mlx4: support BIG TCP packets

mlx4 supports LSOv2 just fine.

IPv6 stack inserts a temporary Hop-by-Hop header
with JUMBO TLV for big packets.

We need to ignore the HBH header when populating TX descriptor.

Tested:

Before: (not enabling bigger TSO/GRO packets)

ip link set dev eth0 gso_max_size 65536 gro_max_size 65536

netperf -H lpaa18 -t TCP_RR -T2,2 -l 10 -Cc -- -r 70000,70000
MIGRATED TCP REQUEST/RESPONSE TEST from ::0 (::) port 0 AF_INET6 to lpaa18.prod.google.com () port 0 AF_INET6 : first burst 0 : cpu bind
Local /Remote
Socket Size   Request Resp.  Elapsed Trans.   CPU    CPU    S.dem   S.dem
Send   Recv   Size    Size   Time    Rate     local  remote local   remote
bytes  bytes  bytes   bytes  secs.   per sec  % S    % S    us/Tr   us/Tr

262144 540000 70000   70000  10.00   6591.45  0.86   1.34   62.490  97.446
262144 540000

After: (enabling bigger TSO/GRO packets)

ip link set dev eth0 gso_max_size 185000 gro_max_size 185000

netperf -H lpaa18 -t TCP_RR -T2,2 -l 10 -Cc -- -r 70000,70000
MIGRATED TCP REQUEST/RESPONSE TEST from ::0 (::) port 0 AF_INET6 to lpaa18.prod.google.com () port 0 AF_INET6 : first burst 0 : cpu bind
Local /Remote
Socket Size   Request Resp.  Elapsed Trans.   CPU    CPU    S.dem   S.dem
Send   Recv   Size    Size   Time    Rate     local  remote local   remote
bytes  bytes  bytes   bytes  secs.   per sec  % S    % S    us/Tr   us/Tr

262144 540000 70000   70000  10.00   8383.95  0.95   1.01   54.432  57.584
262144 540000
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Acked-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -3417,6 +3417,9 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	dev->min_mtu = ETH_MIN_MTU;
 	dev->max_mtu = priv->max_mtu;
 
+	/* supports LSOv2 packets. */
+	netif_set_tso_max_size(dev, GSO_MAX_SIZE);
+
 	mdev->pndev[port] = dev;
 	mdev->upper[port] = NULL;
 

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

@@ -43,6 +43,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/indirect_call_wrapper.h>
+#include <net/ipv6.h>
 
 #include "mlx4_en.h"
 
@@ -634,19 +635,28 @@ static int get_real_size(const struct sk_buff *skb,
 			 struct net_device *dev,
 			 int *lso_header_size,
 			 bool *inline_ok,
-			 void **pfrag)
+			 void **pfrag,
+			 int *hopbyhop)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	int real_size;
 
 	if (shinfo->gso_size) {
 		*inline_ok = false;
-		if (skb->encapsulation)
+		*hopbyhop = 0;
+		if (skb->encapsulation) {
 			*lso_header_size = (skb_inner_transport_header(skb) - skb->data) + inner_tcp_hdrlen(skb);
-		else
+		} else {
+			/* Detects large IPV6 TCP packets and prepares for removal of
+			 * HBH header that has been pushed by ip6_xmit(),
+			 * mainly so that tcpdump can dissect them.
+			 */
+			if (ipv6_has_hopopt_jumbo(skb))
+				*hopbyhop = sizeof(struct hop_jumbo_hdr);
 			*lso_header_size = skb_transport_offset(skb) + tcp_hdrlen(skb);
+		}
 		real_size = CTRL_SIZE + shinfo->nr_frags * DS_SIZE +
-			ALIGN(*lso_header_size + 4, DS_SIZE);
+			ALIGN(*lso_header_size - *hopbyhop + 4, DS_SIZE);
 		if (unlikely(*lso_header_size != skb_headlen(skb))) {
 			/* We add a segment for the skb linear buffer only if
 			 * it contains data */
@@ -873,6 +883,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	int desc_size;
 	int real_size;
 	u32 index, bf_index;
+	struct ipv6hdr *h6;
 	__be32 op_own;
 	int lso_header_size;
 	void *fragptr = NULL;
@@ -881,6 +892,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	bool stop_queue;
 	bool inline_ok;
 	u8 data_offset;
+	int hopbyhop;
 	bool bf_ok;
 
 	tx_ind = skb_get_queue_mapping(skb);
@@ -890,7 +902,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto tx_drop;
 
 	real_size = get_real_size(skb, shinfo, dev, &lso_header_size,
-				  &inline_ok, &fragptr);
+				  &inline_ok, &fragptr, &hopbyhop);
 	if (unlikely(!real_size))
 		goto tx_drop_count;
 
@@ -943,7 +955,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		data = &tx_desc->data;
 		data_offset = offsetof(struct mlx4_en_tx_desc, data);
 	} else {
-		int lso_align = ALIGN(lso_header_size + 4, DS_SIZE);
+		int lso_align = ALIGN(lso_header_size - hopbyhop + 4, DS_SIZE);
 
 		data = (void *)&tx_desc->lso + lso_align;
 		data_offset = offsetof(struct mlx4_en_tx_desc, lso) + lso_align;
@@ -1008,14 +1020,31 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 			((ring->prod & ring->size) ?
 				cpu_to_be32(MLX4_EN_BIT_DESC_OWN) : 0);
 
+		lso_header_size -= hopbyhop;
 		/* Fill in the LSO prefix */
 		tx_desc->lso.mss_hdr_size = cpu_to_be32(
 			shinfo->gso_size << 16 | lso_header_size);
 
-		/* Copy headers;
-		 * note that we already verified that it is linear */
-		memcpy(tx_desc->lso.header, skb->data, lso_header_size);
 
+		if (unlikely(hopbyhop)) {
+			/* remove the HBH header.
+			 * Layout: [Ethernet header][IPv6 header][HBH][TCP header]
+			 */
+			memcpy(tx_desc->lso.header, skb->data, ETH_HLEN + sizeof(*h6));
+			h6 = (struct ipv6hdr *)((char *)tx_desc->lso.header + ETH_HLEN);
+			h6->nexthdr = IPPROTO_TCP;
+			/* Copy the TCP header after the IPv6 one */
+			memcpy(h6 + 1,
+			       skb->data + ETH_HLEN + sizeof(*h6) +
+					sizeof(struct hop_jumbo_hdr),
+			       tcp_hdrlen(skb));
+			/* Leave ipv6 payload_len set to 0, as LSO v2 specs request. */
+		} else {
+			/* Copy headers;
+			 * note that we already verified that it is linear
+			 */
+			memcpy(tx_desc->lso.header, skb->data, lso_header_size);
+		}
 		ring->tso_packets++;
 
 		i = shinfo->gso_segs;