		if (wc->wr_id & IPOIB_OP_CM)
+			ipoib_cm_handle_tx_wc(dev, wc);
+		else
+			ipoib_ib_handle_tx_wc(dev, wc);
+	}
+
+	if (n < budget) {
+		napi_complete(napi);
+		if (unlikely(ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP |
+					      IB_CQ_REPORT_MISSED_EVENTS)) &&
+		    napi_schedule(napi))
+			goto poll_more;
+	}
+	return n < 0 ? 0 : n;
 }
 
-static void drain_tx_cq(struct net_device *dev)
+void ipoib_ib_rx_completion(struct ib_cq *cq, void *ctx_ptr)
 {
-	struct ipoib_dev_priv *priv = ipoib_priv(dev);
+	struct ipoib_dev_priv *priv = ctx_ptr;
 
-	netif_tx_lock(dev);
-	while (poll_tx(priv))
-		; /* nothing */
+	napi_schedule(&priv->recv_napi);
+}
 
-	if (netif_queue_stopped(dev))
-		mod_timer(&priv->poll_timer, jiffies + 1);
+/* The function will force napi_schedule */
+void ipoib_napi_schedule_work(struct work_struct *work)
+{
+	struct ipoib_dev_priv *priv =
+		container_of(work, struct ipoib_dev_priv, reschedule_napi_work);
+	bool ret;
 
-	netif_tx_unlock(dev);
+	do {
+		ret = napi_schedule(&priv->send_napi);
+		if (!ret)
+			msleep(3);
+	} while (!ret && netif_queue_stopped(priv->dev) &&
+		 test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags));
 }
 
-void ipoib_send_comp_handler(struct ib_cq *cq, void *dev_ptr)
+void ipoib_ib_tx_completion(struct ib_cq *cq, void *ctx_ptr)
 {
-	struct ipoib_dev_priv *priv = ipoib_priv(dev_ptr);
+	struct ipoib_dev_priv *priv = ctx_ptr;
+	bool ret;
 
-	mod_timer(&priv->poll_timer, jiffies);
+	ret = napi_schedule(&priv->send_napi);
+	/*
+	 * if the queue is closed the driver must be able to schedule napi,
+	 * otherwise we can end with closed queue forever, because no new
+	 * packets to send and napi callback might not get new event after
+	 * its re-arm of the napi.
+	 */
+	if (!ret && netif_queue_stopped(priv->dev))
+		schedule_work(&priv->reschedule_napi_work);
 }
 
 static inline int post_send(struct ipoib_dev_priv *priv,
@@ -517,7 +569,6 @@ static inline int post_send(struct ipoib_dev_priv *priv,
 			    struct ipoib_tx_buf *tx_req,
 			    void *head, int hlen)
 {
-	struct ib_send_wr *bad_wr;
 	struct sk_buff *skb = tx_req->skb;
 
 	ipoib_build_sge(priv, tx_req);
@@ -534,7 +585,7 @@ static inline int post_send(struct ipoib_dev_priv *priv,
 	} else
 		priv->tx_wr.wr.opcode	= IB_WR_SEND;
 
-	return ib_post_send(priv->qp, &priv->tx_wr.wr, &bad_wr);
+	return ib_post_send(priv->qp, &priv->tx_wr.wr, NULL);
 }
 
 int ipoib_send(struct net_device *dev, struct sk_buff *skb,
@@ -544,10 +595,10 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb,
 	struct ipoib_tx_buf *tx_req;
 	int hlen, rc;
 	void *phead;
-	unsigned usable_sge = priv->max_send_sge - !!skb_headlen(skb);
+	unsigned int usable_sge = priv->max_send_sge - !!skb_headlen(skb);
 
 	if (skb_is_gso(skb)) {
-		hlen = skb_transport_offset(skb) + tcp_hdrlen(skb);
+		hlen = skb_tcp_all_headers(skb);
 		phead = skb->data;
 		if (unlikely(!skb_pull(skb, hlen))) {
 			ipoib_warn(priv, "linear data too small\n");
@@ -609,23 +660,26 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb,
 		priv->tx_wr.wr.send_flags |= IB_SEND_IP_CSUM;
 	else
 		priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM;
-
-	if (++priv->tx_outstanding == ipoib_sendq_size) {
+	/* increase the tx_head after send success, but use it for queue state */
+	if ((priv->global_tx_head - priv->global_tx_tail) ==
+	    ipoib_sendq_size - 1) {
 		ipoib_dbg(priv, "TX ring full, stopping kernel net queue\n");
-		if (ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP))
-			ipoib_warn(priv, "request notify on send CQ failed\n");
 		netif_stop_queue(dev);
 	}
 
 	skb_orphan(skb);
 	skb_dst_drop(skb);
 
