11 files changed, 113 insertions, 165 deletions

diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index b78b8c0856ab..d48af2180745 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -122,25 +122,16 @@ void retransmit_timer(struct timer_list *t)
 	spin_lock_irqsave(&qp->state_lock, flags);
 	if (qp->valid) {
 		qp->comp.timeout = 1;
-		rxe_sched_task(&qp->comp.task);
+		rxe_sched_task(&qp->send_task);
 	}
 	spin_unlock_irqrestore(&qp->state_lock, flags);
 }
 
 void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb)
 {
-	int must_sched;
-
+	rxe_counter_inc(SKB_TO_PKT(skb)->rxe, RXE_CNT_SENDER_SCHED);
 	skb_queue_tail(&qp->resp_pkts, skb);
-
-	must_sched = skb_queue_len(&qp->resp_pkts) > 1;
-	if (must_sched != 0)
-		rxe_counter_inc(SKB_TO_PKT(skb)->rxe, RXE_CNT_COMPLETER_SCHED);
-
-	if (must_sched)
-		rxe_sched_task(&qp->comp.task);
-	else
-		rxe_run_task(&qp->comp.task);
+	rxe_sched_task(&qp->send_task);
 }
 
 static inline enum comp_state get_wqe(struct rxe_qp *qp,
@@ -325,7 +316,7 @@ static inline enum comp_state check_ack(struct rxe_qp *qp,
 					qp->comp.psn = pkt->psn;
 					if (qp->req.wait_psn) {
 						qp->req.wait_psn = 0;
-						rxe_sched_task(&qp->req.task);
+						qp->req.again = 1;
 					}
 				}
 				return COMPST_ERROR_RETRY;
@@ -476,7 +467,7 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 	 */
 	if (qp->req.wait_fence) {
 		qp->req.wait_fence = 0;
-		rxe_sched_task(&qp->req.task);
+		qp->req.again = 1;
 	}
 }
 
@@ -515,7 +506,7 @@ static inline enum comp_state complete_ack(struct rxe_qp *qp,
 		if (qp->req.need_rd_atomic) {
 			qp->comp.timeout_retry = 0;
 			qp->req.need_rd_atomic = 0;
-			rxe_sched_task(&qp->req.task);
+			qp->req.again = 1;
 		}
 	}
 
@@ -541,7 +532,7 @@ static inline enum comp_state complete_wqe(struct rxe_qp *qp,
 
 		if (qp->req.wait_psn) {
 			qp->req.wait_psn = 0;
-			rxe_sched_task(&qp->req.task);
+			qp->req.again = 1;
 		}
 	}
 
@@ -654,6 +645,8 @@ int rxe_completer(struct rxe_qp *qp)
 	int ret;
 	unsigned long flags;
 
+	qp->req.again = 0;
+
 	spin_lock_irqsave(&qp->state_lock, flags);
 	if (!qp->valid || qp_state(qp) == IB_QPS_ERR ||
 			  qp_state(qp) == IB_QPS_RESET) {
@@ -737,7 +730,7 @@ int rxe_completer(struct rxe_qp *qp)
 
 			if (qp->req.wait_psn) {
 				qp->req.wait_psn = 0;
-				rxe_sched_task(&qp->req.task);
+				qp->req.again = 1;
 			}
 
 			state = COMPST_DONE;
@@ -792,7 +785,7 @@ int rxe_completer(struct rxe_qp *qp)
 							RXE_CNT_COMP_RETRY);
 					qp->req.need_retry = 1;
 					qp->comp.started_retry = 1;
-					rxe_sched_task(&qp->req.task);
+					qp->req.again = 1;
 				}
 				goto done;
 
