net: Add l3mdev rule

Currently, VRFs require 1 oif and 1 iif rule per address family per
VRF. As the number of VRF devices increases it brings scalability
issues with the increasing rule list. All of the VRF rules have the
same format with the exception of the specific table id to direct the
lookup. Since the table id is available from the oif or iif in the
loopup, the VRF rules can be consolidated to a single rule that pulls
the table from the VRF device.

This patch introduces a new rule attribute l3mdev. The l3mdev rule
means the table id used for the lookup is pulled from the L3 master
device (e.g., VRF) rather than being statically defined. With the
l3mdev rule all of the basic VRF FIB rules are reduced to 1 l3mdev
rule per address family (IPv4 and IPv6).

If an admin wishes to insert higher priority rules for specific VRFs
those rules will co-exist with the l3mdev rule. This capability means
current VRF scripts will co-exist with this new simpler implementation.

Currently, the rules list for both ipv4 and ipv6 look like this:
    $ ip  ru ls
    1000:       from all oif vrf1 lookup 1001
    1000:       from all iif vrf1 lookup 1001
    1000:       from all oif vrf2 lookup 1002
    1000:       from all iif vrf2 lookup 1002
    1000:       from all oif vrf3 lookup 1003
    1000:       from all iif vrf3 lookup 1003
    1000:       from all oif vrf4 lookup 1004
    1000:       from all iif vrf4 lookup 1004
    1000:       from all oif vrf5 lookup 1005
    1000:       from all iif vrf5 lookup 1005
    1000:       from all oif vrf6 lookup 1006
    1000:       from all iif vrf6 lookup 1006
    1000:       from all oif vrf7 lookup 1007
    1000:       from all iif vrf7 lookup 1007
    1000:       from all oif vrf8 lookup 1008
    1000:       from all iif vrf8 lookup 1008
    ...
    32765:      from all lookup local
    32766:      from all lookup main
    32767:      from all lookup default

With the l3mdev rule the list is just the following regardless of the
number of VRFs:
    $ ip ru ls
    1000:       from all lookup [l3mdev table]
    32765:      from all lookup local
    32766:      from all lookup main
    32767:      from all lookup default

(Note: the above pretty print of the rule is based on an iproute2
       prototype. Actual verbage may change)

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 34 insertions, 2 deletions

diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 59160de702b6..456e4a6006ab 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -17,7 +17,8 @@ struct fib_rule {
         u32                     flags;
         u32                     table;
         u8                      action;
-        /* 3 bytes hole, try to use */
+        u8                      l3mdev;
+        /* 2 bytes hole, try to use */
         u32                     target;
         __be64                  tun_id;
         struct fib_rule __rcu   *ctarget;
@@ -36,6 +37,7 @@ struct fib_lookup_arg {
         void                    *lookup_ptr;
         void                    *result;
         struct fib_rule         *rule;
+        u32                     table;
         int                     flags;
 #define FIB_LOOKUP_NOREF                1
 #define FIB_LOOKUP_IGNORE_LINKSTATE     2
@@ -89,7 +91,8 @@ struct fib_rules_ops {
         [FRA_TABLE]     = { .type = NLA_U32 }, \
         [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \
         [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \
-        [FRA_GOTO]      = { .type = NLA_U32 }
+        [FRA_GOTO]      = { .type = NLA_U32 }, \
+        [FRA_L3MDEV]    = { .type = NLA_U8 }
 
 static inline void fib_rule_get(struct fib_rule *rule)
 {
@@ -102,6 +105,20 @@ static inline void fib_rule_put(struct fib_rule *rule)
                 kfree_rcu(rule, rcu);
 }
 
+#ifdef CONFIG_NET_L3_MASTER_DEV
+static inline u32 fib_rule_get_table(struct fib_rule *rule,
+                                     struct fib_lookup_arg *arg)
+{
+        return rule->l3mdev ? arg->table : rule->table;
+}
+#else
+static inline u32 fib_rule_get_table(struct fib_rule *rule,
+                                     struct fib_lookup_arg *arg)
+{
+        return rule->table;
+}
+#endif
+
 static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla)
 {
         if (nla[FRA_TABLE])
@@ -117,4 +134,7 @@ int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags,
                      struct fib_lookup_arg *);
 int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table,
                          u32 flags);
+
+int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh);
+int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh);
 #endif
diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
index 374388dc01c8..34f33eb96a5e 100644
--- a/include/net/l3mdev.h
+++ b/include/net/l3mdev.h
@@ -11,6 +11,8 @@
 #ifndef _NET_L3MDEV_H_
 #define _NET_L3MDEV_H_
 
+#include <net/fib_rules.h>
+
 /**
  * struct l3mdev_ops - l3mdev operations
  *
@@ -41,6 +43,9 @@ struct l3mdev_ops {
 
 #ifdef CONFIG_NET_L3_MASTER_DEV
 
+int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
+                          struct fib_lookup_arg *arg);
+
 int l3mdev_master_ifindex_rcu(const struct net_device *dev);
 static inline int l3mdev_master_ifindex(struct net_device *dev)
 {
@@ -236,6 +241,13 @@ struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb)
 {
         return skb;
 }
+
+static inline
+int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
+                          struct fib_lookup_arg *arg)
+{
+        return 1;
+}
 #endif
 
 #endif /* _NET_L3MDEV_H_ */