From 1bfa26ff8c4b7512f4e4efa6df211239223033d4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 23 Mar 2018 07:56:58 -0700 Subject: ipv6: fix possible deadlock in rt6_age_examine_exception() syzbot reported a LOCKDEP splat [1] in rt6_age_examine_exception() rt6_age_examine_exception() is called while rt6_exception_lock is held. This lock is the lower one in the lock hierarchy, thus we can not call dst_neigh_lookup() function, as it can fallback to neigh_create() We should instead do a pure RCU lookup. As a bonus we avoid a pair of atomic operations on neigh refcount. [1] WARNING: possible circular locking dependency detected 4.16.0-rc4+ #277 Not tainted syz-executor7/4015 is trying to acquire lock: (&ndev->lock){++--}, at: [<00000000416dce19>] __ipv6_dev_mc_dec+0x45/0x350 net/ipv6/mcast.c:928 but task is already holding lock: (&tbl->lock){++-.}, at: [<00000000b5cb1d65>] neigh_ifdown+0x3d/0x250 net/core/neighbour.c:292 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&tbl->lock){++-.}: __raw_write_lock_bh include/linux/rwlock_api_smp.h:203 [inline] _raw_write_lock_bh+0x31/0x40 kernel/locking/spinlock.c:312 __neigh_create+0x87e/0x1d90 net/core/neighbour.c:528 neigh_create include/net/neighbour.h:315 [inline] ip6_neigh_lookup+0x9a7/0xba0 net/ipv6/route.c:228 dst_neigh_lookup include/net/dst.h:405 [inline] rt6_age_examine_exception net/ipv6/route.c:1609 [inline] rt6_age_exceptions+0x381/0x660 net/ipv6/route.c:1645 fib6_age+0xfb/0x140 net/ipv6/ip6_fib.c:2033 fib6_clean_node+0x389/0x580 net/ipv6/ip6_fib.c:1919 fib6_walk_continue+0x46c/0x8a0 net/ipv6/ip6_fib.c:1845 fib6_walk+0x91/0xf0 net/ipv6/ip6_fib.c:1893 fib6_clean_tree+0x1e6/0x340 net/ipv6/ip6_fib.c:1970 __fib6_clean_all+0x1f4/0x3a0 net/ipv6/ip6_fib.c:1986 fib6_clean_all net/ipv6/ip6_fib.c:1997 [inline] fib6_run_gc+0x16b/0x3c0 net/ipv6/ip6_fib.c:2053 ndisc_netdev_event+0x3c2/0x4a0 net/ipv6/ndisc.c:1781 notifier_call_chain+0x136/0x2c0 kernel/notifier.c:93 __raw_notifier_call_chain kernel/notifier.c:394 [inline] raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401 call_netdevice_notifiers_info+0x32/0x70 net/core/dev.c:1707 call_netdevice_notifiers net/core/dev.c:1725 [inline] __dev_notify_flags+0x262/0x430 net/core/dev.c:6960 dev_change_flags+0xf5/0x140 net/core/dev.c:6994 devinet_ioctl+0x126a/0x1ac0 net/ipv4/devinet.c:1080 inet_ioctl+0x184/0x310 net/ipv4/af_inet.c:919 sock_do_ioctl+0xef/0x390 net/socket.c:957 sock_ioctl+0x36b/0x610 net/socket.c:1081 vfs_ioctl fs/ioctl.c:46 [inline] do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:686 SYSC_ioctl fs/ioctl.c:701 [inline] SyS_ioctl+0x8f/0xc0 fs/ioctl.c:692 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x42/0xb7 -> #2 (rt6_exception_lock){+.-.}: __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline] _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168 spin_lock_bh include/linux/spinlock.h:315 [inline] rt6_flush_exceptions+0x21/0x210 net/ipv6/route.c:1367 fib6_del_route net/ipv6/ip6_fib.c:1677 [inline] fib6_del+0x624/0x12c0 net/ipv6/ip6_fib.c:1761 __ip6_del_rt+0xc7/0x120 net/ipv6/route.c:2980 ip6_del_rt+0x132/0x1a0 net/ipv6/route.c:2993 __ipv6_dev_ac_dec+0x3b1/0x600 net/ipv6/anycast.c:332 ipv6_dev_ac_dec net/ipv6/anycast.c:345 [inline] ipv6_sock_ac_close+0x2b4/0x3e0 net/ipv6/anycast.c:200 inet6_release+0x48/0x70 net/ipv6/af_inet6.c:433 sock_release+0x8d/0x1e0 net/socket.c:594 sock_close+0x16/0x20 net/socket.c:1149 __fput+0x327/0x7e0 fs/file_table.c:209 ____fput+0x15/0x20 fs/file_table.c:243 task_work_run+0x199/0x270 kernel/task_work.c:113 exit_task_work include/linux/task_work.h:22 [inline] do_exit+0x9bb/0x1ad0 kernel/exit.c:865 do_group_exit+0x149/0x400 kernel/exit.c:968 get_signal+0x73a/0x16d0 kernel/signal.c:2469 do_signal+0x90/0x1e90 arch/x86/kernel/signal.c:809 exit_to_usermode_loop+0x258/0x2f0 arch/x86/entry/common.c:162 prepare_exit_to_usermode arch/x86/entry/common.c:196 [inline] syscall_return_slowpath arch/x86/entry/common.c:265 [inline] do_syscall_64+0x6ec/0x940 arch/x86/entry/common.c:292 entry_SYSCALL_64_after_hwframe+0x42/0xb7 -> #1 (&(&tb->tb6_lock)->rlock){+.-.}: __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline] _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168 spin_lock_bh include/linux/spinlock.h:315 [inline] __ip6_ins_rt+0x56/0x90 net/ipv6/route.c:1007 ip6_route_add+0x141/0x190 net/ipv6/route.c:2955 addrconf_prefix_route+0x44f/0x620 net/ipv6/addrconf.c:2359 fixup_permanent_addr net/ipv6/addrconf.c:3368 [inline] addrconf_permanent_addr net/ipv6/addrconf.c:3391 [inline] addrconf_notify+0x1ad2/0x2310 net/ipv6/addrconf.c:3460 notifier_call_chain+0x136/0x2c0 kernel/notifier.c:93 __raw_notifier_call_chain kernel/notifier.c:394 [inline] raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401 call_netdevice_notifiers_info+0x32/0x70 net/core/dev.c:1707 call_netdevice_notifiers net/core/dev.c:1725 [inline] __dev_notify_flags+0x15d/0x430 net/core/dev.c:6958 dev_change_flags+0xf5/0x140 net/core/dev.c:6994 do_setlink+0xa22/0x3bb0 net/core/rtnetlink.c:2357 rtnl_newlink+0xf37/0x1a50 net/core/rtnetlink.c:2965 rtnetlink_rcv_msg+0x57f/0xb10 net/core/rtnetlink.c:4641 netlink_rcv_skb+0x14b/0x380 net/netlink/af_netlink.c:2444 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:4659 netlink_unicast_kernel net/netlink/af_netlink.c:1308 [inline] netlink_unicast+0x4c4/0x6b0 net/netlink/af_netlink.c:1334 netlink_sendmsg+0xa4a/0xe60 net/netlink/af_netlink.c:1897 sock_sendmsg_nosec net/socket.c:629 [inline] sock_sendmsg+0xca/0x110 net/socket.c:639 ___sys_sendmsg+0x767/0x8b0 net/socket.c:2047 __sys_sendmsg+0xe5/0x210 net/socket.c:2081 SYSC_sendmsg net/socket.c:2092 [inline] SyS_sendmsg+0x2d/0x50 net/socket.c:2088 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x42/0xb7 -> #0 (&ndev->lock){++--}: lock_acquire+0x1d5/0x580 kernel/locking/lockdep.c:3920 __raw_write_lock_bh include/linux/rwlock_api_smp.h:203 [inline] _raw_write_lock_bh+0x31/0x40 kernel/locking/spinlock.c:312 __ipv6_dev_mc_dec+0x45/0x350 net/ipv6/mcast.c:928 ipv6_dev_mc_dec+0x110/0x1f0 net/ipv6/mcast.c:961 pndisc_destructor+0x21a/0x340 net/ipv6/ndisc.c:392 pneigh_ifdown net/core/neighbour.c:695 [inline] neigh_ifdown+0x149/0x250 net/core/neighbour.c:294 rt6_disable_ip+0x537/0x700 net/ipv6/route.c:3874 addrconf_ifdown+0x14b/0x14f0 net/ipv6/addrconf.c:3633 addrconf_notify+0x5f8/0x2310 net/ipv6/addrconf.c:3557 notifier_call_chain+0x136/0x2c0 kernel/notifier.c:93 __raw_notifier_call_chain kernel/notifier.c:394 [inline] raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401 call_netdevice_notifiers_info+0x32/0x70 net/core/dev.c:1707 call_netdevice_notifiers net/core/dev.c:1725 [inline] __dev_notify_flags+0x262/0x430 net/core/dev.c:6960 dev_change_flags+0xf5/0x140 net/core/dev.c:6994 devinet_ioctl+0x126a/0x1ac0 net/ipv4/devinet.c:1080 inet_ioctl+0x184/0x310 net/ipv4/af_inet.c:919 packet_ioctl+0x1ff/0x310 net/packet/af_packet.c:4066 sock_do_ioctl+0xef/0x390 net/socket.c:957 sock_ioctl+0x36b/0x610 net/socket.c:1081 vfs_ioctl fs/ioctl.c:46 [inline] do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:686 SYSC_ioctl fs/ioctl.c:701 [inline] SyS_ioctl+0x8f/0xc0 fs/ioctl.c:692 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x42/0xb7 other info that might help us debug this: Chain exists of: &ndev->lock --> rt6_exception_lock --> &tbl->lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&tbl->lock); lock(rt6_exception_lock); lock(&tbl->lock); lock(&ndev->lock); *** DEADLOCK *** 2 locks held by syz-executor7/4015: #0: (rtnl_mutex){+.+.}, at: [<00000000a2f16daa>] rtnl_lock+0x17/0x20 net/core/rtnetlink.c:74 #1: (&tbl->lock){++-.}, at: [<00000000b5cb1d65>] neigh_ifdown+0x3d/0x250 net/core/neighbour.c:292 stack backtrace: CPU: 0 PID: 4015 Comm: syz-executor7 Not tainted 4.16.0-rc4+ #277 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x194/0x24d lib/dump_stack.c:53 print_circular_bug.isra.38+0x2cd/0x2dc kernel/locking/lockdep.c:1223 check_prev_add kernel/locking/lockdep.c:1863 [inline] check_prevs_add kernel/locking/lockdep.c:1976 [inline] validate_chain kernel/locking/lockdep.c:2417 [inline] __lock_acquire+0x30a8/0x3e00 kernel/locking/lockdep.c:3431 lock_acquire+0x1d5/0x580 kernel/locking/lockdep.c:3920 __raw_write_lock_bh include/linux/rwlock_api_smp.h:203 [inline] _raw_write_lock_bh+0x31/0x40 kernel/locking/spinlock.c:312 __ipv6_dev_mc_dec+0x45/0x350 net/ipv6/mcast.c:928 ipv6_dev_mc_dec+0x110/0x1f0 net/ipv6/mcast.c:961 pndisc_destructor+0x21a/0x340 net/ipv6/ndisc.c:392 pneigh_ifdown net/core/neighbour.c:695 [inline] neigh_ifdown+0x149/0x250 net/core/neighbour.c:294 rt6_disable_ip+0x537/0x700 net/ipv6/route.c:3874 addrconf_ifdown+0x14b/0x14f0 net/ipv6/addrconf.c:3633 addrconf_notify+0x5f8/0x2310 net/ipv6/addrconf.c:3557 notifier_call_chain+0x136/0x2c0 kernel/notifier.c:93 __raw_notifier_call_chain kernel/notifier.c:394 [inline] raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401 call_netdevice_notifiers_info+0x32/0x70 net/core/dev.c:1707 call_netdevice_notifiers net/core/dev.c:1725 [inline] __dev_notify_flags+0x262/0x430 net/core/dev.c:6960 dev_change_flags+0xf5/0x140 net/core/dev.c:6994 devinet_ioctl+0x126a/0x1ac0 net/ipv4/devinet.c:1080 inet_ioctl+0x184/0x310 net/ipv4/af_inet.c:919 packet_ioctl+0x1ff/0x310 net/packet/af_packet.c:4066 sock_do_ioctl+0xef/0x390 net/socket.c:957 sock_ioctl+0x36b/0x610 net/socket.c:1081 vfs_ioctl fs/ioctl.c:46 [inline] do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:686 SYSC_ioctl fs/ioctl.c:701 [inline] SyS_ioctl+0x8f/0xc0 fs/ioctl.c:692 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x42/0xb7 Fixes: c757faa8bfa2 ("ipv6: prepare fib6_age() for exception table") Signed-off-by: Eric Dumazet Cc: Wei Wang Cc: Martin KaFai Lau Acked-by: Wei Wang Signed-off-by: David S. Miller --- net/ipv6/route.