mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-16 15:26:42 +07:00
5a86d68bcf
When network namespace is destroyed, cleanup_net() is called.
cleanup_net() holds pernet_ops_rwsem then calls each ->exit callback.
So that clusterip_tg_destroy() is called by cleanup_net().
And clusterip_tg_destroy() calls unregister_netdevice_notifier().
But both cleanup_net() and clusterip_tg_destroy() hold same
lock(pernet_ops_rwsem). hence deadlock occurrs.
After this patch, only 1 notifier is registered when module is inserted.
And all of configs are added to per-net list.
test commands:
%ip netns add vm1
%ip netns exec vm1 bash
%ip link set lo up
%iptables -A INPUT -p tcp -i lo -d 192.168.0.5 --dport 80 \
-j CLUSTERIP --new --hashmode sourceip \
--clustermac 01:00:5e:00:00:20 --total-nodes 2 --local-node 1
%exit
%ip netns del vm1
splat looks like:
[ 341.809674] ============================================
[ 341.809674] WARNING: possible recursive locking detected
[ 341.809674] 4.19.0-rc5+ #16 Tainted: G W
[ 341.809674] --------------------------------------------
[ 341.809674] kworker/u4:2/87 is trying to acquire lock:
[ 341.809674] 000000005da2d519 (pernet_ops_rwsem){++++}, at: unregister_netdevice_notifier+0x8c/0x460
[ 341.809674]
[ 341.809674] but task is already holding lock:
[ 341.809674] 000000005da2d519 (pernet_ops_rwsem){++++}, at: cleanup_net+0x119/0x900
[ 341.809674]
[ 341.809674] other info that might help us debug this:
[ 341.809674] Possible unsafe locking scenario:
[ 341.809674]
[ 341.809674] CPU0
[ 341.809674] ----
[ 341.809674] lock(pernet_ops_rwsem);
[ 341.809674] lock(pernet_ops_rwsem);
[ 341.809674]
[ 341.809674] *** DEADLOCK ***
[ 341.809674]
[ 341.809674] May be due to missing lock nesting notation
[ 341.809674]
[ 341.809674] 3 locks held by kworker/u4:2/87:
[ 341.809674] #0: 00000000d9df6c92 ((wq_completion)"%s""netns"){+.+.}, at: process_one_work+0xafe/0x1de0
[ 341.809674] #1: 00000000c2cbcee2 (net_cleanup_work){+.+.}, at: process_one_work+0xb60/0x1de0
[ 341.809674] #2: 000000005da2d519 (pernet_ops_rwsem){++++}, at: cleanup_net+0x119/0x900
[ 341.809674]
[ 341.809674] stack backtrace:
[ 341.809674] CPU: 1 PID: 87 Comm: kworker/u4:2 Tainted: G W 4.19.0-rc5+ #16
[ 341.809674] Workqueue: netns cleanup_net
[ 341.809674] Call Trace:
[ ... ]
[ 342.070196] down_write+0x93/0x160
[ 342.070196] ? unregister_netdevice_notifier+0x8c/0x460
[ 342.070196] ? down_read+0x1e0/0x1e0
[ 342.070196] ? sched_clock_cpu+0x126/0x170
[ 342.070196] ? find_held_lock+0x39/0x1c0
[ 342.070196] unregister_netdevice_notifier+0x8c/0x460
[ 342.070196] ? register_netdevice_notifier+0x790/0x790
[ 342.070196] ? __local_bh_enable_ip+0xe9/0x1b0
[ 342.070196] ? __local_bh_enable_ip+0xe9/0x1b0
[ 342.070196] ? clusterip_tg_destroy+0x372/0x650 [ipt_CLUSTERIP]
