net/mlx5e: Separate between ethtool and netdev software stats folding

mlx5e_grp_sw_update_stats can be called from two threads,
1) ndo_get_stats64
2) get_ethtool_stats

For this reason and to minimize concurrency issue impact on 64bit machines
mlx5e_grp_sw_update_stats folds the software stats into a temporary
variable then copies it to the global driver stats, both ethtool and ndo
statistics callbacks will use the global software stats variable to report
whatever stats they need.

Actually ndo_get_stats64 doesn't need to fold the whole software stats
(mlx5e_grp_sw_update_stats), all it needs is five counters to fill the
rtnl_link_stats64 relevant stats parameter.

Hence this patch introduces a simpler helper function to fold software
stats for ndo_get_stats64 which will work directly on rtnl_link_stats64
stats parameter and not on the global or even temporary mlx5e_sw_stats
variable.

Since now mlx5e_grp_sw_update_stats is not called by ndo_get_stats64 we
can make it static and remove the temp var.

Unlike mlx5e_grp_sw_update_stats the new fold stats function doesn't
need to zero out the output statistics parameter since it is already
done by the stack @dev_get_stats().

This patch is fixing stack usage of mlx5e_grp_sw_update_stats on
x86 gcc-4.9 and higher, the concurrency issue between mlx5's
ndo_get_stats64 and get_ethtool_stats is resolved as well.

Fixes: 8bfaf07f ("net/mlx5e: Present SW stats when state is not opened")
Reported-by: Arnd Bergmann <arnd@arndb.de>
Reported-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -3521,11 +3521,32 @@ static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	}
 }
 
+static void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s)
+{
+	int i;
+
+	for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++) {
+		struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i];
+		struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
+		int j;
+
+		s->rx_packets   += rq_stats->packets;
+		s->rx_bytes     += rq_stats->bytes;
+
+		for (j = 0; j < priv->max_opened_tc; j++) {
+			struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
+
+			s->tx_packets    += sq_stats->packets;
+			s->tx_bytes      += sq_stats->bytes;
+			s->tx_dropped    += sq_stats->dropped;
+		}
+	}
+}
+
 void
 mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_sw_stats *sstats = &priv->stats.sw;
 	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 
@@ -3540,12 +3561,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 		stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok);
 		stats->tx_bytes   = PPORT_802_3_GET(pstats, a_octets_transmitted_ok);
 	} else {
-		mlx5e_grp_sw_update_stats(priv);
-		stats->rx_packets = sstats->rx_packets;
-		stats->rx_bytes   = sstats->rx_bytes;
-		stats->tx_packets = sstats->tx_packets;
-		stats->tx_bytes   = sstats->tx_bytes;
-		stats->tx_dropped = sstats->tx_queue_dropped;
+		mlx5e_fold_sw_stats64(priv, stats);
 	}
 
 	stats->rx_dropped = priv->stats.qcnt.rx_out_of_buffer;

drivers/net/ethernet/mellanox/mlx5/core/en_stats.c

@@ -127,9 +127,9 @@ static int mlx5e_grp_sw_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
 	return idx;
 }
 
-void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
+static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 {
-	struct mlx5e_sw_stats temp, *s = &temp;
+	struct mlx5e_sw_stats *s = &priv->stats.sw;
 	int i;
 
 	memset(s, 0, sizeof(*s));
@@ -212,8 +212,6 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_cqes		+= sq_stats->cqes;
 		}
 	}
-
-	memcpy(&priv->stats.sw, s, sizeof(*s));
 }
 
 static const struct counter_desc q_stats_desc[] = {

drivers/net/ethernet/mellanox/mlx5/core/en_stats.h

@@ -277,7 +277,6 @@ struct mlx5e_stats_grp {
 extern const struct mlx5e_stats_grp mlx5e_stats_grps[];
 extern const int mlx5e_num_stats_grps;
 
-void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv);
 void mlx5e_grp_802_3_update_stats(struct mlx5e_priv *priv);
 
 #endif /* __MLX5_EN_STATS_H__ */