IB/{hfi1, qib, rdmavt}: Move logic to allocate receive WQE into rdmavt

Moving receive-side WQE allocation logic into rdmavt will allow
further code reuse between qib and hfi1 drivers.

Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Brian Welty <brian.welty@intel.com>
Signed-off-by: Harish Chegondi <harish.chegondi@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

12 files changed, 170 insertions, 324 deletions

diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index da58046a02ea..79ee2b9e28c6 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -2123,7 +2123,7 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 	/* OK, process the packet. */
 	switch (opcode) {
 	case OP(SEND_FIRST):
-		ret = hfi1_rvt_get_rwqe(qp, 0);
+		ret = rvt_get_rwqe(qp, false);
 		if (ret < 0)
 			goto nack_op_err;
 		if (!ret)
@@ -2149,7 +2149,7 @@ send_middle:
 
 	case OP(RDMA_WRITE_LAST_WITH_IMMEDIATE):
 		/* consume RWQE */
-		ret = hfi1_rvt_get_rwqe(qp, 1);
+		ret = rvt_get_rwqe(qp, true);
 		if (ret < 0)
 			goto nack_op_err;
 		if (!ret)
@@ -2159,7 +2159,7 @@ send_middle:
 	case OP(SEND_ONLY):
 	case OP(SEND_ONLY_WITH_IMMEDIATE):
 	case OP(SEND_ONLY_WITH_INVALIDATE):
-		ret = hfi1_rvt_get_rwqe(qp, 0);
+		ret = rvt_get_rwqe(qp, false);
 		if (ret < 0)
 			goto nack_op_err;
 		if (!ret)
@@ -2271,7 +2271,7 @@ send_last:
 			goto send_middle;
 		else if (opcode == OP(RDMA_WRITE_ONLY))
 			goto no_immediate_data;
-		ret = hfi1_rvt_get_rwqe(qp, 1);
+		ret = rvt_get_rwqe(qp, true);
 		if (ret < 0)
 			goto nack_op_err;
 		if (!ret) {
diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c
index c0071ca4147a..ef4c566e206f 100644
--- a/drivers/infiniband/hw/hfi1/ruc.c
+++ b/drivers/infiniband/hw/hfi1/ruc.c
@@ -53,156 +53,6 @@
 #include "verbs_txreq.h"
 #include "trace.h"
 
