IB/hfi1: Performance improvements for 4.16

index 591697d..3d9c32c 100644
@@ -371,4 +371,13 @@ static inline void iowait_starve_find_max(struct iowait *w, u8 *max,
 	}
 }
 
+/**
+ * iowait_packet_queued() - determine if a packet is already built
+ * @wait: the wait structure
+ */
+static inline bool iowait_packet_queued(struct iowait *wait)
+{
+	return !list_empty(&wait->tx_head);
+}
+
 #endif

index 5507910..d30dd1a 100644
@@ -565,7 +565,7 @@ void qp_iter_print(struct seq_file *s, struct rvt_qp_iter *iter)
 	if (qp->s_ack_queue)
 		e = &qp->s_ack_queue[qp->s_tail_ack_queue];
 	seq_printf(s,
-		   "N %d %s QP %x R %u %s %u %u %u f=%x %u %u %u %u %u %u SPSN %x %x %x %x %x RPSN %x S(%u %u %u %u %u %u %u) R(%u %u %u) RQP %x LID %x SL %u MTU %u %u %u %u %u SDE %p,%u SC %p,%u SCQ %u %u PID %d OS %x %x E %x %x %x RNR %d %s %d\n",
+		   "N %d %s QP %x R %u %s %u %u f=%x %u %u %u %u %u %u SPSN %x %x %x %x %x RPSN %x S(%u %u %u %u %u %u %u) R(%u %u %u) RQP %x LID %x SL %u MTU %u %u %u %u %u SDE %p,%u SC %p,%u SCQ %u %u PID %d OS %x %x E %x %x %x RNR %d %s %d\n",
 		   iter->n,
 		   qp_idle(qp) ? "I" : "B",
 		   qp->ibqp.qp_num,

@@ -573,7 +573,6 @@ void qp_iter_print(struct seq_file *s, struct rvt_qp_iter *iter)
 		   qp_type_str[qp->ibqp.qp_type],
 		   qp->state,
 		   wqe ? wqe->wr.opcode : 0,
-		   qp->s_hdrwords,
 		   qp->s_flags,
 		   iowait_sdma_pending(&priv->s_iowait),
 		   iowait_pio_pending(&priv->s_iowait),

@@ -795,7 +794,6 @@ void notify_error_qp(struct rvt_qp *qp)
 	}
 
 	if (!(qp->s_flags & RVT_S_BUSY)) {
-		qp->s_hdrwords = 0;
 		if (qp->s_rdma_mr) {
 			rvt_put_mr(qp->s_rdma_mr);
 			qp->s_rdma_mr = NULL;

index c06d2f8..b2d4cba 100644
@@ -51,12 +51,25 @@
 #include <rdma/rdmavt_qp.h>
 #include "verbs.h"
 #include "sdma.h"
+#include "verbs_txreq.h"
 
 extern unsigned int hfi1_qp_table_size;
 
 extern const struct rvt_operation_params hfi1_post_parms[];
 
 /*
+ * Send if not busy or waiting for I/O and either
+ * a RC response is pending or we can process send work requests.
+ */
+static inline int hfi1_send_ok(struct rvt_qp *qp)
+{
+	return !(qp->s_flags & (RVT_S_BUSY | RVT_S_ANY_WAIT_IO)) &&
+		(verbs_txreq_queued(qp) ||
+		(qp->s_flags & RVT_S_RESP_PENDING) ||
+		 !(qp->s_flags & RVT_S_ANY_WAIT_SEND));
+}
+
+/*
  * free_ahg - clear ahg from QP
  */
 static inline void clear_ahg(struct rvt_qp *qp)

index 68d5c3c..524c12f 100644
@@ -226,12 +226,10 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp,
 		bth2 = mask_psn(qp->s_ack_psn);
 	}
 	qp->s_rdma_ack_cnt++;
-	qp->s_hdrwords = hwords;
 	ps->s_txreq->sde = priv->s_sde;
 	ps->s_txreq->s_cur_size = len;
+	ps->s_txreq->hdr_dwords = hwords;
 	hfi1_make_ruc_header(qp, ohdr, bth0, bth2, middle, ps);
-	/* pbc */
-	ps->s_txreq->hdr_dwords = qp->s_hdrwords + 2;
 	return 1;
 
 bail:

@@ -387,7 +385,6 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 						       : IB_WC_SUCCESS);
 				if (local_ops)
 					atomic_dec(&qp->local_ops_pending);
-				qp->s_hdrwords = 0;
 				goto done_free_tx;
 			}
 

@@ -690,7 +687,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 		bth2 |= IB_BTH_REQ_ACK;
 	}
 	qp->s_len -= len;
-	qp->s_hdrwords = hwords;
+	ps->s_txreq->hdr_dwords = hwords;
 	ps->s_txreq->sde = priv->s_sde;
 	ps->s_txreq->ss = ss;
 	ps->s_txreq->s_cur_size = len;

@@ -701,8 +698,6 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 		bth2,
 		middle,
 		ps);
-	/* pbc */
-	ps->s_txreq->hdr_dwords = qp->s_hdrwords + 2;
 	return 1;
 
 done_free_tx:

@@ -716,7 +711,6 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 bail_no_tx:
 	ps->s_txreq = NULL;
 	qp->s_flags &= ~RVT_S_BUSY;
-	qp->s_hdrwords = 0;
 	return 0;
 }
 

index 2c7fc6e..0cced9a 100644
@@ -757,8 +757,9 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 	u32 slid;
 	u16 pkey = hfi1_get_pkey(ibp, qp->s_pkey_index);
 	u8 l4 = OPA_16B_L4_IB_LOCAL;
-	u8 extra_bytes = hfi1_get_16b_padding((qp->s_hdrwords << 2),
-				   ps->s_txreq->s_cur_size);
+	u8 extra_bytes = hfi1_get_16b_padding(
+				(ps->s_txreq->hdr_dwords << 2),
+				ps->s_txreq->s_cur_size);
 	u32 nwords = SIZE_OF_CRC + ((ps->s_txreq->s_cur_size +
 				 extra_bytes + SIZE_OF_LT) >> 2);
 	u8 becn = 0;

