route: Add multipath_hash in flowi_common to make user-define hash

Current fib_multipath_hash_policy can make hash based on the L3 or
L4. But it only work on the outer IP. So a specific tunnel always
has the same hash value. But a specific tunnel may contain so many
inner connections.

This patch provide a generic multipath_hash in floi_common. It can
make a user-define hash which can mix with L3 or L4 hash.

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

6 files changed, 13 insertions, 6 deletions

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index ad5a9b9e1466..536c23c578c3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -305,7 +305,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev,
 
         parms = mlxsw_sp_ipip_netdev_parms4(to_dev);
         ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp,
-                            0, 0, parms.link, tun->fwmark);
+                            0, 0, parms.link, tun->fwmark, 0);
 
         rt = ip_route_output_key(tun->net, &fl4);
         if (IS_ERR(rt))
diff --git a/include/net/flow.h b/include/net/flow.h
index 93f2c9a0f098..a50fb77a0b27 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -40,6 +40,7 @@ struct flowi_common {
         __u32   flowic_secid;
         kuid_t  flowic_uid;
         struct flowi_tunnel flowic_tun_key;
+        __u32           flowic_multipath_hash;
 };
 
 union flowi_uli {
@@ -78,6 +79,7 @@ struct flowi4 {
 #define flowi4_secid            __fl_common.flowic_secid
 #define flowi4_tun_key          __fl_common.flowic_tun_key
 #define flowi4_uid              __fl_common.flowic_uid
+#define flowi4_multipath_hash   __fl_common.flowic_multipath_hash
 
         /* (saddr,daddr) must be grouped, same order as in IP header */
         __be32                  saddr;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index f069f64ebf29..af645604f328 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -241,7 +241,7 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4,
                                        int proto,
                                        __be32 daddr, __be32 saddr,
                                        __be32 key, __u8 tos, int oif,
-                                       __u32 mark)
+                                       __u32 mark, __u32 tun_inner_hash)
 {
         memset(fl4, 0, sizeof(*fl4));
         fl4->flowi4_oif = oif;
@@ -251,6 +251,7 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4,
         fl4->flowi4_proto = proto;
         fl4->fl4_gre_key = key;
         fl4->flowi4_mark = mark;
+        fl4->flowi4_multipath_hash = tun_inner_hash;
 }
 
 int ip_tunnel_init(struct net_device *dev);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 0f4925a0d6b2..fd219f7bd3ea 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -578,7 +578,7 @@ static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
         key = &info->key;
         ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src,
                             tunnel_id_to_key32(key->tun_id), key->tos, 0,
-                            skb->mark);
+                            skb->mark, skb_get_hash(skb));
         rt = ip_route_output_key(dev_net(dev), &fl4);
         if (IS_ERR(rt))
                 return PTR_ERR(rt);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 2973067b831d..2756fb725bf0 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -310,7 +310,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
                 ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr,
                                     iph->saddr, tunnel->parms.o_key,
                                     RT_TOS(iph->tos), tunnel->parms.link,
-                                    tunnel->fwmark);
+                                    tunnel->fwmark, 0);
                 rt = ip_route_output_key(tunnel->net, &fl4);
 
                 if (!IS_ERR(rt)) {
@@ -584,7 +584,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
         }
         ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src,
                             tunnel_id_to_key32(key->tun_id), RT_TOS(tos),
-                            0, skb->mark);
+                            0, skb->mark, skb_get_hash(skb));
         if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
                 goto tx_error;
 
@@ -744,7 +744,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
         ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
                             tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
-                            tunnel->fwmark);
+                            tunnel->fwmark, skb_get_hash(skb));
 
         if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
                 goto tx_error;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ecc12a768191..7cf4c8305071 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1820,6 +1820,7 @@ out:
 int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
                        const struct sk_buff *skb, struct flow_keys *flkeys)
 {
+        u32 multipath_hash = fl4->flowi4_multipath_hash;
         struct flow_keys hash_keys;
         u32 mhash;
 
@@ -1870,6 +1871,9 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
         }
         mhash = flow_hash_from_keys(&hash_keys);
 
+        if (multipath_hash)
+                mhash = jhash_2words(mhash, multipath_hash, 0);
+
         return mhash >> 1;
 }
 #endif /* CONFIG_IP_ROUTE_MULTIPATH */