diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 6db2276f5c13..ddfcf2fe40ca 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -73,6 +73,7 @@
 
 #include "chip_registers.h"
 #include "common.h"
+#include "opfn.h"
 #include "verbs.h"
 #include "pio.h"
 #include "chip.h"
diff --git a/drivers/infiniband/hw/hfi1/opfn.h b/drivers/infiniband/hw/hfi1/opfn.h
new file mode 100644
index 000000000000..1a2b3449df67
--- /dev/null
+++ b/drivers/infiniband/hw/hfi1/opfn.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
+/*
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ */
+#ifndef _HFI1_OPFN_H
+#define _HFI1_OPFN_H
+
+/**
+ * DOC: Omni Path Feature Negotion (OPFN)
+ *
+ * OPFN is a discovery protocol for Intel Omni-Path fabric that
+ * allows two RC QPs to negotiate a common feature that both QPs
+ * can support. Currently, the only OPA feature that OPFN
+ * supports is TID RDMA.
+ *
+ * Architecture
+ *
+ * OPFN involves the communication between two QPs on the HFI
+ * level on an Omni-Path fabric, and ULPs have no knowledge of
+ * OPFN at all.
+ *
+ * Implementation
+ *
+ * OPFN extends the existing IB RC protocol with the following
+ * changes:
+ * -- Uses Bit 24 (reserved) of DWORD 1 of Base Transport
+ *    Header (BTH1) to indicate that the RC QP supports OPFN;
+ * -- Uses a combination of RC COMPARE_SWAP opcode (0x13) and
+ *    the address U64_MAX (0xFFFFFFFFFFFFFFFF) as an OPFN
+ *    request; The 64-bit data carried with the request/response
+ *    contains the parameters for negotiation and will be
+ *    defined in tid_rdma.c file;
+ * -- Defines IB_WR_RESERVED3 as IB_WR_OPFN.
+ *
+ * The OPFN communication will be triggered when an RC QP
+ * receives a request with Bit 24 of BTH1 set. The responder QP
+ * will then post send an OPFN request with its local
+ * parameters, which will be sent to the requester QP once all
+ * existing requests on the responder QP side have been sent.
+ * Once the requester QP receives the OPFN request, it will
+ * keep a copy of the responder QP's parameters, and return a
+ * response packet with its own local parameters. The responder
+ * QP receives the response packet and keeps a copy of the requester
+ * QP's parameters. After this exchange, each side has the parameters
+ * for both sides and therefore can select the right parameters
+ * for future transactions
+ */
+
+/* STL Verbs Extended */
+#define IB_BTHE_E_SHIFT           24
+
+#endif /* _HFI1_OPFN_H */
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index be603f35d7e4..940e9236c328 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -89,8 +89,8 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp,
 	struct rvt_ack_entry *e;
 	u32 hwords;
 	u32 len;
-	u32 bth0;
-	u32 bth2;
+	u32 bth0, bth2;
+	u32 bth1 = qp->remote_qpn | (HFI1_CAP_IS_KSET(OPFN) << IB_BTHE_E_SHIFT);
 	int middle = 0;
 	u32 pmtu = qp->pmtu;
 	struct hfi1_qp_priv *priv = qp->priv;
@@ -229,7 +229,7 @@ normal:
 	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);
+	hfi1_make_ruc_header(qp, ohdr, bth0, bth1, bth2, middle, ps);
 	return 1;
 
 bail:
@@ -262,8 +262,8 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	struct rvt_swqe *wqe;
 	u32 hwords;
 	u32 len;
-	u32 bth0 = 0;
-	u32 bth2;
+	u32 bth0 = 0, bth2;
+	u32 bth1 = qp->remote_qpn | (HFI1_CAP_IS_KSET(OPFN) << IB_BTHE_E_SHIFT);
 	u32 pmtu = qp->pmtu;
 	char newreq;
 	int middle = 0;
@@ -693,6 +693,7 @@ no_flow_control:
 		qp,
 		ohdr,
 		bth0 | (qp->s_state << 24),
+		bth1,
 		bth2,
 		middle,
 		ps);
@@ -796,6 +797,11 @@ static inline void hfi1_make_rc_ack_9B(struct hfi1_packet *packet,
 	if (qp->s_mig_state == IB_MIG_MIGRATED)
 		bth0 |= IB_BTH_MIG_REQ;
 	bth1 = (!!is_fecn) << IB_BECN_SHIFT;
+	/*
+	 * Inline ACKs go out without the use of the Verbs send engine, so
+	 * we need to set the STL Verbs Extended bit here
+	 */
+	bth1 |= HFI1_CAP_IS_KSET(OPFN) << IB_BTHE_E_SHIFT;
 	hfi1_make_bth_aeth(qp, ohdr, bth0, bth1);
 }
 
diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c
index 7fb317c711df..f96c0f544cb0 100644
--- a/drivers/infiniband/hw/hfi1/ruc.c
+++ b/drivers/infiniband/hw/hfi1/ruc.c
@@ -250,7 +250,6 @@ static inline void hfi1_make_ruc_bth(struct rvt_qp *qp,
 				     struct ib_other_headers *ohdr,
 				     u32 bth0, u32 bth1, u32 bth2)
 {
-	bth1 |= qp->remote_qpn;
 	ohdr->bth[0] = cpu_to_be32(bth0);
 	ohdr->bth[1] = cpu_to_be32(bth1);
 	ohdr->bth[2] = cpu_to_be32(bth2);
@@ -272,13 +271,13 @@ static inline void hfi1_make_ruc_bth(struct rvt_qp *qp,
  */
 static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 					    struct ib_other_headers *ohdr,
-					    u32 bth0, u32 bth2, int middle,
+					    u32 bth0, u32 bth1, u32 bth2,
+					    int middle,
 					    struct hfi1_pkt_state *ps)
 {
 	struct hfi1_qp_priv *priv = qp->priv;
 	struct hfi1_ibport *ibp = ps->ibp;
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
-	u32 bth1 = 0;
 	u32 slid;
 	u16 pkey = hfi1_get_pkey(ibp, qp->s_pkey_index);
 	u8 l4 = OPA_16B_L4_IB_LOCAL;
@@ -360,12 +359,12 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
  */
 static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
 					   struct ib_other_headers *ohdr,
-					   u32 bth0, u32 bth2, int middle,
+					   u32 bth0, u32 bth1, u32 bth2,
+					   int middle,
 					   struct hfi1_pkt_state *ps)
 {
 	struct hfi1_qp_priv *priv = qp->priv;
 	struct hfi1_ibport *ibp = ps->ibp;
-	u32 bth1 = 0;
 	u16 pkey = hfi1_get_pkey(ibp, qp->s_pkey_index);
 	u16 lrh0 = HFI1_LRH_BTH;
 	u8 extra_bytes = -ps->s_txreq->s_cur_size & 3;
@@ -415,7 +414,7 @@ static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
 
 typedef void (*hfi1_make_ruc_hdr)(struct rvt_qp *qp,
 				  struct ib_other_headers *ohdr,
-				  u32 bth0, u32 bth2, int middle,
+				  u32 bth0, u32 bth1, u32 bth2, int middle,
 				  struct hfi1_pkt_state *ps);
 
 /* We support only two types - 9B and 16B for now */
@@ -425,7 +424,7 @@ static const hfi1_make_ruc_hdr hfi1_ruc_header_tbl[2] = {
 };
 
 void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
-			  u32 bth0, u32 bth2, int middle,
+			  u32 bth0, u32 bth1, u32 bth2, int middle,
 			  struct hfi1_pkt_state *ps)
 {
 	struct hfi1_qp_priv *priv = qp->priv;
@@ -446,7 +445,8 @@ void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
 	priv->s_ahg->ahgidx = 0;
 
 	/* Make the appropriate header */
-	hfi1_ruc_header_tbl[priv->hdr_type](qp, ohdr, bth0, bth2, middle, ps);
+	hfi1_ruc_header_tbl[priv->hdr_type](qp, ohdr, bth0, bth1, bth2, middle,
+					    ps);
 }
 
 /* when sending, force a reschedule every one of these periods */
diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c
index 6ba47037c424..4ed4fcfabd6c 100644
--- a/drivers/infiniband/hw/hfi1/uc.c
+++ b/drivers/infiniband/hw/hfi1/uc.c
@@ -271,7 +271,8 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	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);
+			     qp->remote_qpn, mask_psn(qp->s_psn++),
+			     middle, ps);
 	return 1;
 
 done_free_tx:
diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h
index 1ad0b14bdb3c..8834119184b3 100644
--- a/drivers/infiniband/hw/hfi1/verbs.h
+++ b/drivers/infiniband/hw/hfi1/verbs.h
@@ -72,6 +72,7 @@ struct hfi1_packet;
 
 #include "iowait.h"
 #include "tid_rdma.h"
+#include "opfn.h"
 
 #define HFI1_MAX_RDMA_ATOMIC     16
 
@@ -356,7 +357,7 @@ u32 hfi1_make_grh(struct hfi1_ibport *ibp, struct ib_grh *hdr,
 		  const struct ib_global_route *grh, u32 hwords, u32 nwords);
 
 void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
-			  u32 bth0, u32 bth2, int middle,
+			  u32 bth0, u32 bth1, u32 bth2, int middle,
 			  struct hfi1_pkt_state *ps);
 
 void _hfi1_do_send(struct work_struct *work);