linux/net/ipv4
Eric Dumazet 0a0f7f8414 tcp: tcp_rtx_synack() can be called from process context
[ Upstream commit 0a375c8224 ]

Laurent reported the enclosed report [1]

This bug triggers with following coditions:

0) Kernel built with CONFIG_DEBUG_PREEMPT=y

1) A new passive FastOpen TCP socket is created.
   This FO socket waits for an ACK coming from client to be a complete
   ESTABLISHED one.
2) A socket operation on this socket goes through lock_sock()
   release_sock() dance.
3) While the socket is owned by the user in step 2),
   a retransmit of the SYN is received and stored in socket backlog.
4) At release_sock() time, the socket backlog is processed while
   in process context.
5) A SYNACK packet is cooked in response of the SYN retransmit.
6) -> tcp_rtx_synack() is called in process context.

Before blamed commit, tcp_rtx_synack() was always called from BH handler,
from a timer handler.

Fix this by using TCP_INC_STATS() & NET_INC_STATS()
which do not assume caller is in non preemptible context.

[1]
BUG: using __this_cpu_add() in preemptible [00000000] code: epollpep/2180
caller is tcp_rtx_synack.part.0+0x36/0xc0
CPU: 10 PID: 2180 Comm: epollpep Tainted: G           OE     5.16.0-0.bpo.4-amd64 #1  Debian 5.16.12-1~bpo11+1
Hardware name: Supermicro SYS-5039MC-H8TRF/X11SCD-F, BIOS 1.7 11/23/2021
Call Trace:
 <TASK>
 dump_stack_lvl+0x48/0x5e
 check_preemption_disabled+0xde/0xe0
 tcp_rtx_synack.part.0+0x36/0xc0
 tcp_rtx_synack+0x8d/0xa0
 ? kmem_cache_alloc+0x2e0/0x3e0
 ? apparmor_file_alloc_security+0x3b/0x1f0
 inet_rtx_syn_ack+0x16/0x30
 tcp_check_req+0x367/0x610
 tcp_rcv_state_process+0x91/0xf60
 ? get_nohz_timer_target+0x18/0x1a0
 ? lock_timer_base+0x61/0x80
 ? preempt_count_add+0x68/0xa0
 tcp_v4_do_rcv+0xbd/0x270
 __release_sock+0x6d/0xb0
 release_sock+0x2b/0x90
 sock_setsockopt+0x138/0x1140
 ? __sys_getsockname+0x7e/0xc0
 ? aa_sk_perm+0x3e/0x1a0
 __sys_setsockopt+0x198/0x1e0
 __x64_sys_setsockopt+0x21/0x30
 do_syscall_64+0x38/0xc0
 entry_SYSCALL_64_after_hwframe+0x44/0xae