-/*
- * Validate a RWQE and fill in the SGE state.
- * Return 1 if OK.
- */
-static int init_sge(struct rvt_qp *qp, struct rvt_rwqe *wqe)
-{
-	int i, j, ret;
-	struct ib_wc wc;
-	struct rvt_lkey_table *rkt;
-	struct rvt_pd *pd;
-	struct rvt_sge_state *ss;
-
-	rkt = &to_idev(qp->ibqp.device)->rdi.lkey_table;
-	pd = ibpd_to_rvtpd(qp->ibqp.srq ? qp->ibqp.srq->pd : qp->ibqp.pd);
-	ss = &qp->r_sge;
-	ss->sg_list = qp->r_sg_list;
-	qp->r_len = 0;
-	for (i = j = 0; i < wqe->num_sge; i++) {
-		if (wqe->sg_list[i].length == 0)
-			continue;
-		/* Check LKEY */
-		ret = rvt_lkey_ok(rkt, pd, j ? &ss->sg_list[j - 1] : &ss->sge,
-				  NULL, &wqe->sg_list[i],
-				  IB_ACCESS_LOCAL_WRITE);
-		if (unlikely(ret <= 0))
-			goto bad_lkey;
-		qp->r_len += wqe->sg_list[i].length;
-		j++;
-	}
-	ss->num_sge = j;
-	ss->total_len = qp->r_len;
-	ret = 1;
-	goto bail;
-
-bad_lkey:
-	while (j) {
-		struct rvt_sge *sge = --j ? &ss->sg_list[j - 1] : &ss->sge;
-
-		rvt_put_mr(sge->mr);
-	}
-	ss->num_sge = 0;
-	memset(&wc, 0, sizeof(wc));
-	wc.wr_id = wqe->wr_id;
-	wc.status = IB_WC_LOC_PROT_ERR;
-	wc.opcode = IB_WC_RECV;
-	wc.qp = &qp->ibqp;
-	/* Signal solicited completion event. */
-	rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc, 1);
-	ret = 0;
-bail:
-	return ret;
-}
-
-/**
- * hfi1_rvt_get_rwqe - copy the next RWQE into the QP's RWQE
- * @qp: the QP
- * @wr_id_only: update qp->r_wr_id only, not qp->r_sge
- *
- * Return -1 if there is a local error, 0 if no RWQE is available,
- * otherwise return 1.
- *
- * Can be called from interrupt level.
- */
-int hfi1_rvt_get_rwqe(struct rvt_qp *qp, int wr_id_only)
-{
-	unsigned long flags;
-	struct rvt_rq *rq;
-	struct rvt_rwq *wq;
-	struct rvt_srq *srq;
-	struct rvt_rwqe *wqe;
-	void (*handler)(struct ib_event *, void *);
-	u32 tail;
-	int ret;
-
-	if (qp->ibqp.srq) {
-		srq = ibsrq_to_rvtsrq(qp->ibqp.srq);
-		handler = srq->ibsrq.event_handler;
-		rq = &srq->rq;
-	} else {
-		srq = NULL;
-		handler = NULL;
-		rq = &qp->r_rq;
-	}
-
-	spin_lock_irqsave(&rq->lock, flags);
-	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK)) {
-		ret = 0;
-		goto unlock;
-	}
-
-	wq = rq->wq;
-	tail = wq->tail;
-	/* Validate tail before using it since it is user writable. */
-	if (tail >= rq->size)
-		tail = 0;
-	if (unlikely(tail == wq->head)) {
-		ret = 0;
-		goto unlock;
-	}
-	/* Make sure entry is read after head index is read. */
-	smp_rmb();
-	wqe = rvt_get_rwqe_ptr(rq, tail);
-	/*
-	 * Even though we update the tail index in memory, the verbs
-	 * consumer is not supposed to post more entries until a
-	 * completion is generated.
-	 */
-	if (++tail >= rq->size)
-		tail = 0;
-	wq->tail = tail;
-	if (!wr_id_only && !init_sge(qp, wqe)) {
-		ret = -1;
-		goto unlock;
-	}
-	qp->r_wr_id = wqe->wr_id;
-
-	ret = 1;
-	set_bit(RVT_R_WRID_VALID, &qp->r_aflags);
-	if (handler) {
-		u32 n;
-
-		/*
-		 * Validate head pointer value and compute
-		 * the number of remaining WQEs.
-		 */
-		n = wq->head;
-		if (n >= rq->size)
-			n = 0;
-		if (n < tail)
-			n += rq->size - tail;
-		else
-			n -= tail;
-		if (n < srq->limit) {
-			struct ib_event ev;
-
-			srq->limit = 0;
-			spin_unlock_irqrestore(&rq->lock, flags);
-			ev.device = qp->ibqp.device;
-			ev.element.srq = qp->ibqp.srq;
-			ev.event = IB_EVENT_SRQ_LIMIT_REACHED;
-			handler(&ev, srq->ibsrq.srq_context);
-			goto bail;
-		}
-	}
-unlock:
-	spin_unlock_irqrestore(&rq->lock, flags);
-bail:
-	return ret;
-}
-
 static int gid_ok(union ib_gid *gid, __be64 gid_prefix, __be64 id)
 {
 	return (gid->global.interface_id == id &&
@@ -423,7 +273,7 @@ again:
 		/* FALLTHROUGH */
 	case IB_WR_SEND:
 send:
-		ret = hfi1_rvt_get_rwqe(qp, 0);
+		ret = rvt_get_rwqe(qp, false);
 		if (ret < 0)
 			goto op_err;
 		if (!ret)
@@ -435,7 +285,7 @@ send:
 			goto inv_err;
 		wc.wc_flags = IB_WC_WITH_IMM;
 		wc.ex.imm_data = wqe->wr.ex.imm_data;
-		ret = hfi1_rvt_get_rwqe(qp, 1);
+		ret = rvt_get_rwqe(qp, true);
 		if (ret < 0)
 			goto op_err;
 		if (!ret)
diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c
index 9d7a3110c14c..b7b671017e59 100644
--- a/drivers/infiniband/hw/hfi1/uc.c
+++ b/drivers/infiniband/hw/hfi1/uc.c
@@ -397,7 +397,7 @@ send_first:
 		if (test_and_clear_bit(RVT_R_REWIND_SGE, &qp->r_aflags)) {
 			qp->r_sge = qp->s_rdma_read_sge;
 		} else {
-			ret = hfi1_rvt_get_rwqe(qp, 0);
+			ret = rvt_get_rwqe(qp, false);
 			if (ret < 0)
 				goto op_err;
 			if (!ret)
@@ -542,7 +542,7 @@ rdma_last_imm:
 		if (test_and_clear_bit(RVT_R_REWIND_SGE, &qp->r_aflags)) {
 			rvt_put_ss(&qp->s_rdma_read_sge);
 		} else {
-			ret = hfi1_rvt_get_rwqe(qp, 1);
+			ret = rvt_get_rwqe(qp, true);
 			if (ret < 0)
 				goto op_err;
 			if (!ret)
diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c
index 69c17a5ef038..6ad203f6da88 100644
--- a/drivers/infiniband/hw/hfi1/ud.c
+++ b/drivers/infiniband/hw/hfi1/ud.c
@@ -163,7 +163,7 @@ static void ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 	} else {
 		int ret;
 