@@ -843,8 +836,9 @@ done:
 	ret = 0;
 	goto out;
 exit:
-	ret = -EAGAIN;
+	ret = (qp->req.again) ? 0 : -EAGAIN;
 out:
+	qp->req.again = 0;
 	if (pkt)
 		free_pkt(pkt);
 	return ret;
diff --git a/drivers/infiniband/sw/rxe/rxe_hw_counters.c b/drivers/infiniband/sw/rxe/rxe_hw_counters.c
index a012522b577a..437917a7d8f2 100644
--- a/drivers/infiniband/sw/rxe/rxe_hw_counters.c
+++ b/drivers/infiniband/sw/rxe/rxe_hw_counters.c
@@ -14,7 +14,7 @@ static const struct rdma_stat_desc rxe_counter_descs[] = {
 	[RXE_CNT_RCV_RNR].name             =  "rcvd_rnr_err",
 	[RXE_CNT_SND_RNR].name             =  "send_rnr_err",
 	[RXE_CNT_RCV_SEQ_ERR].name         =  "rcvd_seq_err",
-	[RXE_CNT_COMPLETER_SCHED].name     =  "ack_deferred",
+	[RXE_CNT_SENDER_SCHED].name        =  "ack_deferred",
 	[RXE_CNT_RETRY_EXCEEDED].name      =  "retry_exceeded_err",
 	[RXE_CNT_RNR_RETRY_EXCEEDED].name  =  "retry_rnr_exceeded_err",
 	[RXE_CNT_COMP_RETRY].name          =  "completer_retry_err",
diff --git a/drivers/infiniband/sw/rxe/rxe_hw_counters.h b/drivers/infiniband/sw/rxe/rxe_hw_counters.h
index 71f4d4fa9dc8..051f9e1c3852 100644
--- a/drivers/infiniband/sw/rxe/rxe_hw_counters.h
+++ b/drivers/infiniband/sw/rxe/rxe_hw_counters.h
@@ -18,7 +18,7 @@ enum rxe_counters {
 	RXE_CNT_RCV_RNR,
 	RXE_CNT_SND_RNR,
 	RXE_CNT_RCV_SEQ_ERR,
-	RXE_CNT_COMPLETER_SCHED,
+	RXE_CNT_SENDER_SCHED,
 	RXE_CNT_RETRY_EXCEEDED,
 	RXE_CNT_RNR_RETRY_EXCEEDED,
 	RXE_CNT_COMP_RETRY,
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index 746110898a0e..ded46119151b 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -164,7 +164,8 @@ void rxe_dealloc(struct ib_device *ib_dev);
 
 int rxe_completer(struct rxe_qp *qp);
 int rxe_requester(struct rxe_qp *qp);
-int rxe_responder(struct rxe_qp *qp);
+int rxe_sender(struct rxe_qp *qp);
+int rxe_receiver(struct rxe_qp *qp);
 
 /* rxe_icrc.c */
 int rxe_icrc_init(struct rxe_dev *rxe);
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index cd59666158b1..ca9a82e1c4c7 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -345,46 +345,52 @@ int rxe_prepare(struct rxe_av *av, struct rxe_pkt_info *pkt,
 
 static void rxe_skb_tx_dtor(struct sk_buff *skb)
 {
-	struct sock *sk = skb->sk;
-	struct rxe_qp *qp = sk->sk_user_data;
-	int skb_out = atomic_dec_return(&qp->skb_out);
+	struct net_device *ndev = skb->dev;
+	struct rxe_dev *rxe;
+	unsigned int qp_index;
+	struct rxe_qp *qp;
+	int skb_out;
+
+	rxe = rxe_get_dev_from_net(ndev);
+	if (!rxe && is_vlan_dev(ndev))
+		rxe = rxe_get_dev_from_net(vlan_dev_real_dev(ndev));
+	if (WARN_ON(!rxe))
+		return;
+
+	qp_index = (int)(uintptr_t)skb->sk->sk_user_data;
+	if (!qp_index)
+		return;
 
-	if (unlikely(qp->need_req_skb &&
-		     skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW))
-		rxe_sched_task(&qp->req.task);
+	qp = rxe_pool_get_index(&rxe->qp_pool, qp_index);
+	if (!qp)
+		goto put_dev;
+
+	skb_out = atomic_dec_return(&qp->skb_out);
+	if (qp->need_req_skb && skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW)
+		rxe_sched_task(&qp->send_task);
 
 	rxe_put(qp);
+put_dev:
+	ib_device_put(&rxe->ib_dev);
+	sock_put(skb->sk);
 }
 
 static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt)
 {
 	int err;
+	struct sock *sk = pkt->qp->sk->sk;
 
+	sock_hold(sk);
+	skb->sk = sk;
 	skb->destructor = rxe_skb_tx_dtor;
-	skb->sk = pkt->qp->sk->sk;
-
-	rxe_get(pkt->qp);
 	atomic_inc(&pkt->qp->skb_out);
 