Fixes: 168a8f5805 ("tcp: TCP Fast Open Server - main code path")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Laurent Fasnacht <laurent.fasnacht@proton.ch>
Acked-by: Neal Cardwell <ncardwell@google.com>
Link: https://lore.kernel.org/r/20220530213713.601888-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2022-06-14 18:32:36 +02:00
..
bpfilter net: Revert "net: optimize the sockptr_t for unified kernel/user address spaces" 2020-08-10 12:06:44 -07:00
netfilter netfilter: ipt_CLUSTERIP: fix refcount leak in clusterip_tg_check() 2022-01-27 10:54:00 +01:00
af_inet.c gso: do not skip outer ip header in case of ipip and net_failover 2022-03-02 11:42:49 +01:00
ah4.c xfrm: Use actual socket sk instead of skb socket for xfrm_output_resume 2021-04-14 08:42:05 +02:00
arp.c ipv4: Invalidate neighbour for broadcast address upon address addition 2022-04-13 21:00:57 +02:00
bpf_tcp_ca.c bpf: Change bpf_sk_storage_*() to accept ARG_PTR_TO_BTF_ID_SOCK_COMMON 2020-09-25 13:58:01 -07:00
cipso_ipv4.c net: ipv4: fix memory leak in netlbl_cipsov4_add_std 2021-06-23 14:42:41 +02:00
datagram.c
devinet.c net: return correct error code 2021-12-08 09:03:18 +01:00
esp4_offload.c esp: Fix BEET mode inter address family tunneling on GSO 2022-03-16 14:15:57 +01:00
esp4.c esp: limit skb_page_frag_refill use to a single page 2022-04-27 13:53:48 +02:00
fib_frontend.c ipv4: Invalidate neighbour for broadcast address upon address addition 2022-04-13 21:00:57 +02:00
fib_lookup.h
fib_notifier.c
fib_rules.c ipv4: convert fib_num_tclassid_users to atomic_t 2021-12-08 09:03:26 +01:00
fib_semantics.c net: ipv4: fix route with nexthop object delete warning 2022-04-13 21:01:04 +02:00
fib_trie.c ipv4: Silence suspicious RCU usage warning 2020-08-26 15:58:48 -07:00
fou.c genetlink: move to smaller ops wherever possible 2020-10-02 19:11:11 -07:00
gre_demux.c erspan: fix version 1 check in gre_parse_header() 2021-01-12 20:18:12 +01:00
gre_offload.c net: gre: recompute gre csum for sctp over gre tunnels 2020-08-03 15:29:44 -07:00
icmp.c lsm,selinux: pass flowi_common instead of flowi to the LSM hooks 2022-06-09 10:21:09 +02:00
igmp.c net: igmp: respect RCU rules in ip_mc_source() and ip_mc_msfilter() 2022-05-12 12:25:43 +02:00
inet_connection_sock.c lsm,selinux: pass flowi_common instead of flowi to the LSM hooks 2022-06-09 10:21:09 +02:00
inet_diag.c inet_diag: fix kernel-infoleak for UDP sockets 2021-12-22 09:30:53 +01:00
inet_fragment.c inet: frags: annotate races around fqdir->dead and fqdir->high_thresh 2022-01-27 10:54:33 +01:00
inet_hashtables.c secure_seq: use the 64 bits of the siphash for port offset calculation 2022-05-30 09:33:23 +02:00
inet_timewait_sock.c
inetpeer.c
ip_forward.c
ip_fragment.c inet: frags: annotate races around fqdir->dead and fqdir->high_thresh 2022-01-27 10:54:33 +01:00
ip_gre.c ip_gre, ip6_gre: Fix race condition on o_seqno in collect_md mode 2022-05-09 09:05:04 +02:00
ip_input.c
ip_options.c net: clean up codestyle for net/ipv4 2020-08-25 06:28:02 -07:00
ip_output.c lsm,selinux: pass flowi_common instead of flowi to the LSM hooks 2022-06-09 10:21:09 +02:00
ip_sockglue.c net: Remove duplicated midx check against 0 2020-08-25 06:23:59 -07:00
ip_tunnel_core.c tunnels: Fix off-by-one in lower MTU bounds for ICMP/ICMPv6 replies 2020-11-09 15:39:39 -08:00
ip_tunnel.c net: Set true network header for ECN decapsulation 2021-08-04 12:46:42 +02:00
ip_vti.c net: always use icmp{,v6}_ndo_send from ndo_start_xmit 2021-03-17 17:06:12 +01:00
ipcomp.c ipcomp: assign if_id to child tunnel from parent tunnel 2020-07-09 12:55:37 +02:00
ipconfig.c net: ipconfig: Don't override command-line hostnames or domains 2021-06-18 10:00:05 +02:00
ipip.c net: ipip: implement header_ops->parse_protocol for AF_PACKET 2020-06-30 12:29:39 -07:00
ipmr_base.c
ipmr.c ipmr,ip6mr: acquire RTNL before calling ip[6]mr_free_table() on failure path 2022-02-16 12:54:25 +01:00
Kconfig net: ipv4: remove duplicate "the the" phrase in Kconfig text 2020-08-18 16:02:16 -07:00
Makefile udp_tunnel: add central NIC RX port offload infrastructure 2020-07-10 13:54:00 -07:00
