net/mlx5e: Use PARTIAL_GSO for UDP segmentation

This patch removes the splitting of UDP_GSO_L4 packets in the driver,
and exposes UDP_GSO_L4 as a PARTIAL_GSO feature. Thus, the network stack
is not responsible for splitting the packet into two.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

drivers/net/ethernet/mellanox/mlx5/core/Makefile

@@ -14,8 +14,8 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
 		fpga/ipsec.o fpga/tls.o
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
-		en_tx.o en_rx.o en_dim.o en_txrx.o en_accel/rxtx.o en_stats.o  \
-		vxlan.o en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
+		en_tx.o en_rx.o en_dim.o en_txrx.o en_stats.o vxlan.o          \
+		en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
 
 mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
 

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

@@ -38,14 +38,22 @@
 #include <linux/netdevice.h>
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/tls_rxtx.h"
-#include "en_accel/rxtx.h"
 #include "en.h"
 
-static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
-						    struct mlx5e_txqsq *sq,
-						    struct net_device *dev,
-						    struct mlx5e_tx_wqe **wqe,
-						    u16 *pi)
+static inline void
+mlx5e_udp_gso_handle_tx_skb(struct sk_buff *skb)
+{
+	int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr);
+
+	udp_hdr(skb)->len = htons(payload_len);
+}
+
+static inline struct sk_buff *
+mlx5e_accel_handle_tx(struct sk_buff *skb,
+		      struct mlx5e_txqsq *sq,
+		      struct net_device *dev,
+		      struct mlx5e_tx_wqe **wqe,
+		      u16 *pi)
 {
 #ifdef CONFIG_MLX5_EN_TLS
 	if (test_bit(MLX5E_SQ_STATE_TLS, &sq->state)) {
@@ -63,11 +71,8 @@ static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
 	}
 #endif
 
-	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
-		skb = mlx5e_udp_gso_handle_tx_skb(dev, sq, skb, wqe, pi);
-		if (unlikely(!skb))
-			return NULL;
-	}
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+		mlx5e_udp_gso_handle_tx_skb(skb);
 
