bnxt_en: Enhance TX pri counters

The priority packet and byte counters in ethtool -S are returned by
the driver based on the pri2cos mapping.  The assumption is that each
priority is mapped to one and only one hardware CoS queue.  In a
special RoCE configuration, the FW uses combined CoS queue 0 and CoS
queue 1 for the priority mapped to CoS queue 0.  In this special
case, we need to add the CoS queue 0 and CoS queue 1 counters for
the priority packet and byte counters.

Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20251126215648.1885936-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: Michael Chan

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -8506,6 +8506,11 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 
 	if (flags & FUNC_QCFG_RESP_FLAGS_ENABLE_RDMA_SRIOV)
 		bp->fw_cap |= BNXT_FW_CAP_ENABLE_RDMA_SRIOV;
+	if (resp->roce_bidi_opt_mode &
+	    FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_DEDICATED)
+		bp->cos0_cos1_shared = 1;
+	else
+		bp->cos0_cos1_shared = 0;
 
 	switch (resp->port_partition_type) {
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0:

drivers/net/ethernet/broadcom/bnxt/bnxt.h

@@ -2424,6 +2424,7 @@ struct bnxt {
 	u8			tc_to_qidx[BNXT_MAX_QUEUE];
 	u8			q_ids[BNXT_MAX_QUEUE];
 	u8			max_q;
+	u8			cos0_cos1_shared;
 	u8			num_tc;
 
 	u16			max_pfcwd_tmo_ms;

drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c

@@ -688,16 +688,22 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 				buf[j] = *(rx_port_stats_ext + n);
 			}
 			for (i = 0; i < 8; i++, j++) {
-				long n = bnxt_tx_bytes_pri_arr[i].base_off +
-					 bp->pri2cos_idx[i];
+				u8 cos_idx = bp->pri2cos_idx[i];
+				long n;
 
+				n = bnxt_tx_bytes_pri_arr[i].base_off + cos_idx;
 				buf[j] = *(tx_port_stats_ext + n);
+				if (bp->cos0_cos1_shared && !cos_idx)
+					buf[j] += *(tx_port_stats_ext + n + 1);
 			}
 			for (i = 0; i < 8; i++, j++) {
-				long n = bnxt_tx_pkts_pri_arr[i].base_off +
-					 bp->pri2cos_idx[i];
+				u8 cos_idx = bp->pri2cos_idx[i];
+				long n;
 
+				n = bnxt_tx_pkts_pri_arr[i].base_off + cos_idx;
 				buf[j] = *(tx_port_stats_ext + n);
+				if (bp->cos0_cos1_shared && !cos_idx)
+					buf[j] += *(tx_port_stats_ext + n + 1);
 			}
 		}
 	}