BGP: Long-lived graceful restart

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

3 files changed, 66 insertions, 0 deletions

diff --git a/nest/protocol.h b/nest/protocol.h
index 4fb76e2b..af988c88 100644
--- a/nest/protocol.h
+++ b/nest/protocol.h
@@ -213,6 +213,7 @@ 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 0834da45..ab1ba50e 100644
--- a/nest/route.h
+++ b/nest/route.h
@@ -219,6 +219,7 @@ 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
@@ -241,6 +242,7 @@ 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); }
@@ -279,6 +281,7 @@ int rt_examine(rtable *t, ip_addr prefix, int pxlen, struct proto *p, struct fil
 rte *rt_export_merged(struct announce_hook *ah, net *net, rte **rt_free, struct ea_list **tmpa, linpool *pool, int silent);
 void rt_refresh_begin(rtable *t, struct announce_hook *ah);
 void rt_refresh_end(rtable *t, struct announce_hook *ah);
+void rt_modify_stale(rtable *t, struct announce_hook *ah);
 void rte_dump(rte *);
 void rte_free(rte *);
 rte *rte_do_cow(rte *);
diff --git a/nest/rt-table.c b/nest/rt-table.c
index 83f0e713..93075c7b 100644
--- a/nest/rt-table.c
+++ b/nest/rt-table.c
@@ -1295,6 +1295,28 @@ 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, ip_addr prefix, int pxlen, struct proto *p, struct filter *filter)
@@ -1385,6 +1407,29 @@ rt_refresh_end(rtable *t, struct announce_hook *ah)
     rt_schedule_prune(t);
 }
 
+void
+rt_modify_stale(rtable *t, struct announce_hook *ah)
+{
+  int prune = 0;
+  net *n;
+  rte *e;
+
+  FIB_WALK(&t->fib, fn)
+    {
+      n = (net *) fn;
+      for (e = n->routes; e; e = e->next)
+	if ((e->sender == ah) && (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
@@ -1604,6 +1649,7 @@ again:
 
     rescan:
       for (e=n->routes; e; e=e->next)
+      {
 	if (e->sender->proto->flushing || (e->flags & REF_DISCARD))
 	  {
 	    if (*limit <= 0)
@@ -1617,6 +1663,22 @@ again:
 
 	    goto rescan;
 	  }
+
+	if (e->flags & REF_MODIFY)
+	  {
+	    if (*limit <= 0)
+	      {
+		FIB_ITERATE_PUT(fit, fn);
+		return 0;
+	      }
+
+	    rte_modify(e);
+	    (*limit)--;
+
+	    goto rescan;
+	  }
+      }
+
       if (!n->routes)		/* Orphaned FIB entry */
 	{
 	  FIB_ITERATE_PUT(fit, fn);