From 2127d95aef6c795c3bd8b805722c5c46e8fe45dd Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sun, 7 Jan 2018 12:45:03 +0200 Subject: ipv6: Clear nexthop flags upon netdev up Previous patch marked nexthops with the 'dead' and 'linkdown' flags. Clear these flags when the netdev comes back up. Signed-off-by: Ido Schimmel Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_route.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 18e442ea93d8..caad39198c2a 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -169,6 +169,7 @@ void rt6_ifdown(struct net *net, struct net_device *dev); void rt6_mtu_change(struct net_device *dev, unsigned int mtu); void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); +void rt6_sync_up(struct net_device *dev, unsigned int nh_flags); static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { -- cgit v1.2.3 From 4c981e28d373e391b76577635e7e216976b71c57 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sun, 7 Jan 2018 12:45:04 +0200 Subject: ipv6: Prepare to handle multiple netdev events To make IPv6 more in line with IPv4 we need to be able to respond differently to different netdev events. For example, when a netdev is unregistered all the routes using it as their nexthop device should be flushed, whereas when the netdev's carrier changes only the 'linkdown' flag should be toggled. Currently, this is not possible, as the function that traverses the routing tables is not aware of the triggering event. Propagate the triggering event down, so that it could be used in later patches. Signed-off-by: Ido Schimmel Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_route.h | 2 +- net/ipv6/addrconf.c | 4 ++-- net/ipv6/route.c | 37 +++++++++++++++++++++---------------- 3 files changed, 24 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index caad39198c2a..6a2f80cbdf65 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -165,11 +165,11 @@ struct rt6_rtnl_dump_arg { }; int rt6_dump_route(struct rt6_info *rt, void *p_arg); -void rt6_ifdown(struct net *net, struct net_device *dev); void rt6_mtu_change(struct net_device *dev, unsigned int mtu); void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); void rt6_sync_up(struct net_device *dev, unsigned int nh_flags); +void rt6_disable_ip(struct net_device *dev, unsigned long event); static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b6405568ed7b..a13e1ffe87ec 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3580,6 +3580,7 @@ static bool addr_is_local(const struct in6_addr *addr) static int addrconf_ifdown(struct net_device *dev, int how) { + unsigned long event = how ? NETDEV_UNREGISTER : NETDEV_DOWN; struct net *net = dev_net(dev); struct inet6_dev *idev; struct inet6_ifaddr *ifa, *tmp; @@ -3589,8 +3590,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) ASSERT_RTNL(); - rt6_ifdown(net, dev); - neigh_ifdown(&nd_tbl, dev); + rt6_disable_ip(dev, event); idev = __in6_dev_get(dev); if (!idev) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4796d87e0b93..194fe9d9cd85 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2344,7 +2344,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->rt6i_idev = idev; dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 0); - /* Add this dst into uncached_list so that rt6_ifdown() can + /* Add this dst into uncached_list so that rt6_disable_ip() can * do proper release of the net_device */ rt6_uncached_list_add(rt); @@ -3461,7 +3461,10 @@ void rt6_clean_tohost(struct net *net, struct in6_addr *gateway) struct arg_netdev_event { const struct net_device *dev; - unsigned int nh_flags; + union { + unsigned int nh_flags; + unsigned long event; + }; }; static int fib6_ifup(struct rt6_info *rt, void *p_arg) @@ -3488,19 +3491,15 @@ void rt6_sync_up(struct net_device *dev, unsigned int nh_flags) fib6_clean_all(dev_net(dev), fib6_ifup, &arg); } -struct arg_dev_net { - struct net_device *dev; - struct net *net; -}; - /* called with write lock held for table with rt */ -static int fib6_ifdown(struct rt6_info *rt, void *arg) +static int