tg3: Move the [rt]x_dropped counters to tg3_napi

This change moves [rt]x_dropped counters to tg3_napi so that they can be
updated by a single writer, race-free.

Signed-off-by: Alex Pakhunov <alexey.pakhunov@spacex.com>
Signed-off-by: Vincent Wong <vincent.wong2@spacex.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20231113182350.37472-1-alexey.pakhunov@spacex.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: Alex Pakhunov

drivers/net/ethernet/broadcom/tg3.c

@@ -6889,7 +6889,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 				       desc_idx, *post_ptr);
 		drop_it_no_recycle:
 			/* Other statistics kept track of by card. */
-			tp->rx_dropped++;
+			tnapi->rx_dropped++;
 			goto next_pkt;
 		}
 
@@ -8190,7 +8190,7 @@ static netdev_tx_t __tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 drop:
 	dev_kfree_skb_any(skb);
 drop_nofree:
-	tp->tx_dropped++;
+	tnapi->tx_dropped++;
 	return NETDEV_TX_OK;
 }
 
@@ -9405,7 +9405,7 @@ static void __tg3_set_rx_mode(struct net_device *);
 /* tp->lock is held. */
 static int tg3_halt(struct tg3 *tp, int kind, bool silent)
 {
-	int err;
+	int err, i;
 
 	tg3_stop_fw(tp);
 
@@ -9426,6 +9426,13 @@ static int tg3_halt(struct tg3 *tp, int kind, bool silent)
 
 		/* And make sure the next sample is new data */
 		memset(tp->hw_stats, 0, sizeof(struct tg3_hw_stats));
+
+		for (i = 0; i < TG3_IRQ_MAX_VECS; ++i) {
+			struct tg3_napi *tnapi = &tp->napi[i];
+
+			tnapi->rx_dropped = 0;
+			tnapi->tx_dropped = 0;
+		}
 	}
 
 	return err;
@@ -11975,6 +11982,9 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats)
 {
 	struct rtnl_link_stats64 *old_stats = &tp->net_stats_prev;
 	struct tg3_hw_stats *hw_stats = tp->hw_stats;
+	unsigned long rx_dropped;
+	unsigned long tx_dropped;
+	int i;
 
 	stats->rx_packets = old_stats->rx_packets +
 		get_stat64(&hw_stats->rx_ucast_packets) +
@@ -12021,8 +12031,26 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats)
 	stats->rx_missed_errors = old_stats->rx_missed_errors +
 		get_stat64(&hw_stats->rx_discards);
 
-	stats->rx_dropped = tp->rx_dropped;
-	stats->tx_dropped = tp->tx_dropped;
+	/* Aggregate per-queue counters. The per-queue counters are updated
+	 * by a single writer, race-free. The result computed by this loop
+	 * might not be 100% accurate (counters can be updated in the middle of
+	 * the loop) but the next tg3_get_nstats() will recompute the current
+	 * value so it is acceptable.
+	 *
+	 * Note that these counters wrap around at 4G on 32bit machines.
+	 */
+	rx_dropped = (unsigned long)(old_stats->rx_dropped);
+	tx_dropped = (unsigned long)(old_stats->tx_dropped);
+
+	for (i = 0; i < tp->irq_cnt; i++) {
+		struct tg3_napi *tnapi = &tp->napi[i];
+
+		rx_dropped += tnapi->rx_dropped;
+		tx_dropped += tnapi->tx_dropped;
+	}
+
+	stats->rx_dropped = rx_dropped;
+	stats->tx_dropped = tx_dropped;
 }
 
 static int tg3_get_regs_len(struct net_device *dev)

drivers/net/ethernet/broadcom/tg3.h

@@ -3018,6 +3018,7 @@ struct tg3_napi {
 	u16				*rx_rcb_prod_idx;
 	struct tg3_rx_prodring_set	prodring;
 	struct tg3_rx_buffer_desc	*rx_rcb;
+	unsigned long			rx_dropped;
 
 	u32				tx_prod	____cacheline_aligned;
 	u32				tx_cons;
@@ -3026,6 +3027,7 @@ struct tg3_napi {
 	u32				prodmbox;
 	struct tg3_tx_buffer_desc	*tx_ring;
 	struct tg3_tx_ring_info		*tx_buffers;
+	unsigned long			tx_dropped;
 
 	dma_addr_t			status_mapping;
 	dma_addr_t			rx_rcb_mapping;
@@ -3220,8 +3222,6 @@ struct tg3 {
 
 
 	/* begin "everything else" cacheline(s) section */
-	unsigned long			rx_dropped;
-	unsigned long			tx_dropped;
 	struct rtnl_link_stats64	net_stats_prev;
 	struct tg3_ethtool_stats	estats_prev;