metrics.c
netfilter.c netfilter: use actual socket sk rather than skb sk when routing harder 2020-10-30 12:57:39 +01:00
netlink.c
nexthop.c net: nexthop: release IPv6 per-cpu dsts when replacing a nexthop group 2021-12-01 09:19:05 +01:00
ping.c lsm,selinux: pass flowi_common instead of flowi to the LSM hooks 2022-06-09 10:21:09 +02:00
proc.c tcp: switch orphan_count to bare per-cpu counters 2021-11-18 14:04:08 +01:00
protocol.c
raw_diag.c
raw.c lsm,selinux: pass flowi_common instead of flowi to the LSM hooks 2022-06-09 10:21:09 +02:00
route.c xfrm: fix "disable_policy" flag use when arriving from different devices 2022-05-25 09:17:58 +02:00
syncookies.c lsm,selinux: pass flowi_common instead of flowi to the LSM hooks 2022-06-09 10:21:09 +02:00
sysctl_net_ipv4.c net: Make tcp_allowed_congestion_control readonly in non-init netns 2021-04-21 13:00:57 +02:00
tcp_bbr.c tcp_bbr: fix u32 wrap bug in round logic if bbr_init() called after 2B packets 2021-08-18 08:59:13 +02:00
tcp_bic.c
tcp_bpf.c bpf, sockmap: Fix double uncharge the mem of sk_msg 2022-04-08 14:40:21 +02:00
tcp_cdg.c
tcp_cong.c net: Only allow init netns to set default tcp cong to a restricted algo 2021-05-14 09:50:46 +02:00
tcp_cubic.c tcp_cubic: fix spurious Hystart ACK train detections for not-cwnd-limited flows 2021-12-01 09:19:06 +01:00
tcp_dctcp.c
tcp_dctcp.h
tcp_diag.c
tcp_fastopen.c tcp: enable data-less, empty-cookie SYN with TFO_SERVER_COOKIE_NOT_REQD 2021-09-18 13:40:29 +02:00
tcp_highspeed.c Replace HTTP links with HTTPS ones: IPv* 2020-07-06 13:23:03 -07:00
tcp_htcp.c Replace HTTP links with HTTPS ones: IPv* 2020-07-06 13:23:03 -07:00
tcp_hybla.c
tcp_illinois.c
tcp_input.c tcp: fix F-RTO may not work correctly when receiving DSACK 2022-05-09 09:05:06 +02:00
tcp_ipv4.c tcp: md5: Fix overlap between vrf and non-vrf keys 2021-10-27 09:56:48 +02:00
tcp_lp.c
tcp_metrics.c genetlink: move to smaller ops wherever possible 2020-10-02 19:11:11 -07:00
tcp_minisocks.c tcp: md5: incorrect tcp_header_len for incoming connections 2022-05-09 09:05:03 +02:00
tcp_nv.c
tcp_offload.c net, gro: Set inner transport header offset in tcp/udp GRO hook 2021-08-12 13:22:05 +02:00
tcp_output.c tcp: tcp_rtx_synack() can be called from process context 2022-06-14 18:32:36 +02:00
tcp_rate.c tcp: ensure to use the most recently sent skb when filling the rate sample 2022-05-09 09:05:03 +02:00
tcp_recovery.c tcp: fix TLP timer not set when CA_STATE changes from DISORDER to OPEN 2021-02-03 23:28:52 +01:00
tcp_scalable.c net: ipv4: delete repeated words 2020-08-24 17:31:20 -07:00
tcp_timer.c tcp: make TCP_USER_TIMEOUT accurate for zero window probes 2021-02-03 23:28:51 +01:00
tcp_ulp.c
tcp_vegas.c tcp: use semicolons rather than commas to separate statements 2020-10-13 17:11:52 -07:00
tcp_vegas.h
tcp_veno.c Replace HTTP links with HTTPS ones: IPv* 2020-07-06 13:23:03 -07:00
tcp_westwood.c
tcp_yeah.c
tcp.c tcp: make tcp_read_sock() more robust 2022-03-19 13:44:46 +01:00
tunnel4.c tunnel4: add cb_handler to struct xfrm_tunnel 2020-07-09 12:51:36 +02:00
udp_bpf.c bpf, sockmap, udp: sk_prot needs inuse_idx set for proc stats 2021-07-28 14:35:37 +02:00
udp_diag.c
udp_impl.h net: pass a sockptr_t into ->setsockopt 2020-07-24 15:41:54 -07:00
udp_offload.c net, gro: Set inner transport header offset in tcp/udp GRO hook 2021-08-12 13:22:05 +02:00
udp_tunnel_core.c udp_tunnel: add central NIC RX port offload infrastructure 2020-07-10 13:54:00 -07:00
udp_tunnel_nic.c udp_tunnel: Fix end of loop test in udp_tunnel_nic_unregister() 2022-03-02 11:42:51 +01:00
udp_tunnel_stub.c udp_tunnel: add central NIC RX port offload infrastructure 2020-07-10 13:54:00 -07:00
udp.c lsm,selinux: pass flowi_common instead of flowi to the LSM hooks 2022-06-09 10:21:09 +02:00
udplite.c net/ipv4: remove compat_ip_{get,set}sockopt 2020-07-19 18:16:41 -07:00
xfrm4_input.c
xfrm4_output.c
xfrm4_policy.c
xfrm4_protocol.c
xfrm4_state.c
xfrm4_tunnel.c xfrm: interface: fix the priorities for ipip and ipv6 tunnels 2020-10-09 12:29:48 +02:00