Merge branch 'net-support-ipv4-big-tcp'

kuba-moo · kuba-moo · commit 983f507c3043 · 2023-02-01T20:54:30.000-08:00
Xin Long says: ==================== net: support ipv4 big tcp This is similar to the BIG TCP patchset added by Eric for IPv6: https://lwn.net/Articles/895398/ Different from IPv6, IPv4 tot_len is 16-bit long only, and IPv4 header doesn't have exthdrs(options) for the BIG TCP packets' length. To make it simple, as David and Paolo suggested, we set IPv4 tot_len to 0 to indicate this might be a BIG TCP packet and use skb->len as the real IPv4 total length. This will work safely, as all BIG TCP packets are GSO/GRO packets and processed on the same host as they were created; There is no padding in GSO/GRO packets, and skb->len - network_offset is exactly the IPv4 packet total length; Also, before implementing the feature, all those places that may get iph tot_len from BIG TCP packets are taken care with some new APIs: Patch 1 adds some APIs for iph tot_len setting and getting, which are used in all these places where IPv4 BIG TCP packets may reach in Patch 2-7, Patch 8 adds a GSO_TCP tp_status for af_packet users, and Patch 9 add new netlink attributes to make IPv4 BIG TCP independent from IPv6 BIG TCP on configuration, and Patch 10 implements this feature. Note that the similar change as in Patch 2-6 are also needed for IPv6 BIG TCP packets, and will be addressed in another patchset. The similar performance test is done for IPv4 BIG TCP with 25Gbit NIC and 1.5K MTU: No BIG TCP: for i in {1..10}; do netperf -t TCP_RR -H 192.168.100.1 -- -r80000,80000 -O MIN_LATENCY,P90_LATENCY,P99_LATENCY,THROUGHPUT|tail -1; done 168 322 337 3776.49 143 236 277 4654.67 128 258 288 4772.83 171 229 278 4645.77 175 228 243 4678.93 149 239 279 4599.86 164 234 268 4606.94 155 276 289 4235.82 180 255 268 4418.95 168 241 249 4417.82 Enable BIG TCP: ip link set dev ens1f0np0 gro_ipv4_max_size 128000 gso_ipv4_max_size 128000 for i in {1..10}; do netperf -t TCP_RR -H 192.168.100.1 -- -r80000,80000 -O MIN_LATENCY,P90_LATENCY,P99_LATENCY,THROUGHPUT|tail -1; done 161 241 252 4821.73 174 205 217 5098.28 167 208 220 5001.43 164 228 249 4883.98 150 233 249 4914.90 180 233 244 4819.66 154 208 219 5004.92 157 209 247 4999.78 160 218 246 4842.31 174 206 217 5080.99 Thanks for the feedback from Eric and David Ahern. ==================== Link: https://lore.kernel.org/r/cover.1674921359.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
@@ -157,7 +157,7 @@ void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type)
 			return NULL;
 
 		ip4h = ip_hdr(skb);
-		pktlen = ntohs(ip4h->tot_len);
+		pktlen = skb_ip_totlen(skb);
 		if (ip4h->ihl < 5 || ip4h->version != 4)
 			return NULL;
 		if (skb->len < pktlen || pktlen < (ip4h->ihl * 4))
diff --git a/include/linux/ip.h b/include/linux/ip.h
@@ -35,4 +35,25 @@ static inline unsigned int ip_transport_len(const struct sk_buff *skb)
 {
 	return ntohs(ip_hdr(skb)->tot_len) - skb_network_header_len(skb);
 }
+
+static inline unsigned int iph_totlen(const struct sk_buff *skb, const struct iphdr *iph)
+{
+	u32 len = ntohs(iph->tot_len);
+
+	return (len || !skb_is_gso(skb) || !skb_is_gso_tcp(skb)) ?
+	       len : skb->len - skb_network_offset(skb);
+}
+
+static inline unsigned int skb_ip_totlen(const struct sk_buff *skb)
+{
+	return iph_totlen(skb, ip_hdr(skb));
+}
+
+/* IPv4 datagram length is stored into 16bit field (tot_len) */
+#define IP_MAX_MTU	0xFFFFU
+
+static inline void iph_set_totlen(struct iphdr *iph, unsigned int len)
+{
+	iph->tot_len = len <= IP_MAX_MTU ? htons(len) : 0;
+}
 #endif	/* _LINUX_IP_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
@@ -1964,6 +1964,8 @@ enum netdev_ml_priv_type {
  *	@gso_max_segs:	Maximum number of segments that can be passed to the
  *			NIC for GSO
  *	@tso_max_segs:	Device (as in HW) limit on the max TSO segment count
+ * 	@gso_ipv4_max_size:	Maximum size of generic segmentation offload,
+ * 				for IPv4.
  *
  *	@dcbnl_ops:	Data Center Bridging netlink ops
  *	@num_tc:	Number of traffic classes in the net device
@@ -2004,6 +2006,8 @@ enum netdev_ml_priv_type {
  *			keep a list of interfaces to be deleted.
  *	@gro_max_size:	Maximum size of aggregated packet in generic
  *			receive offload (GRO)
+ * 	@gro_ipv4_max_size:	Maximum size of aggregated packet in generic
+ * 				receive offload (GRO), for IPv4.
  *
  *	@dev_addr_shadow:	Copy of @dev_addr to catch direct writes.
  *	@linkwatch_dev_tracker:	refcount tracker used by linkwatch.
@@ -2207,6 +2211,7 @@ struct net_device {
  */
 #define GRO_MAX_SIZE		(8 * 65535u)
 	unsigned int		gro_max_size;
+	unsigned int		gro_ipv4_max_size;
 	rx_handler_func_t __rcu	*rx_handler;
 	void __rcu		*rx_handler_data;
 
@@ -2330,6 +2335,7 @@ struct net_device {
 	u16			gso_max_segs;
 #define TSO_MAX_SEGS		U16_MAX
 	u16			tso_max_segs;
+	unsigned int		gso_ipv4_max_size;
 
 #ifdef CONFIG_DCB
 	const struct dcbnl_rtnl_ops *dcbnl_ops;
diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h
@@ -29,7 +29,7 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt)
 	if (iph->ihl < 5 || iph->version != 4)
 		return -1;
 
-	len = ntohs(iph->tot_len);
+	len = iph_totlen(pkt->skb, iph);
 	thoff = iph->ihl * 4;
 	if (pkt->skb->len < len)
 		return -1;
@@ -64,7 +64,7 @@ static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt)
 	if (iph->ihl < 5 || iph->version != 4)
 		goto inhdr_error;
 
-	len = ntohs(iph->tot_len);
+	len = iph_totlen(pkt->skb, iph);
 	thoff = iph->ihl * 4;
 	if (pkt->skb->len < len) {
 		__IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INTRUNCATEDPKTS);
diff --git a/include/net/route.h b/include/net/route.h
@@ -35,9 +35,6 @@
 #include <linux/cache.h>
 #include <linux/security.h>
 
-/* IPv4 datagram length is stored into 16bit field (tot_len) */
-#define IP_MAX_MTU	0xFFFFU
-
 #define RTO_ONLINK	0x01
 
 #define RT_CONN_FLAGS(sk)   (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
@@ -374,6 +374,9 @@ enum {
 
 	IFLA_DEVLINK_PORT,
 
+	IFLA_GSO_IPV4_MAX_SIZE,
+	IFLA_GRO_IPV4_MAX_SIZE,
+
 	__IFLA_MAX
 };
 
diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h
@@ -115,6 +115,7 @@ struct tpacket_auxdata {
 #define TP_STATUS_BLK_TMO		(1 << 5)
 #define TP_STATUS_VLAN_TPID_VALID	(1 << 6) /* auxdata has valid tp_vlan_tpid */
 #define TP_STATUS_CSUM_VALID		(1 << 7)
+#define TP_STATUS_GSO_TCP		(1 << 8)
 
 /* Tx ring - header status */
 #define TP_STATUS_AVAILABLE	      0
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
@@ -214,7 +214,7 @@ static int br_validate_ipv4(struct net *net, struct sk_buff *skb)
 	if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
 		goto csum_error;
 
