nfp: add a separate counter for packets with CHECKSUM_COMPLETE

We are currently counting packets with CHECKSUM_COMPLETE as
"hw_rx_csum_ok".  This is confusing.  Add a new counter.
To make sure it fits in the same cacheline move the less used
error counter to a different location.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/netronome/nfp/nfp_net.h

@@ -391,6 +391,7 @@ struct nfp_net_rx_ring {
  * @rx_drops:	    Number of packets dropped on RX due to lack of resources
  * @hw_csum_rx_ok:  Counter of packets where the HW checksum was OK
  * @hw_csum_rx_inner_ok: Counter of packets where the inner HW checksum was OK
+ * @hw_csum_rx_complete: Counter of packets with CHECKSUM_COMPLETE reported
  * @hw_csum_rx_error:	 Counter of packets with bad checksums
  * @tx_sync:	    Seqlock for atomic updates of TX stats
  * @tx_pkts:	    Number of Transmitted packets
@@ -434,7 +435,7 @@ struct nfp_net_r_vector {
 	u64 rx_drops;
 	u64 hw_csum_rx_ok;
 	u64 hw_csum_rx_inner_ok;
-	u64 hw_csum_rx_error;
+	u64 hw_csum_rx_complete;
 
 	struct nfp_net_tx_ring *xdp_ring;
 
@@ -446,6 +447,7 @@ struct nfp_net_r_vector {
 	u64 tx_gather;
 	u64 tx_lso;
 
+	u64 hw_csum_rx_error;
 	u64 rx_replace_buf_alloc_fail;
 	u64 tx_errors;
 	u64 tx_busy;

drivers/net/ethernet/netronome/nfp/nfp_net_common.c

@@ -1406,7 +1406,7 @@ static void nfp_net_rx_csum(struct nfp_net_dp *dp,
 		skb->ip_summed = meta->csum_type;
 		skb->csum = meta->csum;
 		u64_stats_update_begin(&r_vec->rx_sync);
-		r_vec->hw_csum_rx_ok++;
+		r_vec->hw_csum_rx_complete++;
 		u64_stats_update_end(&r_vec->rx_sync);
 		return;
 	}

drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c

@@ -179,7 +179,7 @@ static const struct nfp_et_stat nfp_mac_et_stats[] = {
 
 #define NN_ET_GLOBAL_STATS_LEN ARRAY_SIZE(nfp_net_et_stats)
 #define NN_ET_SWITCH_STATS_LEN 9
-#define NN_RVEC_GATHER_STATS	8
+#define NN_RVEC_GATHER_STATS	9
 #define NN_RVEC_PER_Q_STATS	3
 
 static void nfp_net_get_nspinfo(struct nfp_app *app, char *version)
@@ -468,6 +468,7 @@ static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data)
 
 	data = nfp_pr_et(data, "hw_rx_csum_ok");
 	data = nfp_pr_et(data, "hw_rx_csum_inner_ok");
+	data = nfp_pr_et(data, "hw_rx_csum_complete");
 	data = nfp_pr_et(data, "hw_rx_csum_err");
 	data = nfp_pr_et(data, "rx_replace_buf_alloc_fail");
 	data = nfp_pr_et(data, "hw_tx_csum");
@@ -493,18 +494,19 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 			data[0] = nn->r_vecs[i].rx_pkts;
 			tmp[0] = nn->r_vecs[i].hw_csum_rx_ok;
 			tmp[1] = nn->r_vecs[i].hw_csum_rx_inner_ok;
-			tmp[2] = nn->r_vecs[i].hw_csum_rx_error;
-			tmp[3] = nn->r_vecs[i].rx_replace_buf_alloc_fail;
+			tmp[2] = nn->r_vecs[i].hw_csum_rx_complete;
+			tmp[3] = nn->r_vecs[i].hw_csum_rx_error;
+			tmp[4] = nn->r_vecs[i].rx_replace_buf_alloc_fail;
 		} while (u64_stats_fetch_retry(&nn->r_vecs[i].rx_sync, start));
 
 		do {
 			start = u64_stats_fetch_begin(&nn->r_vecs[i].tx_sync);
 			data[1] = nn->r_vecs[i].tx_pkts;
 			data[2] = nn->r_vecs[i].tx_busy;
-			tmp[4] = nn->r_vecs[i].hw_csum_tx;
-			tmp[5] = nn->r_vecs[i].hw_csum_tx_inner;
-			tmp[6] = nn->r_vecs[i].tx_gather;
-			tmp[7] = nn->r_vecs[i].tx_lso;
+			tmp[5] = nn->r_vecs[i].hw_csum_tx;
+			tmp[6] = nn->r_vecs[i].hw_csum_tx_inner;
+			tmp[7] = nn->r_vecs[i].tx_gather;
+			tmp[8] = nn->r_vecs[i].tx_lso;
 		} while (u64_stats_fetch_retry(&nn->r_vecs[i].tx_sync, start));
 
 		data += NN_RVEC_PER_Q_STATS;