GSO: Add GSO type for fixed IPv4 ID

This patch adds support for TSO using IPv4 headers with a fixed IP ID
field.  This is meant to allow us to do a lossless GRO in the case of TCP
flows that use a fixed IP ID such as those that convert IPv6 header to IPv4
headers.

In addition I am adding a feature that for now I am referring to TSO with
IP ID mangling.  Basically when this flag is enabled the device has the
option to either output the flow with incrementing IP IDs or with a fixed
IP ID regardless of what the original IP ID ordering was.  This is useful
in cases where the DF bit is set and we do not care if the original IP ID
value is maintained.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index a734bf4..7cf272a 100644 (file)
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -39,6 +39,7 @@ enum {
        NETIF_F_UFO_BIT,                /* ... UDPv4 fragmentation */
        NETIF_F_GSO_ROBUST_BIT,         /* ... ->SKB_GSO_DODGY */
        NETIF_F_TSO_ECN_BIT,            /* ... TCP ECN support */
+       NETIF_F_TSO_MANGLEID_BIT,       /* ... IPV4 ID mangling allowed */
        NETIF_F_TSO6_BIT,               /* ... TCPv6 segmentation */
        NETIF_F_FSO_BIT,                /* ... FCoE segmentation */
        NETIF_F_GSO_GRE_BIT,            /* ... GRE with TSO */
@@ -120,6 +121,7 @@ enum {
 #define NETIF_F_GSO_SIT                __NETIF_F(GSO_SIT)
 #define NETIF_F_GSO_UDP_TUNNEL __NETIF_F(GSO_UDP_TUNNEL)
 #define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM)
+#define NETIF_F_TSO_MANGLEID   __NETIF_F(TSO_MANGLEID)
 #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX        __NETIF_F(HW_VLAN_STAG_RX)
@@ -147,6 +149,7 @@ enum {
 
 /* List of features with software fallbacks. */
 #define NETIF_F_GSO_SOFTWARE   (NETIF_F_TSO | NETIF_F_TSO_ECN | \
+                                NETIF_F_TSO_MANGLEID | \
                                 NETIF_F_TSO6 | NETIF_F_UFO)
 
 /* List of IP checksum features. Note that NETIF_F_ HW_CSUM should not be

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9884fe9..8e372d0 100644 (file)
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3992,6 +3992,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
        BUILD_BUG_ON(SKB_GSO_UDP     != (NETIF_F_UFO >> NETIF_F_GSO_SHIFT));
        BUILD_BUG_ON(SKB_GSO_DODGY   != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT));
        BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT));
+       BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT));
        BUILD_BUG_ON(SKB_GSO_TCPV6   != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT));
        BUILD_BUG_ON(SKB_GSO_FCOE    != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
        BUILD_BUG_ON(SKB_GSO_GRE     != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT));

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 0073812..5fba166 100644 (file)
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -465,23 +465,25 @@ enum {
        /* This indicates the tcp segment has CWR set. */
        SKB_GSO_TCP_ECN = 1 << 3,
 
-       SKB_GSO_TCPV6 = 1 << 4,
+       SKB_GSO_TCP_FIXEDID = 1 << 4,
 
-       SKB_GSO_FCOE = 1 << 5,
+       SKB_GSO_TCPV6 = 1 << 5,
 
-       SKB_GSO_GRE = 1 << 6,
+       SKB_GSO_FCOE = 1 << 6,
 
-       SKB_GSO_GRE_CSUM = 1 << 7,
+       SKB_GSO_GRE = 1 << 7,
 
-       SKB_GSO_IPIP = 1 << 8,
+       SKB_GSO_GRE_CSUM = 1 << 8,
 
-       SKB_GSO_SIT = 1 << 9,
+       SKB_GSO_IPIP = 1 << 9,
 
-       SKB_GSO_UDP_TUNNEL = 1 << 10,
+       SKB_GSO_SIT = 1 << 10,
 
-       SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11,
+       SKB_GSO_UDP_TUNNEL = 1 << 11,
 
