From 289992eb6c1af89f8e9265276788e99cacd601b2 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 9 Jan 2019 09:57:39 +0000 Subject: net: ipv4: Fix memory leak in network namespace dismantle [ Upstream commit f97f4dd8b3bb9d0993d2491e0f22024c68109184 ] IPv4 routing tables are flushed in two cases: 1. In response to events in the netdev and inetaddr notification chains 2. When a network namespace is being dismantled In both cases only routes associated with a dead nexthop group are flushed. However, a nexthop group will only be marked as dead in case it is populated with actual nexthops using a nexthop device. This is not the case when the route in question is an error route (e.g., 'blackhole', 'unreachable'). Therefore, when a network namespace is being dismantled such routes are not flushed and leaked [1]. To reproduce: # ip netns add blue # ip -n blue route add unreachable 192.0.2.0/24 # ip netns del blue Fix this by not skipping error routes that are not marked with RTNH_F_DEAD when flushing the routing tables. To prevent the flushing of such routes in case #1, add a parameter to fib_table_flush() that indicates if the table is flushed as part of namespace dismantle or not. Note that this problem does not exist in IPv6 since error routes are associated with the loopback device. [1] unreferenced object 0xffff888066650338 (size 56): comm "ip", pid 1206, jiffies 4294786063 (age 26.235s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 b0 1c 62 61 80 88 ff ff ..........ba.... e8 8b a1 64 80 88 ff ff 00 07 00 08 fe 00 00 00 ...d............ backtrace: [<00000000856ed27d>] inet_rtm_newroute+0x129/0x220 [<00000000fcdfc00a>] rtnetlink_rcv_msg+0x397/0xa20 [<00000000cb85801a>] netlink_rcv_skb+0x132/0x380 [<00000000ebc991d2>] netlink_unicast+0x4c0/0x690 [<0000000014f62875>] netlink_sendmsg+0x929/0xe10 [<00000000bac9d967>] sock_sendmsg+0xc8/0x110 [<00000000223e6485>] ___sys_sendmsg+0x77a/0x8f0 [<000000002e94f880>] __sys_sendmsg+0xf7/0x250 [<00000000ccb1fa72>] do_syscall_64+0x14d/0x610 [<00000000ffbe3dae>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<000000003a8b605b>] 0xffffffffffffffff unreferenced object 0xffff888061621c88 (size 48): comm "ip", pid 1206, jiffies 4294786063 (age 26.235s) hex dump (first 32 bytes): 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk 6b 6b 6b 6b 6b 6b 6b 6b d8 8e 26 5f 80 88 ff ff kkkkkkkk..&_.... backtrace: [<00000000733609e3>] fib_table_insert+0x978/0x1500 [<00000000856ed27d>] inet_rtm_newroute+0x129/0x220 [<00000000fcdfc00a>] rtnetlink_rcv_msg+0x397/0xa20 [<00000000cb85801a>] netlink_rcv_skb+0x132/0x380 [<00000000ebc991d2>] netlink_unicast+0x4c0/0x690 [<0000000014f62875>] netlink_sendmsg+0x929/0xe10 [<00000000bac9d967>] sock_sendmsg+0xc8/0x110 [<00000000223e6485>] ___sys_sendmsg+0x77a/0x8f0 [<000000002e94f880>] __sys_sendmsg+0xf7/0x250 [<00000000ccb1fa72>] do_syscall_64+0x14d/0x610 [<00000000ffbe3dae>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<000000003a8b605b>] 0xffffffffffffffff Fixes: 8cced9eff1d4 ("[NETNS]: Enable routing configuration in non-initial namespace.") Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/fib_frontend.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4/fib_frontend.c') diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index ce646572b912..1f7b47ca2243 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -187,7 +187,7 @@ static void fib_flush(struct net *net) struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) - flushed += fib_table_flush(tb); + flushed += fib_table_flush(tb, false); } if (flushed) @@ -1277,7 +1277,7 @@ static void ip_fib_net_exit(struct net *net) hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) { hlist_del(&tb->tb_hlist); - fib_table_flush(tb); + fib_table_flush(tb, true); fib_free_table(tb); } } -- cgit v1.2.3