@@ -778,9 +779,9 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 			grd->sgid_index = 0;
 		grh = &ps->s_txreq->phdr.hdr.opah.u.l.grh;
 		l4 = OPA_16B_L4_IB_GLOBAL;
-		hdrwords = qp->s_hdrwords - 4;
-		qp->s_hdrwords += hfi1_make_grh(ibp, grh, grd,
-						hdrwords, nwords);
+		hdrwords = ps->s_txreq->hdr_dwords - 4;
+		ps->s_txreq->hdr_dwords += hfi1_make_grh(ibp, grh, grd,
+							 hdrwords, nwords);
 		middle = 0;
 	}
 

@@ -814,7 +815,7 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 			  slid,
 			  opa_get_lid(rdma_ah_get_dlid(&qp->remote_ah_attr),
 				      16B),
-			  (qp->s_hdrwords + nwords) >> 1,
+			  (ps->s_txreq->hdr_dwords + nwords) >> 1,
 			  pkey, becn, 0, l4, priv->s_sc);
 }
 

@@ -834,10 +835,10 @@ static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
 
 	if (unlikely(rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)) {
 		struct ib_grh *grh = &ps->s_txreq->phdr.hdr.ibh.u.l.grh;
-		int hdrwords = qp->s_hdrwords - 2;
+		int hdrwords = ps->s_txreq->hdr_dwords - 2;
 
 		lrh0 = HFI1_LRH_GRH;
-		qp->s_hdrwords +=
+		ps->s_txreq->hdr_dwords +=
 			hfi1_make_grh(ibp, grh,
 				      rdma_ah_read_grh(&qp->remote_ah_attr),
 				      hdrwords, nwords);

@@ -866,7 +867,7 @@ static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
 	hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
 	hfi1_make_ib_hdr(&ps->s_txreq->phdr.hdr.ibh,
 			 lrh0,
-			 qp->s_hdrwords + nwords,
+			 ps->s_txreq->hdr_dwords + nwords,
 			 opa_get_lid(rdma_ah_get_dlid(&qp->remote_ah_attr), 9B),
 			 ppd_from_ibp(ibp)->lid |
 				rdma_ah_get_path_bits(&qp->remote_ah_attr));

@@ -1031,7 +1032,7 @@ void hfi1_do_send(struct rvt_qp *qp, bool in_thread)
 	ps.s_txreq = get_waiting_verbs_txreq(qp);
 	do {
 		/* Check for a constructed packet to be sent. */
-		if (qp->s_hdrwords != 0) {
+		if (ps.s_txreq) {
 			spin_unlock_irqrestore(&qp->s_lock, ps.flags);
 			/*
 			 * If the packet cannot be sent now, return and

@@ -1039,8 +1040,6 @@ void hfi1_do_send(struct rvt_qp *qp, bool in_thread)
 			 */
 			if (hfi1_verbs_send(qp, &ps))
 				return;
-			/* Record that s_ahg is empty. */
-			qp->s_hdrwords = 0;
 			/* allow other tasks to run */
 			if (schedule_send_yield(qp, &ps))
 				return;

index 991bbee..fef69d9 100644
@@ -146,7 +146,6 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 							: IB_WC_SUCCESS);
 			if (local_ops)
 				atomic_dec(&qp->local_ops_pending);
-			qp->s_hdrwords = 0;
 			goto done_free_tx;
 		}
 		/*

@@ -269,14 +268,12 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 		break;
 	}
 	qp->s_len -= len;
-	qp->s_hdrwords = hwords;
+	ps->s_txreq->hdr_dwords = hwords;
 	ps->s_txreq->sde = priv->s_sde;
 	ps->s_txreq->ss = &qp->s_sge;
 	ps->s_txreq->s_cur_size = len;
 	hfi1_make_ruc_header(qp, ohdr, bth0 | (qp->s_state << 24),
 			     mask_psn(qp->s_psn++), middle, ps);
-	/* pbc */
-	ps->s_txreq->hdr_dwords = qp->s_hdrwords + 2;
 	return 1;
 
 done_free_tx:

@@ -290,7 +287,6 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 bail_no_tx:
 	ps->s_txreq = NULL;
 	qp->s_flags &= ~RVT_S_BUSY;
-	qp->s_hdrwords = 0;
 	return 0;
 }
 

index beb5091..6b5cd3a 100644
@@ -340,15 +340,15 @@ void hfi1_make_ud_req_9B(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 	extra_bytes = -wqe->length & 3;
 	nwords = ((wqe->length + extra_bytes) >> 2) + SIZE_OF_CRC;
 	/* header size in dwords LRH+BTH+DETH = (8+12+8)/4. */
-	qp->s_hdrwords = 7;
+	ps->s_txreq->hdr_dwords = 7;
 	if (wqe->wr.opcode == IB_WR_SEND_WITH_IMM)
-		qp->s_hdrwords++;
+		ps->s_txreq->hdr_dwords++;
 
 	if (rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH) {
 		grh = &ps->s_txreq->phdr.hdr.ibh.u.l.grh;
-		qp->s_hdrwords += hfi1_make_grh(ibp, grh,
-						rdma_ah_read_grh(ah_attr),
-						qp->s_hdrwords - 2, nwords);
+		ps->s_txreq->hdr_dwords +=
+			hfi1_make_grh(ibp, grh, rdma_ah_read_grh(ah_attr),
+				      ps->s_txreq->hdr_dwords - 2, nwords);
 		lrh0 = HFI1_LRH_GRH;
 		ohdr = &ps->s_txreq->phdr.hdr.ibh.u.l.oth;
 	} else {

@@ -381,7 +381,7 @@ void hfi1_make_ud_req_9B(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 		}
 	}
 	hfi1_make_bth_deth(qp, wqe, ohdr, &pkey, extra_bytes, false);
-	len = qp->s_hdrwords + nwords;
+	len = ps->s_txreq->hdr_dwords + nwords;
 
 	/* Setup the packet */
 	ps->s_txreq->phdr.hdr.hdr_type = HFI1_PKT_TYPE_9B;

@@ -405,12 +405,12 @@ void hfi1_make_ud_req_16B(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 	ppd = ppd_from_ibp(ibp);
 	ah_attr = &ibah_to_rvtah(wqe->ud_wr.ah)->attr;
 	/* header size in dwords 16B LRH+BTH+DETH = (16+12+8)/4. */
-	qp->s_hdrwords = 9;
+	ps->s_txreq->hdr_dwords = 9;
 	if (wqe->wr.opcode == IB_WR_SEND_WITH_IMM)
-		qp->s_hdrwords++;
+		ps->s_txreq->hdr_dwords++;
 
