staging/rdma/hfi1: Fix header size calculation for RC/UC QPs with GRH enabled

There is a header size counter in both the QP struture and the txreq
structure. The counter in the txreq structure is not updated properly
for RC and UC queue pairs with GRH enabled, and thus causing SDMA
send to fail. This patch fixes the RC and UC path.

Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: Dean Luick <dean.luick@intel.com>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Jianxin Xiong <jianxin.xiong@intel.com>
Signed-off-by: Jubin John <jubin.john@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/staging/rdma/hfi1/rc.c

@@ -358,11 +358,11 @@ normal:
 	}
 	qp->s_rdma_ack_cnt++;
 	qp->s_hdrwords = hwords;
-	/* pbc */
-	ps->s_txreq->hdr_dwords = hwords + 2;
 	ps->s_txreq->sde = priv->s_sde;
 	qp->s_cur_size = len;
 	hfi1_make_ruc_header(qp, ohdr, bth0, bth2, middle, ps);
+	/* pbc */
+	ps->s_txreq->hdr_dwords = qp->s_hdrwords + 2;
 	return 1;
 
 bail:
@@ -763,8 +763,6 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	}
 	qp->s_len -= len;
 	qp->s_hdrwords = hwords;
-	/* pbc */
-	ps->s_txreq->hdr_dwords = hwords + 2;
 	ps->s_txreq->sde = priv->s_sde;
 	qp->s_cur_sge = ss;
 	qp->s_cur_size = len;
@@ -775,6 +773,8 @@ 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:

drivers/staging/rdma/hfi1/uc.c

@@ -239,13 +239,13 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	}
 	qp->s_len -= len;
 	qp->s_hdrwords = hwords;
-	/* pbc */
-	ps->s_txreq->hdr_dwords = qp->s_hdrwords + 2;
 	ps->s_txreq->sde = priv->s_sde;
 	qp->s_cur_sge = &qp->s_sge;
 	qp->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: