From 4f823defdd5b106a5e89745ee8b163c71855de1e Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 30 Oct 2015 10:23:33 +0200 Subject: ipv4: fix to not remove local route on link down When fib_netdev_event calls fib_disable_ip on NETDEV_DOWN event we should not delete the local routes if the local address is still present. The confusion comes from the fact that both fib_netdev_event and fib_inetaddr_event use the NETDEV_DOWN constant. Fix it by returning back the variable 'force'. Steps to reproduce: modprobe dummy ifconfig dummy0 192.168.168.1 up ifconfig dummy0 down ip route list table local | grep dummy | grep host local 192.168.168.1 dev dummy0 proto kernel scope host src 192.168.168.1 Fixes: 8a3d03166f19 ("net: track link-status of ipv4 nexthops") Signed-off-by: Julian Anastasov Signed-off-by: David S. Miller --- net/ipv4/fib_frontend.c | 13 +++++++------ net/ipv4/fib_semantics.c | 11 ++++++++--- 2 files changed, 15 insertions(+), 9 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 690bcbc59f26..457b2cd75b85 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1110,9 +1110,10 @@ static void nl_fib_lookup_exit(struct net *net) net->ipv4.fibnl = NULL; } -static void fib_disable_ip(struct net_device *dev, unsigned long event) +static void fib_disable_ip(struct net_device *dev, unsigned long event, + bool force) { - if (fib_sync_down_dev(dev, event)) + if (fib_sync_down_dev(dev, event, force)) fib_flush(dev_net(dev)); rt_cache_flush(dev_net(dev)); arp_ifdown(dev); @@ -1140,7 +1141,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, /* Last address was deleted from this interface. * Disable IP. */ - fib_disable_ip(dev, event); + fib_disable_ip(dev, event, true); } else { rt_cache_flush(dev_net(dev)); } @@ -1157,7 +1158,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo unsigned int flags; if (event == NETDEV_UNREGISTER) { - fib_disable_ip(dev, event); + fib_disable_ip(dev, event, true); rt_flush_dev(dev); return NOTIFY_DONE; } @@ -1178,14 +1179,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo rt_cache_flush(net); break; case NETDEV_DOWN: - fib_disable_ip(dev, event); + fib_disable_ip(dev, event, false); break; case NETDEV_CHANGE: flags = dev_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) fib_sync_up(dev, RTNH_F_LINKDOWN); else - fib_sync_down_dev(dev, event); + fib_sync_down_dev(dev, event, false); /* fall through */ case NETDEV_CHANGEMTU: rt_cache_flush(net); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 064bd3caaa4f..2aa5b5e7da75 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1281,7 +1281,13 @@ int fib_sync_down_addr(struct net *net, __be32 local) return ret; } -int fib_sync_down_dev(struct net_device *dev, unsigned long event) +/* Event force Flags Description + * NETDEV_CHANGE 0 LINKDOWN Carrier OFF, not for scope host + * NETDEV_DOWN 0 LINKDOWN|DEAD Link down, not for scope host + * NETDEV_DOWN 1 LINKDOWN|DEAD Last address removed + * NETDEV_UNREGISTER 1 LINKDOWN|DEAD Device removed + */ +int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force) { int ret = 0; int scope = RT_SCOPE_NOWHERE; @@ -1290,8 +1296,7 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event) struct hlist_head *head = &fib_info_devhash[hash]; struct fib_nh *nh; - if (event == NETDEV_UNREGISTER || - event == NETDEV_DOWN) + if (force) scope = -1; hlist_for_each_entry(nh, head, nh_hash) { -- cgit v1.2.3 From c9b3292eeb52c6834e972eb5b8fe38914771ed12 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 30 Oct 2015 10:23:34 +0200 Subject: ipv4: update RTNH_F_LINKDOWN flag on UP event When nexthop is part of multipath route we should clear the LINKDOWN flag when link goes UP or when first address is added. This is needed because we always set LINKDOWN flag when DEAD flag was set but now on UP the nexthop is not dead anymore. Examples when LINKDOWN bit can