-		ret = hfi1_rvt_get_rwqe(qp, 0);
+		ret = rvt_get_rwqe(qp, false);
 		if (ret < 0) {
 			rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
 			goto bail_unlock;
@@ -974,7 +974,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 	} else {
 		int ret;
 
-		ret = hfi1_rvt_get_rwqe(qp, 0);
+		ret = rvt_get_rwqe(qp, false);
 		if (ret < 0) {
 			rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
 			return;
diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h
index 081ca52e6621..a16fe5d3f7c4 100644
--- a/drivers/infiniband/hw/hfi1/verbs.h
+++ b/drivers/infiniband/hw/hfi1/verbs.h
@@ -328,8 +328,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet);
 
 int hfi1_lookup_pkey_idx(struct hfi1_ibport *ibp, u16 pkey);
 
-int hfi1_rvt_get_rwqe(struct rvt_qp *qp, int wr_id_only);
-
 void hfi1_migrate_qp(struct rvt_qp *qp);
 
 int hfi1_check_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c
index c9955d48c50f..f35fdeb14347 100644
--- a/drivers/infiniband/hw/qib/qib_rc.c
+++ b/drivers/infiniband/hw/qib/qib_rc.c
@@ -1828,7 +1828,7 @@ void qib_rc_rcv(struct qib_ctxtdata *rcd, struct ib_header *hdr,
 	/* OK, process the packet. */
 	switch (opcode) {
 	case OP(SEND_FIRST):
-		ret = qib_get_rwqe(qp, 0);
+		ret = rvt_get_rwqe(qp, false);
 		if (ret < 0)
 			goto nack_op_err;
 		if (!ret)
@@ -1849,7 +1849,7 @@ send_middle:
 
 	case OP(RDMA_WRITE_LAST_WITH_IMMEDIATE):
 		/* consume RWQE */
-		ret = qib_get_rwqe(qp, 1);
+		ret = rvt_get_rwqe(qp, true);
 		if (ret < 0)
 			goto nack_op_err;
 		if (!ret)
@@ -1858,7 +1858,7 @@ send_middle:
 