-	if (skb->protocol == htons(ETH_P_IP)) {
+	if (skb->protocol == htons(ETH_P_IP))
 		err = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
-	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+	else
 		err = ip6_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
-	} else {
-		rxe_dbg_qp(pkt->qp, "Unknown layer 3 protocol: %d\n",
-				skb->protocol);
-		atomic_dec(&pkt->qp->skb_out);
-		rxe_put(pkt->qp);
-		kfree_skb(skb);
-		return -EINVAL;
-	}
-
-	if (unlikely(net_xmit_eval(err))) {
-		rxe_dbg_qp(pkt->qp, "error sending packet: %d\n", err);
-		return -EAGAIN;
-	}
 
-	return 0;
+	return err;
 }
 
 /* fix up a send packet to match the packets
@@ -392,8 +398,15 @@ static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt)
  */
 static int rxe_loopback(struct sk_buff *skb, struct rxe_pkt_info *pkt)
 {
+	struct sock *sk = pkt->qp->sk->sk;
+
 	memcpy(SKB_TO_PKT(skb), pkt, sizeof(*pkt));
 
+	sock_hold(sk);
+	skb->sk = sk;
+	skb->destructor = rxe_skb_tx_dtor;
+	atomic_inc(&pkt->qp->skb_out);
+
 	if (skb->protocol == htons(ETH_P_IP))
 		skb_pull(skb, sizeof(struct iphdr));
 	else
@@ -440,12 +453,6 @@ int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
 		return err;
 	}
 
-	if ((qp_type(qp) != IB_QPT_RC) &&
-	    (pkt->mask & RXE_END_MASK)) {
-		pkt->wqe->state = wqe_state_done;
-		rxe_sched_task(&qp->comp.task);
-	}
-
 	rxe_counter_inc(rxe, RXE_CNT_SENT_PKTS);
 	goto done;
 
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c
index 6215c6de3a84..67567d62195e 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.c
+++ b/drivers/infiniband/sw/rxe/rxe_pool.c
@@ -119,7 +119,7 @@ void rxe_pool_cleanup(struct rxe_pool *pool)
 int __rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_elem *elem,
 				bool sleepable)
 {
-	int err;
+	int err = -EINVAL;
 	gfp_t gfp_flags;
 
 	if (atomic_inc_return(&pool->num_elem) > pool->max_elem)
@@ -147,7 +147,7 @@ int __rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_elem *elem,
 
 err_cnt:
 	atomic_dec(&pool->num_elem);
-	return -EINVAL;
+	return err;
 }
 
 void *rxe_pool_get_index(struct rxe_pool *pool, u32 index)
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index e3589c02013e..d2f7b5195c19 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -244,7 +244,7 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp,
 	err = sock_create_kern(&init_net, AF_INET, SOCK_DGRAM, 0, &qp->sk);
 	if (err < 0)
 		return err;
-	qp->sk->sk->sk_user_data = qp;
+	qp->sk->sk->sk_user_data = (void *)(uintptr_t)qp->elem.index;
 
 	/* pick a source UDP port number for this QP based on
 	 * the source QPN. this spreads traffic for different QPs
@@ -265,8 +265,7 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp,
 	qp->req.opcode		= -1;
 	qp->comp.opcode		= -1;
 
-	rxe_init_task(&qp->req.task, qp, rxe_requester);
-	rxe_init_task(&qp->comp.task, qp, rxe_completer);
+	rxe_init_task(&qp->send_task, qp, rxe_sender);
 
 	qp->qp_timeout_jiffies = 0; /* Can't be set for UD/UC in modify_qp */
 	if (init->qp_type == IB_QPT_RC) {
@@ -337,7 +336,7 @@ static int rxe_qp_init_resp(struct rxe_dev *rxe, struct rxe_qp *qp,
 			return err;
 	}
 
-	rxe_init_task(&qp->resp.task, qp, rxe_responder);
+	rxe_init_task(&qp->recv_task, qp, rxe_receiver);
 
 	qp->resp.opcode		= OPCODE_NONE;
 	qp->resp.msn		= 0;
@@ -514,14 +513,12 @@ err1:
 static void rxe_qp_reset(struct rxe_qp *qp)
 {
 	/* stop tasks from running */
-	rxe_disable_task(&qp->resp.task);
-	rxe_disable_task(&qp->comp.task);
-	rxe_disable_task(&qp->req.task);
+	rxe_disable_task(&qp->recv_task);
+	rxe_disable_task(&qp->send_task);
 