-       SKB_GSO_TUNNEL_REMCSUM = 1 << 12,
+       SKB_GSO_UDP_TUNNEL_CSUM = 1 << 12,
+
+       SKB_GSO_TUNNEL_REMCSUM = 1 << 13,
 };
 
 #if BITS_PER_LONG > 32

diff --git a/net/core/dev.c b/net/core/dev.c
index 09fb1ac..e896b19 100644 (file)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2825,14 +2825,36 @@ static netdev_features_t dflt_features_check(const struct sk_buff *skb,
        return vlan_features_check(skb, features);
 }
 
+static netdev_features_t gso_features_check(const struct sk_buff *skb,
+                                           struct net_device *dev,
+                                           netdev_features_t features)
+{
+       u16 gso_segs = skb_shinfo(skb)->gso_segs;
+
+       if (gso_segs > dev->gso_max_segs)
+               return features & ~NETIF_F_GSO_MASK;
+
+       /* Make sure to clear the IPv4 ID mangling feature if
+        * the IPv4 header has the potential to be fragmented.
+        */
+       if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) {
+               struct iphdr *iph = skb->encapsulation ?
+                                   inner_ip_hdr(skb) : ip_hdr(skb);
+
+               if (!(iph->frag_off & htons(IP_DF)))
+                       features &= ~NETIF_F_TSO_MANGLEID;
+       }
+
+       return features;
+}
+
 netdev_features_t netif_skb_features(struct sk_buff *skb)
 {
        struct net_device *dev = skb->dev;
        netdev_features_t features = dev->features;
-       u16 gso_segs = skb_shinfo(skb)->gso_segs;
 
-       if (gso_segs > dev->gso_max_segs)
-               features &= ~NETIF_F_GSO_MASK;
+       if (skb_is_gso(skb))
+               features = gso_features_check(skb, dev, features);
 
        /* If encapsulation offload request, verify we are testing
         * hardware encapsulation features instead of standard
@@ -6976,9 +6998,11 @@ int register_netdevice(struct net_device *dev)
        dev->features |= NETIF_F_SOFT_FEATURES;
        dev->wanted_features = dev->features & dev->hw_features;
 
-       if (!(dev->flags & IFF_LOOPBACK)) {
+       if (!(dev->flags & IFF_LOOPBACK))
                dev->hw_features |= NETIF_F_NOCACHE_COPY;
-       }
+
+       if (dev->hw_features & NETIF_F_TSO)
+               dev->hw_features |= NETIF_F_TSO_MANGLEID;
 
        /* Make NETIF_F_HIGHDMA inheritable to VLAN devices.
         */

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 6a7f996..9494c41 100644 (file)
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -79,6 +79,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
        [NETIF_F_UFO_BIT] =              "tx-udp-fragmentation",
        [NETIF_F_GSO_ROBUST_BIT] =       "tx-gso-robust",
        [NETIF_F_TSO_ECN_BIT] =          "tx-tcp-ecn-segmentation",
+       [NETIF_F_TSO_MANGLEID_BIT] =     "tx-tcp-mangleid-segmentation",
        [NETIF_F_TSO6_BIT] =             "tx-tcp6-segmentation",
        [NETIF_F_FSO_BIT] =              "tx-fcoe-segmentation",
        [NETIF_F_GSO_GRE_BIT] =          "tx-gre-segmentation",