 	/* SW provides space for CRC and LT for bypass packets. */
-	extra_bytes = hfi1_get_16b_padding((qp->s_hdrwords << 2),
+	extra_bytes = hfi1_get_16b_padding((ps->s_txreq->hdr_dwords << 2),
 					   wqe->length);
 	nwords = ((wqe->length + extra_bytes + SIZE_OF_LT) >> 2) + SIZE_OF_CRC;
 

@@ -428,8 +428,8 @@ void hfi1_make_ud_req_16B(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 			grd->sgid_index = 0;
 		}
 		grh = &ps->s_txreq->phdr.hdr.opah.u.l.grh;
-		qp->s_hdrwords += hfi1_make_grh(ibp, grh, grd,
-					qp->s_hdrwords - 4, nwords);
+		ps->s_txreq->hdr_dwords += hfi1_make_grh(ibp, grh, grd,
+					ps->s_txreq->hdr_dwords - 4, nwords);
 		ohdr = &ps->s_txreq->phdr.hdr.opah.u.l.oth;
 		l4 = OPA_16B_L4_IB_GLOBAL;
 	} else {

@@ -452,7 +452,7 @@ void hfi1_make_ud_req_16B(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 
 	hfi1_make_bth_deth(qp, wqe, ohdr, &pkey, extra_bytes, true);
 	/* Convert dwords to flits */
-	len = (qp->s_hdrwords + nwords) >> 1;
+	len = (ps->s_txreq->hdr_dwords + nwords) >> 1;
 
 	/* Setup the packet */
 	ps->s_txreq->phdr.hdr.hdr_type = HFI1_PKT_TYPE_16B;

@@ -564,8 +564,6 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	priv->s_ahg->ahgcount = 0;
 	priv->s_ahg->ahgidx = 0;
 	priv->s_ahg->tx_flags = 0;
-	/* pbc */
-	ps->s_txreq->hdr_dwords = qp->s_hdrwords + 2;
 
 	return 1;
 

@@ -580,7 +578,6 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 bail_no_tx:
 	ps->s_txreq = NULL;
 	qp->s_flags &= ~RVT_S_BUSY;
-	qp->s_hdrwords = 0;
 	return 0;
 }
 

index b8776a3..471d55c 100644
@@ -835,7 +835,7 @@ static int build_verbs_tx_desc(
 {
 	int ret = 0;
 	struct hfi1_sdma_header *phdr = &tx->phdr;
-	u16 hdrbytes = tx->hdr_dwords << 2;
+	u16 hdrbytes = (tx->hdr_dwords + sizeof(pbc) / 4) << 2;
 	u8 extra_bytes = 0;
 
 	if (tx->phdr.hdr.hdr_type) {

@@ -901,7 +901,7 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 {
 	struct hfi1_qp_priv *priv = qp->priv;
 	struct hfi1_ahg_info *ahg_info = priv->s_ahg;
-	u32 hdrwords = qp->s_hdrwords;
+	u32 hdrwords = ps->s_txreq->hdr_dwords;
 	u32 len = ps->s_txreq->s_cur_size;
 	u32 plen;
 	struct hfi1_ibdev *dev = ps->dev;

@@ -919,7 +919,7 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 	} else {
 		dwords = (len + 3) >> 2;
 	}
-	plen = hdrwords + dwords + 2;
+	plen = hdrwords + dwords + sizeof(pbc) / 4;
 
 	tx = ps->s_txreq;
 	if (!sdma_txreq_built(&tx->txreq)) {

@@ -1038,7 +1038,7 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 			u64 pbc)
 {
 	struct hfi1_qp_priv *priv = qp->priv;
-	u32 hdrwords = qp->s_hdrwords;
+	u32 hdrwords = ps->s_txreq->hdr_dwords;
 	struct rvt_sge_state *ss = ps->s_txreq->ss;
 	u32 len = ps->s_txreq->s_cur_size;
 	u32 dwords;

@@ -1064,7 +1064,7 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 		dwords = (len + 3) >> 2;
 		hdr = (u32 *)&ps->s_txreq->phdr.hdr.ibh;
 	}
-	plen = hdrwords + dwords + 2;
+	plen = hdrwords + dwords + sizeof(pbc) / 4;
 
 	/* only RC/UC use complete */
 	switch (qp->ibqp.qp_type) {

index 87d1285..c2aeb32 100644
@@ -246,17 +246,6 @@ struct hfi1_ibdev {
 }
 
 /*
- * Send if not busy or waiting for I/O and either
- * a RC response is pending or we can process send work requests.
- */
-static inline int hfi1_send_ok(struct rvt_qp *qp)
-{
-	return !(qp->s_flags & (RVT_S_BUSY | RVT_S_ANY_WAIT_IO)) &&
-		(qp->s_hdrwords || (qp->s_flags & RVT_S_RESP_PENDING) ||
-		 !(qp->s_flags & RVT_S_ANY_WAIT_SEND));
-}
-
-/*
  * This must be called with s_lock held.
  */
 void hfi1_bad_pkey(struct hfi1_ibport *ibp, u32 key, u32 sl,

index cec7a4b..729244c 100644
@@ -113,6 +113,13 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
 	return NULL;
 }
 
+static inline bool verbs_txreq_queued(struct rvt_qp *qp)
+{
+	struct hfi1_qp_priv *priv = qp->priv;
+
+	return iowait_packet_queued(&priv->s_iowait);
+}
+
 void hfi1_put_txreq(struct verbs_txreq *tx);
 int verbs_txreq_init(struct hfi1_ibdev *dev);
 void verbs_txreq_exit(struct hfi1_ibdev *dev);

index 524c12f..70aa82b 100644
@@ -2035,7 +2035,6 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 	struct rvt_qp *qp = packet->qp;
 	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct ib_other_headers *ohdr = packet->ohdr;
-	u32 bth0 = be32_to_cpu(ohdr->bth[0]);
 	u32 opcode = packet->opcode;
 	u32 hdrsize = packet->hlen;
 	u32 psn = ib_bth_get_psn(packet->ohdr);