 	/* drain work and packet queuesc */
-	rxe_requester(qp);
-	rxe_completer(qp);
-	rxe_responder(qp);
+	rxe_sender(qp);
+	rxe_receiver(qp);
 
 	if (qp->rq.queue)
 		rxe_queue_reset(qp->rq.queue);
@@ -548,9 +545,8 @@ static void rxe_qp_reset(struct rxe_qp *qp)
 	cleanup_rd_atomic_resources(qp);
 
 	/* reenable tasks */
-	rxe_enable_task(&qp->resp.task);
-	rxe_enable_task(&qp->comp.task);
-	rxe_enable_task(&qp->req.task);
+	rxe_enable_task(&qp->recv_task);
+	rxe_enable_task(&qp->send_task);
 }
 
 /* move the qp to the error state */
@@ -562,9 +558,8 @@ void rxe_qp_error(struct rxe_qp *qp)
 	qp->attr.qp_state = IB_QPS_ERR;
 
 	/* drain work and packet queues */
-	rxe_sched_task(&qp->resp.task);
-	rxe_sched_task(&qp->comp.task);
-	rxe_sched_task(&qp->req.task);
+	rxe_sched_task(&qp->recv_task);
+	rxe_sched_task(&qp->send_task);
 	spin_unlock_irqrestore(&qp->state_lock, flags);
 }
 
@@ -575,8 +570,7 @@ static void rxe_qp_sqd(struct rxe_qp *qp, struct ib_qp_attr *attr,
 
 	spin_lock_irqsave(&qp->state_lock, flags);
 	qp->attr.sq_draining = 1;
-	rxe_sched_task(&qp->comp.task);
-	rxe_sched_task(&qp->req.task);
+	rxe_sched_task(&qp->send_task);
 	spin_unlock_irqrestore(&qp->state_lock, flags);
 }
 
@@ -821,19 +815,15 @@ static void rxe_qp_do_cleanup(struct work_struct *work)
 		del_timer_sync(&qp->rnr_nak_timer);
 	}
 
-	if (qp->resp.task.func)
-		rxe_cleanup_task(&qp->resp.task);
+	if (qp->recv_task.func)
+		rxe_cleanup_task(&qp->recv_task);
 
-	if (qp->req.task.func)
-		rxe_cleanup_task(&qp->req.task);
-
-	if (qp->comp.task.func)
-		rxe_cleanup_task(&qp->comp.task);
+	if (qp->send_task.func)
+		rxe_cleanup_task(&qp->send_task);
 
 	/* flush out any receive wr's or pending requests */
-	rxe_requester(qp);
-	rxe_completer(qp);
-	rxe_responder(qp);
+	rxe_sender(qp);
+	rxe_receiver(qp);
 
 	if (qp->sq.queue)
 		rxe_queue_cleanup(qp->sq.queue);
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index d8c41fd626a9..cd14c4c2dff9 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -108,7 +108,7 @@ void rnr_nak_timer(struct timer_list *t)
 		/* request a send queue retry */
 		qp->req.need_retry = 1;
 		qp->req.wait_for_rnr_timer = 0;
-		rxe_sched_task(&qp->req.task);
+		rxe_sched_task(&qp->send_task);
 	}
 	spin_unlock_irqrestore(&qp->state_lock, flags);
 }
@@ -545,6 +545,8 @@ static void update_wqe_state(struct rxe_qp *qp,
 	if (pkt->mask & RXE_END_MASK) {
 		if (qp_type(qp) == IB_QPT_RC)
 			wqe->state = wqe_state_pending;
+		else
+			wqe->state = wqe_state_done;
 	} else {
 		wqe->state = wqe_state_processing;
 	}
@@ -573,30 +575,6 @@ static void update_wqe_psn(struct rxe_qp *qp,
 		qp->req.psn = (qp->req.psn + 1) & BTH_PSN_MASK;
 }
 
