Merge branch 'ipip_gso'

Eric Dumazet says:

====================
net: Implement GSO/TSO support for IPIP

This patch serie implements GSO/TSO support for IPIP

David, please note it applies after "ipv4: gso: send_check() & segment() cleanups"
( http://patchwork.ozlabs.org/patch/284714/ )

Broadcom bnx2x driver is now enabled for TSO support of IPIP traffic

Before patch :

lpq83:~# ./netperf -H 7.7.9.84 -Cc
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.9.84 () port 0 AF_INET
Recv   Send    Send                          Utilization       Service Demand
Socket Socket  Message  Elapsed              Send     Recv     Send    Recv
Size   Size    Size     Time     Throughput  local    remote   local   remote
bytes  bytes   bytes    secs.    10^6bits/s  % S      % S      us/KB   us/KB

 87380  16384  16384    10.00      3357.88   5.09     3.70     2.983   2.167

After patch :

lpq83:~# ./netperf -H 7.7.9.84 -Cc
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.9.84 () port 0 AF_INET
Recv   Send    Send                          Utilization       Service Demand
Socket Socket  Message  Elapsed              Send     Recv     Send    Recv
Size   Size    Size     Time     Throughput  local    remote   local   remote
bytes  bytes   bytes    secs.    10^6bits/s  % S      % S      us/KB   us/KB

 87380  16384  16384    10.00      8532.40   2.55     7.73     0.588   1.781
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c

@@ -12260,10 +12260,12 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev,
 		NETIF_F_RXCSUM | NETIF_F_LRO | NETIF_F_GRO |
 		NETIF_F_RXHASH | NETIF_F_HW_VLAN_CTAG_TX;
 	if (!CHIP_IS_E1x(bp)) {
-		dev->hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL;
+		dev->hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL |
+				    NETIF_F_GSO_IPIP;
 		dev->hw_enc_features =
 			NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG |
 			NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 |
+			NETIF_F_GSO_IPIP |
 			NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL;
 	}
 

include/linux/netdev_features.h

@@ -42,6 +42,7 @@ enum {
 	NETIF_F_TSO6_BIT,		/* ... TCPv6 segmentation */
 	NETIF_F_FSO_BIT,		/* ... FCoE segmentation */
 	NETIF_F_GSO_GRE_BIT,		/* ... GRE with TSO */
+	NETIF_F_GSO_IPIP_BIT,		/* ... IPIP tunnel with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_BIT,	/* ... UDP TUNNEL with TSO */
 	NETIF_F_GSO_MPLS_BIT,		/* ... MPLS segmentation */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
@@ -107,6 +108,7 @@ enum {
 #define NETIF_F_RXFCS		__NETIF_F(RXFCS)
 #define NETIF_F_RXALL		__NETIF_F(RXALL)
 #define NETIF_F_GSO_GRE		__NETIF_F(GSO_GRE)
+#define NETIF_F_GSO_IPIP	__NETIF_F(GSO_IPIP)
 #define NETIF_F_GSO_UDP_TUNNEL	__NETIF_F(GSO_UDP_TUNNEL)
 #define NETIF_F_GSO_MPLS	__NETIF_F(GSO_MPLS)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)

include/linux/skbuff.h

@@ -318,9 +318,11 @@ enum {
 
 	SKB_GSO_GRE = 1 << 6,
 
-	SKB_GSO_UDP_TUNNEL = 1 << 7,
+	SKB_GSO_IPIP = 1 << 7,
 
-	SKB_GSO_MPLS = 1 << 8,
+	SKB_GSO_UDP_TUNNEL = 1 << 8,
+
+	SKB_GSO_MPLS = 1 << 9,
 };
 
