diff options
author | David Ahern <dsahern@gmail.com> | 2019-05-25 00:43:08 +0300 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2019-05-29 07:37:30 +0300 |
commit | 430a049190de3c9e219f43084de9f1122da04570 (patch) | |
tree | b846b64bcf7696f24db792a5c710a008f643ff4c /include/net/nexthop.h | |
parent | b513bd035f4044aa2667fb01418918523a049b9c (diff) | |
download | linux-430a049190de3c9e219f43084de9f1122da04570.tar.xz |
nexthop: Add support for nexthop groups
Allow the creation of nexthop groups which reference other nexthop
objects to create multipath routes:
+--------------+
+------------+ +--------------+ |
| nh nh_grp --->| nh_grp_entry |-+
+------------+ +---------|----+
^ | | +------------+
+----------------+ +--->| nh, weight |
nh_parent +------------+
A group entry points to a nexthop with a weight for that hop within the
group. The nexthop has a list_head, grp_list, for tracking which groups
it is a member of and the group entry has a reference back to the parent.
The grp_list is used when a nexthop is deleted - to efficiently remove
it from groups using it.
If a nexthop group spec is given, no other attributes can be set. Each
nexthop id in a group spec must already exist.
Similar to single nexthops, the specification of a nexthop group can be
updated so that data is managed with rcu locking.
Add path selection function to account for multiple paths and add
ipv{4,6}_good_nh helpers to know that if a neighbor entry exists it is
in a good state.
Update NETDEV event handling to rebalance multipath nexthop groups if
a nexthop is deleted due to a link event (down or unregister).
When a nexthop is removed any groups using it are updated. Groups using a
nexthop a tracked via a grp_list.
Nexthop dumps can be limited to groups only by adding NHA_GROUPS to the
request.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/net/nexthop.h')
-rw-r--r-- | include/net/nexthop.h | 98 |
1 files changed, 97 insertions, 1 deletions
diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 7cde03337e14..6e1b8f53624c 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -35,6 +35,9 @@ struct nh_config { struct in6_addr ipv6; } gw; + struct nlattr *nh_grp; + u16 nh_grp_type; + struct nlattr *nh_encap; u16 nh_encap_type; @@ -56,20 +59,39 @@ struct nh_info { }; }; +struct nh_grp_entry { + struct nexthop *nh; + u8 weight; + atomic_t upper_bound; + + struct list_head nh_list; + struct nexthop *nh_parent; /* nexthop of group with this entry */ +}; + +struct nh_group { + u16 num_nh; + bool mpath; + bool has_v4; + struct nh_grp_entry nh_entries[0]; +}; + struct nexthop { struct rb_node rb_node; /* entry on netns rbtree */ + struct list_head grp_list; /* nh group entries using this nh */ struct net *net; u32 id; u8 protocol; /* app managing this nh */ u8 nh_flags; + bool is_group; refcount_t refcnt; struct rcu_head rcu; union { struct nh_info __rcu *nh_info; + struct nh_group __rcu *nh_grp; }; }; @@ -88,12 +110,86 @@ static inline void nexthop_put(struct nexthop *nh) call_rcu(&nh->rcu, nexthop_free_rcu); } +static inline bool nexthop_is_multipath(const struct nexthop *nh) +{ + if (nh->is_group) { + struct nh_group *nh_grp; + + nh_grp = rcu_dereference_rtnl(nh->nh_grp); + return nh_grp->mpath; + } + return false; +} + +struct nexthop *nexthop_select_path(struct nexthop *nh, int hash); + +static inline unsigned int nexthop_num_path(const struct nexthop *nh) +{ + unsigned int rc = 1; + + if (nexthop_is_multipath(nh)) { + struct nh_group *nh_grp; + + nh_grp = rcu_dereference_rtnl(nh->nh_grp); + rc = nh_grp->num_nh; + } else { + const struct nh_info *nhi; + + nhi = rcu_dereference_rtnl(nh->nh_info); + if (nhi->reject_nh) + rc = 0; + } + + return rc; +} + +static inline +struct nexthop *nexthop_mpath_select(const struct nexthop *nh, int nhsel) +{ + const struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp); + + /* for_nexthops macros in fib_semantics.c grabs a pointer to + * the nexthop before checking nhsel + */ + if (nhsel > nhg->num_nh) + return NULL; + + return nhg->nh_entries[nhsel].nh; +} + +static inline +int nexthop_mpath_fill_node(struct sk_buff *skb, struct nexthop *nh) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + int i; + + for (i = 0; i < nhg->num_nh; i++) { + struct nexthop *nhe = nhg->nh_entries[i].nh; + struct nh_info *nhi = rcu_dereference_rtnl(nhe->nh_info); + struct fib_nh_common *nhc = &nhi->fib_nhc; + int weight = nhg->nh_entries[i].weight; + + if (fib_add_nexthop(skb, nhc, weight) < 0) + return -EMSGSIZE; + } + + return 0; +} + /* called with rcu lock */ static inline bool nexthop_is_blackhole(const struct nexthop *nh) { const struct nh_info *nhi; - nhi = rcu_dereference(nh->nh_info); + if (nexthop_is_multipath(nh)) { + if (nexthop_num_path(nh) > 1) + return false; + nh = nexthop_mpath_select(nh, 0); + if (!nh) + return false; + } + + nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->reject_nh; } #endif |