be forgotten when no NETDEV_CHANGE is delivered: - link goes down (LINKDOWN is set), then link goes UP and device shows carrier OK but LINKDOWN remains set - last address is deleted (LINKDOWN is set), then address is added and device shows carrier OK but LINKDOWN remains set Steps to reproduce: modprobe dummy ifconfig dummy0 192.168.168.1 up here add a multipath route where one nexthop is for dummy0: ip route add 1.2.3.4 nexthop dummy0 nexthop SOME_OTHER_DEVICE ifconfig dummy0 down ifconfig dummy0 up now ip route shows nexthop that is not dead. Now set the sysctl var: echo 1 > /proc/sys/net/ipv4/conf/dummy0/ignore_routes_with_linkdown now ip route will show a dead nexthop because the forgotten RTNH_F_LINKDOWN is propagated as RTNH_F_DEAD. Fixes: 8a3d03166f19 ("net: track link-status of ipv4 nexthops") Signed-off-by: Julian Anastasov Signed-off-by: David S. Miller --- net/ipv4/fib_semantics.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 2aa5b5e7da75..e966f8599b4a 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1445,6 +1445,13 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags) if (!(dev->flags & IFF_UP)) return 0; + if (nh_flags & RTNH_F_DEAD) { + unsigned int flags = dev_get_flags(dev); + + if (flags & (IFF_RUNNING | IFF_LOWER_UP)) + nh_flags |= RTNH_F_LINKDOWN; + } + prev_fi = NULL; hash = fib_devindex_hashfn(dev->ifindex); head = &fib_info_devhash[hash]; -- cgit v1.2.3 From 44f49dd8b5a606870a1f21101522a0f9c4414784 Mon Sep 17 00:00:00 2001 From: Ani Sinha Date: Fri, 30 Oct 2015 16:54:31 -0700 Subject: ipmr: fix possible race resulting from improper usage of IP_INC_STATS_BH() in preemptible context. Fixes the following kernel BUG : BUG: using __this_cpu_add() in preemptible [00000000] code: bash/2758 caller is __this_cpu_preempt_check+0x13/0x15 CPU: 0 PID: 2758 Comm: bash Tainted: P O 3.18.19 #2 ffffffff8170eaca ffff880110d1b788 ffffffff81482b2a 0000000000000000 0000000000000000 ffff880110d1b7b8 ffffffff812010ae ffff880007cab800 ffff88001a060800 ffff88013a899108 ffff880108b84240 ffff880110d1b7c8 Call Trace: [] dump_stack+0x52/0x80 [] check_preemption_disabled+0xce/0xe1 [] __this_cpu_preempt_check+0x13/0x15 [] ipmr_queue_xmit+0x647/0x70c [] ip_mr_forward+0x32f/0x34e [] ip_mroute_setsockopt+0xe03/0x108c [] ? get_parent_ip+0x11/0x42 [] ? pollwake+0x4d/0x51 [] ? default_wake_function+0x0/0xf [] ? get_parent_ip+0x11/0x42 [] ? __wake_up_common+0x45/0x77 [] ? _raw_spin_unlock_irqrestore+0x1d/0x32 [] ? __wake_up_sync_key+0x4a/0x53 [] ? sock_def_readable+0x71/0x75 [] do_ip_setsockopt+0x9d/0xb55 [] ? unix_seqpacket_sendmsg+0x3f/0x41 [] ? sock_sendmsg+0x6d/0x86 [] ? sockfd_lookup_light+0x12/0x5d [] ? SyS_sendto+0xf3/0x11b [] ? new_sync_read+0x82/0xaa [] compat_ip_setsockopt+0x3b/0x99 [] compat_raw_setsockopt+0x11/0x32 [] compat_sock_common_setsockopt+0x18/0x1f [] compat_SyS_setsockopt+0x1a9/0x1cf [] compat_SyS_socketcall+0x180/0x1e3 [] cstar_dispatch+0x7/0x1e Signed-off-by: Ani Sinha Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/ipmr.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 866ee89f5254..8e8203d5c520 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1682,8 +1682,8 @@ static inline int ipmr_forward_finish(struct sock *sk, struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); - IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); - IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len); + IP_INC_STATS(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_ADD_STATS(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len); if (unlikely(opt->optlen)) ip_forward_options(skb); @@ -1745,7 +1745,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, * to blackhole. */ - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_FRAGFAILS); + IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); ip_rt_put(rt); goto out_free; } -- cgit v1.2.3