linux/net/ipv4
Dan Streetman eeca98948d xfrm: dst_entries_init() per-net dst_ops
[ Upstream commit a8a572a6b5 ]

Remove the dst_entries_init/destroy calls for xfrm4 and xfrm6 dst_ops
templates; their dst_entries counters will never be used.  Move the
xfrm dst_ops initialization from the common xfrm/xfrm_policy.c to
xfrm4/xfrm4_policy.c and xfrm6/xfrm6_policy.c, and call dst_entries_init
and dst_entries_destroy for each net namespace.

The ipv4 and ipv6 xfrms each create dst_ops template, and perform
dst_entries_init on the templates.  The template values are copied to each
net namespace's xfrm.xfrm*_dst_ops.  The problem there is the dst_ops
pcpuc_entries field is a percpu counter and cannot be used correctly by
simply copying it to another object.

The result of this is a very subtle bug; changes to the dst entries
counter from one net namespace may sometimes get applied to a different
net namespace dst entries counter.  This is because of how the percpu
counter works; it has a main count field as well as a pointer to the
percpu variables.  Each net namespace maintains its own main count
variable, but all point to one set of percpu variables.  When any net
namespace happens to change one of the percpu variables to outside its
small batch range, its count is moved to the net namespace's main count
variable.  So with multiple net namespaces operating concurrently, the
dst_ops entries counter can stray from the actual value that it should
be; if counts are consistently moved from one net namespace to another
(which my testing showed is likely), then one net namespace winds up
with a negative dst_ops count while another winds up with a continually
increasing count, eventually reaching its gc_thresh limit, which causes
all new traffic on the net namespace to fail with -ENOBUFS.

Signed-off-by: Dan Streetman <dan.streetman@canonical.com>
Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
History 2016-01-31 11:23:38 -08:00
..
netfilter netfilter: ensure number of counters is >0 in do_replace() 2015-05-20 13:46:49 +02:00
af_inet.c net: add validation for the socket syscall protocol argument 2016-01-22 20:54:13 -08:00
ah4.c ipsec: Remove obsolete MAX_AH_AUTH_LEN 2014-09-18 10:54:36 +02:00
arp.c netfilter: Pass socket pointer down through okfn(). 2015-04-07 15:25:55 -04:00
cipso_ipv4.c ipv4: coding style: comparison for inequality with NULL 2015-04-03 12:11:15 -04:00
datagram.c ipv6: lock socket in ip6_datagram_connect() 2015-09-29 19:26:22 +02:00
devinet.c ipv4: coding style: comparison for inequality with NULL 2015-04-03 12:11:15 -04:00
esp4.c esp4: Use high-order sequence number bits for IV generation 2015-05-13 09:34:53 +02:00
fib_frontend.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2015-04-06 22:34:15 -04:00
fib_lookup.h ipv4: FIB Local/MAIN table collapse 2015-03-11 16:22:14 -04:00
fib_rules.c ipv4: coding style: comparison for equality with NULL 2015-04-03 12:11:15 -04:00
fib_semantics.c ipv4: coding style: comparison for equality with NULL 2015-04-03 12:11:15 -04:00
fib_trie.c fib_trie: leaf_walk_rcu should not compute key if key is less than pn->key 2015-12-09 14:03:10 -05:00
fou.c fou: clean up socket with kfree_rcu 2016-01-22 20:54:16 -08:00
geneve.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2015-04-14 15:44:14 -04:00
gre_demux.c net: Fix GRE RX to use skb_transport_header for GRE header offset 2014-09-08 15:23:05 -07:00