 #if BITS_PER_LONG > 32
@@ -2722,9 +2724,12 @@ static inline struct sec_path *skb_sec_path(struct sk_buff *skb)
 /* Keeps track of mac header offset relative to skb->head.
  * It is useful for TSO of Tunneling protocol. e.g. GRE.
  * For non-tunnel skb it points to skb_mac_header() and for
- * tunnel skb it points to outer mac header. */
+ * tunnel skb it points to outer mac header.
+ * Keeps track of level of encapsulation of network headers.
+ */
 struct skb_gso_cb {
-	int mac_offset;
+	int	mac_offset;
+	int	encap_level;
 };
 #define SKB_GSO_CB(skb) ((struct skb_gso_cb *)(skb)->cb)
 

include/net/gre.h

@@ -38,7 +38,13 @@ void gre_offload_exit(void);
 
 void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 		      int hdr_len);
-struct sk_buff *gre_handle_offloads(struct sk_buff *skb, bool gre_csum);
+
+static inline struct sk_buff *gre_handle_offloads(struct sk_buff *skb,
+						  bool gre_csum)
+{
+	return iptunnel_handle_offloads(skb, gre_csum, SKB_GSO_GRE);
+}
+
 
 static inline int ip_gre_calc_hlen(__be16 o_flags)
 {

include/net/ip_tunnels.h

@@ -150,6 +150,9 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb,
 		  __be32 src, __be32 dst, __u8 proto,
 		  __u8 tos, __u8 ttl, __be16 df, bool xnet);
 
+struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum,
+					 int gso_type_mask);
+
 static inline void iptunnel_xmit_stats(int err,
 				       struct net_device_stats *err_stats,
 				       struct pcpu_tstats __percpu *stats)

net/core/dev.c

@@ -2377,6 +2377,8 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 	}
 
 	SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb);
+	SKB_GSO_CB(skb)->encap_level = 0;
+
 	skb_reset_mac_header(skb);
 	skb_reset_mac_len(skb);
 

net/core/ethtool.c

@@ -81,6 +81,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_TSO6_BIT] =             "tx-tcp6-segmentation",
 	[NETIF_F_FSO_BIT] =              "tx-fcoe-segmentation",
 	[NETIF_F_GSO_GRE_BIT] =		 "tx-gre-segmentation",
+	[NETIF_F_GSO_IPIP_BIT] =	 "tx-ipip-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_BIT] =	 "tx-udp_tnl-segmentation",
 	[NETIF_F_GSO_MPLS_BIT] =	 "tx-mpls-segmentation",
 

net/core/skbuff.c

@@ -903,6 +903,9 @@ EXPORT_SYMBOL(skb_clone);
 
 static void skb_headers_offset_update(struct sk_buff *skb, int off)
 {
+	/* Only adjust this if it actually is csum_start rather than csum */
+	if (skb->ip_summed == CHECKSUM_PARTIAL)
+		skb->csum_start += off;
 	/* {transport,network,mac}_header and tail are relative to skb->head */
 	skb->transport_header += off;
 	skb->network_header   += off;
@@ -1109,9 +1112,6 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 #endif
 	skb->tail	      += off;
 	skb_headers_offset_update(skb, nhead);
-	/* Only adjust this if it actually is csum_start rather than csum */
-	if (skb->ip_summed == CHECKSUM_PARTIAL)
-		skb->csum_start += nhead;
 	skb->cloned   = 0;
 	skb->hdr_len  = 0;
 	skb->nohdr    = 0;
@@ -1176,7 +1176,6 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
 					NUMA_NO_NODE);
 	int oldheadroom = skb_headroom(skb);
 	int head_copy_len, head_copy_off;
-	int off;
 
 	if (!n)
 		return NULL;
@@ -1200,11 +1199,7 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
 
 	copy_skb_header(n, skb);
 
-	off                  = newheadroom - oldheadroom;
-	if (n->ip_summed == CHECKSUM_PARTIAL)
-		n->csum_start += off;
-
-	skb_headers_offset_update(n, off);
+	skb_headers_offset_update(n, newheadroom - oldheadroom);
 
 	return n;
 }
@@ -2837,14 +2832,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 		__copy_skb_header(nskb, skb);
 		nskb->mac_len = skb->mac_len;
 