+	if (netif_queue_stopped(dev))
+		if (ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP |
+				     IB_CQ_REPORT_MISSED_EVENTS) < 0)
+			ipoib_warn(priv, "request notify on send CQ failed\n");
+
 	rc = post_send(priv, priv->tx_head & (ipoib_sendq_size - 1),
 		       address, dqpn, tx_req, phead, hlen);
 	if (unlikely(rc)) {
 		ipoib_warn(priv, "post_send failed, error %d\n", rc);
 		++dev->stats.tx_errors;
-		--priv->tx_outstanding;
 		ipoib_dma_unmap_tx(priv, tx_req);
 		dev_kfree_skb_any(skb);
 		if (netif_queue_stopped(dev))
@@ -636,64 +690,58 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb,
 
 		rc = priv->tx_head;
 		++priv->tx_head;
+		++priv->global_tx_head;
 	}
-
-	if (unlikely(priv->tx_outstanding > MAX_SEND_CQE))
-		while (poll_tx(priv))
-			; /* nothing */
-
 	return rc;
 }
 
-static void __ipoib_reap_ah(struct net_device *dev)
+static void ipoib_reap_dead_ahs(struct ipoib_dev_priv *priv)
 {
-	struct ipoib_dev_priv *priv = ipoib_priv(dev);
 	struct ipoib_ah *ah, *tah;
-	LIST_HEAD(remove_list);
 	unsigned long flags;
 
-	netif_tx_lock_bh(dev);
+	netif_tx_lock_bh(priv->dev);
 	spin_lock_irqsave(&priv->lock, flags);
 
 	list_for_each_entry_safe(ah, tah, &priv->dead_ahs, list)
 		if ((int) priv->tx_tail - (int) ah->last_send >= 0) {
 			list_del(&ah->list);
-			rdma_destroy_ah(ah->ah);
+			rdma_destroy_ah(ah->ah, 0);
 			kfree(ah);
 		}
 
 	spin_unlock_irqrestore(&priv->lock, flags);
-	netif_tx_unlock_bh(dev);
+	netif_tx_unlock_bh(priv->dev);
 }
 
 void ipoib_reap_ah(struct work_struct *work)
 {
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, ah_reap_task.work);
-	struct net_device *dev = priv->dev;
 
-	__ipoib_reap_ah(dev);
+	ipoib_reap_dead_ahs(priv);
 
 	if (!test_bit(IPOIB_STOP_REAPER, &priv->flags))
 		queue_delayed_work(priv->wq, &priv->ah_reap_task,
 				   round_jiffies_relative(HZ));
 }
 
-static void ipoib_flush_ah(struct net_device *dev)
+static void ipoib_start_ah_reaper(struct ipoib_dev_priv *priv)
 {
-	struct ipoib_dev_priv *priv = ipoib_priv(dev);
-
-	cancel_delayed_work(&priv->ah_reap_task);
-	flush_workqueue(priv->wq);
-	ipoib_reap_ah(&priv->ah_reap_task.work);
+	clear_bit(IPOIB_STOP_REAPER, &priv->flags);
+	queue_delayed_work(priv->wq, &priv->ah_reap_task,
+			   round_jiffies_relative(HZ));
 }
 
-static void ipoib_stop_ah(struct net_device *dev)
+static void ipoib_stop_ah_reaper(struct ipoib_dev_priv *priv)
 {
-	struct ipoib_dev_priv *priv = ipoib_priv(dev);
-
 	set_bit(IPOIB_STOP_REAPER, &priv->flags);
-	ipoib_flush_ah(dev);
+	cancel_delayed_work(&priv->ah_reap_task);
+	/*
+	 * After ipoib_stop_ah_reaper() we always go through
+	 * ipoib_reap_dead_ahs() which ensures the work is really stopped and
+	 * does a final flush out of the dead_ah's list
+	 */
 }
 
 static int recvs_pending(struct net_device *dev)
@@ -709,6 +757,47 @@ static int recvs_pending(struct net_device *dev)
 	return pending;
 }
 