gre_offload.c ipv6: gre: support SIT encapsulation 2015-12-09 14:03:10 -05:00
icmp.c ipv4: coding style: comparison for equality with NULL 2015-04-03 12:11:15 -04:00
igmp.c ipv4: coding style: comparison for inequality with NULL 2015-04-03 12:11:15 -04:00
inet_connection_sock.c inet: fix race in reqsk_queue_unlink() 2015-10-27 09:51:50 +09:00
inet_diag.c tcp: prepare CC get_info() access from getsockopt() 2015-04-29 17:10:38 -04:00
inet_fragment.c ipv4: coding style: comparison for equality with NULL 2015-04-03 12:11:15 -04:00
inet_hashtables.c tcp/dccp: get rid of central timewait timer 2015-04-13 16:40:05 -04:00
inet_lro.c lro: remove dead code 2013-12-29 16:34:25 -05:00
inet_timewait_sock.c tcp/dccp: fix timewait races in timer handling 2016-01-31 11:23:37 -08:00
inetpeer.c inet: remove dead inetpeer sequence code 2014-09-08 16:42:42 -07:00
ip_forward.c ip_forward: Drop frames with attached skb->sk 2015-04-20 14:07:33 -04:00
ip_fragment.c inet: frags: fix defragmented packet's IP header for af_packet 2015-09-29 19:26:23 +02:00
ip_gre.c ipv4: coding style: comparison for equality with NULL 2015-04-03 12:11:15 -04:00
ip_input.c netfilter: Pass socket pointer down through okfn(). 2015-04-07 15:25:55 -04:00
ip_options.c ipv4: coding style: comparison for inequality with NULL 2015-04-03 12:11:15 -04:00
ip_output.c net: preserve IP control block during GSO segmentation 2016-01-31 11:23:36 -08:00
ip_sockglue.c ip: report the original address of ICMP messages 2015-07-10 09:49:30 -07:00
ip_tunnel.c ip_tunnel: fix ipv4 pmtu check to honor inner ip header df 2015-09-29 19:26:21 +02:00
ip_tunnel_core.c ipv4: ip_tunnel: use net namespace from rtable not socket 2015-04-08 12:09:42 -04:00
ip_vti.c ip_vti/ip6_vti: Preserve skb->mark after rcv_cb call 2015-05-28 06:23:32 +02:00
ipcomp.c ipv4: coding style: comparison for equality with NULL 2015-04-03 12:11:15 -04:00
ipconfig.c ipv4: coding style: comparison for equality with NULL 2015-04-03 12:11:15 -04:00
ipip.c ipv4: coding style: comparison for equality with NULL 2015-04-03 12:11:15 -04:00
ipmr.c net: ipmr: fix static mfc/dev leaks on table destruction 2015-12-14 21:24:31 -08:00
Kconfig net: Move fou_build_header into fou.c and refactor 2014-11-05 16:30:02 -05:00
Makefile net: Add Geneve tunneling protocol driver 2014-10-06 00:32:20 -04:00
netfilter.c netfilter: Use nf_hook_state in nf_queue_entry. 2015-04-04 12:25:22 -04:00
ping.c ipv4: Missing sk_nulls_node_init() in ping_unhash(). 2015-05-01 22:02:47 -04:00
proc.c tcp/dccp: get rid of central timewait timer 2015-04-13 16:40:05 -04:00
protocol.c net: Export inet_offloads and inet6_offloads 2014-09-19 17:15:31 -04:00
raw.c Merge branch 'for-davem' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2015-04-13 18:18:05 -04:00
route.c ipv4: Avoid crashing in ip_error 2015-05-22 14:23:40 -04:00
syncookies.c tcp: fix ipv4 mapped request socks 2015-03-25 00:57:48 -04:00
sysctl_net_ipv4.c ipv4: disable BH when changing ip local port range 2015-12-09 14:03:13 -05:00
tcp.c tcp: Do not call tcp_fastopen_reset_cipher from interrupt context 2015-07-10 09:49:29 -07:00
tcp_bic.c tcp: stretch ACK fixes prep 2015-01-28 22:18:37 -08:00
tcp_cong.c tcp: fix child sockets to use system default congestion control if not set 2015-05-31 21:49:14 -07:00
tcp_cubic.c tcp: restore 1.5x per RTT limit to CUBIC cwnd growth in congestion avoidance 2015-03-11 16:51:51 -04:00
