![Ido Schimmel](/assets/img/avatar_default.png)
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>
149 lines
3.7 KiB
C
149 lines
3.7 KiB
C
#ifndef __NET_FIB_RULES_H
|
|
#define __NET_FIB_RULES_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/fib_rules.h>
|
|
#include <net/flow.h>
|
|
#include <net/rtnetlink.h>
|
|
|
|
struct fib_kuid_range {
|
|
kuid_t start;
|
|
kuid_t end;
|
|
};
|
|
|
|
struct fib_rule {
|
|
struct list_head list;
|
|
int iifindex;
|
|
int oifindex;
|
|
u32 mark;
|
|
u32 mark_mask;
|
|
u32 flags;
|
|
u32 table;
|
|
u8 action;
|
|
u8 l3mdev;
|
|
/* 2 bytes hole, try to use */
|
|
u32 target;
|
|
__be64 tun_id;
|
|
struct fib_rule __rcu *ctarget;
|
|
struct net *fr_net;
|
|
|
|
atomic_t refcnt;
|
|
u32 pref;
|
|
int suppress_ifgroup;
|
|
int suppress_prefixlen;
|
|
char iifname[IFNAMSIZ];
|
|
char oifname[IFNAMSIZ];
|
|
struct fib_kuid_range uid_range;
|
|
struct rcu_head rcu;
|
|
};
|
|
|
|
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
|
|
};
|
|
|
|
struct fib_rules_ops {
|
|
int family;
|
|
struct list_head list;
|
|
int rule_size;
|
|
int addr_size;
|
|
int unresolved_rules;
|
|
int nr_goto_rules;
|
|
|
|
int (*action)(struct fib_rule *,
|
|
struct flowi *, int,
|
|
struct fib_lookup_arg *);
|
|
bool (*suppress)(struct fib_rule *,
|
|
struct fib_lookup_arg *);
|
|
int (*match)(struct fib_rule *,
|
|
struct flowi *, int);
|
|
int (*configure)(struct fib_rule *,
|
|
struct sk_buff *,
|
|
struct fib_rule_hdr *,
|
|
struct nlattr **);
|
|
int (*delete)(struct fib_rule *);
|
|
int (*compare)(struct fib_rule *,
|
|
struct fib_rule_hdr *,
|
|
struct nlattr **);
|
|
int (*fill)(struct fib_rule *, struct sk_buff *,
|
|
struct fib_rule_hdr *);
|
|
size_t (*nlmsg_payload)(struct fib_rule *);
|
|
|
|
/* Called after modifications to the rules set, must flush
|
|
* the route cache if one exists. */
|
|
void (*flush_cache)(struct fib_rules_ops *ops);
|
|
|
|
int nlgroup;
|
|
const struct nla_policy *policy;
|
|
struct list_head rules_list;
|
|
struct module *owner;
|
|
struct net *fro_net;
|
|
struct rcu_head rcu;
|
|
};
|
|
|
|
#define FRA_GENERIC_POLICY \
|
|
[FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \
|
|
[FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \
|
|
[FRA_PRIORITY] = { .type = NLA_U32 }, \
|
|
[FRA_FWMARK] = { .type = NLA_U32 }, \
|
|
[FRA_FWMASK] = { .type = NLA_U32 }, \
|
|
[FRA_TABLE] = { .type = NLA_U32 }, \
|
|
[FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \
|
|
[FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \
|
|
[FRA_GOTO] = { .type = NLA_U32 }, \
|
|
[FRA_L3MDEV] = { .type = NLA_U8 }, \
|
|
[FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) }
|
|
|
|
static inline void fib_rule_get(struct fib_rule *rule)
|
|
{
|
|
atomic_inc(&rule->refcnt);
|
|
}
|
|
|
|
static inline void fib_rule_put(struct fib_rule *rule)
|
|
{
|
|
if (atomic_dec_and_test(&rule->refcnt))
|
|
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])
|
|
return nla_get_u32(nla[FRA_TABLE]);
|
|
return frh->table;
|
|
}
|
|
|
|
struct fib_rules_ops *fib_rules_register(const struct fib_rules_ops *,
|
|
struct net *);
|
|
void fib_rules_unregister(struct fib_rules_ops *);
|
|
|
|
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);
|
|
#endif
|