+static void check_qp_movement_and_print(struct ipoib_dev_priv *priv,
+					struct ib_qp *qp,
+					enum ib_qp_state new_state)
+{
+	struct ib_qp_attr qp_attr;
+	struct ib_qp_init_attr query_init_attr;
+	int ret;
+
+	ret = ib_query_qp(qp, &qp_attr, IB_QP_STATE, &query_init_attr);
+	if (ret) {
+		ipoib_warn(priv, "%s: Failed to query QP\n", __func__);
+		return;
+	}
+	/* print according to the new-state and the previous state.*/
+	if (new_state == IB_QPS_ERR && qp_attr.qp_state == IB_QPS_RESET)
+		ipoib_dbg(priv, "Failed modify QP, IB_QPS_RESET to IB_QPS_ERR, acceptable\n");
+	else
+		ipoib_warn(priv, "Failed to modify QP to state: %d from state: %d\n",
+			   new_state, qp_attr.qp_state);
+}
+
+static void ipoib_napi_enable(struct net_device *dev)
+{
+	struct ipoib_dev_priv *priv = ipoib_priv(dev);
+
+	netdev_lock_ops_to_full(dev);
+	napi_enable_locked(&priv->recv_napi);
+	napi_enable_locked(&priv->send_napi);
+	netdev_unlock_full_to_ops(dev);
+}
+
+static void ipoib_napi_disable(struct net_device *dev)
+{
+	struct ipoib_dev_priv *priv = ipoib_priv(dev);
+
+	netdev_lock_ops_to_full(dev);
+	napi_disable_locked(&priv->recv_napi);
+	napi_disable_locked(&priv->send_napi);
+	netdev_unlock_full_to_ops(dev);
+}
+
 int ipoib_ib_dev_stop_default(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
@@ -718,7 +807,7 @@ int ipoib_ib_dev_stop_default(struct net_device *dev)
 	int i;
 
 	if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
-		napi_disable(&priv->napi);
+		ipoib_napi_disable(dev);
 
 	ipoib_cm_dev_stop(dev);
 
@@ -728,7 +817,7 @@ int ipoib_ib_dev_stop_default(struct net_device *dev)
 	 */
 	qp_attr.qp_state = IB_QPS_ERR;
 	if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE))
-		ipoib_warn(priv, "Failed to modify QP to ERROR state\n");
+		check_qp_movement_and_print(priv, priv->qp, IB_QPS_ERR);
 
 	/* Wait for all sends and receives to complete */
 	begin = jiffies;
@@ -750,7 +839,7 @@ int ipoib_ib_dev_stop_default(struct net_device *dev)
 				ipoib_dma_unmap_tx(priv, tx_req);
 				dev_kfree_skb_any(tx_req->skb);
 				++priv->tx_tail;
-				--priv->tx_outstanding;
+				++priv->global_tx_tail;
 			}
 
 			for (i = 0; i < ipoib_recvq_size; ++i) {
@@ -776,7 +865,6 @@ int ipoib_ib_dev_stop_default(struct net_device *dev)
 	ipoib_dbg(priv, "All sends and receives done.\n");
 
 timeout:
-	del_timer_sync(&priv->poll_timer);
 	qp_attr.qp_state = IB_QPS_RESET;
 	if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE))
 		ipoib_warn(priv, "Failed to modify QP to RESET state\n");
@@ -786,23 +874,6 @@ timeout:
 	return 0;
 }
 
-int ipoib_ib_dev_stop(struct net_device *dev)
-{
-	struct ipoib_dev_priv *priv = ipoib_priv(dev);
-
-	priv->rn_ops->ndo_stop(dev);
-
-	clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
-	ipoib_flush_ah(dev);
-
-	return 0;
-}
-
-void ipoib_ib_tx_timer_func(unsigned long ctx)
-{
-	drain_tx_cq((struct net_device *)ctx);
-}
-
 int ipoib_ib_dev_open_default(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
@@ -827,7 +898,7 @@ int ipoib_ib_dev_open_default(struct net_device *dev)
 	}
 
 	if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
-		napi_enable(&priv->napi);
+		ipoib_napi_enable(dev);
 
 	return 0;
 out:
@@ -846,10 +917,7 @@ int ipoib_ib_dev_open(struct net_device *dev)
 		return -1;
 	}
 