 	case OP(SEND_ONLY):
 	case OP(SEND_ONLY_WITH_IMMEDIATE):
-		ret = qib_get_rwqe(qp, 0);
+		ret = rvt_get_rwqe(qp, false);
 		if (ret < 0)
 			goto nack_op_err;
 		if (!ret)
@@ -1949,7 +1949,7 @@ send_last:
 			goto send_middle;
 		else if (opcode == OP(RDMA_WRITE_ONLY))
 			goto no_immediate_data;
-		ret = qib_get_rwqe(qp, 1);
+		ret = rvt_get_rwqe(qp, true);
 		if (ret < 0)
 			goto nack_op_err;
 		if (!ret) {
diff --git a/drivers/infiniband/hw/qib/qib_ruc.c b/drivers/infiniband/hw/qib/qib_ruc.c
index 4662cc7bde92..f8a7de795beb 100644
--- a/drivers/infiniband/hw/qib/qib_ruc.c
+++ b/drivers/infiniband/hw/qib/qib_ruc.c
@@ -38,156 +38,6 @@
 #include "qib_mad.h"
 
 /*
- * Validate a RWQE and fill in the SGE state.
- * Return 1 if OK.
- */
-static int qib_init_sge(struct rvt_qp *qp, struct rvt_rwqe *wqe)
-{
-	int i, j, ret;
-	struct ib_wc wc;
-	struct rvt_lkey_table *rkt;
-	struct rvt_pd *pd;
-	struct rvt_sge_state *ss;
-
-	rkt = &to_idev(qp->ibqp.device)->rdi.lkey_table;
-	pd = ibpd_to_rvtpd(qp->ibqp.srq ? qp->ibqp.srq->pd : qp->ibqp.pd);
-	ss = &qp->r_sge;
-	ss->sg_list = qp->r_sg_list;
-	qp->r_len = 0;
-	for (i = j = 0; i < wqe->num_sge; i++) {
-		if (wqe->sg_list[i].length == 0)
-			continue;
-		/* Check LKEY */
-		ret = rvt_lkey_ok(rkt, pd, j ? &ss->sg_list[j - 1] : &ss->sge,
-				  NULL, &wqe->sg_list[i],
-				  IB_ACCESS_LOCAL_WRITE);
-		if (unlikely(ret <= 0))
-			goto bad_lkey;
-		qp->r_len += wqe->sg_list[i].length;
-		j++;
-	}
-	ss->num_sge = j;
-	ss->total_len = qp->r_len;
-	ret = 1;
-	goto bail;
-
-bad_lkey:
-	while (j) {
-		struct rvt_sge *sge = --j ? &ss->sg_list[j - 1] : &ss->sge;
-
-		rvt_put_mr(sge->mr);
-	}
-	ss->num_sge = 0;
-	memset(&wc, 0, sizeof(wc));
-	wc.wr_id = wqe->wr_id;
-	wc.status = IB_WC_LOC_PROT_ERR;
-	wc.opcode = IB_WC_RECV;
-	wc.qp = &qp->ibqp;
-	/* Signal solicited completion event. */
-	rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc, 1);
-	ret = 0;
-bail:
-	return ret;
-}
-
-/**
- * qib_get_rwqe - copy the next RWQE into the QP's RWQE
- * @qp: the QP
- * @wr_id_only: update qp->r_wr_id only, not qp->r_sge
- *
- * Return -1 if there is a local error, 0 if no RWQE is available,
- * otherwise return 1.
- *
- * Can be called from interrupt level.
- */
-int qib_get_rwqe(struct rvt_qp *qp, int wr_id_only)
-{
-	unsigned long flags;
-	struct rvt_rq *rq;
-	struct rvt_rwq *wq;
-	struct rvt_srq *srq;
-	struct rvt_rwqe *wqe;
-	void (*handler)(struct ib_event *, void *);
-	u32 tail;
-	int ret;
-
-	if (qp->ibqp.srq) {
-		srq = ibsrq_to_rvtsrq(qp->ibqp.srq);
-		handler = srq->ibsrq.event_handler;
-		rq = &srq->rq;
-	} else {
-		srq = NULL;
-		handler = NULL;
-		rq = &qp->r_rq;
-	}
-
-	spin_lock_irqsave(&rq->lock, flags);
-	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK)) {
-		ret = 0;
-		goto unlock;
-	}
-
-	wq = rq->wq;
-	tail = wq->tail;
