IB/hfi1: Remove dependence on qp->s_cur_size

The qp->s_cur_size field assumes that the S_BUSY bit protects
the field from modification after the slock is dropped. Scaling the
send engine to multiple cores would break that assumption.

Correct the issue by carrying the payload size in the txreq structure.

Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Don Hiatt <don.hiatt@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/hfi1/rc.c

@@ -351,7 +351,7 @@ normal:
 	qp->s_rdma_ack_cnt++;
 	qp->s_hdrwords = hwords;
 	ps->s_txreq->sde = priv->s_sde;
-	qp->s_cur_size = len;
+	ps->s_txreq->s_cur_size = len;
 	hfi1_make_ruc_header(qp, ohdr, bth0, bth2, middle, ps);
 	/* pbc */
 	ps->s_txreq->hdr_dwords = qp->s_hdrwords + 2;
@@ -802,7 +802,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	qp->s_hdrwords = hwords;
 	ps->s_txreq->sde = priv->s_sde;
 	qp->s_cur_sge = ss;
-	qp->s_cur_size = len;
+	ps->s_txreq->s_cur_size = len;
 	hfi1_make_ruc_header(
 		qp,
 		ohdr,

drivers/infiniband/hw/hfi1/ruc.c

@@ -767,8 +767,8 @@ void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
 	u32 bth1;
 
 	/* Construct the header. */
-	extra_bytes = -qp->s_cur_size & 3;
-	nwords = (qp->s_cur_size + extra_bytes) >> 2;
+	extra_bytes = -ps->s_txreq->s_cur_size & 3;
+	nwords = (ps->s_txreq->s_cur_size + extra_bytes) >> 2;
 	lrh0 = HFI1_LRH_BTH;
 	if (unlikely(qp->remote_ah_attr.ah_flags & IB_AH_GRH)) {
 		qp->s_hdrwords += hfi1_make_grh(ibp,

drivers/infiniband/hw/hfi1/uc.c

@@ -259,7 +259,7 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	qp->s_hdrwords = hwords;
 	ps->s_txreq->sde = priv->s_sde;
 	qp->s_cur_sge = &qp->s_sge;
-	qp->s_cur_size = len;
+	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 */

drivers/infiniband/hw/hfi1/ud.c

@@ -354,7 +354,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 
 	/* header size in 32-bit words LRH+BTH+DETH = (8+12+8)/4. */
 	qp->s_hdrwords = 7;
-	qp->s_cur_size = wqe->length;
+	ps->s_txreq->s_cur_size = wqe->length;
 	qp->s_cur_sge = &qp->s_sge;
 	qp->s_srate = ah_attr->static_rate;
 	qp->srate_mbps = ib_rate_to_mbps(qp->s_srate);

drivers/infiniband/hw/hfi1/verbs.c

@@ -895,7 +895,7 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 	struct hfi1_ahg_info *ahg_info = priv->s_ahg;
 	u32 hdrwords = qp->s_hdrwords;
 	struct rvt_sge_state *ss = qp->s_cur_sge;
-	u32 len = qp->s_cur_size;
+	u32 len = ps->s_txreq->s_cur_size;
 	u32 plen = hdrwords + ((len + 3) >> 2) + 2; /* includes pbc */
 	struct hfi1_ibdev *dev = ps->dev;
 	struct hfi1_pportdata *ppd = ps->ppd;
@@ -1012,7 +1012,7 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 	struct hfi1_qp_priv *priv = qp->priv;
 	u32 hdrwords = qp->s_hdrwords;
 	struct rvt_sge_state *ss = qp->s_cur_sge;
-	u32 len = qp->s_cur_size;
+	u32 len = ps->s_txreq->s_cur_size;
 	u32 dwords = (len + 3) >> 2;
 	u32 plen = hdrwords + dwords + 2; /* includes pbc */
 	struct hfi1_pportdata *ppd = ps->ppd;
@@ -1240,7 +1240,7 @@ static inline send_routine get_send_routine(struct rvt_qp *qp,
 		u8 op = get_opcode(h);
 
 		if (piothreshold &&
-		    qp->s_cur_size <= min(piothreshold, qp->pmtu) &&
+		    tx->s_cur_size <= min(piothreshold, qp->pmtu) &&
 		    (BIT(op & OPMASK) & pio_opmask[op >> 5]) &&
 		    iowait_sdma_pending(&priv->s_iowait) == 0 &&
 		    !sdma_txreq_built(&tx->txreq))

drivers/infiniband/hw/hfi1/verbs_txreq.h

@@ -65,6 +65,7 @@ struct verbs_txreq {
 	struct sdma_engine     *sde;
 	struct send_context     *psc;
 	u16                     hdr_dwords;
+	u16			s_cur_size;
 };
 
 struct hfi1_ibdev;