-	len = ntohs(iph->tot_len);
+	len = skb_ip_totlen(skb);
 	if (skb->len < len) {
 		__IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS);
 		goto drop;
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -212,7 +212,7 @@ static int nf_ct_br_ip_check(const struct sk_buff *skb)
 	    iph->version != 4)
 		return -1;
 
-	len = ntohs(iph->tot_len);
+	len = skb_ip_totlen(skb);
 	if (skb->len < nhoff + len ||
 	    len < (iph->ihl * 4))
                 return -1;
@@ -256,7 +256,7 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb,
 		if (!pskb_may_pull(skb, sizeof(struct iphdr)))
 			return NF_ACCEPT;
 
-		len = ntohs(ip_hdr(skb)->tot_len);
+		len = skb_ip_totlen(skb);
 		if (pskb_trim_rcsum(skb, len))
 			return NF_ACCEPT;
 
diff --git a/net/core/dev.c b/net/core/dev.c
@@ -3001,6 +3001,8 @@ void netif_set_tso_max_size(struct net_device *dev, unsigned int size)
 	dev->tso_max_size = min(GSO_MAX_SIZE, size);
 	if (size < READ_ONCE(dev->gso_max_size))
 		netif_set_gso_max_size(dev, size);
+	if (size < READ_ONCE(dev->gso_ipv4_max_size))
+		netif_set_gso_ipv4_max_size(dev, size);
 }
 EXPORT_SYMBOL(netif_set_tso_max_size);
 
@@ -10614,6 +10616,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev->gso_max_size = GSO_LEGACY_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
 	dev->gro_max_size = GRO_LEGACY_MAX_SIZE;
+	dev->gso_ipv4_max_size = GSO_LEGACY_MAX_SIZE;
+	dev->gro_ipv4_max_size = GRO_LEGACY_MAX_SIZE;
 	dev->tso_max_size = TSO_LEGACY_MAX_SIZE;
 	dev->tso_max_segs = TSO_MAX_SEGS;
 	dev->upper_level = 1;
diff --git a/net/core/dev.h b/net/core/dev.h
@@ -100,6 +100,8 @@ static inline void netif_set_gso_max_size(struct net_device *dev,
 {
 	/* dev->gso_max_size is read locklessly from sk_setup_caps() */
 	WRITE_ONCE(dev->gso_max_size, size);
+	if (size <= GSO_LEGACY_MAX_SIZE)
+		WRITE_ONCE(dev->gso_ipv4_max_size, size);
 }
 
 static inline void netif_set_gso_max_segs(struct net_device *dev,
@@ -114,6 +116,22 @@ static inline void netif_set_gro_max_size(struct net_device *dev,
 {
 	/* This pairs with the READ_ONCE() in skb_gro_receive() */
 	WRITE_ONCE(dev->gro_max_size, size);
+	if (size <= GRO_LEGACY_MAX_SIZE)
+		WRITE_ONCE(dev->gro_ipv4_max_size, size);
+}
+
+static inline void netif_set_gso_ipv4_max_size(struct net_device *dev,
+					       unsigned int size)
+{
+	/* dev->gso_ipv4_max_size is read locklessly from sk_setup_caps() */
+	WRITE_ONCE(dev->gso_ipv4_max_size, size);
+}
+
+static inline void netif_set_gro_ipv4_max_size(struct net_device *dev,
+					       unsigned int size)
+{
+	/* This pairs with the READ_ONCE() in skb_gro_receive() */
+	WRITE_ONCE(dev->gro_ipv4_max_size, size);
 }
 
 #endif
diff --git a/net/core/gro.c b/net/core/gro.c
@@ -162,16 +162,18 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 	struct sk_buff *lp;
 	int segs;
 
-	/* pairs with WRITE_ONCE() in netif_set_gro_max_size() */
-	gro_max_size = READ_ONCE(p->dev->gro_max_size);
+	/* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */
+	gro_max_size = p->protocol == htons(ETH_P_IPV6) ?
+			READ_ONCE(p->dev->gro_max_size) :
+				READ_ONCE(p->dev->gro_ipv4_max_size);
 
 	if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush))
 		return -E2BIG;
 