[ 342.070196] ? trace_hardirqs_on+0x93/0x210
[ 342.070196] ? __bpf_trace_preemptirq_template+0x10/0x10
[ 342.070196] ? clusterip_tg_destroy+0x372/0x650 [ipt_CLUSTERIP]
[ 342.123094] clusterip_tg_destroy+0x3ad/0x650 [ipt_CLUSTERIP]
[ 342.123094] ? clusterip_net_init+0x3d0/0x3d0 [ipt_CLUSTERIP]
[ 342.123094] ? cleanup_match+0x17d/0x200 [ip_tables]
[ 342.123094] ? xt_unregister_table+0x215/0x300 [x_tables]
[ 342.123094] ? kfree+0xe2/0x2a0
[ 342.123094] cleanup_entry+0x1d5/0x2f0 [ip_tables]
[ 342.123094] ? cleanup_match+0x200/0x200 [ip_tables]
[ 342.123094] __ipt_unregister_table+0x9b/0x1a0 [ip_tables]
[ 342.123094] iptable_filter_net_exit+0x43/0x80 [iptable_filter]
[ 342.123094] ops_exit_list.isra.10+0x94/0x140
[ 342.123094] cleanup_net+0x45b/0x900
[ ... ]
Fixes:
|
||
|---|---|---|
| .. | ||
| bpfilter | ||
| netfilter | ||
| af_inet.c | ||
| ah4.c | ||
| arp.c | ||
| cipso_ipv4.c | ||
| datagram.c | ||
| devinet.c | ||
| esp4_offload.c | ||
| esp4.c | ||
| fib_frontend.c | ||
| fib_lookup.h | ||
| fib_notifier.c | ||
| fib_rules.c | ||
| fib_semantics.c | ||
| fib_trie.c | ||
| fou.c | ||
| gre_demux.c | ||
| gre_offload.c | ||
| icmp.c | ||
| igmp.c | ||
| inet_connection_sock.c | ||
| inet_diag.c | ||
| inet_fragment.c | ||
| inet_hashtables.c | ||
| inet_timewait_sock.c | ||
| inetpeer.c | ||
| ip_forward.c | ||
| ip_fragment.c | ||
| ip_gre.c | ||
| ip_input.c | ||
| ip_options.c | ||
| ip_output.c | ||
| ip_sockglue.c | ||
| ip_tunnel_core.c | ||
| ip_tunnel.c | ||
| ip_vti.c | ||
| ipcomp.c | ||
| ipconfig.c | ||
| ipip.c | ||
| ipmr_base.c | ||
| ipmr.c | ||
| Kconfig | ||
| Makefile | ||
| metrics.c | ||
| netfilter.c | ||
| netlink.c | ||
| ping.c | ||
| proc.c | ||
| protocol.c | ||
| raw_diag.c | ||
| raw.c | ||
| route.c | ||
| syncookies.c | ||
| sysctl_net_ipv4.c | ||
| tcp_bbr.c | ||
| tcp_bic.c | ||
| tcp_bpf.c | ||
| tcp_cdg.c | ||
| tcp_cong.c | ||
| tcp_cubic.c | ||
| tcp_dctcp.c | ||
| tcp_dctcp.h | ||
| tcp_diag.c | ||
| tcp_fastopen.c | ||
| tcp_highspeed.c | ||
| tcp_htcp.c | ||
| tcp_hybla.c | ||
| tcp_illinois.c | ||
| tcp_input.c | ||
| tcp_ipv4.c | ||
| tcp_lp.c | ||
| tcp_metrics.c | ||
| tcp_minisocks.c | ||
| tcp_nv.c | ||
| tcp_offload.c | ||
| tcp_output.c | ||
| tcp_rate.c | ||
| tcp_recovery.c | ||
| tcp_scalable.c | ||
| tcp_timer.c | ||
| tcp_ulp.c | ||
| tcp_vegas.c | ||
| tcp_vegas.h | ||
| tcp_veno.c | ||
| tcp_westwood.c | ||
| tcp_yeah.c | ||
| tcp.c | ||
| tunnel4.c | ||
| udp_diag.c | ||
| udp_impl.h | ||
| udp_offload.c | ||
| udp_tunnel.c | ||
| udp.c | ||
| udplite.c | ||
| xfrm4_input.c | ||
| xfrm4_mode_beet.c | ||
| xfrm4_mode_transport.c | ||
| xfrm4_mode_tunnel.c | ||
| xfrm4_output.c | ||
| xfrm4_policy.c | ||
| xfrm4_protocol.c | ||
| xfrm4_state.c | ||
| xfrm4_tunnel.c | ||