-	/* Validate tail before using it since it is user writable. */
-	if (tail >= rq->size)
-		tail = 0;
-	if (unlikely(tail == wq->head)) {
-		ret = 0;
-		goto unlock;
-	}
-	/* Make sure entry is read after head index is read. */
-	smp_rmb();
-	wqe = rvt_get_rwqe_ptr(rq, tail);
-	/*
-	 * Even though we update the tail index in memory, the verbs
-	 * consumer is not supposed to post more entries until a
-	 * completion is generated.
-	 */
-	if (++tail >= rq->size)
-		tail = 0;
-	wq->tail = tail;
-	if (!wr_id_only && !qib_init_sge(qp, wqe)) {
-		ret = -1;
-		goto unlock;
-	}
-	qp->r_wr_id = wqe->wr_id;
-
-	ret = 1;
-	set_bit(RVT_R_WRID_VALID, &qp->r_aflags);
-	if (handler) {
-		u32 n;
-
-		/*
-		 * Validate head pointer value and compute
-		 * the number of remaining WQEs.
-		 */
-		n = wq->head;
-		if (n >= rq->size)
-			n = 0;
-		if (n < tail)
-			n += rq->size - tail;
-		else
-			n -= tail;
-		if (n < srq->limit) {
-			struct ib_event ev;
-
-			srq->limit = 0;
-			spin_unlock_irqrestore(&rq->lock, flags);
-			ev.device = qp->ibqp.device;
-			ev.element.srq = qp->ibqp.srq;
-			ev.event = IB_EVENT_SRQ_LIMIT_REACHED;
-			handler(&ev, srq->ibsrq.srq_context);
-			goto bail;
-		}
-	}
-unlock:
-	spin_unlock_irqrestore(&rq->lock, flags);
-bail:
-	return ret;
-}
-
-/*
  * Switch to alternate path.
  * The QP s_lock should be held and interrupts disabled.
  */
@@ -419,7 +269,7 @@ again:
 		wc.ex.imm_data = wqe->wr.ex.imm_data;
 		/* FALLTHROUGH */
 	case IB_WR_SEND:
-		ret = qib_get_rwqe(qp, 0);
+		ret = rvt_get_rwqe(qp, false);
 		if (ret < 0)
 			goto op_err;
 		if (!ret)
@@ -431,7 +281,7 @@ again:
 			goto inv_err;
 		wc.wc_flags = IB_WC_WITH_IMM;
 		wc.ex.imm_data = wqe->wr.ex.imm_data;
-		ret = qib_get_rwqe(qp, 1);
+		ret = rvt_get_rwqe(qp, true);
 		if (ret < 0)
 			goto op_err;
 		if (!ret)
diff --git a/drivers/infiniband/hw/qib/qib_uc.c b/drivers/infiniband/hw/qib/qib_uc.c
index 840eec6ebc33..3e54bc11e0ae 100644
--- a/drivers/infiniband/hw/qib/qib_uc.c
+++ b/drivers/infiniband/hw/qib/qib_uc.c
@@ -335,7 +335,7 @@ send_first:
 		if (test_and_clear_bit(RVT_R_REWIND_SGE, &qp->r_aflags))
 			qp->r_sge = qp->s_rdma_read_sge;
 		else {
-			ret = qib_get_rwqe(qp, 0);
+			ret = rvt_get_rwqe(qp, false);
 			if (ret < 0)
 				goto op_err;
 			if (!ret)
@@ -471,7 +471,7 @@ rdma_last_imm:
 		if (test_and_clear_bit(RVT_R_REWIND_SGE, &qp->r_aflags))
 			rvt_put_ss(&qp->s_rdma_read_sge);
 		else {
-			ret = qib_get_rwqe(qp, 1);
+			ret = rvt_get_rwqe(qp, true);
 			if (ret < 0)
 				goto op_err;
 			if (!ret)
diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c
index 3e4ff77260c2..f8d029a2390f 100644
--- a/drivers/infiniband/hw/qib/qib_ud.c
+++ b/drivers/infiniband/hw/qib/qib_ud.c
@@ -139,7 +139,7 @@ static void qib_ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 	else {
 		int ret;
 