 	if (unlikely(p->len + len >= GRO_LEGACY_MAX_SIZE)) {
-		if (p->protocol != htons(ETH_P_IPV6) ||
-		    skb_headroom(p) < sizeof(struct hop_jumbo_hdr) ||
-		    ipv6_hdr(p)->nexthdr != IPPROTO_TCP ||
+		if (NAPI_GRO_CB(skb)->proto != IPPROTO_TCP ||
+		    (p->protocol == htons(ETH_P_IPV6) &&
+		     skb_headroom(p) < sizeof(struct hop_jumbo_hdr)) ||
 		    p->encapsulation)
 			return -E2BIG;
 	}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
@@ -1074,6 +1074,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(4) /* IFLA_GSO_MAX_SEGS */
 	       + nla_total_size(4) /* IFLA_GSO_MAX_SIZE */
 	       + nla_total_size(4) /* IFLA_GRO_MAX_SIZE */
+	       + nla_total_size(4) /* IFLA_GSO_IPV4_MAX_SIZE */
+	       + nla_total_size(4) /* IFLA_GRO_IPV4_MAX_SIZE */
 	       + nla_total_size(4) /* IFLA_TSO_MAX_SIZE */
 	       + nla_total_size(4) /* IFLA_TSO_MAX_SEGS */
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
@@ -1807,6 +1809,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	    nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) ||
 	    nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) ||
 	    nla_put_u32(skb, IFLA_GRO_MAX_SIZE, dev->gro_max_size) ||
+	    nla_put_u32(skb, IFLA_GSO_IPV4_MAX_SIZE, dev->gso_ipv4_max_size) ||
+	    nla_put_u32(skb, IFLA_GRO_IPV4_MAX_SIZE, dev->gro_ipv4_max_size) ||
 	    nla_put_u32(skb, IFLA_TSO_MAX_SIZE, dev->tso_max_size) ||
 	    nla_put_u32(skb, IFLA_TSO_MAX_SEGS, dev->tso_max_segs) ||
 #ifdef CONFIG_RPS
@@ -1968,6 +1972,8 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_TSO_MAX_SIZE]	= { .type = NLA_REJECT },
 	[IFLA_TSO_MAX_SEGS]	= { .type = NLA_REJECT },
 	[IFLA_ALLMULTI]		= { .type = NLA_REJECT },
+	[IFLA_GSO_IPV4_MAX_SIZE]	= { .type = NLA_U32 },
+	[IFLA_GRO_IPV4_MAX_SIZE]	= { .type = NLA_U32 },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2883,6 +2889,29 @@ static int do_setlink(const struct sk_buff *skb,
 		}
 	}
 
+	if (tb[IFLA_GSO_IPV4_MAX_SIZE]) {
+		u32 max_size = nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]);
+
+		if (max_size > dev->tso_max_size) {
+			err = -EINVAL;
+			goto errout;
+		}
+
+		if (dev->gso_ipv4_max_size ^ max_size) {
+			netif_set_gso_ipv4_max_size(dev, max_size);
+			status |= DO_SETLINK_MODIFIED;
+		}
+	}
+
+	if (tb[IFLA_GRO_IPV4_MAX_SIZE]) {
+		u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]);
+
+		if (dev->gro_ipv4_max_size ^ gro_max_size) {
+			netif_set_gro_ipv4_max_size(dev, gro_max_size);
+			status |= DO_SETLINK_MODIFIED;
+		}
+	}
+
 	if (tb[IFLA_OPERSTATE])
 		set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
 
@@ -3325,6 +3354,10 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 		netif_set_gso_max_segs(dev, nla_get_u32(tb[IFLA_GSO_MAX_SEGS]));
 	if (tb[IFLA_GRO_MAX_SIZE])
 		netif_set_gro_max_size(dev, nla_get_u32(tb[IFLA_GRO_MAX_SIZE]));
+	if (tb[IFLA_GSO_IPV4_MAX_SIZE])
+		netif_set_gso_ipv4_max_size(dev, nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]));
+	if (tb[IFLA_GRO_IPV4_MAX_SIZE])
+		netif_set_gro_ipv4_max_size(dev, nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]));
 
 	return dev;
 }
diff --git a/net/core/sock.c b/net/core/sock.c
@@ -2373,17 +2373,22 @@ void sk_free_unlock_clone(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(sk_free_unlock_clone);
 
