staging/hfi1: Fix Xmit Wait calculation

Total XMIT wait needs to sum the xmit wait values of all the VLs not just
those requested in the query.  Also, make the algorithm used for both
PortStatus and PortDataCounters the same.

Reviewed-by: Arthur Kepner <arthur.kepner@intel.com>
Reviewed-by: Breyer, Scott J <scott.j.breyer@intel.com>
Signed-off-by: Ira Weiny <iweiny@gmail.com>
Signed-off-by: Jubin John <jubin.john@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/staging/rdma/hfi1/mad.c

@@ -2279,17 +2279,23 @@ static void a0_portstatus(struct hfi1_pportdata *ppd,
 {
 	if (!is_bx(ppd->dd)) {
 		unsigned long vl;
-		u64 max_vl_xmit_wait = 0, tmp;
+		u64 sum_vl_xmit_wait = 0;
 		u32 vl_all_mask = VL_MASK_ALL;
 
 		for_each_set_bit(vl, (unsigned long *)&(vl_all_mask),
 				 8 * sizeof(vl_all_mask)) {
-			tmp = read_port_cntr(ppd, C_TX_WAIT_VL,
-					     idx_from_vl(vl));
-			if (tmp > max_vl_xmit_wait)
-				max_vl_xmit_wait = tmp;
+			u64 tmp = sum_vl_xmit_wait +
+				  read_port_cntr(ppd, C_TX_WAIT_VL,
+						 idx_from_vl(vl));
+			if (tmp < sum_vl_xmit_wait) {
+				/* we wrapped */
+				sum_vl_xmit_wait = (u64)~0;
+				break;
+			}
+			sum_vl_xmit_wait = tmp;
 		}
-		rsp->port_xmit_wait = cpu_to_be64(max_vl_xmit_wait);
+		if (be64_to_cpu(rsp->port_xmit_wait) > sum_vl_xmit_wait)
+			rsp->port_xmit_wait = cpu_to_be64(sum_vl_xmit_wait);
 	}
 }
 
@@ -2491,18 +2497,19 @@ static u64 get_error_counter_summary(struct ib_device *ibdev, u8 port,
 	return error_counter_summary;
 }
 
-static void a0_datacounters(struct hfi1_devdata *dd, struct _port_dctrs *rsp,
+static void a0_datacounters(struct hfi1_pportdata *ppd, struct _port_dctrs *rsp,
 			    u32 vl_select_mask)
 {
-	if (!is_bx(dd)) {
+	if (!is_bx(ppd->dd)) {
 		unsigned long vl;
-		int vfi = 0;
 		u64 sum_vl_xmit_wait = 0;
+		u32 vl_all_mask = VL_MASK_ALL;
 
-		for_each_set_bit(vl, (unsigned long *)&(vl_select_mask),
-				8 * sizeof(vl_select_mask)) {
+		for_each_set_bit(vl, (unsigned long *)&(vl_all_mask),
+				 8 * sizeof(vl_all_mask)) {
 			u64 tmp = sum_vl_xmit_wait +
-				be64_to_cpu(rsp->vls[vfi++].port_vl_xmit_wait);
+				  read_port_cntr(ppd, C_TX_WAIT_VL,
+						 idx_from_vl(vl));
 			if (tmp < sum_vl_xmit_wait) {
 				/* we wrapped */
 				sum_vl_xmit_wait = (u64) ~0;
@@ -2665,7 +2672,7 @@ static int pma_get_opa_datacounters(struct opa_pma_mad *pmp,
 		vfi++;
 	}
 
-	a0_datacounters(dd, rsp, vl_select_mask);
+	a0_datacounters(ppd, rsp, vl_select_mask);
 
 	if (resp_len)
 		*resp_len += response_data_size;