ipv4: fib_rules: Check if rule is a default rule

Currently, when non-default (custom) FIB rules are used, devices capable
of layer 3 offloading flush their tables and let the kernel do the
forwarding instead.

When these devices' drivers are loaded they register to the FIB
notification chain, which lets them know about the existence of any
custom FIB rules. This is done by sending a RULE_ADD notification based
on the value of 'net->ipv4.fib_has_custom_rules'.

This approach is problematic when VRF offload is taken into account, as
upon the creation of the first VRF netdev, a l3mdev rule is programmed
to direct skbs to the VRF's table.

Instead of merely reading the above value and sending a single RULE_ADD
notification, we should iterate over all the FIB rules and send a
detailed notification for each, thereby allowing offloading drivers to
sanitize the rules they don't support and potentially flush their
tables.

While l3mdev rules are uniquely marked, the default rules are not.
Therefore, when they are being notified they might invoke offloading
drivers to unnecessarily flush their tables.

Solve this by adding an helper to check if a FIB rule is a default rule.
Namely, its selector should match all packets and its action should
point to the local, main or default tables.

As noted by David Ahern, uniquely marking the default rules is
insufficient. When using VRFs, it's common to avoid false hits by moving
the rule for the local table to just before the main table:

Default configuration:
$ ip rule show
0:      from all lookup local
32766:  from all lookup main
32767:  from all lookup default

Common configuration with VRFs:
$ ip rule show
1000:   from all lookup [l3mdev-table]
32765:  from all lookup local
32766:  from all lookup main
32767:  from all lookup default

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 8dbfdf728cd8ce901b3b05f0e58b4eeee25051fe..1243b9c7694e309f49dde4a5bf38cd1387dfecb7 100644 (file)
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -141,6 +141,7 @@ 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);
+bool fib_rule_matchall(const struct fib_rule *rule);
 
 int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh);
 int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh);

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index d9cee9659978b5013b62b55d1f27312d99f6ed21..da6fa7b1555822325753949e1418d28b7fdcf046 100644 (file)
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -311,6 +311,11 @@ static inline int fib_lookup(struct net *net, const struct flowi4 *flp,
        return err;
 }
 
+static inline bool fib4_rule_default(const struct fib_rule *rule)
+{
+       return true;
+}
+
 #else /* CONFIG_IP_MULTIPLE_TABLES */
 int __net_init fib4_rules_init(struct net *net);
 void __net_exit fib4_rules_exit(struct net *net);
@@ -355,6 +360,8 @@ out:
        return err;
 }
 
+bool fib4_rule_default(const struct fib_rule *rule);
+
 #endif /* CONFIG_IP_MULTIPLE_TABLES */
 
 /* Exported by fib_frontend.c */

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index b6791d94841d56cf8b1027d3ba2d71dd21302caf..816e3ccb0ec9ffc41442300f64cc63c97d1af879 100644 (file)
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -23,6 +23,20 @@ static const struct fib_kuid_range fib_kuid_range_unset = {
        KUIDT_INIT(~0),
 };
 
+bool fib_rule_matchall(const struct fib_rule *rule)
+{
+       if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id ||
+           rule->flags)
+               return false;
+       if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1)
+               return false;
+       if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) ||
+           !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end))
+               return false;
+       return true;
+}
+EXPORT_SYMBOL_GPL(fib_rule_matchall);
+
 int fib_default_rule_add(struct fib_rules_ops *ops,
                         u32 pref, u32 table, u32 flags)
 {

diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 289210903d5847ad7b88bbd0595e84edc8eb0f83..d531bc94b15ea23bb6f291388e83d06b0de50d8f 100644 (file)
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -47,6 +47,27 @@ struct fib4_rule {
 #endif
 };
 
+static bool fib4_rule_matchall(const struct fib_rule *rule)
+{
+       struct fib4_rule *r = container_of(rule, struct fib4_rule, common);
+
+       if (r->dst_len || r->src_len || r->tos)
+               return false;
+       return fib_rule_matchall(rule);
+}
+
+bool fib4_rule_default(const struct fib_rule *rule)
+{
+       if (!fib4_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL ||
+           rule->l3mdev)
+               return false;
+       if (rule->table != RT_TABLE_LOCAL && rule->table != RT_TABLE_MAIN &&
+           rule->table != RT_TABLE_DEFAULT)
+               return false;
+       return true;
+}
+EXPORT_SYMBOL_GPL(fib4_rule_default);
+
 int __fib_lookup(struct net *net, struct flowi4 *flp,
                 struct fib_result *res, unsigned int flags)
 {