-		ret = qib_get_rwqe(qp, 0);
+		ret = rvt_get_rwqe(qp, false);
 		if (ret < 0) {
 			rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
 			goto bail_unlock;
@@ -534,7 +534,7 @@ void qib_ud_rcv(struct qib_ibport *ibp, struct ib_header *hdr,
 	else {
 		int ret;
 
-		ret = qib_get_rwqe(qp, 0);
+		ret = rvt_get_rwqe(qp, false);
 		if (ret < 0) {
 			rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
 			return;
diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h
index f887737ac142..f9a46768a19a 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.h
+++ b/drivers/infiniband/hw/qib/qib_verbs.h
@@ -321,8 +321,6 @@ void qib_ud_rcv(struct qib_ibport *ibp, struct ib_header *hdr,
 
 void mr_rcu_callback(struct rcu_head *list);
 
-int qib_get_rwqe(struct rvt_qp *qp, int wr_id_only);
-
 void qib_migrate_qp(struct rvt_qp *qp);
 
 int qib_ruc_check_hdr(struct qib_ibport *ibp, struct ib_header *hdr,
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index c82e6bb3d77c..6e9a351f45fb 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -1987,6 +1987,155 @@ int rvt_post_srq_recv(struct ib_srq *ibsrq, struct ib_recv_wr *wr,
 	return 0;
 }
 