@@ -2233,7 +2232,7 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 		wc.port_num = 0;
 		/* Signal completion event if the solicited bit is set. */
 		rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc,
-			     (bth0 & IB_BTH_SOLICITED) != 0);
+			     ib_bth_is_solicited(ohdr));
 		break;
 
 	case OP(RDMA_WRITE_ONLY):

index fef69d9..8030c38 100644
@@ -478,8 +478,7 @@ void hfi1_uc_rcv(struct hfi1_packet *packet)
 		wc.port_num = 0;
 		/* Signal completion event if the solicited bit is set. */
 		rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc,
-			     (ohdr->bth[0] &
-			      cpu_to_be32(IB_BTH_SOLICITED)) != 0);
+			     ib_bth_is_solicited(ohdr));
 		break;
 
 	case OP(RDMA_WRITE_FIRST):

index 6b5cd3a..cff2fd8 100644
@@ -1045,8 +1045,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 	wc.port_num = qp->port_num;
 	/* Signal completion event if the solicited bit is set. */
 	rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc,
-		     (ohdr->bth[0] &
-		      cpu_to_be32(IB_BTH_SOLICITED)) != 0);
+		     ib_bth_is_solicited(ohdr));
 	return;
 
 drop:

index e4a9ba1..61d3bc6 100644
@@ -1916,8 +1916,7 @@ void qib_rc_rcv(struct qib_ctxtdata *rcd, struct ib_header *hdr,
 		wc.port_num = 0;
 		/* Signal completion event if the solicited bit is set. */
 		rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc,
-			     (ohdr->bth[0] &
-			      cpu_to_be32(IB_BTH_SOLICITED)) != 0);
+			     ib_bth_is_solicited(ohdr));
 		break;
 
 	case OP(RDMA_WRITE_FIRST):

index bddcc37..d311db6 100644
@@ -403,8 +403,7 @@ void qib_uc_rcv(struct qib_ibport *ibp, struct ib_header *hdr,
 		wc.port_num = 0;
 		/* Signal completion event if the solicited bit is set. */
 		rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc,
-			     (ohdr->bth[0] &
-				cpu_to_be32(IB_BTH_SOLICITED)) != 0);
+			     ib_bth_is_solicited(ohdr));
 		break;
 
 	case OP(RDMA_WRITE_FIRST):

index 15962ed..59a4f03 100644
@@ -581,8 +581,7 @@ void qib_ud_rcv(struct qib_ibport *ibp, struct ib_header *hdr,
 	wc.port_num = qp->port_num;
 	/* Signal completion event if the solicited bit is set. */
 	rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc,
-		     (ohdr->bth[0] &
-			cpu_to_be32(IB_BTH_SOLICITED)) != 0);
+		     ib_bth_is_solicited(ohdr));
 	return;
 
 drop:

index c124d51..6a86d14 100644
@@ -331,4 +331,8 @@ static inline u8 ib_bth_get_tver(struct ib_other_headers *ohdr)
 		    IB_BTH_TVER_MASK);
 }
 
+static inline bool ib_bth_is_solicited(struct ib_other_headers *ohdr)
+{
+	return !!(ohdr->bth[0] & cpu_to_be32(IB_BTH_SOLICITED));
+}
 #endif                          /* IB_HDRS_H */

index 067b29f..bb1a41b 100644
@@ -1440,6 +1440,8 @@ static int hfi1_setup_9B_packet(struct hfi1_packet *packet)
 	packet->extra_byte = 0;
 	packet->fecn = ib_bth_get_fecn(packet->ohdr);
 	packet->becn = ib_bth_get_becn(packet->ohdr);
+	packet->pkey = ib_bth_get_pkey(packet->ohdr);
+	packet->migrated = ib_bth_is_migration(packet->ohdr);
 
 	return 0;
 drop:

@@ -1506,6 +1508,8 @@ static int hfi1_setup_bypass_packet(struct hfi1_packet *packet)
 	packet->extra_byte = SIZE_OF_LT;
 	packet->fecn = hfi1_16B_get_fecn(packet->hdr);
 	packet->becn = hfi1_16B_get_becn(packet->hdr);
+	packet->pkey = hfi1_16B_get_pkey(packet->hdr);
+	packet->migrated = opa_bth_is_migration(packet->ohdr);
 
 	if (hfi1_bypass_ingress_pkt_check(packet))
 		goto drop;

index 5757d0e..2c257ac 100644
@@ -341,6 +341,7 @@ struct hfi1_packet {
 	u32 slid;
 	u16 tlen;
 	s16 etail;
+	u16 pkey;
 	u8 hlen;
 	u8 numpkt;
 	u8 rsize;

@@ -353,6 +354,7 @@ struct hfi1_packet {
 	u8 opcode;
 	bool becn;
 	bool fecn;
+	bool migrated;
 };
 
 /* Packet types */

index 0cced9a..6434207 100644
@@ -225,19 +225,8 @@ int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct hfi1_packet *packet)
 	u32 dlid = packet->dlid;
 	u32 slid = packet->slid;
 	u32 sl = packet->sl;
-	int migrated;
-	u32 bth0, bth1;
-	u16 pkey;
-
-	bth0 = be32_to_cpu(packet->ohdr->bth[0]);
-	bth1 = be32_to_cpu(packet->ohdr->bth[1]);
-	if (packet->etype == RHF_RCV_TYPE_BYPASS) {
-		pkey = hfi1_16B_get_pkey(packet->hdr);
-		migrated = bth1 & OPA_BTH_MIG_REQ;
-	} else {
-		pkey = ib_bth_get_pkey(packet->ohdr);
-		migrated = bth0 & IB_BTH_MIG_REQ;
-	}
+	bool migrated = packet->migrated;
+	u16 pkey = packet->pkey;
 
 	if (qp->s_mig_state == IB_MIG_ARMED && migrated) {
 		if (!packet->grh) {

index c2aeb32..958f0c9 100644
@@ -405,6 +405,11 @@ static inline void cacheless_memcpy(void *dst, void *src, size_t n)
 	__copy_user_nocache(dst, (void __user *)src, n, 0);
 }
 
