6 files changed, 142 insertions, 45 deletions

diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c
index 0ae2ff8cf81e..0335a3df74d5 100644
--- a/drivers/infiniband/sw/rdmavt/cq.c
+++ b/drivers/infiniband/sw/rdmavt/cq.c
@@ -107,7 +107,7 @@ void rvt_cq_enter(struct rvt_cq *cq, struct ib_wc *entry, bool solicited)
 		wc->uqueue[head].src_qp = entry->src_qp;
 		wc->uqueue[head].wc_flags = entry->wc_flags;
 		wc->uqueue[head].pkey_index = entry->pkey_index;
-		wc->uqueue[head].slid = entry->slid;
+		wc->uqueue[head].slid = ib_slid_cpu16(entry->slid);
 		wc->uqueue[head].sl = entry->sl;
 		wc->uqueue[head].dlid_path_bits = entry->dlid_path_bits;
 		wc->uqueue[head].port_num = entry->port_num;
diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c
index aa5f9ea318e4..1b3801f78e78 100644
--- a/drivers/infiniband/sw/rdmavt/mr.c
+++ b/drivers/infiniband/sw/rdmavt/mr.c
@@ -778,23 +778,52 @@ out:
 }
 
 /**
+ * rvt_sge_adjacent - is isge compressible
+ * @last_sge: last outgoing SGE written
+ * @sge: SGE to check
+ *
+ * If adjacent will update last_sge to add length.
+ *
+ * Return: true if isge is adjacent to last sge
+ */
+static inline bool rvt_sge_adjacent(struct rvt_sge *last_sge,
+				    struct ib_sge *sge)
+{
+	if (last_sge && sge->lkey == last_sge->mr->lkey &&
+	    ((uint64_t)(last_sge->vaddr + last_sge->length) == sge->addr)) {
+		if (sge->lkey) {
+			if (unlikely((sge->addr - last_sge->mr->user_base +
+			      sge->length > last_sge->mr->length)))
+				return false; /* overrun, caller will catch */
+		} else {
+			last_sge->length += sge->length;
+		}
+		last_sge->sge_length += sge->length;
+		trace_rvt_sge_adjacent(last_sge, sge);
+		return true;
+	}
+	return false;
+}
+
+/**
  * rvt_lkey_ok - check IB SGE for validity and initialize
  * @rkt: table containing lkey to check SGE against
  * @pd: protection domain
  * @isge: outgoing internal SGE
+ * @last_sge: last outgoing SGE written
  * @sge: SGE to check
  * @acc: access flags
  *
  * Check the IB SGE for validity and initialize our internal version
  * of it.
  *
- * Return: 1 if valid and successful, otherwise returns 0.
- *
- * increments the reference count upon success
+ * Increments the reference count when a new sge is stored.
  *
+ * Return: 0 if compressed, 1 if added , otherwise returns -errno.
  */
 int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
-		struct rvt_sge *isge, struct ib_sge *sge, int acc)
+		struct rvt_sge *isge, struct rvt_sge *last_sge,
+		struct ib_sge *sge, int acc)
 {
 	struct rvt_mregion *mr;
 	unsigned n, m;
@@ -804,12 +833,14 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
 	 * We use LKEY == zero for kernel virtual addresses
 	 * (see rvt_get_dma_mr() and dma_virt_ops).
 	 */
-	rcu_read_lock();
 	if (sge->lkey == 0) {
 		struct rvt_dev_info *dev = ib_to_rvt(pd->ibpd.device);
 
 		if (pd->user)
-			goto bail;
+			return -EINVAL;
+		if (rvt_sge_adjacent(last_sge, sge))
+			return 0;
+		rcu_read_lock();
 		mr = rcu_dereference(dev->dma_mr);
 		if (!mr)
 			goto bail;
@@ -824,6 +855,9 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
 		isge->n = 0;
 		goto ok;
 	}
+	if (rvt_sge_adjacent(last_sge, sge))
+		return 0;
+	rcu_read_lock();
 	mr = rcu_dereference(rkt->table[sge->lkey >> rkt->shift]);
 	if (!mr)
 		goto bail;
@@ -874,12 +908,13 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
 	isge->m = m;
 	isge->n = n;
 ok:
+	trace_rvt_sge_new(isge, sge);
 	return 1;
 bail_unref:
 	rvt_put_mr(mr);
 bail:
 	rcu_read_unlock();
-	return 0;
+	return -EINVAL;
 }
 EXPORT_SYMBOL(rvt_lkey_ok);
 
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 8876ee7bc326..1878a97364aa 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -421,15 +421,6 @@ bail:
 	return ret;
 }
 
-static void free_qpn(struct rvt_qpn_table *qpt, u32 qpn)
-{
-	struct rvt_qpn_map *map;
-
-	map = qpt->map + qpn / RVT_BITS_PER_PAGE;
-	if (map->page)
-		clear_bit(qpn & RVT_BITS_PER_PAGE_MASK, map->page);
-}
-
 /**
  * rvt_clear_mr_refs - Drop help mr refs
  * @qp: rvt qp data structure
@@ -645,6 +636,19 @@ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 	lockdep_assert_held(&qp->s_lock);
 }
 