-static void sk_trim_gso_size(struct sock *sk)
+static u32 sk_dst_gso_max_size(struct sock *sk, struct dst_entry *dst)
 {
-	if (sk->sk_gso_max_size <= GSO_LEGACY_MAX_SIZE)
-		return;
+	bool is_ipv6 = false;
+	u32 max_size;
+
 #if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family == AF_INET6 &&
-	    sk_is_tcp(sk) &&
-	    !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
-		return;
+	is_ipv6 = (sk->sk_family == AF_INET6 &&
+		   !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr));
 #endif
-	sk->sk_gso_max_size = GSO_LEGACY_MAX_SIZE;
+	/* pairs with the WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */
+	max_size = is_ipv6 ? READ_ONCE(dst->dev->gso_max_size) :
+			READ_ONCE(dst->dev->gso_ipv4_max_size);
+	if (max_size > GSO_LEGACY_MAX_SIZE && !sk_is_tcp(sk))
+		max_size = GSO_LEGACY_MAX_SIZE;
+
+	return max_size - (MAX_TCP_HEADER + 1);
 }
 
 void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
@@ -2403,10 +2408,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 			sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
 		} else {
 			sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
-			/* pairs with the WRITE_ONCE() in netif_set_gso_max_size() */
-			sk->sk_gso_max_size = READ_ONCE(dst->dev->gso_max_size);
-			sk_trim_gso_size(sk);
-			sk->sk_gso_max_size -= (MAX_TCP_HEADER + 1);
+			sk->sk_gso_max_size = sk_dst_gso_max_size(sk, dst);
 			/* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */
 			max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1);
 		}
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
@@ -1485,6 +1485,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
 	if (unlikely(ip_fast_csum((u8 *)iph, 5)))
 		goto out;
 
+	NAPI_GRO_CB(skb)->proto = proto;
 	id = ntohl(*(__be32 *)&iph->id);
 	flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF));
 	id >>= 16;
@@ -1618,9 +1619,9 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 int inet_gro_complete(struct sk_buff *skb, int nhoff)
 {
-	__be16 newlen = htons(skb->len - nhoff);
 	struct iphdr *iph = (struct iphdr *)(skb->data + nhoff);
 	const struct net_offload *ops;
+	__be16 totlen = iph->tot_len;
 	int proto = iph->protocol;
 	int err = -ENOSYS;
 
@@ -1629,8 +1630,8 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)
 		skb_set_inner_network_header(skb, nhoff);
 	}
 
-	csum_replace2(&iph->check, iph->tot_len, newlen);
-	iph->tot_len = newlen;
+	iph_set_totlen(iph, skb->len - nhoff);
+	csum_replace2(&iph->check, totlen, iph->tot_len);
 
 	ops = rcu_dereference(inet_offloads[proto]);
 	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
@@ -2222,7 +2222,7 @@ int cipso_v4_skbuff_setattr(struct sk_buff *skb,
 		memset((char *)(iph + 1) + buf_len, 0, opt_len - buf_len);
 	if (len_delta != 0) {
 		iph->ihl = 5 + (opt_len >> 2);
-		iph->tot_len = htons(skb->len);
+		iph_set_totlen(iph, skb->len);
 	}
 	ip_send_check(iph);
 
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
@@ -511,7 +511,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 	if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
 		goto csum_error;
 
-	len = ntohs(iph->tot_len);
+	len = iph_totlen(skb, iph);
 	if (skb->len < len) {
 		drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL;
 		__IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
@@ -100,7 +100,7 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct iphdr *iph = ip_hdr(skb);
 
-	iph->tot_len = htons(skb->len);
+	iph_set_totlen(iph, skb->len);
 	ip_send_check(iph);
 
 	/* if egress device is enslaved to an L3 master device pass the
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -994,7 +994,7 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af,
 		old_dsfield = ipv4_get_dsfield(old_iph);
 		*ttl = old_iph->ttl;
 		if (payload_len)
-			*payload_len = ntohs(old_iph->tot_len);
+			*payload_len = skb_ip_totlen(skb);
 	}
 
 	/* Implement full-functionality option for ECN encapsulation */
diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c
diff --git a/net/netfilter/xt_length.c b/net/netfilter/xt_length.c
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