+/*
+ * Validate a RWQE and fill in the SGE state.
+ * Return 1 if OK.
+ */
+static int init_sge(struct rvt_qp *qp, struct rvt_rwqe *wqe)
+{
+	int i, j, ret;
+	struct ib_wc wc;
+	struct rvt_lkey_table *rkt;
+	struct rvt_pd *pd;
+	struct rvt_sge_state *ss;
+	struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device);
+
+	rkt = &rdi->lkey_table;
+	pd = ibpd_to_rvtpd(qp->ibqp.srq ? qp->ibqp.srq->pd : qp->ibqp.pd);
+	ss = &qp->r_sge;
+	ss->sg_list = qp->r_sg_list;
+	qp->r_len = 0;
+	for (i = j = 0; i < wqe->num_sge; i++) {
+		if (wqe->sg_list[i].length == 0)
+			continue;
+		/* Check LKEY */
+		ret = rvt_lkey_ok(rkt, pd, j ? &ss->sg_list[j - 1] : &ss->sge,
+				  NULL, &wqe->sg_list[i],
+				  IB_ACCESS_LOCAL_WRITE);
+		if (unlikely(ret <= 0))
+			goto bad_lkey;
+		qp->r_len += wqe->sg_list[i].length;
+		j++;
+	}
+	ss->num_sge = j;
+	ss->total_len = qp->r_len;
+	return 1;
+
+bad_lkey:
+	while (j) {
+		struct rvt_sge *sge = --j ? &ss->sg_list[j - 1] : &ss->sge;
+
+		rvt_put_mr(sge->mr);
+	}
+	ss->num_sge = 0;
+	memset(&wc, 0, sizeof(wc));
+	wc.wr_id = wqe->wr_id;
+	wc.status = IB_WC_LOC_PROT_ERR;
+	wc.opcode = IB_WC_RECV;
+	wc.qp = &qp->ibqp;
+	/* Signal solicited completion event. */
+	rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc, 1);
+	return 0;
+}
+
+/**
+ * rvt_get_rwqe - copy the next RWQE into the QP's RWQE
+ * @qp: the QP
+ * @wr_id_only: update qp->r_wr_id only, not qp->r_sge
+ *
+ * Return -1 if there is a local error, 0 if no RWQE is available,
+ * otherwise return 1.
+ *
+ * Can be called from interrupt level.
+ */
+int rvt_get_rwqe(struct rvt_qp *qp, bool wr_id_only)
+{
+	unsigned long flags;
+	struct rvt_rq *rq;
+	struct rvt_rwq *wq;
+	struct rvt_srq *srq;
+	struct rvt_rwqe *wqe;
+	void (*handler)(struct ib_event *, void *);
+	u32 tail;
+	int ret;
+
+	if (qp->ibqp.srq) {
+		srq = ibsrq_to_rvtsrq(qp->ibqp.srq);
+		handler = srq->ibsrq.event_handler;
+		rq = &srq->rq;
+	} else {
+		srq = NULL;
+		handler = NULL;
+		rq = &qp->r_rq;
+	}
+
+	spin_lock_irqsave(&rq->lock, flags);
+	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK)) {
+		ret = 0;
+		goto unlock;
+	}
+
+	wq = rq->wq;
+	tail = wq->tail;
+	/* Validate tail before using it since it is user writable. */
+	if (tail >= rq->size)
+		tail = 0;
+	if (unlikely(tail == wq->head)) {
+		ret = 0;
+		goto unlock;
+	}
+	/* Make sure entry is read after head index is read. */
+	smp_rmb();
+	wqe = rvt_get_rwqe_ptr(rq, tail);
+	/*
+	 * Even though we update the tail index in memory, the verbs
+	 * consumer is not supposed to post more entries until a
+	 * completion is generated.
+	 */
+	if (++tail >= rq->size)
+		tail = 0;
+	wq->tail = tail;
+	if (!wr_id_only && !init_sge(qp, wqe)) {
+		ret = -1;
+		goto unlock;
+	}
+	qp->r_wr_id = wqe->wr_id;
+
+	ret = 1;
+	set_bit(RVT_R_WRID_VALID, &qp->r_aflags);
+	if (handler) {
+		u32 n;
+
+		/*
+		 * Validate head pointer value and compute
+		 * the number of remaining WQEs.
+		 */
+		n = wq->head;
+		if (n >= rq->size)
+			n = 0;
+		if (n < tail)
+			n += rq->size - tail;
+		else
+			n -= tail;
+		if (n < srq->limit) {
+			struct ib_event ev;
+
+			srq->limit = 0;
+			spin_unlock_irqrestore(&rq->lock, flags);
+			ev.device = qp->ibqp.device;
+			ev.element.srq = qp->ibqp.srq;
+			ev.event = IB_EVENT_SRQ_LIMIT_REACHED;
+			handler(&ev, srq->ibsrq.srq_context);
+			goto bail;
+		}
+	}
+unlock:
+	spin_unlock_irqrestore(&rq->lock, flags);
+bail:
+	return ret;
+}
+EXPORT_SYMBOL(rvt_get_rwqe);
+
 /**
  * qp_comm_est - handle trap with QP established
  * @qp: the QP
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index 89ab88c342b6..1145a4c154b2 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -663,6 +663,7 @@ static inline unsigned long rvt_timeout_to_jiffies(u8 timeout)
 extern const int  ib_rvt_state_ops[];
 
 struct rvt_dev_info;
+int rvt_get_rwqe(struct rvt_qp *qp, bool wr_id_only);
 void rvt_comm_est(struct rvt_qp *qp);
 int rvt_error_qp(struct rvt_qp *qp, enum ib_wc_status err);
 void rvt_rc_error(struct rvt_qp *qp, enum ib_wc_status err);