BGP: Long-lived graceful restart

The patch implements long-lived graceful restart for BGP, namely
draft-uttaro-idr-bgp-persistence-03.

3 files changed, 63 insertions, 0 deletions

diff --git a/nest/protocol.h b/nest/protocol.h
index f0b65598..343ce523 100644
--- a/nest/protocol.h
+++ b/nest/protocol.h
@@ -229,6 +229,7 @@ struct proto {
   int (*rte_better)(struct rte *, struct rte *);
   int (*rte_same)(struct rte *, struct rte *);
   int (*rte_mergable)(struct rte *, struct rte *);
+  struct rte * (*rte_modify)(struct rte *, struct linpool *);
   void (*rte_insert)(struct network *, struct rte *);
   void (*rte_remove)(struct network *, struct rte *);
 
diff --git a/nest/route.h b/nest/route.h
index cad15440..2ec1dc7f 100644
--- a/nest/route.h
+++ b/nest/route.h
@@ -231,6 +231,7 @@ typedef struct rte {
 #ifdef CONFIG_BGP
     struct {
       u8 suppressed;			/* Used for deterministic MED comparison */
+      s8 stale;				/* Route is LLGR_STALE, -1 if unknown */
     } bgp;
 #endif
 #ifdef CONFIG_BABEL
@@ -254,6 +255,7 @@ typedef struct rte {
 #define REF_FILTERED	2		/* Route is rejected by import filter */
 #define REF_STALE	4		/* Route is stale in a refresh cycle */
 #define REF_DISCARD	8		/* Route is scheduled for discard */
+#define REF_MODIFY	16		/* Route is scheduled for modify */
 
 /* Route is valid for propagation (may depend on other flags in the future), accepts NULL */
 static inline int rte_is_valid(rte *r) { return r && !(r->flags & REF_FILTERED); }
@@ -297,6 +299,7 @@ int rt_examine(rtable *t, net_addr *a, struct proto *p, struct filter *filter);
 rte *rt_export_merged(struct channel *c, net *net, rte **rt_free, linpool *pool, int silent);
 void rt_refresh_begin(rtable *t, struct channel *c);
 void rt_refresh_end(rtable *t, struct channel *c);
+void rt_modify_stale(rtable *t, struct channel *c);
 void rt_schedule_prune(rtable *t);
 void rte_dump(rte *);
 void rte_free(rte *);
diff --git a/nest/rt-table.c b/nest/rt-table.c
index 9dcbda05..036b34c4 100644
--- a/nest/rt-table.c
+++ b/nest/rt-table.c
@@ -1437,6 +1437,28 @@ rte_discard(rte *old)	/* Non-filtered route deletion, used during garbage collec
   rte_update_unlock();
 }
 
+/* Modify existing route by protocol hook, used for long-lived graceful restart */
+static inline void
+rte_modify(rte *old)
+{
+  rte_update_lock();
+
+  rte *new = old->sender->proto->rte_modify(old, rte_update_pool);
+  if (new != old)
+  {
+    if (new)
+    {
+      if (!rta_is_cached(new->attrs))
+	new->attrs = rta_lookup(new->attrs);
+      new->flags = (old->flags & ~REF_MODIFY) | REF_COW;
+    }
+
+    rte_recalculate(old->sender, old->net, new, old->attrs->src);
+  }
+
+  rte_update_unlock();
+}
+
 /* Check rtable for best route to given net whether it would be exported do p */
 int
 rt_examine(rtable *t, net_addr *a, struct proto *p, struct filter *filter)
@@ -1521,6 +1543,26 @@ rt_refresh_end(rtable *t, struct channel *c)
     rt_schedule_prune(t);
 }
 
+void
+rt_modify_stale(rtable *t, struct channel *c)
+{
+  int prune = 0;
+
+  FIB_WALK(&t->fib, net, n)
+    {
+      rte *e;
+      for (e = n->routes; e; e = e->next)
+	if ((e->sender == c) && (e->flags & REF_STALE) && !(e->flags & REF_FILTERED))
+	  {
+	    e->flags |= REF_MODIFY;
+	    prune = 1;
+	  }
+    }
+  FIB_WALK_END;
+
+  if (prune)
+    rt_schedule_prune(t);
+}
 
 /**
  * rte_dump - dump a route
@@ -1712,6 +1754,7 @@ again:
 
     rescan:
       for (e=n->routes; e; e=e->next)
+      {
 	if (e->sender->flush_active || (e->flags & REF_DISCARD))
 	  {
 	    if (limit <= 0)
@@ -1727,6 +1770,22 @@ again:
 	    goto rescan;
 	  }
 
+	if (e->flags & REF_MODIFY)
+	  {
+	    if (limit <= 0)
+	      {
+		FIB_ITERATE_PUT(fit);
+		ev_schedule(tab->rt_event);
+		return;
+	      }
+
+	    rte_modify(e);
+	    limit--;
+
+	    goto rescan;
+	  }
+      }
+
       if (!n->routes)		/* Orphaned FIB entry */
 	{
 	  FIB_ITERATE_PUT(fit);