-static void save_state(struct rxe_send_wqe *wqe,
-		       struct rxe_qp *qp,
-		       struct rxe_send_wqe *rollback_wqe,
-		       u32 *rollback_psn)
-{
-	rollback_wqe->state = wqe->state;
-	rollback_wqe->first_psn = wqe->first_psn;
-	rollback_wqe->last_psn = wqe->last_psn;
-	rollback_wqe->dma = wqe->dma;
-	*rollback_psn = qp->req.psn;
-}
-
-static void rollback_state(struct rxe_send_wqe *wqe,
-			   struct rxe_qp *qp,
-			   struct rxe_send_wqe *rollback_wqe,
-			   u32 rollback_psn)
-{
-	wqe->state = rollback_wqe->state;
-	wqe->first_psn = rollback_wqe->first_psn;
-	wqe->last_psn = rollback_wqe->last_psn;
-	wqe->dma = rollback_wqe->dma;
-	qp->req.psn = rollback_psn;
-}
-
 static void update_state(struct rxe_qp *qp, struct rxe_pkt_info *pkt)
 {
 	qp->req.opcode = pkt->opcode;
@@ -655,12 +633,6 @@ static int rxe_do_local_ops(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 	wqe->status = IB_WC_SUCCESS;
 	qp->req.wqe_index = queue_next_index(qp->sq.queue, qp->req.wqe_index);
 
-	/* There is no ack coming for local work requests
-	 * which can lead to a deadlock. So go ahead and complete
-	 * it now.
-	 */
-	rxe_sched_task(&qp->comp.task);
-
 	return 0;
 }
 
@@ -676,8 +648,6 @@ int rxe_requester(struct rxe_qp *qp)
 	int opcode;
 	int err;
 	int ret;
-	struct rxe_send_wqe rollback_wqe;
-	u32 rollback_psn;
 	struct rxe_queue *q = qp->sq.queue;
 	struct rxe_ah *ah;
 	struct rxe_av *av;
@@ -786,7 +756,6 @@ int rxe_requester(struct rxe_qp *qp)
 						       qp->req.wqe_index);
 			wqe->state = wqe_state_done;
 			wqe->status = IB_WC_SUCCESS;
-			rxe_sched_task(&qp->comp.task);
 			goto done;
 		}
 		payload = mtu;
@@ -799,9 +768,6 @@ int rxe_requester(struct rxe_qp *qp)
 	pkt.mask = rxe_opcode[opcode].mask;
 	pkt.wqe = wqe;
 
-	/* save wqe state before we build and send packet */
-	save_state(wqe, qp, &rollback_wqe, &rollback_psn);
-
 	av = rxe_get_av(&pkt, &ah);
 	if (unlikely(!av)) {
 		rxe_dbg_qp(qp, "Failed no address vector\n");
@@ -834,31 +800,14 @@ int rxe_requester(struct rxe_qp *qp)
 	if (ah)
 		rxe_put(ah);
 
-	/* update wqe state as though we had sent it */
-	update_wqe_state(qp, wqe, &pkt);
-	update_wqe_psn(qp, wqe, &pkt, payload);
-
 	err = rxe_xmit_packet(qp, &pkt, skb);
 	if (err) {
-		if (err != -EAGAIN) {
-			wqe->status = IB_WC_LOC_QP_OP_ERR;
-			goto err;
-		}
-
-		/* the packet was dropped so reset wqe to the state
-		 * before we sent it so we can try to resend
-		 */
-		rollback_state(wqe, qp, &rollback_wqe, rollback_psn);
-
-		/* force a delay until the dropped packet is freed and
-		 * the send queue is drained below the low water mark
-		 */
-		qp->need_req_skb = 1;
-
-		rxe_sched_task(&qp->req.task);
-		goto exit;
+		wqe->status = IB_WC_LOC_QP_OP_ERR;
+		goto err;
 	}
 
+	update_wqe_state(qp, wqe, &pkt);
+	update_wqe_psn(qp, wqe, &pkt, payload);
 	update_state(qp, &pkt);
 