fib6_ifdown(struct rt6_info *rt, void *p_arg) { - const struct arg_dev_net *adn = arg; - const struct net_device *dev = adn->dev; + const struct arg_netdev_event *arg = p_arg; + const struct net_device *dev = arg->dev; + const struct net *net = dev_net(dev); if (rt->dst.dev == dev && - rt != adn->net->ipv6.ip6_null_entry && + rt != net->ipv6.ip6_null_entry && (rt->rt6i_nsiblings == 0 || netdev_unregistering(dev) || !rt->rt6i_idev->cnf.ignore_routes_with_linkdown)) { rt->rt6i_nh_flags |= (RTNH_F_DEAD | RTNH_F_LINKDOWN); @@ -3510,15 +3509,21 @@ static int fib6_ifdown(struct rt6_info *rt, void *arg) return 0; } -void rt6_ifdown(struct net *net, struct net_device *dev) +static void rt6_sync_down_dev(struct net_device *dev, unsigned long event) { - struct arg_dev_net adn = { + struct arg_netdev_event arg = { .dev = dev, - .net = net, + .event = event, }; - fib6_clean_all(net, fib6_ifdown, &adn); - rt6_uncached_list_flush_dev(net, dev); + fib6_clean_all(dev_net(dev), fib6_ifdown, &arg); +} + +void rt6_disable_ip(struct net_device *dev, unsigned long event) +{ + rt6_sync_down_dev(dev, event); + rt6_uncached_list_flush_dev(dev_net(dev), dev); + neigh_ifdown(&nd_tbl, dev); } struct rt6_mtu_change_arg { -- cgit v1.2.3 From 27c6fa73f93b81671a77bdaa242473c3bda0ac4a Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sun, 7 Jan 2018 12:45:05 +0200 Subject: ipv6: Set nexthop flags upon carrier change Similar to IPv4, when the carrier of a netdev changes we should toggle the 'linkdown' flag on all the nexthops using it as their nexthop device. This will later allow us to test for the presence of this flag during route lookup and dump. Up until commit 4832c30d5458 ("net: ipv6: put host and anycast routes on device with address") host and anycast routes used the loopback netdev as their nexthop device and thus were not marked with the 'linkdown' flag. The patch preserves this behavior and allows one to ping the local address even when the nexthop device does not have a carrier and the 'ignore_routes_with_linkdown' sysctl is set. Signed-off-by: Ido Schimmel Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_route.h | 1 + net/ipv6/addrconf.c | 2 ++ net/ipv6/route.c | 23 +++++++++++++++++------ 3 files changed, 20 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 6a2f80cbdf65..34cd3b0c6ded 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -170,6 +170,7 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); void rt6_sync_up(struct net_device *dev, unsigned int nh_flags); void rt6_disable_ip(struct net_device *dev, unsigned long event); +void rt6_sync_down_dev(struct net_device *dev, unsigned long event); static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index a13e1ffe87ec..2435f7ab070b 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3438,6 +3438,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, } else if (event == NETDEV_CHANGE) { if (!addrconf_link_ready(dev)) { /* device is still not ready. */ + rt6_sync_down_dev(dev, event); break; } @@ -3449,6 +3450,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, * multicast snooping switches */ ipv6_mc_up(idev); + rt6_sync_up(dev, RTNH_F_LINKDOWN); break; } idev->if_flags |= IF_READY; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 194fe9d9cd85..2fd36c7dd143 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3498,18 +3498,29 @@ static int fib6_ifdown(struct rt6_info *rt, void *p_arg) const struct net_device *dev = arg->dev; const struct net *net = dev_net(dev); - if (rt->dst.dev == dev && - rt != net->ipv6.ip6_null_entry && - (rt->rt6i_nsiblings == 0 || netdev_unregistering(dev) || - !rt->rt6i_idev->cnf.ignore_routes_with_linkdown)) { - rt->rt6i_nh_flags |= (RTNH_F_DEAD | RTNH_F_LINKDOWN); + if (rt->dst.dev != dev || rt == net->ipv6.ip6_null_entry) + return 0; + + switch (arg->event) { + case NETDEV_UNREGISTER: return -1; + case NETDEV_DOWN: + if (rt->rt6i_nsiblings == 0 || + !rt->rt6i_idev->cnf.ignore_routes_with_linkdown) + return -1; + rt->rt6i_nh_flags |= RTNH_F_DEAD; + /* fall through */ + case