net/ipv6: Add knob to skip DELROUTE message on device down

Another difference between IPv4 and IPv6 is the generation of RTM_DELROUTE
notifications when a device is taken down (admin down) or deleted. IPv4
does not generate a message for routes evicted by the down or delete;
IPv6 does. A NOS at scale really needs to avoid these messages and have
IPv4 and IPv6 behave similarly, relying on userspace to handle link
notifications and evict the routes.

At this point existing user behavior needs to be preserved. Since
notifications are a global action (not per app) the only way to preserve
existing behavior and allow the messages to be skipped is to add a new
sysctl (net/ipv6/route/skip_notify_on_dev_down) which can be set to
disable the notificatioons.

IPv6 route code already supports the option to skip the message (it is
used for multipath routes for example). Besides the new sysctl we need
to pass the skip_notify setting through the generic fib6_clean and
fib6_walk functions to fib6_clean_node and to set skip_notify on calls
to __ip_del_rt for the addrconf_ifdown path.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 15 insertions, 5 deletions

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e14d244c551f..9ba72d94d60f 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -47,6 +47,7 @@ struct fib6_cleaner {
 	int (*func)(struct fib6_info *, void *arg);
 	int sernum;
 	void *arg;
+	bool skip_notify;
 };
 
 #ifdef CONFIG_IPV6_SUBTREES
@@ -1956,6 +1957,7 @@ static int fib6_clean_node(struct fib6_walker *w)
 	struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w);
 	struct nl_info info = {
 		.nl_net = c->net,
+		.skip_notify = c->skip_notify,
 	};
 
 	if (c->sernum != FIB6_NO_SERNUM_CHANGE &&
@@ -2007,7 +2009,7 @@ static int fib6_clean_node(struct fib6_walker *w)
 
 static void fib6_clean_tree(struct net *net, struct fib6_node *root,
 			    int (*func)(struct fib6_info *, void *arg),
-			    int sernum, void *arg)
+			    int sernum, void *arg, bool skip_notify)
 {
 	struct fib6_cleaner c;
 
@@ -2019,13 +2021,14 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
 	c.sernum = sernum;
 	c.arg = arg;
 	c.net = net;
+	c.skip_notify = skip_notify;
 
 	fib6_walk(net, &c.w);
 }
 
 static void __fib6_clean_all(struct net *net,
 			     int (*func)(struct fib6_info *, void *),
-			     int sernum, void *arg)
+			     int sernum, void *arg, bool skip_notify)
 {
 	struct fib6_table *table;
 	struct hlist_head *head;
@@ -2037,7 +2040,7 @@ static void __fib6_clean_all(struct net *net,
 		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
 			spin_lock_bh(&table->tb6_lock);
 			fib6_clean_tree(net, &table->tb6_root,
-					func, sernum, arg);
+					func, sernum, arg, skip_notify);
 			spin_unlock_bh(&table->tb6_lock);
 		}
 	}
@@ -2047,14 +2050,21 @@ static void __fib6_clean_all(struct net *net,
 void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *),
 		    void *arg)
 {
-	__fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg);
+	__fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, false);
+}
+
+void fib6_clean_all_skip_notify(struct net *net,
+				int (*func)(struct fib6_info *, void *),
+				void *arg)
+{
+	__fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, true);
 }
 
 static void fib6_flush_trees(struct net *net)
 {
 	int new_sernum = fib6_new_sernum(net);
 
-	__fib6_clean_all(net, NULL, new_sernum, NULL);
+	__fib6_clean_all(net, NULL, new_sernum, NULL, false);
 }
 
 /*