tcp_dctcp.c tcp: prepare CC get_info() access from getsockopt() 2015-04-29 17:10:38 -04:00
tcp_diag.c ipv4: coding style: comparison for inequality with NULL 2015-04-03 12:11:15 -04:00
tcp_fastopen.c tcp: Do not call tcp_fastopen_reset_cipher from interrupt context 2015-07-10 09:49:29 -07:00
tcp_highspeed.c tcp: whitespace fixes 2014-09-01 18:12:45 -07:00
tcp_htcp.c tcp: whitespace fixes 2014-09-01 18:12:45 -07:00
tcp_hybla.c tcp: whitespace fixes 2014-09-01 18:12:45 -07:00
tcp_illinois.c tcp: prepare CC get_info() access from getsockopt() 2015-04-29 17:10:38 -04:00
tcp_input.c tcp: initialize tp->copied_seq in case of cross SYN connection 2015-12-14 21:24:31 -08:00
tcp_ipv4.c net: fix IP early demux races 2016-01-22 20:54:14 -08:00
tcp_lp.c tcp: remove in_flight parameter from cong_avoid() methods 2014-05-03 19:23:07 -04:00
tcp_memcontrol.c memcg: cleanup static keys decrement 2015-02-12 18:54:10 -08:00
tcp_metrics.c tcp: RFC7413 option support for Fast Open client 2015-04-07 18:36:39 -04:00
tcp_minisocks.c tcp/dccp: fix timewait races in timer handling 2016-01-31 11:23:37 -08:00
tcp_offload.c tcp: cleanup static functions 2015-02-28 16:56:51 -05:00
tcp_output.c tcp: restore fastopen with no data in SYN packet 2016-01-22 20:54:16 -08:00
tcp_probe.c tcp: whitespace fixes 2014-09-01 18:12:45 -07:00
tcp_scalable.c tcp: stretch ACK fixes prep 2015-01-28 22:18:37 -08:00
tcp_timer.c tcp: disable Fast Open on timeouts after handshake 2015-12-14 21:24:30 -08:00
tcp_vegas.c tcp: prepare CC get_info() access from getsockopt() 2015-04-29 17:10:38 -04:00
tcp_vegas.h tcp: prepare CC get_info() access from getsockopt() 2015-04-29 17:10:38 -04:00
tcp_veno.c tcp: stretch ACK fixes prep 2015-01-28 22:18:37 -08:00
tcp_westwood.c tcp_westwood: fix tcp_westwood_info() 2015-05-05 19:50:09 -04:00
tcp_yeah.c tcp_yeah: don't set ssthresh below 2 2016-01-31 11:23:36 -08:00
tunnel4.c net: Convert printks to pr_<level> 2012-03-11 23:42:51 -07:00
udp.c udp: fix dst races with multicast early demux 2015-09-29 19:26:25 +02:00
udp_diag.c ipv4: coding style: comparison for equality with NULL 2015-04-03 12:11:15 -04:00
udp_impl.h net: Remove iocb argument from sendmsg and recvmsg 2015-03-02 13:06:31 -05:00
udp_offload.c ipv4: coding style: comparison for inequality with NULL 2015-04-03 12:11:15 -04:00
udp_tunnel.c udp_tunnel: Pass UDP socket down through udp_tunnel{, 6}_xmit_skb(). 2015-04-07 15:29:08 -04:00
udplite.c net: Eliminate no_check from protosw 2014-05-23 16:28:53 -04:00
xfrm4_input.c netfilter: Pass socket pointer down through okfn(). 2015-04-07 15:25:55 -04:00
xfrm4_mode_beet.c ipv4: ERROR: code indent should use tabs where possible 2013-12-26 13:43:21 -05:00
xfrm4_mode_transport.c [IPSEC]: Use IPv6 calling convention as the convention for x->mode->output 2007-10-10 16:55:54 -07:00
xfrm4_mode_tunnel.c ipv4: hash net ptr into fragmentation bucket selection 2015-03-25 14:07:04 -04:00
xfrm4_output.c netfilter: Pass socket pointer down through okfn(). 2015-04-07 15:25:55 -04:00
xfrm4_policy.c xfrm: dst_entries_init() per-net dst_ops 2016-01-31 11:23:38 -08:00
xfrm4_protocol.c xfrm4: Remove duplicate semicolon 2014-06-30 07:49:47 +02:00
xfrm4_state.c inet: make no_pmtu_disc per namespace and kill ipv4_config 2013-12-18 16:58:20 -05:00
xfrm4_tunnel.c sit: add IPv4 over IPv4 support 2013-05-31 17:19:05 -07:00