net: stmmac: fix ethtool per-queue statistics

Fix per-queue statistics for devices with more than one queue.

The output data pointer is currently reset in each loop iteration,
effectively summing all queue statistics in the first four u64 values.

The summary values are not even labeled correctly. For example, if eth0 has
2 queues, ethtool -S eth0 shows:

     q0_tx_pkt_n: 374 (actually tx_pkt_n over all queues)
     q0_tx_irq_n: 23  (actually tx_normal_irq_n over all queues)
     q1_tx_pkt_n: 462 (actually rx_pkt_n over all queues)
     q1_tx_irq_n: 446 (actually rx_normal_irq_n over all queues)
     q0_rx_pkt_n: 0
     q0_rx_irq_n: 0
     q1_rx_pkt_n: 0
     q1_rx_irq_n: 0

Fixes: 133466c3 ("net: stmmac: use per-queue 64 bit statistics where necessary")
Cc: stable@vger.kernel.org
Signed-off-by: Petr Tesarik <petr@tesarici.cz>
Reviewed-by: Jisheng Zhang <jszhang@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c

@@ -543,15 +543,12 @@ static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
 	u32 rx_cnt = priv->plat->rx_queues_to_use;
 	unsigned int start;
 	int q, stat;
-	u64 *pos;
 	char *p;
 
-	pos = data;
 	for (q = 0; q < tx_cnt; q++) {
 		struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[q];
 		struct stmmac_txq_stats snapshot;
 
-		data = pos;
 		do {
 			start = u64_stats_fetch_begin(&txq_stats->syncp);
 			snapshot = *txq_stats;
@@ -559,17 +556,15 @@ static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
 
 		p = (char *)&snapshot + offsetof(struct stmmac_txq_stats, tx_pkt_n);
 		for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) {
-			*data++ += (*(u64 *)p);
+			*data++ = (*(u64 *)p);
 			p += sizeof(u64);
 		}
 	}
 
-	pos = data;
 	for (q = 0; q < rx_cnt; q++) {
 		struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[q];
 		struct stmmac_rxq_stats snapshot;
 
-		data = pos;
 		do {
 			start = u64_stats_fetch_begin(&rxq_stats->syncp);
 			snapshot = *rxq_stats;
@@ -577,7 +572,7 @@ static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
 
 		p = (char *)&snapshot + offsetof(struct stmmac_rxq_stats, rx_pkt_n);
 		for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) {
-			*data++ += (*(u64 *)p);
+			*data++ = (*(u64 *)p);
 			p += sizeof(u64);
 		}
 	}