+static inline bool opa_bth_is_migration(struct ib_other_headers *ohdr)
+{
+	return !!(ohdr->bth[1] & cpu_to_be32(OPA_BTH_MIG_REQ));
+}
+
 extern const enum ib_wc_opcode ib_hfi1_wc_opcode[];
 
 extern const u8 hdr_len_by_opcode[];

index 6a86d14..2aa19ec 100644
@@ -335,4 +335,9 @@ static inline bool ib_bth_is_solicited(struct ib_other_headers *ohdr)
 {
 	return !!(ohdr->bth[0] & cpu_to_be32(IB_BTH_SOLICITED));
 }
+
+static inline bool ib_bth_is_migration(struct ib_other_headers *ohdr)
+{
+	return !!(ohdr->bth[0] & cpu_to_be32(IB_BTH_MIG_REQ));
+}
 #endif                          /* IB_HDRS_H */

index bb1a41b..0de4654 100644
@@ -634,9 +634,10 @@ static void __prescan_rxq(struct hfi1_packet *packet)
 	}
 }
 
-static void process_rcv_qp_work(struct hfi1_ctxtdata *rcd)
+static void process_rcv_qp_work(struct hfi1_packet *packet)
 {
 	struct rvt_qp *qp, *nqp;
+	struct hfi1_ctxtdata *rcd = packet->rcd;
 
 	/*
 	 * Iterate over all QPs waiting to respond.

@@ -646,7 +647,8 @@ static void process_rcv_qp_work(struct hfi1_ctxtdata *rcd)
 		list_del_init(&qp->rspwait);
 		if (qp->r_flags & RVT_R_RSP_NAK) {
 			qp->r_flags &= ~RVT_R_RSP_NAK;
-			hfi1_send_rc_ack(rcd, qp, 0);
+			packet->qp = qp;
+			hfi1_send_rc_ack(packet, 0);
 		}
 		if (qp->r_flags & RVT_R_RSP_SEND) {
 			unsigned long flags;

@@ -667,7 +669,7 @@ static noinline int max_packet_exceeded(struct hfi1_packet *packet, int thread)
 	if (thread) {
 		if ((packet->numpkt & (MAX_PKT_RECV_THREAD - 1)) == 0)
 			/* allow defered processing */
-			process_rcv_qp_work(packet->rcd);
+			process_rcv_qp_work(packet);
 		cond_resched();
 		return RCV_PKT_OK;
 	} else {

@@ -809,7 +811,7 @@ int handle_receive_interrupt_nodma_rtail(struct hfi1_ctxtdata *rcd, int thread)
 			last = RCV_PKT_DONE;
 		process_rcv_update(last, &packet);
 	}
-	process_rcv_qp_work(rcd);
+	process_rcv_qp_work(&packet);
 	rcd->head = packet.rhqoff;
 bail:
 	finish_packet(&packet);

@@ -838,7 +840,7 @@ int handle_receive_interrupt_dma_rtail(struct hfi1_ctxtdata *rcd, int thread)
 			last = RCV_PKT_DONE;
 		process_rcv_update(last, &packet);
 	}
-	process_rcv_qp_work(rcd);
+	process_rcv_qp_work(&packet);
 	rcd->head = packet.rhqoff;
 bail:
 	finish_packet(&packet);

@@ -1068,7 +1070,7 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread)
 		process_rcv_update(last, &packet);
 	}
 
-	process_rcv_qp_work(rcd);
+	process_rcv_qp_work(&packet);
 	rcd->head = packet.rhqoff;
 
 bail:

index 70aa82b..daf50cc 100644
@@ -730,14 +730,16 @@ static inline void hfi1_make_bth_aeth(struct rvt_qp *qp,
 	ohdr->bth[2] = cpu_to_be32(mask_psn(qp->r_ack_psn));
 }
 
-static inline void hfi1_queue_rc_ack(struct rvt_qp *qp, bool is_fecn)
+static inline void hfi1_queue_rc_ack(struct hfi1_packet *packet, bool is_fecn)
 {
-	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct rvt_qp *qp = packet->qp;
+	struct hfi1_ibport *ibp;
 	unsigned long flags;
 
 	spin_lock_irqsave(&qp->s_lock, flags);
 	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK))
 		goto unlock;
+	ibp = rcd_to_iport(packet->rcd);
 	this_cpu_inc(*ibp->rvp.rc_qacks);
 	qp->s_flags |= RVT_S_ACK_PENDING | RVT_S_RESP_PENDING;
 	qp->s_nak_state = qp->r_nak_state;

@@ -751,13 +753,14 @@ static inline void hfi1_queue_rc_ack(struct rvt_qp *qp, bool is_fecn)
 	spin_unlock_irqrestore(&qp->s_lock, flags);
 }
 
-static inline void hfi1_make_rc_ack_9B(struct rvt_qp *qp,
+static inline void hfi1_make_rc_ack_9B(struct hfi1_packet *packet,
 				       struct hfi1_opa_header *opa_hdr,
 				       u8 sc5, bool is_fecn,
 				       u64 *pbc_flags, u32 *hwords,
 				       u32 *nwords)
 {
-	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct rvt_qp *qp = packet->qp;
+	struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd);
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	struct ib_header *hdr = &opa_hdr->ibh;
 	struct ib_other_headers *ohdr;

@@ -798,13 +801,14 @@ static inline void hfi1_make_rc_ack_9B(struct rvt_qp *qp,
 	hfi1_make_bth_aeth(qp, ohdr, bth0, bth1);
 }
 
-static inline void hfi1_make_rc_ack_16B(struct rvt_qp *qp,
+static inline void hfi1_make_rc_ack_16B(struct hfi1_packet *packet,
 					struct hfi1_opa_header *opa_hdr,
 					u8 sc5, bool is_fecn,
 					u64 *pbc_flags, u32 *hwords,
 					u32 *nwords)
 {
-	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct rvt_qp *qp = packet->qp;
+	struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd);
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	struct hfi1_16b_header *hdr = &opa_hdr->opah;
 	struct ib_other_headers *ohdr;

@@ -850,7 +854,7 @@ static inline void hfi1_make_rc_ack_16B(struct rvt_qp *qp,
 	hfi1_make_bth_aeth(qp, ohdr, bth0, bth1);
 }
 