 	return skb;
 }

drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c

@@ -1,109 +0,0 @@
-#include "en_accel/rxtx.h"
-
-static void mlx5e_udp_gso_prepare_last_skb(struct sk_buff *skb,
-					   struct sk_buff *nskb,
-					   int remaining)
-{
-	int bytes_needed = remaining, remaining_headlen, remaining_page_offset;
-	int headlen = skb_transport_offset(skb) + sizeof(struct udphdr);
-	int payload_len = remaining + sizeof(struct udphdr);
-	int k = 0, i, j;
-
-	skb_copy_bits(skb, 0, nskb->data, headlen);
-	nskb->dev = skb->dev;
-	skb_reset_mac_header(nskb);
-	skb_set_network_header(nskb, skb_network_offset(skb));
-	skb_set_transport_header(nskb, skb_transport_offset(skb));
-	skb_set_tail_pointer(nskb, headlen);
-
-	/* How many frags do we need? */
-	for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) {
-		bytes_needed -= skb_frag_size(&skb_shinfo(skb)->frags[i]);
-		k++;
-		if (bytes_needed <= 0)
-			break;
-	}
-
-	/* Fill the first frag and split it if necessary */
-	j = skb_shinfo(skb)->nr_frags - k;
-	remaining_page_offset = -bytes_needed;
-	skb_fill_page_desc(nskb, 0,
-			   skb_shinfo(skb)->frags[j].page.p,
-			   skb_shinfo(skb)->frags[j].page_offset + remaining_page_offset,
-			   skb_shinfo(skb)->frags[j].size - remaining_page_offset);
-
-	skb_frag_ref(skb, j);
-
-	/* Fill the rest of the frags */
-	for (i = 1; i < k; i++) {
-		j = skb_shinfo(skb)->nr_frags - k + i;
-
-		skb_fill_page_desc(nskb, i,
-				   skb_shinfo(skb)->frags[j].page.p,
-				   skb_shinfo(skb)->frags[j].page_offset,
-				   skb_shinfo(skb)->frags[j].size);
-		skb_frag_ref(skb, j);
-	}
-	skb_shinfo(nskb)->nr_frags = k;
-
-	remaining_headlen = remaining - skb->data_len;
-
-	/* headlen contains remaining data? */
-	if (remaining_headlen > 0)
-		skb_copy_bits(skb, skb->len - remaining, nskb->data + headlen,
-			      remaining_headlen);
-	nskb->len = remaining + headlen;
-	nskb->data_len =  payload_len - sizeof(struct udphdr) +
-		max_t(int, 0, remaining_headlen);
-	nskb->protocol = skb->protocol;
-	if (nskb->protocol == htons(ETH_P_IP)) {
-		ip_hdr(nskb)->id = htons(ntohs(ip_hdr(nskb)->id) +
-					 skb_shinfo(skb)->gso_segs);
-		ip_hdr(nskb)->tot_len =
-			htons(payload_len + sizeof(struct iphdr));
-	} else {
-		ipv6_hdr(nskb)->payload_len = htons(payload_len);
-	}
-	udp_hdr(nskb)->len = htons(payload_len);
-	skb_shinfo(nskb)->gso_size = 0;
-	nskb->ip_summed = skb->ip_summed;
-	nskb->csum_start = skb->csum_start;
-	nskb->csum_offset = skb->csum_offset;
-	nskb->queue_mapping = skb->queue_mapping;
-}
-
-/* might send skbs and update wqe and pi */
-struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev,
-					    struct mlx5e_txqsq *sq,
-					    struct sk_buff *skb,
-					    struct mlx5e_tx_wqe **wqe,
-					    u16 *pi)
-{
-	int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr);
-	int headlen = skb_transport_offset(skb) + sizeof(struct udphdr);
-	int remaining = (skb->len - headlen) % skb_shinfo(skb)->gso_size;
-	struct sk_buff *nskb;
-
-	if (skb->protocol == htons(ETH_P_IP))
-		ip_hdr(skb)->tot_len = htons(payload_len + sizeof(struct iphdr));
-	else
-		ipv6_hdr(skb)->payload_len = htons(payload_len);
-	udp_hdr(skb)->len = htons(payload_len);
-	if (!remaining)
-		return skb;
-
-	sq->stats->udp_seg_rem++;
-	nskb = alloc_skb(max_t(int, headlen, headlen + remaining - skb->data_len), GFP_ATOMIC);
-	if (unlikely(!nskb)) {
-		sq->stats->dropped++;
-		return NULL;
-	}
-
-	mlx5e_udp_gso_prepare_last_skb(skb, nskb, remaining);
-
-	skb_shinfo(skb)->gso_segs--;
-	pskb_trim(skb, skb->len - remaining);
-	mlx5e_sq_xmit(sq, skb, *wqe, *pi);
-	mlx5e_sq_fetch_wqe(sq, wqe, pi);
-	return nskb;
-}

drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h

@@ -1,14 +0,0 @@
-
-#ifndef __MLX5E_EN_ACCEL_RX_TX_H__
-#define __MLX5E_EN_ACCEL_RX_TX_H__
-
-#include <linux/skbuff.h>
-#include "en.h"
-
-struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev,
-					    struct mlx5e_txqsq *sq,
-					    struct sk_buff *skb,
-					    struct mlx5e_tx_wqe **wqe,
-					    u16 *pi);
-
-#endif

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

@@ -4538,7 +4538,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->hw_features      |= NETIF_F_HW_VLAN_STAG_TX;
 
 	if (mlx5e_vxlan_allowed(mdev) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
-		netdev->hw_features     |= NETIF_F_GSO_PARTIAL;
 		netdev->hw_enc_features |= NETIF_F_IP_CSUM;
 		netdev->hw_enc_features |= NETIF_F_IPV6_CSUM;
 		netdev->hw_enc_features |= NETIF_F_TSO;
@@ -4563,6 +4562,11 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 						NETIF_F_GSO_GRE_CSUM;
 	}
 
+	netdev->hw_features	                 |= NETIF_F_GSO_PARTIAL;
+	netdev->gso_partial_features             |= NETIF_F_GSO_UDP_L4;
+	netdev->hw_features                      |= NETIF_F_GSO_UDP_L4;
+	netdev->features                         |= NETIF_F_GSO_UDP_L4;
+
 	mlx5_query_port_fcs(mdev, &fcs_supported, &fcs_enabled);
 
 	if (fcs_supported)
@@ -4595,9 +4599,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->features         |= NETIF_F_HIGHDMA;
 	netdev->features         |= NETIF_F_HW_VLAN_STAG_FILTER;
 
-	netdev->features         |= NETIF_F_GSO_UDP_L4;
-	netdev->hw_features      |= NETIF_F_GSO_UDP_L4;
-
 	netdev->priv_flags       |= IFF_UNICAST_FLT;
 
 	mlx5e_set_netdev_dev_addr(netdev);