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 8217cd2..5bbea9a 100644 (file)
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1195,10 +1195,10 @@ EXPORT_SYMBOL(inet_sk_rebuild_header);
 static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
                                        netdev_features_t features)
 {
+       bool udpfrag = false, fixedid = false, encap;
        struct sk_buff *segs = ERR_PTR(-EINVAL);
        const struct net_offload *ops;
        unsigned int offset = 0;
-       bool udpfrag, encap;
        struct iphdr *iph;
        int proto;
        int nhoff;
@@ -1217,6 +1217,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
                       SKB_GSO_TCPV6 |
                       SKB_GSO_UDP_TUNNEL |
                       SKB_GSO_UDP_TUNNEL_CSUM |
+                      SKB_GSO_TCP_FIXEDID |
                       SKB_GSO_TUNNEL_REMCSUM |
                       0)))
                goto out;
@@ -1248,11 +1249,14 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 
        segs = ERR_PTR(-EPROTONOSUPPORT);
 
-       if (skb->encapsulation &&
-           skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
-               udpfrag = proto == IPPROTO_UDP && encap;
-       else
-               udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
+       if (!skb->encapsulation || encap) {
+               udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
+               fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID);
+
+               /* fixed ID is invalid if DF bit is not set */
+               if (fixedid && !(iph->frag_off & htons(IP_DF)))
+                       goto out;
+       }
 
        ops = rcu_dereference(inet_offloads[proto]);
        if (likely(ops && ops->callbacks.gso_segment))
@@ -1265,12 +1269,11 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
        do {
                iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
                if (udpfrag) {
-                       iph->id = htons(id);
                        iph->frag_off = htons(offset >> 3);
                        if (skb->next)
                                iph->frag_off |= htons(IP_MF);
                        offset += skb->len - nhoff - ihl;
-               } else {
+               } else if (!fixedid) {
                        iph->id = htons(id++);
                }
                iph->tot_len = htons(skb->len - nhoff);

diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 6a5bd43..6376b0c 100644 (file)
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -32,6 +32,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
                                  SKB_GSO_UDP |
                                  SKB_GSO_DODGY |
                                  SKB_GSO_TCP_ECN |
+                                 SKB_GSO_TCP_FIXEDID |
                                  SKB_GSO_GRE |
                                  SKB_GSO_GRE_CSUM |
                                  SKB_GSO_IPIP |

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 773083b..08dd25d 100644 (file)
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -89,6 +89,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
                             ~(SKB_GSO_TCPV4 |
                               SKB_GSO_DODGY |
                               SKB_GSO_TCP_ECN |
+                              SKB_GSO_TCP_FIXEDID |
                               SKB_GSO_TCPV6 |
                               SKB_GSO_GRE |
                               SKB_GSO_GRE_CSUM |
@@ -98,7 +99,8 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
                               SKB_GSO_UDP_TUNNEL_CSUM |
                               SKB_GSO_TUNNEL_REMCSUM |
                               0) ||
-                            !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
+                            !(type & (SKB_GSO_TCPV4 |
+                                      SKB_GSO_TCPV6))))
                        goto out;
 
                skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 204af22..b3a7793 100644 (file)
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -73,6 +73,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
                       SKB_GSO_UDP |
                       SKB_GSO_DODGY |
                       SKB_GSO_TCP_ECN |
+                      SKB_GSO_TCP_FIXEDID |
+                      SKB_GSO_TCPV6 |
                       SKB_GSO_GRE |
                       SKB_GSO_GRE_CSUM |
                       SKB_GSO_IPIP |
@@ -80,7 +82,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
                       SKB_GSO_UDP_TUNNEL |
                       SKB_GSO_UDP_TUNNEL_CSUM |
                       SKB_GSO_TUNNEL_REMCSUM |
-                      SKB_GSO_TCPV6 |
                       0)))
                goto out;
 

diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c
index 0183b32..bbcf604 100644 (file)
--- a/net/mpls/mpls_gso.c
+++ b/net/mpls/mpls_gso.c
@@ -31,6 +31,7 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
                                  SKB_GSO_TCPV6 |
                                  SKB_GSO_UDP |
                                  SKB_GSO_DODGY |
+                                 SKB_GSO_TCP_FIXEDID |
                                  SKB_GSO_TCP_ECN)))
                goto out;