-typedef void (*hfi1_make_rc_ack)(struct rvt_qp *qp,
+typedef void (*hfi1_make_rc_ack)(struct hfi1_packet *packet,
 				 struct hfi1_opa_header *opa_hdr,
 				 u8 sc5, bool is_fecn,
 				 u64 *pbc_flags, u32 *hwords,

@@ -870,9 +874,10 @@ typedef void (*hfi1_make_rc_ack)(struct rvt_qp *qp,
  * Note that RDMA reads and atomics are handled in the
  * send side QP state and send engine.
  */
-void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd,
-		      struct rvt_qp *qp, bool is_fecn)
+void hfi1_send_rc_ack(struct hfi1_packet *packet, bool is_fecn)
 {
+	struct hfi1_ctxtdata *rcd = packet->rcd;
+	struct rvt_qp *qp = packet->qp;
 	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct hfi1_qp_priv *priv = qp->priv;
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);

@@ -889,14 +894,14 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd,
 
 	/* Don't send ACK or NAK if a RDMA read or atomic is pending. */
 	if (qp->s_flags & RVT_S_RESP_PENDING) {
-		hfi1_queue_rc_ack(qp, is_fecn);
+		hfi1_queue_rc_ack(packet, is_fecn);
 		return;
 	}
 
 	/* Ensure s_rdma_ack_cnt changes are committed */
 	smp_read_barrier_depends();
 	if (qp->s_rdma_ack_cnt) {
-		hfi1_queue_rc_ack(qp, is_fecn);
+		hfi1_queue_rc_ack(packet, is_fecn);
 		return;
 	}
 

@@ -905,7 +910,7 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd,
 		return;
 
 	/* Make the appropriate header */
-	hfi1_make_rc_ack_tbl[priv->hdr_type](qp, &opa_hdr, sc5, is_fecn,
+	hfi1_make_rc_ack_tbl[priv->hdr_type](packet, &opa_hdr, sc5, is_fecn,
 					     &pbc_flags, &hwords, &nwords);
 
 	plen = 2 /* PBC */ + hwords + nwords;

@@ -919,7 +924,7 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd,
 		 * so that when enough buffer space becomes available,
 		 * the ACK is sent ahead of other outgoing packets.
 		 */
-		hfi1_queue_rc_ack(qp, is_fecn);
+		hfi1_queue_rc_ack(packet, is_fecn);
 		return;
 	}
 	trace_ack_output_ibhdr(dd_from_ibdev(qp->ibqp.device),

@@ -1537,7 +1542,7 @@ static void rc_rcv_resp(struct hfi1_packet *packet)
 	void *data = packet->payload;
 	u32 tlen = packet->tlen;
 	struct rvt_qp *qp = packet->qp;
-	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct hfi1_ibport *ibp;
 	struct ib_other_headers *ohdr = packet->ohdr;
 	struct rvt_swqe *wqe;
 	enum ib_wc_status status;

@@ -1695,6 +1700,7 @@ static void rc_rcv_resp(struct hfi1_packet *packet)
 	goto ack_err;
 
 ack_seq_err:
+	ibp = rcd_to_iport(rcd);
 	rdma_seq_err(qp, ibp, psn, rcd);
 	goto ack_done;
 

@@ -2476,7 +2482,7 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 	qp->r_nak_state = IB_NAK_REMOTE_ACCESS_ERROR;
 	qp->r_ack_psn = qp->r_psn;
 send_ack:
-	hfi1_send_rc_ack(rcd, qp, is_fecn);
+	hfi1_send_rc_ack(packet, is_fecn);
 }
 
 void hfi1_rc_hdrerr(

index 958f0c9..6fb11aa 100644
@@ -358,8 +358,7 @@ void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
 void hfi1_send_complete(struct rvt_qp *qp, struct rvt_swqe *wqe,
 			enum ib_wc_status status);
 
-void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
-		      bool is_fecn);
+void hfi1_send_rc_ack(struct hfi1_packet *packet, bool is_fecn);
 
 int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps);
 

index 0de4654..0a9bc18 100644
@@ -1440,8 +1440,6 @@ static int hfi1_setup_9B_packet(struct hfi1_packet *packet)
 	packet->sc = hfi1_9B_get_sc5(hdr, packet->rhf);
 	packet->pad = ib_bth_get_pad(packet->ohdr);
 	packet->extra_byte = 0;
-	packet->fecn = ib_bth_get_fecn(packet->ohdr);
-	packet->becn = ib_bth_get_becn(packet->ohdr);
 	packet->pkey = ib_bth_get_pkey(packet->ohdr);
 	packet->migrated = ib_bth_is_migration(packet->ohdr);
 

@@ -1508,8 +1506,6 @@ static int hfi1_setup_bypass_packet(struct hfi1_packet *packet)
 	packet->sl = ibp->sc_to_sl[packet->sc];
 	packet->pad = hfi1_16B_bth_get_pad(packet->ohdr);
 	packet->extra_byte = SIZE_OF_LT;
-	packet->fecn = hfi1_16B_get_fecn(packet->hdr);
-	packet->becn = hfi1_16B_get_becn(packet->hdr);
 	packet->pkey = hfi1_16B_get_pkey(packet->hdr);
 	packet->migrated = opa_bth_is_migration(packet->ohdr);
 

index 2c257ac..105d11d 100644
@@ -352,8 +352,6 @@ struct hfi1_packet {
 	u8 sc;
 	u8 sl;
 	u8 opcode;
-	bool becn;
-	bool fecn;
 	bool migrated;
 };
 

@@ -1781,19 +1779,15 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 static inline bool process_ecn(struct rvt_qp *qp, struct hfi1_packet *pkt,
 			       bool do_cnp)
 {
-	struct ib_other_headers *ohdr = pkt->ohdr;
-
-	u32 bth1;
-	bool becn = false;
-	bool fecn = false;
+	bool becn;
+	bool fecn;
 
 	if (pkt->etype == RHF_RCV_TYPE_BYPASS) {
 		fecn = hfi1_16B_get_fecn(pkt->hdr);
 		becn = hfi1_16B_get_becn(pkt->hdr);
 	} else {
-		bth1 = be32_to_cpu(ohdr->bth[1]);
-		fecn = bth1 & IB_FECN_SMASK;
-		becn = bth1 & IB_BECN_SMASK;
+		fecn = ib_bth_get_fecn(pkt->ohdr);
+		becn = ib_bth_get_becn(pkt->ohdr);
 	}
 	if (unlikely(fecn || becn)) {
 		hfi1_process_ecn_slowpath(qp, pkt, do_cnp);