+/** rvt_free_qpn - Free a qpn from the bit map
+ * @qpt: QP table
+ * @qpn: queue pair number to free
+ */
+static void rvt_free_qpn(struct rvt_qpn_table *qpt, u32 qpn)
+{
+	struct rvt_qpn_map *map;
+
+	map = qpt->map + (qpn & RVT_QPN_MASK) / RVT_BITS_PER_PAGE;
+	if (map->page)
+		clear_bit(qpn & RVT_BITS_PER_PAGE_MASK, map->page);
+}
+
 /**
  * rvt_create_qp - create a queue pair for a device
  * @ibpd: the protection domain who's device we create the queue pair for
@@ -914,7 +918,7 @@ bail_ip:
 		kref_put(&qp->ip->ref, rvt_release_mmap_info);
 
 bail_qpn:
-	free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num);
+	rvt_free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num);
 
 bail_rq_wq:
 	if (!qp->ip)
@@ -1301,19 +1305,6 @@ inval:
 	return -EINVAL;
 }
 
-/** rvt_free_qpn - Free a qpn from the bit map
- * @qpt: QP table
- * @qpn: queue pair number to free
- */
-static void rvt_free_qpn(struct rvt_qpn_table *qpt, u32 qpn)
-{
-	struct rvt_qpn_map *map;
-
-	map = qpt->map + qpn / RVT_BITS_PER_PAGE;
-	if (map->page)
-		clear_bit(qpn & RVT_BITS_PER_PAGE_MASK, map->page);
-}
-
 /**
  * rvt_destroy_qp - destroy a queue pair
  * @ibqp: the queue pair to destroy
@@ -1695,22 +1686,23 @@ static int rvt_post_one_wr(struct rvt_qp *qp,
 	wqe->length = 0;
 	j = 0;
 	if (wr->num_sge) {
+		struct rvt_sge *last_sge = NULL;
+
 		acc = wr->opcode >= IB_WR_RDMA_READ ?
 			IB_ACCESS_LOCAL_WRITE : 0;
 		for (i = 0; i < wr->num_sge; i++) {
 			u32 length = wr->sg_list[i].length;
-			int ok;
 
 			if (length == 0)
 				continue;
-			ok = rvt_lkey_ok(rkt, pd, &wqe->sg_list[j],
-					 &wr->sg_list[i], acc);
-			if (!ok) {
-				ret = -EINVAL;
+			ret = rvt_lkey_ok(rkt, pd, &wqe->sg_list[j], last_sge,
+					  &wr->sg_list[i], acc);
+			if (unlikely(ret < 0))
 				goto bail_inval_free;
-			}
 			wqe->length += length;
-			j++;
+			if (ret)
+				last_sge = &wqe->sg_list[j];
+			j += ret;
 		}
 		wqe->wr.num_sge = j;
 	}
@@ -1757,7 +1749,7 @@ static int rvt_post_one_wr(struct rvt_qp *qp,
 		wqe->wr.send_flags &= ~RVT_SEND_RESERVE_USED;
 		qp->s_avail--;
 	}
-	trace_rvt_post_one_wr(qp, wqe);
+	trace_rvt_post_one_wr(qp, wqe, wr->num_sge);
 	smp_wmb(); /* see request builders */
 	qp->s_head = next;
 
diff --git a/drivers/infiniband/sw/rdmavt/trace_mr.h b/drivers/infiniband/sw/rdmavt/trace_mr.h
index 3318a6c36373..976e482930a3 100644
--- a/drivers/infiniband/sw/rdmavt/trace_mr.h
+++ b/drivers/infiniband/sw/rdmavt/trace_mr.h
@@ -103,6 +103,68 @@ DEFINE_EVENT(
 	TP_PROTO(struct rvt_mregion *mr, u16 m, u16 n, void *v, size_t len),
 	TP_ARGS(mr, m, n, v, len));
 