-	clear_bit(IPOIB_STOP_REAPER, &priv->flags);
-	queue_delayed_work(priv->wq, &priv->ah_reap_task,
-			   round_jiffies_relative(HZ));
-
+	ipoib_start_ah_reaper(priv);
 	if (priv->rn_ops->ndo_open(dev)) {
 		pr_warn("%s: Failed to open dev\n", dev->name);
 		goto dev_stop;
@@ -860,23 +928,34 @@ int ipoib_ib_dev_open(struct net_device *dev)
 	return 0;
 
 dev_stop:
-	set_bit(IPOIB_STOP_REAPER, &priv->flags);
-	cancel_delayed_work(&priv->ah_reap_task);
-	set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
-	ipoib_ib_dev_stop(dev);
+	ipoib_stop_ah_reaper(priv);
 	return -1;
 }
 
+void ipoib_ib_dev_stop(struct net_device *dev)
+{
+	struct ipoib_dev_priv *priv = ipoib_priv(dev);
+
+	priv->rn_ops->ndo_stop(dev);
+
+	clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
+	ipoib_stop_ah_reaper(priv);
+}
+
 void ipoib_pkey_dev_check_presence(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
+	struct rdma_netdev *rn = netdev_priv(dev);
 
 	if (!(priv->pkey & 0x7fff) ||
 	    ib_find_pkey(priv->ca, priv->port, priv->pkey,
-			 &priv->pkey_index))
+			 &priv->pkey_index)) {
 		clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
-	else
+	} else {
+		if (rn->set_id)
+			rn->set_id(dev, priv->pkey_index);
 		set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
+	}
 }
 
 void ipoib_ib_dev_up(struct net_device *dev)
@@ -938,8 +1017,9 @@ void ipoib_drain_cq(struct net_device *dev)
 					ipoib_cm_handle_rx_wc(dev, priv->ibwc + i);
 				else
 					ipoib_ib_handle_rx_wc(dev, priv->ibwc + i);
-			} else
-				ipoib_cm_handle_tx_wc(dev, priv->ibwc + i);
+			} else {
+				pr_warn("%s: Got unexpected wqe id\n", __func__);
+			}
 		}
 	} while (n == IPOIB_NUM_WC);
 
@@ -977,19 +1057,6 @@ static inline int update_parent_pkey(struct ipoib_dev_priv *priv)
 		 */
 		priv->dev->broadcast[8] = priv->pkey >> 8;
 		priv->dev->broadcast[9] = priv->pkey & 0xff;
-
-		/*
-		 * Update the broadcast address in the priv->broadcast object,
-		 * in case it already exists, otherwise no one will do that.
-		 */
-		if (priv->broadcast) {
-			spin_lock_irq(&priv->lock);
-			memcpy(priv->broadcast->mcmember.mgid.raw,
-			       priv->dev->broadcast + 4,
-			sizeof(union ib_gid));
-			spin_unlock_irq(&priv->lock);
-		}
-
 		return 0;
 	}
 
@@ -1019,14 +1086,12 @@ static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv)
 {
 	union ib_gid search_gid;
 	union ib_gid gid0;
-	union ib_gid *netdev_gid;
 	int err;
 	u16 index;
-	u8 port;
+	u32 port;
 	bool ret = false;
 
-	netdev_gid = (union ib_gid *)(priv->dev->dev_addr + 4);
-	if (ib_query_gid(priv->ca, priv->port, 0, &gid0, NULL))
+	if (rdma_query_gid(priv->ca, priv->port, 0, &gid0))
 		return false;
 
 	netif_addr_lock_bh(priv->dev);
@@ -1035,15 +1100,15 @@ static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv)
 	 * to do it later
 	 */
 	priv->local_gid.global.subnet_prefix = gid0.global.subnet_prefix;
-	netdev_gid->global.subnet_prefix = gid0.global.subnet_prefix;
+	dev_addr_mod(priv->dev, 4, (u8 *)&gid0.global.subnet_prefix,
+		     sizeof(gid0.global.subnet_prefix));
 	search_gid.global.subnet_prefix = gid0.global.subnet_prefix;
 
 	search_gid.global.interface_id = priv->local_gid.global.interface_id;
 
 	netif_addr_unlock_bh(priv->dev);
 
-	err = ib_find_gid(priv->ca, &search_gid, IB_GID_TYPE_IB,
-			  priv->dev, &port, &index);
+	err = ib_find_gid(priv->ca, &search_gid, &port, &index);
 
 	netif_addr_lock_bh(priv->dev);
 