@@ -2419,7 +2413,7 @@ static inline void hfi1_make_ib_hdr(struct ib_header *hdr,
 static inline void hfi1_make_16b_hdr(struct hfi1_16b_header *hdr,
 				     u32 slid, u32 dlid,
 				     u16 len, u16 pkey,
-				     u8 becn, u8 fecn, u8 l4,
+				     bool becn, bool fecn, u8 l4,
 				     u8 sc)
 {
 	u32 lrh0 = 0;

index daf50cc..93ea03c 100644
@@ -814,7 +814,7 @@ static inline void hfi1_make_rc_ack_16B(struct hfi1_packet *packet,
 	struct ib_other_headers *ohdr;
 	u32 bth0, bth1 = 0;
 	u16 len, pkey;
-	u8 becn = !!is_fecn;
+	bool becn = is_fecn;
 	u8 l4 = OPA_16B_L4_IB_LOCAL;
 	u8 extra_bytes;
 

index 6434207..4252722 100644
@@ -751,7 +751,7 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 				ps->s_txreq->s_cur_size);
 	u32 nwords = SIZE_OF_CRC + ((ps->s_txreq->s_cur_size +
 				 extra_bytes + SIZE_OF_LT) >> 2);
-	u8 becn = 0;
+	bool becn = false;
 
 	if (unlikely(rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH) &&
 	    hfi1_check_mcast(rdma_ah_get_dlid(&qp->remote_ah_attr))) {

@@ -789,7 +789,7 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 	if (qp->s_flags & RVT_S_ECN) {
 		qp->s_flags &= ~RVT_S_ECN;
 		/* we recently received a FECN, so return a BECN */
-		becn = 1;
+		becn = true;
 	}
 	hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
 

index 959a804..89bd985 100644
@@ -138,7 +138,7 @@ u8 hfi1_trace_opa_hdr_len(struct hfi1_opa_header *opa_hdr)
 }
 
 void hfi1_trace_parse_9b_bth(struct ib_other_headers *ohdr,
-			     u8 *ack, u8 *becn, u8 *fecn, u8 *mig,
+			     u8 *ack, bool *becn, bool *fecn, u8 *mig,
 			     u8 *se, u8 *pad, u8 *opcode, u8 *tver,
 			     u16 *pkey, u32 *psn, u32 *qpn)
 {

@@ -184,7 +184,7 @@ void hfi1_trace_parse_9b_hdr(struct ib_header *hdr, bool sc5,
 }
 
 void hfi1_trace_parse_16b_hdr(struct hfi1_16b_header *hdr,
-			      u8 *age, u8 *becn, u8 *fecn,
+			      u8 *age, bool *becn, bool *fecn,
 			      u8 *l4, u8 *rc, u8 *sc,
 			      u16 *entropy, u16 *len, u16 *pkey,
 			      u32 *dlid, u32 *slid)

@@ -207,7 +207,7 @@ void hfi1_trace_parse_16b_hdr(struct hfi1_16b_header *hdr,
 #define LRH_16B_PRN "age:%d becn:%d fecn:%d l4:%d " \
 		    "rc:%d sc:%d pkey:0x%.4x entropy:0x%.4x"
 const char *hfi1_trace_fmt_lrh(struct trace_seq *p, bool bypass,
-			       u8 age, u8 becn, u8 fecn, u8 l4,
+			       u8 age, bool becn, bool fecn, u8 l4,
 			       u8 lnh, const char *lnh_name, u8 lver,
 			       u8 rc, u8 sc, u8 sl, u16 entropy,
 			       u16 len, u16 pkey, u32 dlid, u32 slid)

@@ -235,7 +235,7 @@ void hfi1_trace_parse_16b_hdr(struct hfi1_16b_header *hdr,
 	"op:0x%.2x,%s se:%d m:%d pad:%d tver:%d " \
 	"qpn:0x%.6x a:%d psn:0x%.8x"
 const char *hfi1_trace_fmt_bth(struct trace_seq *p, bool bypass,
-			       u8 ack, u8 becn, u8 fecn, u8 mig,
+			       u8 ack, bool becn, bool fecn, u8 mig,
 			       u8 se, u8 pad, u8 opcode, const char *opname,
 			       u8 tver, u16 pkey, u32 psn, u32 qpn)
 {

index fb63127..2847626 100644
@@ -101,7 +101,7 @@
 u8 hfi1_trace_packet_hdr_len(struct hfi1_packet *packet);
 const char *hfi1_trace_get_packet_l4_str(u8 l4);
 void hfi1_trace_parse_9b_bth(struct ib_other_headers *ohdr,
-			     u8 *ack, u8 *becn, u8 *fecn, u8 *mig,
+			     u8 *ack, bool *becn, bool *fecn, u8 *mig,
 			     u8 *se, u8 *pad, u8 *opcode, u8 *tver,
 			     u16 *pkey, u32 *psn, u32 *qpn);
 void hfi1_trace_parse_9b_hdr(struct ib_header *hdr, bool sc5,

@@ -112,19 +112,19 @@ void hfi1_trace_parse_16b_bth(struct ib_other_headers *ohdr,
 			      u8 *pad, u8 *se, u8 *tver,
 			      u32 *psn, u32 *qpn);
 void hfi1_trace_parse_16b_hdr(struct hfi1_16b_header *hdr,
-			      u8 *age, u8 *becn, u8 *fecn,
+			      u8 *age, bool *becn, bool *fecn,
 			      u8 *l4, u8 *rc, u8 *sc,
 			      u16 *entropy, u16 *len, u16 *pkey,
 			      u32 *dlid, u32 *slid);
 
 const char *hfi1_trace_fmt_lrh(struct trace_seq *p, bool bypass,
-			       u8 age, u8 becn, u8 fecn, u8 l4,
+			       u8 age, bool becn, bool fecn, u8 l4,
 			       u8 lnh, const char *lnh_name, u8 lver,
 			       u8 rc, u8 sc, u8 sl, u16 entropy,
 			       u16 len, u16 pkey, u32 dlid, u32 slid);
 
 const char *hfi1_trace_fmt_bth(struct trace_seq *p, bool bypass,
-			       u8 ack, u8 becn, u8 fecn, u8 mig,
+			       u8 ack, bool becn, bool fecn, u8 mig,
 			       u8 se, u8 pad, u8 opcode, const char *opname,
 			       u8 tver, u16 pkey, u32 psn, u32 qpn);
 