NETDEV_CHANGE: + if (rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) + break; + rt->rt6i_nh_flags |= RTNH_F_LINKDOWN; + break; } return 0; } -static void rt6_sync_down_dev(struct net_device *dev, unsigned long event) +void rt6_sync_down_dev(struct net_device *dev, unsigned long event) { struct arg_netdev_event arg = { .dev = dev, -- cgit v1.2.3 From a2c554d3f8f65dd9c46a55811efad8156e328f85 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sun, 7 Jan 2018 12:45:11 +0200 Subject: ipv6: Add explicit flush indication to routes When routes that are a part of a multipath route are evaluated by fib6_ifdown() in response to NETDEV_DOWN and NETDEV_UNREGISTER events the state of their sibling routes is not considered. This will change in subsequent patches in order to align IPv6 with IPv4's behavior. For example, when the last sibling in a multipath route becomes dead, the entire multipath route needs to be removed. To prevent the tree walker from re-evaluating all the sibling routes each time, we can simply evaluate them once - when the first sibling is traversed. If we determine the entire multipath route needs to be removed, then the 'should_flush' bit is set in all the siblings, which will cause the walker to flush them when it traverses them. Signed-off-by: Ido Schimmel Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 44d96a91e745..affea1aa6ae4 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -173,7 +173,8 @@ struct rt6_info { unsigned short rt6i_nfheader_len; u8 rt6i_protocol; u8 exception_bucket_flushed:1, - unused:7; + should_flush:1, + unused:6; }; #define for_each_fib6_node_rt_rcu(fn) \ -- cgit v1.2.3 From 4a8e56ee2c8551e674f69ba007aabede8f0b88d9 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sun, 7 Jan 2018 12:45:13 +0200 Subject: ipv6: Export sernum update function We are going to allow dead routes to stay in the FIB tree (e.g., when they are part of a multipath route, directly connected route with no carrier) and revive them when their nexthop device gains carrier or when it is put administratively up. This is equivalent to the addition of the route to the FIB tree and we should therefore take care of updating the sernum of all the parent nodes of the node where the route is stored. Otherwise, we risk sockets caching and using sub-optimal dst entries. Export the function that performs the above, so that it could be invoked from fib6_ifup() later on. Signed-off-by: Ido Schimmel Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 1 + net/ipv6/ip6_fib.c | 11 ++++++++--- 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index affea1aa6ae4..ddf53dd1e948 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -405,6 +405,7 @@ unsigned int fib6_tables_seq_read(struct net *net); int fib6_tables_dump(struct net *net, struct notifier_block *nb); void fib6_update_sernum(struct rt6_info *rt); +void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt); #ifdef CONFIG_IPV6_MULTIPLE_TABLES int fib6_rules_init(void); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 5e4b5eef0ddd..c1bbe7bf9fdd 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1102,8 +1102,8 @@ void fib6_force_start_gc(struct net *net) jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } -static void fib6_update_sernum_upto_root(struct rt6_info *rt, - int sernum) +static void __fib6_update_sernum_upto_root(struct rt6_info *rt, + int sernum) { struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, lockdep_is_held(&rt->rt6i_table->tb6_lock)); @@ -1117,6 +1117,11 @@ static void fib6_update_sernum_upto_root(struct rt6_info *rt, } } +void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt) +{ + __fib6_update_sernum_upto_root(rt, fib6_new_sernum(net)); +} + /* * Add routing information to the routing tree. * / @@ -1230,7 +1235,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, err = fib6_add_rt2node(fn, rt, info, mxc, extack); if (!err) { - fib6_update_sernum_upto_root(rt, sernum); + __fib6_update_sernum_upto_root(rt, sernum); fib6_start_gc(info->nl_net, rt); } -- cgit v1.2.3