 	/* A non-zero return value will cause rxe_do_task to
@@ -878,3 +827,20 @@ exit:
 out:
 	return ret;
 }
+
+int rxe_sender(struct rxe_qp *qp)
+{
+	int req_ret;
+	int comp_ret;
+
+	/* process the send queue */
+	req_ret = rxe_requester(qp);
+
+	/* process the response queue */
+	comp_ret = rxe_completer(qp);
+
+	/* exit the task loop if both requester and completer
+	 * are ready
+	 */
+	return (req_ret && comp_ret) ? -EAGAIN : 0;
+}
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 963382f625d7..c6a7fa3054fa 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -49,18 +49,8 @@ static char *resp_state_name[] = {
 /* rxe_recv calls here to add a request packet to the input queue */
 void rxe_resp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb)
 {
-	int must_sched;
-	struct rxe_pkt_info *pkt = SKB_TO_PKT(skb);
-
 	skb_queue_tail(&qp->req_pkts, skb);
-
-	must_sched = (pkt->opcode == IB_OPCODE_RC_RDMA_READ_REQUEST) ||
-			(skb_queue_len(&qp->req_pkts) > 1);
-
-	if (must_sched)
-		rxe_sched_task(&qp->resp.task);
-	else
-		rxe_run_task(&qp->resp.task);
+	rxe_sched_task(&qp->recv_task);
 }
 
 static inline enum resp_states get_req(struct rxe_qp *qp,
@@ -1485,7 +1475,7 @@ static void flush_recv_queue(struct rxe_qp *qp, bool notify)
 	qp->resp.wqe = NULL;
 }
 
-int rxe_responder(struct rxe_qp *qp)
+int rxe_receiver(struct rxe_qp *qp)
 {
 	struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
 	enum resp_states state;
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 614581989b38..c7d4d8ab5a09 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -888,6 +888,7 @@ static int rxe_post_send_kernel(struct rxe_qp *qp,
 {
 	int err = 0;
 	unsigned long flags;
+	int good = 0;
 
 	spin_lock_irqsave(&qp->sq.sq_lock, flags);
 	while (ibwr) {
@@ -895,18 +896,16 @@ static int rxe_post_send_kernel(struct rxe_qp *qp,
 		if (err) {
 			*bad_wr = ibwr;
 			break;
+		} else {
+			good++;
 		}
 		ibwr = ibwr->next;
 	}
 	spin_unlock_irqrestore(&qp->sq.sq_lock, flags);
 
-	if (!err)
-		rxe_sched_task(&qp->req.task);
-
-	spin_lock_irqsave(&qp->state_lock, flags);
-	if (qp_state(qp) == IB_QPS_ERR)
-		rxe_sched_task(&qp->comp.task);
-	spin_unlock_irqrestore(&qp->state_lock, flags);
+	/* kickoff processing of any posted wqes */
+	if (good)
+		rxe_sched_task(&qp->send_task);
 
 	return err;
 }
@@ -936,7 +935,7 @@ static int rxe_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 
 	if (qp->is_user) {
 		/* Utilize process context to do protocol processing */
-		rxe_run_task(&qp->req.task);
+		rxe_sched_task(&qp->send_task);
 	} else {
 		err = rxe_post_send_kernel(qp, wr, bad_wr);
 		if (err)
@@ -1046,7 +1045,7 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
 
 	spin_lock_irqsave(&qp->state_lock, flags);
 	if (qp_state(qp) == IB_QPS_ERR)
-		rxe_sched_task(&qp->resp.task);
+		rxe_sched_task(&qp->recv_task);
 	spin_unlock_irqrestore(&qp->state_lock, flags);
 
 	return err;
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index ccb9d19ffe8a..3c1354f82283 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -113,7 +113,7 @@ struct rxe_req_info {
 	int			need_retry;
 	int			wait_for_rnr_timer;
 	int			noack_pkts;
-	struct rxe_task		task;
+	int			again;
 };
 
 struct rxe_comp_info {
@@ -124,7 +124,6 @@ struct rxe_comp_info {
 	int			started_retry;
 	u32			retry_cnt;
 	u32			rnr_retry;
-	struct rxe_task		task;
 };
 
 enum rdatm_res_state {
@@ -196,7 +195,6 @@ struct rxe_resp_info {
 	unsigned int		res_head;
 	unsigned int		res_tail;
 	struct resp_res		*res;
-	struct rxe_task		task;
 };
 
 struct rxe_qp {
@@ -229,6 +227,9 @@ struct rxe_qp {
 	struct sk_buff_head	req_pkts;
 	struct sk_buff_head	resp_pkts;
 
+	struct rxe_task		send_task;
+	struct rxe_task		recv_task;
+
 	struct rxe_req_info	req;
 	struct rxe_comp_info	comp;
 	struct rxe_resp_info	resp;