diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 487a58f9c192..d9c9f86a30df 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -367,6 +367,8 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev,
 
 	spin_lock_bh(&priv->stats_lock);
 
+	mlx4_en_fold_software_stats(dev);
+
 	for (i = 0; i < NUM_MAIN_STATS; i++, bitmap_iterator_inc(&it))
 		if (bitmap_iterator_test(&it))
 			data[index++] = ((unsigned long *)&dev->stats)[i];
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index ea76b28b728b..12ea3405f442 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1324,6 +1324,7 @@ mlx4_en_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
 	spin_lock_bh(&priv->stats_lock);
+	mlx4_en_fold_software_stats(dev);
 	netdev_stats_to_stats64(stats, &dev->stats);
 	spin_unlock_bh(&priv->stats_lock);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 1eb4c1e10bad..c6c4f1238923 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -147,6 +147,39 @@ static unsigned long en_stats_adder(__be64 *start, __be64 *next, int num)
 	return ret;
 }
 
+void mlx4_en_fold_software_stats(struct net_device *dev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	unsigned long packets, bytes;
+	int i;
+
+	if (mlx4_is_master(mdev->dev))
+		return;
+
+	packets = 0;
+	bytes = 0;
+	for (i = 0; i < priv->rx_ring_num; i++) {
+		const struct mlx4_en_rx_ring *ring = priv->rx_ring[i];
+
+		packets += READ_ONCE(ring->packets);
+		bytes   += READ_ONCE(ring->bytes);
+	}
+	dev->stats.rx_packets = packets;
+	dev->stats.rx_bytes = bytes;
+
+	packets = 0;
+	bytes = 0;
+	for (i = 0; i < priv->tx_ring_num[TX]; i++) {
+		const struct mlx4_en_tx_ring *ring = priv->tx_ring[TX][i];
+
+		packets += READ_ONCE(ring->packets);
+		bytes   += READ_ONCE(ring->bytes);
+	}
+	dev->stats.tx_packets = packets;
+	dev->stats.tx_bytes = bytes;
+}
+
 int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 {
 	struct mlx4_counter tmp_counter_stats;
@@ -159,6 +192,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	u64 in_mod = reset << 8 | port;
 	int err;
 	int i, counter_index;
+	unsigned long sw_tx_dropped = 0;
 	unsigned long sw_rx_dropped = 0;
 
 	mailbox = mlx4_alloc_cmd_mailbox(mdev->dev);
@@ -174,8 +208,8 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 
 	spin_lock_bh(&priv->stats_lock);
 
-	stats->rx_packets = 0;
-	stats->rx_bytes = 0;
+	mlx4_en_fold_software_stats(dev);
+
 	priv->port_stats.rx_chksum_good = 0;
 	priv->port_stats.rx_chksum_none = 0;
 	priv->port_stats.rx_chksum_complete = 0;
@@ -183,19 +217,16 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	priv->xdp_stats.rx_xdp_tx      = 0;
 	priv->xdp_stats.rx_xdp_tx_full = 0;
 	for (i = 0; i < priv->rx_ring_num; i++) {
-		stats->rx_packets += priv->rx_ring[i]->packets;
-		stats->rx_bytes += priv->rx_ring[i]->bytes;
-		sw_rx_dropped += priv->rx_ring[i]->dropped;
-		priv->port_stats.rx_chksum_good += priv->rx_ring[i]->csum_ok;
-		priv->port_stats.rx_chksum_none += priv->rx_ring[i]->csum_none;
-		priv->port_stats.rx_chksum_complete += priv->rx_ring[i]->csum_complete;
-		priv->xdp_stats.rx_xdp_drop    += priv->rx_ring[i]->xdp_drop;
-		priv->xdp_stats.rx_xdp_tx      += priv->rx_ring[i]->xdp_tx;
-		priv->xdp_stats.rx_xdp_tx_full += priv->rx_ring[i]->xdp_tx_full;
+		const struct mlx4_en_rx_ring *ring = priv->rx_ring[i];
+
+		sw_rx_dropped			+= READ_ONCE(ring->dropped);
+		priv->port_stats.rx_chksum_good += READ_ONCE(ring->csum_ok);
+		priv->port_stats.rx_chksum_none += READ_ONCE(ring->csum_none);
+		priv->port_stats.rx_chksum_complete += READ_ONCE(ring->csum_complete);
+		priv->xdp_stats.rx_xdp_drop	+= READ_ONCE(ring->xdp_drop);
+		priv->xdp_stats.rx_xdp_tx	+= READ_ONCE(ring->xdp_tx);
+		priv->xdp_stats.rx_xdp_tx_full	+= READ_ONCE(ring->xdp_tx_full);
 	}
-	stats->tx_packets = 0;
-	stats->tx_bytes = 0;
-	stats->tx_dropped = 0;
 	priv->port_stats.tx_chksum_offload = 0;
 	priv->port_stats.queue_stopped = 0;
 	priv->port_stats.wake_queue = 0;
@@ -205,15 +236,14 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	for (i = 0; i < priv->tx_ring_num[TX]; i++) {
 		const struct mlx4_en_tx_ring *ring = priv->tx_ring[TX][i];
 
-		stats->tx_packets += ring->packets;
-		stats->tx_bytes += ring->bytes;
-		stats->tx_dropped += ring->tx_dropped;
-		priv->port_stats.tx_chksum_offload += ring->tx_csum;
-		priv->port_stats.queue_stopped     += ring->queue_stopped;
-		priv->port_stats.wake_queue        += ring->wake_queue;
-		priv->port_stats.tso_packets       += ring->tso_packets;
-		priv->port_stats.xmit_more         += ring->xmit_more;
+		sw_tx_dropped			   += READ_ONCE(ring->tx_dropped);
+		priv->port_stats.tx_chksum_offload += READ_ONCE(ring->tx_csum);
+		priv->port_stats.queue_stopped     += READ_ONCE(ring->queue_stopped);
+		priv->port_stats.wake_queue        += READ_ONCE(ring->wake_queue);
+		priv->port_stats.tso_packets       += READ_ONCE(ring->tso_packets);
+		priv->port_stats.xmit_more         += READ_ONCE(ring->xmit_more);
 	}
+
 	if (mlx4_is_master(mdev->dev)) {
 		stats->rx_packets = en_stats_adder(&mlx4_en_stats->RTOT_prio_0,
 						   &mlx4_en_stats->RTOT_prio_1,
@@ -251,7 +281,8 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	stats->rx_length_errors = be32_to_cpu(mlx4_en_stats->RdropLength);
 	stats->rx_crc_errors = be32_to_cpu(mlx4_en_stats->RCRC);
 	stats->rx_fifo_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
-	stats->tx_dropped += be32_to_cpu(mlx4_en_stats->TDROP);
+	stats->tx_dropped = be32_to_cpu(mlx4_en_stats->TDROP) +
+			    sw_tx_dropped;
 
 	/* RX stats */
 	priv->pkstats.rx_multicast_packets = stats->multicast;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 574bcbb1b38f..20a936428f4a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -755,6 +755,7 @@ void mlx4_en_rx_irq(struct mlx4_cq *mcq);
 int mlx4_SET_MCAST_FLTR(struct mlx4_dev *dev, u8 port, u64 mac, u64 clear, u8 mode);
 int mlx4_SET_VLAN_FLTR(struct mlx4_dev *dev, struct mlx4_en_priv *priv);
 
+void mlx4_en_fold_software_stats(struct net_device *dev);
 int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset);
 int mlx4_en_QUERY_PORT(struct mlx4_en_dev *mdev, u8 port);