xprtrdma: Fix max_send_wr computation

For FRWR, the computation of max_send_wr is split between
frwr_op_open and rpcrdma_ep_create, which makes it difficult to tell
that the max_send_wr result is currently incorrect if frwr_op_open
has to reduce the credit limit to accommodate a small max_qp_wr.
This is a problem now that extra WRs are needed for backchannel
operations and a drain CQE.

So, refactor the computation so that it is all done in ->ro_open,
and fix the FRWR version of this computation so that it
accommodates HCAs with small max_qp_wr correctly.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

net/sunrpc/xprtrdma/fmr_ops.c

@@ -159,10 +159,32 @@ fmr_op_recover_mr(struct rpcrdma_mr *mr)
 	fmr_op_release_mr(mr);
 }
 
+/* On success, sets:
+ *	ep->rep_attr.cap.max_send_wr
+ *	ep->rep_attr.cap.max_recv_wr
+ *	cdata->max_requests
+ *	ia->ri_max_segs
+ */
 static int
 fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
 	    struct rpcrdma_create_data_internal *cdata)
 {
+	int max_qp_wr;
+
+	max_qp_wr = ia->ri_device->attrs.max_qp_wr;
+	max_qp_wr -= RPCRDMA_BACKWARD_WRS;
+	max_qp_wr -= 1;
+	if (max_qp_wr < RPCRDMA_MIN_SLOT_TABLE)
+		return -ENOMEM;
+	if (cdata->max_requests > max_qp_wr)
+		cdata->max_requests = max_qp_wr;
+	ep->rep_attr.cap.max_send_wr = cdata->max_requests;
+	ep->rep_attr.cap.max_send_wr += RPCRDMA_BACKWARD_WRS;
+	ep->rep_attr.cap.max_send_wr += 1; /* for ib_drain_sq */
+	ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
+	ep->rep_attr.cap.max_recv_wr += RPCRDMA_BACKWARD_WRS;
+	ep->rep_attr.cap.max_recv_wr += 1; /* for ib_drain_rq */
+
 	ia->ri_max_segs = max_t(unsigned int, 1, RPCRDMA_MAX_DATA_SEGS /
 				RPCRDMA_MAX_FMR_SGES);
 	return 0;

net/sunrpc/xprtrdma/frwr_ops.c

@@ -205,12 +205,22 @@ frwr_op_recover_mr(struct rpcrdma_mr *mr)
 	frwr_op_release_mr(mr);
 }
 
+/* On success, sets:
+ *	ep->rep_attr.cap.max_send_wr
+ *	ep->rep_attr.cap.max_recv_wr
+ *	cdata->max_requests
+ *	ia->ri_max_segs
+ *
+ * And these FRWR-related fields:
+ *	ia->ri_max_frwr_depth
+ *	ia->ri_mrtype
+ */
 static int
 frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
 	     struct rpcrdma_create_data_internal *cdata)
 {
 	struct ib_device_attr *attrs = &ia->ri_device->attrs;
-	int depth, delta;
+	int max_qp_wr, depth, delta;
 
 	ia->ri_mrtype = IB_MR_TYPE_MEM_REG;
 	if (attrs->device_cap_flags & IB_DEVICE_SG_GAPS_REG)
@@ -244,14 +254,26 @@ frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
 		} while (delta > 0);
 	}
 
-	ep->rep_attr.cap.max_send_wr *= depth;
-	if (ep->rep_attr.cap.max_send_wr > attrs->max_qp_wr) {
-		cdata->max_requests = attrs->max_qp_wr / depth;
+	max_qp_wr = ia->ri_device->attrs.max_qp_wr;
+	max_qp_wr -= RPCRDMA_BACKWARD_WRS;
+	max_qp_wr -= 1;
+	if (max_qp_wr < RPCRDMA_MIN_SLOT_TABLE)
+		return -ENOMEM;
+	if (cdata->max_requests > max_qp_wr)
+		cdata->max_requests = max_qp_wr;
+	ep->rep_attr.cap.max_send_wr = cdata->max_requests * depth;
+	if (ep->rep_attr.cap.max_send_wr > max_qp_wr) {
+		cdata->max_requests = max_qp_wr / depth;
 		if (!cdata->max_requests)
 			return -EINVAL;
 		ep->rep_attr.cap.max_send_wr = cdata->max_requests *
 					       depth;
 	}
+	ep->rep_attr.cap.max_send_wr += RPCRDMA_BACKWARD_WRS;
+	ep->rep_attr.cap.max_send_wr += 1; /* for ib_drain_sq */
+	ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
+	ep->rep_attr.cap.max_recv_wr += RPCRDMA_BACKWARD_WRS;
+	ep->rep_attr.cap.max_recv_wr += 1; /* for ib_drain_rq */
 
 	ia->ri_max_segs = max_t(unsigned int, 1, RPCRDMA_MAX_DATA_SEGS /
 				ia->ri_max_frwr_depth);

net/sunrpc/xprtrdma/verbs.c

@@ -501,8 +501,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 		  struct rpcrdma_create_data_internal *cdata)
 {
 	struct rpcrdma_connect_private *pmsg = &ep->rep_cm_private;
-	unsigned int max_qp_wr, max_sge;
 	struct ib_cq *sendcq, *recvcq;
+	unsigned int max_sge;
 	int rc;
 
 	max_sge = min_t(unsigned int, ia->ri_device->attrs.max_sge,
@@ -513,29 +513,13 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 	}
 	ia->ri_max_send_sges = max_sge;
 
-	if (ia->ri_device->attrs.max_qp_wr <= RPCRDMA_BACKWARD_WRS) {
-		dprintk("RPC:       %s: insufficient wqe's available\n",
-			__func__);
-		return -ENOMEM;
-	}
-	max_qp_wr = ia->ri_device->attrs.max_qp_wr - RPCRDMA_BACKWARD_WRS - 1;
-
-	/* check provider's send/recv wr limits */
-	if (cdata->max_requests > max_qp_wr)
-		cdata->max_requests = max_qp_wr;
+	rc = ia->ri_ops->ro_open(ia, ep, cdata);
+	if (rc)
+		return rc;
 
 	ep->rep_attr.event_handler = rpcrdma_qp_async_error_upcall;
 	ep->rep_attr.qp_context = ep;
 	ep->rep_attr.srq = NULL;
-	ep->rep_attr.cap.max_send_wr = cdata->max_requests;
-	ep->rep_attr.cap.max_send_wr += RPCRDMA_BACKWARD_WRS;
-	ep->rep_attr.cap.max_send_wr += 1;	/* drain cqe */
-	rc = ia->ri_ops->ro_open(ia, ep, cdata);
-	if (rc)
-		return rc;
-	ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
-	ep->rep_attr.cap.max_recv_wr += RPCRDMA_BACKWARD_WRS;
-	ep->rep_attr.cap.max_recv_wr += 1;	/* drain cqe */
 	ep->rep_attr.cap.max_send_sge = max_sge;
 	ep->rep_attr.cap.max_recv_sge = 1;
 	ep->rep_attr.cap.max_inline_data = 0;