net/mlx4_en: Optimize loopback related checks in data path

Currently there are relatively complex conditional checks in the fast path,
for TX loopback enabling and resulting RX filter logic.
Move elaborate if's out of data path, replace them with a single flag
for each state and update that state from appropriate places.
Also, in native (non SRIOV) mode and not in loopback or in selftest,
there is no need to try and filter out packets that HW loopback-ed,
as in native mode we do not loopback packets anymore.
Signed-off-by: NYan Burman <yanb@mellanox.com>
Signed-off-by: NAmir Vadai <amirv@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx4/en_main.c

@@ -95,6 +95,28 @@ int en_print(const char *level, const struct mlx4_en_priv *priv,
 	return i;
 }
 
+void mlx4_en_update_loopback_state(struct net_device *dev,
+				   netdev_features_t features)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	priv->flags &= ~(MLX4_EN_FLAG_RX_FILTER_NEEDED|
+			MLX4_EN_FLAG_ENABLE_HW_LOOPBACK);
+
+	/* Drop the packet if SRIOV is not enabled
+	 * and not performing the selftest or flb disabled
+	 */
+	if (mlx4_is_mfunc(priv->mdev->dev) &&
+	    !(features & NETIF_F_LOOPBACK) && !priv->validate_loopback)
+		priv->flags |= MLX4_EN_FLAG_RX_FILTER_NEEDED;
+
+	/* Set dmac in Tx WQE if we are in SRIOV mode or if loopback selftest
+	 * is requested
+	 */
+	if (mlx4_is_mfunc(priv->mdev->dev) || priv->validate_loopback)
+		priv->flags |= MLX4_EN_FLAG_ENABLE_HW_LOOPBACK;
+}
+
 static int mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 {
 	struct mlx4_en_profile *params = &mdev->profile;

drivers/net/ethernet/mellanox/mlx4/en_netdev.c

@@ -1563,6 +1563,8 @@ static int mlx4_en_set_features(struct net_device *netdev,
 		priv->ctrl_flags &=
 			cpu_to_be32(~MLX4_WQE_CTRL_FORCE_LOOPBACK);
 
+	mlx4_en_update_loopback_state(netdev, features);
+
 	return 0;
 
 }
@@ -1731,6 +1733,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	en_warn(priv, "Using %d TX rings\n", prof->tx_ring_num);
 	en_warn(priv, "Using %d RX rings\n", prof->rx_ring_num);
 
+	mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
+
 	/* Configure port */
 	mlx4_en_calc_rx_buf(dev);
 	err = mlx4_SET_PORT_general(mdev->dev, priv->port,

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -563,9 +563,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	unsigned int length;
 	int polled = 0;
 	int ip_summed;
-	struct ethhdr *ethh;
-	dma_addr_t dma;
-	u64 s_mac;
 	int factor = priv->cqe_factor;
 
 	if (!priv->port_up)
@@ -603,21 +600,27 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			goto next;
 		}
 
-		/* Get pointer to first fragment since we haven't skb yet and
-		 * cast it to ethhdr struct */
+		/* Check if we need to drop the packet if SRIOV is not enabled
+		 * and not performing the selftest or flb disabled
+		 */
+		if (priv->flags & MLX4_EN_FLAG_RX_FILTER_NEEDED) {
+			struct ethhdr *ethh;
+			dma_addr_t dma;
+			u64 s_mac;
+			/* Get pointer to first fragment since we haven't
+			 * skb yet and cast it to ethhdr struct
+			 */
 			dma = be64_to_cpu(rx_desc->data[0].addr);
 			dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh),
 						DMA_FROM_DEVICE);
 			ethh = (struct ethhdr *)(page_address(frags[0].page) +
 						 frags[0].offset);
-		s_mac = mlx4_en_mac_to_u64(ethh->h_source);
 
-		/* If source MAC is equal to our own MAC and not performing
-		 * the selftest or flb disabled - drop the packet */
-		if (s_mac == priv->mac &&
-		    !((dev->features & NETIF_F_LOOPBACK) ||
-		      priv->validate_loopback))
+			/* Drop the packet, since HW loopback-ed it */
+			s_mac = mlx4_en_mac_to_u64(ethh->h_source);
+			if (s_mac == priv->mac)
 				goto next;
+		}
 
 		/*
 		 * Packet is OK - process it.

drivers/net/ethernet/mellanox/mlx4/en_selftest.c

@@ -87,6 +87,8 @@ static int mlx4_en_test_loopback(struct mlx4_en_priv *priv)
         priv->loopback_ok = 0;
 	priv->validate_loopback = 1;
 
+	mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
+
 	/* xmit */
 	if (mlx4_en_test_loopback_xmit(priv)) {
 		en_err(priv, "Transmitting loopback packet failed\n");
@@ -107,6 +109,7 @@ static int mlx4_en_test_loopback(struct mlx4_en_priv *priv)
 mlx4_en_test_loopback_exit:
 
 	priv->validate_loopback = 0;
+	mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
 	return !loopback_ok;
 }
 

drivers/net/ethernet/mellanox/mlx4/en_tx.c

@@ -640,7 +640,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		ring->tx_csum++;
 	}
 
-	if (mlx4_is_mfunc(mdev->dev) || priv->validate_loopback) {
+	if (priv->flags & MLX4_EN_FLAG_ENABLE_HW_LOOPBACK) {
 		/* Copy dst mac address to wqe. This allows loopback in eSwitch,
 		 * so that VFs and PF can communicate with each other
 		 */

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -432,6 +432,17 @@ struct ethtool_flow_id {
 	u64 id;
 };
 
+enum {
+	MLX4_EN_FLAG_PROMISC		= (1 << 0),
+	MLX4_EN_FLAG_MC_PROMISC		= (1 << 1),
+	/* whether we need to enable hardware loopback by putting dmac
+	 * in Tx WQE
+	 */
+	MLX4_EN_FLAG_ENABLE_HW_LOOPBACK	= (1 << 2),
+	/* whether we need to drop packets that hardware loopback-ed */
+	MLX4_EN_FLAG_RX_FILTER_NEEDED	= (1 << 3)
+};
+
 struct mlx4_en_priv {
 	struct mlx4_en_dev *mdev;
 	struct mlx4_en_port_profile *prof;
@@ -481,8 +492,6 @@ struct mlx4_en_priv {
 	struct mlx4_en_rss_map rss_map;
 	__be32 ctrl_flags;
 	u32 flags;
-#define MLX4_EN_FLAG_PROMISC	0x1
-#define MLX4_EN_FLAG_MC_PROMISC	0x2
 	u8 num_tx_rings_p_up;
 	u32 tx_ring_num;
 	u32 rx_ring_num;
@@ -534,6 +543,9 @@ enum mlx4_en_wol {
 
 #define MLX4_EN_WOL_DO_MODIFY (1ULL << 63)
 
+void mlx4_en_update_loopback_state(struct net_device *dev,
+				   netdev_features_t features);
+
 void mlx4_en_destroy_netdev(struct net_device *dev);
 int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 			struct mlx4_en_port_profile *prof);