@@ -148,8 +148,8 @@ void hfi1_trace_parse_16b_hdr(struct hfi1_16b_header *hdr,
 			__field(u8, etype)
 			__field(u8, ack)
 			__field(u8, age)
-			__field(u8, becn)
-			__field(u8, fecn)
+			__field(bool, becn)
+			__field(bool, fecn)
 			__field(u8, l2)
 			__field(u8, l4)
 			__field(u8, lnh)

@@ -290,8 +290,8 @@ void hfi1_trace_parse_16b_hdr(struct hfi1_16b_header *hdr,
 			__field(u8, hdr_type)
 			__field(u8, ack)
 			__field(u8, age)
-			__field(u8, becn)
-			__field(u8, fecn)
+			__field(bool, becn)
+			__field(bool, fecn)
 			__field(u8, l4)
 			__field(u8, lnh)
 			__field(u8, lver)

index 2aa19ec..710c8be 100644
@@ -313,16 +313,14 @@ static inline u32 ib_bth_get_qpn(struct ib_other_headers *ohdr)
 	return (u32)((be32_to_cpu(ohdr->bth[1])) & IB_QPN_MASK);
 }
 
-static inline u8 ib_bth_get_becn(struct ib_other_headers *ohdr)
+static inline bool ib_bth_get_becn(struct ib_other_headers *ohdr)
 {
-	return (u8)((be32_to_cpu(ohdr->bth[1]) >> IB_BECN_SHIFT) &
-		     IB_BECN_MASK);
+	return !!((ohdr->bth[1]) & cpu_to_be32(IB_BECN_SMASK));
 }
 
-static inline u8 ib_bth_get_fecn(struct ib_other_headers *ohdr)
+static inline bool ib_bth_get_fecn(struct ib_other_headers *ohdr)
 {
-	return (u8)((be32_to_cpu(ohdr->bth[1]) >> IB_FECN_SHIFT) &
-		    IB_FECN_MASK);
+	return !!((ohdr->bth[1]) & cpu_to_be32(IB_FECN_SMASK));
 }
 
 static inline u8 ib_bth_get_tver(struct ib_other_headers *ohdr)

index 0a9bc18..98703f1 100644
@@ -256,7 +256,12 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd,
 	u32 mlid_base;
 	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct hfi1_devdata *dd = ppd->dd;
-	struct rvt_dev_info *rdi = &dd->verbs_dev.rdi;
+	struct hfi1_ibdev *verbs_dev = &dd->verbs_dev;
+	struct rvt_dev_info *rdi = &verbs_dev->rdi;
+
+	if ((packet->rhf & RHF_DC_ERR) &&
+	    hfi1_dbg_fault_suppress_err(verbs_dev))
+		return;
 
 	if (packet->rhf & (RHF_VCRC_ERR | RHF_ICRC_ERR))
 		return;

@@ -1552,19 +1557,7 @@ int process_receive_ib(struct hfi1_packet *packet)
 	if (hfi1_setup_9B_packet(packet))
 		return RHF_RCV_CONTINUE;
 
-	trace_hfi1_rcvhdr(packet->rcd->ppd->dd,
-			  packet->rcd->ctxt,
-			  rhf_err_flags(packet->rhf),
-			  RHF_RCV_TYPE_IB,
-			  packet->hlen,
-			  packet->tlen,
-			  packet->updegr,
-			  rhf_egr_index(packet->rhf));
-
-	if (unlikely(
-		 (hfi1_dbg_fault_suppress_err(&packet->rcd->dd->verbs_dev) &&
-		 (packet->rhf & RHF_DC_ERR))))
-		return RHF_RCV_CONTINUE;
+	trace_hfi1_rcvhdr(packet, RHF_RCV_TYPE_IB);
 
 	if (unlikely(rhf_err_flags(packet->rhf))) {
 		handle_eflags(packet);

index 4d487fe..f768415 100644
@@ -63,17 +63,9 @@
 #define TRACE_SYSTEM hfi1_rx
 
 TRACE_EVENT(hfi1_rcvhdr,
-	    TP_PROTO(struct hfi1_devdata *dd,
-		     u32 ctxt,
-		     u64 eflags,
-		     u32 etype,
-		     u32 hlen,
-		     u32 tlen,
-		     u32 updegr,
-		     u32 etail
-		    ),
-	    TP_ARGS(dd, ctxt, eflags, etype, hlen, tlen, updegr, etail),
-	    TP_STRUCT__entry(DD_DEV_ENTRY(dd)
+	    TP_PROTO(struct hfi1_packet *packet, u32 etype),
+	    TP_ARGS(packet, etype),
+	    TP_STRUCT__entry(DD_DEV_ENTRY(packet->rcd->dd)
 			     __field(u64, eflags)
 			     __field(u32, ctxt)
 			     __field(u32, etype)

@@ -82,14 +74,14 @@
 			     __field(u32, updegr)
 			     __field(u32, etail)
 			     ),
-	     TP_fast_assign(DD_DEV_ASSIGN(dd);
-			    __entry->eflags = eflags;
-			    __entry->ctxt = ctxt;
+	     TP_fast_assign(DD_DEV_ASSIGN(packet->rcd->dd);
+			    __entry->eflags = rhf_err_flags(packet->rhf);
+			    __entry->ctxt = packet->rcd->ctxt;
 			    __entry->etype = etype;
-			    __entry->hlen = hlen;
-			    __entry->tlen = tlen;
-			    __entry->updegr = updegr;
-			    __entry->etail = etail;
+			    __entry->hlen = packet->hlen;
+			    __entry->tlen = packet->tlen;
+			    __entry->updegr = packet->updegr;
+			    __entry->etail = rhf_egr_index(packet->rhf);
 			    ),
 	     TP_printk(
 		"[%s] ctxt %d eflags 0x%llx etype %d,%s hlen %d tlen %d updegr %d etail %d",