+DECLARE_EVENT_CLASS(
+	rvt_sge_template,
+	TP_PROTO(struct rvt_sge *sge, struct ib_sge *isge),
+	TP_ARGS(sge, isge),
+	TP_STRUCT__entry(
+		RDI_DEV_ENTRY(ib_to_rvt(sge->mr->pd->device))
+		__field(struct rvt_mregion *, mr)
+		__field(struct rvt_sge *, sge)
+		__field(struct ib_sge *, isge)
+		__field(void *, vaddr)
+		__field(u64, ivaddr)
+		__field(u32, lkey)
+		__field(u32, sge_length)
+		__field(u32, length)
+		__field(u32, ilength)
+		__field(int, user)
+		__field(u16, m)
+		__field(u16, n)
+	),
+	TP_fast_assign(
+		RDI_DEV_ASSIGN(ib_to_rvt(sge->mr->pd->device));
+		__entry->mr = sge->mr;
+		__entry->sge = sge;
+		__entry->isge = isge;
+		__entry->vaddr = sge->vaddr;
+		__entry->ivaddr = isge->addr;
+		__entry->lkey = sge->mr->lkey;
+		__entry->sge_length = sge->sge_length;
+		__entry->length = sge->length;
+		__entry->ilength = isge->length;
+		__entry->m = sge->m;
+		__entry->n = sge->m;
+		__entry->user = ibpd_to_rvtpd(sge->mr->pd)->user;
+	),
+	TP_printk(
+		"[%s] mr %p sge %p isge %p vaddr %p ivaddr %llx lkey %x sge_length %u length %u ilength %u m %u n %u user %u",
+		__get_str(dev),
+		__entry->mr,
+		__entry->sge,
+		__entry->isge,
+		__entry->vaddr,
+		__entry->ivaddr,
+		__entry->lkey,
+		__entry->sge_length,
+		__entry->length,
+		__entry->ilength,
+		__entry->m,
+		__entry->n,
+		__entry->user
+	)
+);
+
+DEFINE_EVENT(
+	rvt_sge_template, rvt_sge_adjacent,
+	TP_PROTO(struct rvt_sge *sge, struct ib_sge *isge),
+	TP_ARGS(sge, isge));
+
+DEFINE_EVENT(
+	rvt_sge_template, rvt_sge_new,
+	TP_PROTO(struct rvt_sge *sge, struct ib_sge *isge),
+	TP_ARGS(sge, isge));
+
 #endif /* __RVT_TRACE_MR_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/drivers/infiniband/sw/rdmavt/trace_tx.h b/drivers/infiniband/sw/rdmavt/trace_tx.h
index a613a2223751..0ef25fc49f25 100644
--- a/drivers/infiniband/sw/rdmavt/trace_tx.h
+++ b/drivers/infiniband/sw/rdmavt/trace_tx.h
@@ -84,12 +84,12 @@ __print_symbolic(opcode,                                   \
 	wr_opcode_name(RESERVED10))
 
 #define POS_PRN \
-"[%s] wqe %p wr_id %llx send_flags %x qpn %x qpt %u psn %x lpsn %x ssn %x length %u opcode 0x%.2x,%s size %u avail %u head %u last %u pid %u num_sge %u"
+"[%s] wqe %p wr_id %llx send_flags %x qpn %x qpt %u psn %x lpsn %x ssn %x length %u opcode 0x%.2x,%s size %u avail %u head %u last %u pid %u num_sge %u wr_num_sge %u"
 
 TRACE_EVENT(
 	rvt_post_one_wr,
-	TP_PROTO(struct rvt_qp *qp, struct rvt_swqe *wqe),
-	TP_ARGS(qp, wqe),
+	TP_PROTO(struct rvt_qp *qp, struct rvt_swqe *wqe, int wr_num_sge),
+	TP_ARGS(qp, wqe, wr_num_sge),
 	TP_STRUCT__entry(
 		RDI_DEV_ENTRY(ib_to_rvt(qp->ibqp.device))
 		__field(u64, wr_id)
@@ -108,6 +108,7 @@ TRACE_EVENT(
 		__field(int, send_flags)
 		__field(pid_t, pid)
 		__field(int, num_sge)
+		__field(int, wr_num_sge)
 	),
 	TP_fast_assign(
 		RDI_DEV_ASSIGN(ib_to_rvt(qp->ibqp.device))
@@ -127,6 +128,7 @@ TRACE_EVENT(
 		__entry->ssn = wqe->ssn;
 		__entry->send_flags = wqe->wr.send_flags;
 		__entry->num_sge = wqe->wr.num_sge;
+		__entry->wr_num_sge = wr_num_sge;
 	),
 	TP_printk(
 		POS_PRN,
@@ -146,7 +148,8 @@ TRACE_EVENT(
 		__entry->head,
 		__entry->last,
 		__entry->pid,
-		__entry->num_sge
+		__entry->num_sge,
+		__entry->wr_num_sge
 	)
 );
 
diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c
index 0d7c6bb551d9..64bdd442078a 100644
--- a/drivers/infiniband/sw/rdmavt/vt.c
+++ b/drivers/infiniband/sw/rdmavt/vt.c
@@ -202,8 +202,13 @@ static int rvt_modify_port(struct ib_device *ibdev, u8 port_num,
 		return -EINVAL;
 
 	rvp = rdi->ports[port_index];
-	rvp->port_cap_flags |= props->set_port_cap_mask;
-	rvp->port_cap_flags &= ~props->clr_port_cap_mask;
+	if (port_modify_mask & IB_PORT_OPA_MASK_CHG) {
+		rvp->port_cap3_flags |= props->set_port_cap_mask;
+		rvp->port_cap3_flags &= ~props->clr_port_cap_mask;
+	} else {
+		rvp->port_cap_flags |= props->set_port_cap_mask;
+		rvp->port_cap_flags &= ~props->clr_port_cap_mask;
+	}
 
 	if (props->set_port_cap_mask || props->clr_port_cap_mask)
 		rdi->driver_f.cap_mask_chg(rdi, port_num);