-		/* nskb and skb might have different headroom */
-		if (nskb->ip_summed == CHECKSUM_PARTIAL)
-			nskb->csum_start += skb_headroom(nskb) - headroom;
-
-		skb_reset_mac_header(nskb);
-		skb_set_network_header(nskb, skb->mac_len);
-		nskb->transport_header = (nskb->network_header +
-					  skb_network_header_len(skb));
+		skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom);
 
 		skb_copy_from_linear_data_offset(skb, -tnl_hlen,
 						 nskb->data - tnl_hlen,

net/ipv4/af_inet.c

@@ -1273,16 +1273,17 @@ out:
 }
 
 static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
-	netdev_features_t features)
+					netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
+	unsigned int offset = 0;
 	struct iphdr *iph;
+	bool tunnel;
 	int proto;
+	int nhoff;
 	int ihl;
 	int id;
-	unsigned int offset = 0;
-	bool tunnel;
 
 	if (unlikely(skb_shinfo(skb)->gso_type &
 		     ~(SKB_GSO_TCPV4 |
@@ -1290,12 +1291,15 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_DODGY |
 		       SKB_GSO_TCP_ECN |
 		       SKB_GSO_GRE |
+		       SKB_GSO_IPIP |
 		       SKB_GSO_TCPV6 |
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_MPLS |
 		       0)))
 		goto out;
 
+	skb_reset_network_header(skb);
+	nhoff = skb_network_header(skb) - skb_mac_header(skb);
 	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
 		goto out;
 
@@ -1312,7 +1316,10 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		goto out;
 	__skb_pull(skb, ihl);
 
-	tunnel = !!skb->encapsulation;
+	tunnel = SKB_GSO_CB(skb)->encap_level > 0;
+	if (tunnel)
+		features = skb->dev->hw_enc_features & netif_skb_features(skb);
+	SKB_GSO_CB(skb)->encap_level += ihl;
 
 	skb_reset_transport_header(skb);
 
@@ -1327,18 +1334,23 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 
 	skb = segs;
 	do {
-		iph = ip_hdr(skb);
+		iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
 		if (!tunnel && proto == IPPROTO_UDP) {
 			iph->id = htons(id);
 			iph->frag_off = htons(offset >> 3);
 			if (skb->next != NULL)
 				iph->frag_off |= htons(IP_MF);
-			offset += (skb->len - skb->mac_len - iph->ihl * 4);
+			offset += skb->len - nhoff - ihl;
 		} else  {
 			iph->id = htons(id++);
 		}
-		iph->tot_len = htons(skb->len - skb->mac_len);
+		iph->tot_len = htons(skb->len - nhoff);
 		ip_send_check(iph);
+		if (tunnel) {
+			skb_reset_inner_headers(skb);
+			skb->encapsulation = 1;
+		}
+		skb->network_header = (u8 *)iph - skb->head;
 	} while ((skb = skb->next));
 
 out:
@@ -1645,6 +1657,13 @@ static struct packet_offload ip_packet_offload __read_mostly = {
 	},
 };
 
+static const struct net_offload ipip_offload = {
+	.callbacks = {
+		.gso_send_check = inet_gso_send_check,
+		.gso_segment	= inet_gso_segment,
+	},
+};
+
 static int __init ipv4_offload_init(void)
 {
 	/*
@@ -1656,6 +1675,7 @@ static int __init ipv4_offload_init(void)
 		pr_crit("%s: Cannot add TCP protocol offload\n", __func__);
 
 	dev_add_offload(&ip_packet_offload);
+	inet_add_offload(&ipip_offload, IPPROTO_IPIP);
 	return 0;
 }
 

net/ipv4/gre_demux.c

@@ -93,35 +93,6 @@ void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 }
 EXPORT_SYMBOL_GPL(gre_build_header);
 
-struct sk_buff *gre_handle_offloads(struct sk_buff *skb, bool gre_csum)
-{
-	int err;
-
-	if (likely(!skb->encapsulation)) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
-
-	if (skb_is_gso(skb)) {
-		err = skb_unclone(skb, GFP_ATOMIC);
-		if (unlikely(err))
-			goto error;
-		skb_shinfo(skb)->gso_type |= SKB_GSO_GRE;
-		return skb;
-	} else if (skb->ip_summed == CHECKSUM_PARTIAL && gre_csum) {
-		err = skb_checksum_help(skb);
-		if (unlikely(err))
-			goto error;
-	} else if (skb->ip_summed != CHECKSUM_PARTIAL)
-		skb->ip_summed = CHECKSUM_NONE;
-
-	return skb;
-error:
-	kfree_skb(skb);
-	return ERR_PTR(err);
-}
-EXPORT_SYMBOL_GPL(gre_handle_offloads);
-
 static __sum16 check_checksum(struct sk_buff *skb)
 {
 	__sum16 csum = 0;