@@ -1073,7 +1138,7 @@ static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv)
 	 * if he sets the device address back to be based on GID index 0,
 	 * he no longer wishs to control it.
 	 *
-	 * If the user doesn't control the the device address,
+	 * If the user doesn't control the device address,
 	 * IPOIB_FLAG_DEV_ADDR_SET is set and ib_find_gid failed it means
 	 * the port GUID has changed and GID at index 0 has changed
 	 * so we need to change priv->local_gid and priv->dev->dev_addr
@@ -1098,8 +1163,8 @@ static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv)
 			if (!test_bit(IPOIB_FLAG_DEV_ADDR_CTRL, &priv->flags)) {
 				memcpy(&priv->local_gid, &gid0,
 				       sizeof(priv->local_gid));
-				memcpy(priv->dev->dev_addr + 4, &gid0,
-				       sizeof(priv->local_gid));
+				dev_addr_mod(priv->dev, 4, (u8 *)&gid0,
+					     sizeof(priv->local_gid));
 				ret = true;
 			}
 		}
@@ -1112,24 +1177,11 @@ out:
 }
 
 static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
-				enum ipoib_flush_level level,
-				int nesting)
+				enum ipoib_flush_level level)
 {
-	struct ipoib_dev_priv *cpriv;
 	struct net_device *dev = priv->dev;
 	int result;
 
-	down_read_nested(&priv->vlan_rwsem, nesting);
-
-	/*
-	 * Flush any child interfaces too -- they might be up even if
-	 * the parent is down.
-	 */
-	list_for_each_entry(cpriv, &priv->child_intfs, list)
-		__ipoib_ib_dev_flush(cpriv, level, nesting + 1);
-
-	up_read(&priv->vlan_rwsem);
-
 	if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags) &&
 	    level != IPOIB_FLUSH_HEAVY) {
 		/* Make sure the dev_addr is set even if not flushing */
@@ -1186,17 +1238,23 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 		ipoib_mcast_dev_flush(dev);
 		if (oper_up)
 			set_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
-		ipoib_flush_ah(dev);
+		ipoib_reap_dead_ahs(priv);
 	}
 
 	if (level >= IPOIB_FLUSH_NORMAL)
 		ipoib_ib_dev_down(dev);
 
 	if (level == IPOIB_FLUSH_HEAVY) {
+		netdev_lock_ops(dev);
 		if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
 			ipoib_ib_dev_stop(dev);
-		if (ipoib_ib_dev_open(dev) != 0)
+
+		result = ipoib_ib_dev_open(dev);
+		netdev_unlock_ops(dev);
+
+		if (result)
 			return;
+
 		if (netif_queue_stopped(dev))
 			netif_start_queue(dev);
 	}
@@ -1218,7 +1276,7 @@ void ipoib_ib_dev_flush_light(struct work_struct *work)
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, flush_light);
 
-	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_LIGHT, 0);
+	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_LIGHT);
 }
 
 void ipoib_ib_dev_flush_normal(struct work_struct *work)
@@ -1226,7 +1284,7 @@ void ipoib_ib_dev_flush_normal(struct work_struct *work)
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, flush_normal);
 
-	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_NORMAL, 0);
+	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_NORMAL);
 }
 
 void ipoib_ib_dev_flush_heavy(struct work_struct *work)
@@ -1234,7 +1292,34 @@ void ipoib_ib_dev_flush_heavy(struct work_struct *work)
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, flush_heavy);
 
-	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY, 0);
+	rtnl_lock();
+	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY);
+	rtnl_unlock();
+}
+
+void ipoib_queue_work(struct ipoib_dev_priv *priv,
+		      enum ipoib_flush_level level)
+{
+	if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
+		struct ipoib_dev_priv *cpriv;
+
+		netdev_lock(priv->dev);
+		list_for_each_entry(cpriv, &priv->child_intfs, list)
+			ipoib_queue_work(cpriv, level);
+		netdev_unlock(priv->dev);
+	}
+
+	switch (level) {
+	case IPOIB_FLUSH_LIGHT:
+		queue_work(ipoib_workqueue, &priv->flush_light);
+		break;
+	case IPOIB_FLUSH_NORMAL:
+		queue_work(ipoib_workqueue, &priv->flush_normal);
+		break;
+	case IPOIB_FLUSH_HEAVY:
+		queue_work(ipoib_workqueue, &priv->flush_heavy);
+		break;
+	}
 }
 
 void ipoib_ib_dev_cleanup(struct net_device *dev)
@@ -1257,7 +1342,7 @@ void ipoib_ib_dev_cleanup(struct net_device *dev)
 	 * the neighbor garbage collection is stopped and reaped.
 	 * That should all be done now, so make a final ah flush.
 	 */
-	ipoib_stop_ah(dev);
+	ipoib_reap_dead_ahs(priv);
 
 	clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);