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'net/ipv6/route.c') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b0d5c64e1978..b33d057ac5eb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1626,11 +1626,10 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, struct neighbour *neigh; __u8 neigh_flags = 0; - neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway); - if (neigh) { + neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); + if (neigh) neigh_flags = neigh->flags; - neigh_release(neigh); - } + if (!(neigh_flags & NTF_ROUTER)) { RT6_TRACE("purging route %p via non-router but gateway\n", rt); @@ -1654,7 +1653,8 @@ void rt6_age_exceptions(struct rt6_info *rt, if (!rcu_access_pointer(rt->rt6i_exception_bucket)) return; - spin_lock_bh(&rt6_exception_lock); + rcu_read_lock_bh(); + spin_lock(&rt6_exception_lock); bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, lockdep_is_held(&rt6_exception_lock)); @@ -1668,7 +1668,8 @@ void rt6_age_exceptions(struct rt6_info *rt, bucket++; } } - spin_unlock_bh(&rt6_exception_lock); + spin_unlock(&rt6_exception_lock); + rcu_read_unlock_bh(); } struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, -- cgit v1.2.3 From b6cdbc85234b072340b8923e69f49ec293f905dc Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 29 Mar 2018 17:44:57 -0700 Subject: net/ipv6: Fix route leaking between VRFs Donald reported that IPv6 route leaking between VRFs is not working. The root cause is the strict argument in the call to rt6_lookup when validating the nexthop spec. ip6_route_check_nh validates the gateway and device (if given) of a route spec. It in turn could call rt6_lookup (e.g., lookup in a given table did not succeed so it falls back to a full lookup) and if so sets the strict argument to 1. That means if the egress device is given, the route lookup needs to return a result with the same device. This strict requirement does not work with VRFs (IPv4 or IPv6) because the oif in the flow struct is overridden with the index of the VRF device to trigger a match on the l3mdev rule and force the lookup to its table. The right long term solution is to add an l3mdev index to the flow struct such that the oif is not overridden. That solution will not backport well, so this patch aims for a simpler solution to relax the strict argument if the route spec device is an l3mdev slave. As done in other places, use the FLOWI_FLAG_SKIP_NH_OIF to know that the RT6_LOOKUP_F_IFACE flag needs to be removed. Fixes: ca254490c8df ("net: Add VRF support to IPv6 stack") Reported-by: Donald Sharp Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/route.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net/ipv6/route.c') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b33d057ac5eb..fc74352fac12 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -919,6 +919,9 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net, struct rt6_info *rt, *rt_cache; struct fib6_node *fn; + if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) + flags &= ~RT6_LOOKUP_F_IFACE; + rcu_read_lock(); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: -- cgit v1.2.3