net/ipv4/gre_offload.c

@@ -39,7 +39,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_UDP |
 				  SKB_GSO_DODGY |
 				  SKB_GSO_TCP_ECN |
-				  SKB_GSO_GRE)))
+				  SKB_GSO_GRE |
+				  SKB_GSO_IPIP)))
 		goto out;
 
 	if (unlikely(!pskb_may_pull(skb, sizeof(*greh))))

net/ipv4/ip_tunnel_core.c

@@ -116,3 +116,36 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(iptunnel_pull_header);
+
+struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb,
+					 bool csum_help,
+					 int gso_type_mask)
+{
+	int err;
+
+	if (likely(!skb->encapsulation)) {
+		skb_reset_inner_headers(skb);
+		skb->encapsulation = 1;
+	}
+
+	if (skb_is_gso(skb)) {
+		err = skb_unclone(skb, GFP_ATOMIC);
+		if (unlikely(err))
+			goto error;
+		skb_shinfo(skb)->gso_type |= gso_type_mask;
+		return skb;
+	}
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL && csum_help) {
+		err = skb_checksum_help(skb);
+		if (unlikely(err))
+			goto error;
+	} else if (skb->ip_summed != CHECKSUM_PARTIAL)
+		skb->ip_summed = CHECKSUM_NONE;
+
+	return skb;
+error:
+	kfree_skb(skb);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(iptunnel_handle_offloads);

net/ipv4/ipip.c

@@ -220,17 +220,17 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (unlikely(skb->protocol != htons(ETH_P_IP)))
 		goto tx_error;
 
-	if (likely(!skb->encapsulation)) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
+	skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP);
+	if (IS_ERR(skb))
+		goto out;
 
 	ip_tunnel_xmit(skb, dev, tiph, tiph->protocol);
 	return NETDEV_TX_OK;
 
 tx_error:
-	dev->stats.tx_errors++;
 	dev_kfree_skb(skb);
+out:
+	dev->stats.tx_errors++;
 	return NETDEV_TX_OK;
 }
 
@@ -275,6 +275,7 @@ static const struct net_device_ops ipip_netdev_ops = {
 #define IPIP_FEATURES (NETIF_F_SG |		\
 		       NETIF_F_FRAGLIST |	\
 		       NETIF_F_HIGHDMA |	\
+		       NETIF_F_GSO_SOFTWARE |	\
 		       NETIF_F_HW_CSUM)
 
 static void ipip_tunnel_setup(struct net_device *dev)

net/ipv4/tcp_offload.c

@@ -56,6 +56,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 			       SKB_GSO_TCP_ECN |
 			       SKB_GSO_TCPV6 |
 			       SKB_GSO_GRE |
+			       SKB_GSO_IPIP |
 			       SKB_GSO_MPLS |
 			       SKB_GSO_UDP_TUNNEL |
 			       0) ||

net/ipv4/udp_offload.c

@@ -52,6 +52,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 
 		if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
 				      SKB_GSO_UDP_TUNNEL |
+				      SKB_GSO_IPIP |
 				      SKB_GSO_GRE | SKB_GSO_MPLS) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;

net/ipv6/ip6_offload.c

@@ -96,6 +96,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_DODGY |
 		       SKB_GSO_TCP_ECN |
 		       SKB_GSO_GRE |
+		       SKB_GSO_IPIP |
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_MPLS |
 		       SKB_GSO_TCPV6 |

net/ipv6/udp_offload.c

@@ -64,6 +64,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 				      SKB_GSO_DODGY |
 				      SKB_GSO_UDP_TUNNEL |
 				      SKB_GSO_GRE |
+				      SKB_GSO_IPIP |
 				      SKB_GSO_MPLS) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;

net/mpls/mpls_gso.c

@@ -33,6 +33,7 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_DODGY |
 				  SKB_GSO_TCP_ECN |
 				  SKB_GSO_GRE |
+				  SKB_GSO_IPIP |
 				  SKB_GSO_MPLS)))
 		goto out;