forge/linux-uconsole
1
0
Fork 0
Code Issues 1 Pull requests Projects Releases Packages Wiki Activity Actions
linux-uconsole/net/ipv4
History
Ilpo Järvinen 61c66cc52d tcp: prevent bogus FRTO undos with non-SACK flows 
[ Upstream commit 1236f22fba ]

If SACK is not enabled and the first cumulative ACK after the RTO
retransmission covers more than the retransmitted skb, a spurious
FRTO undo will trigger (assuming FRTO is enabled for that RTO).
The reason is that any non-retransmitted segment acknowledged will
set FLAG_ORIG_SACK_ACKED in tcp_clean_rtx_queue even if there is
no indication that it would have been delivered for real (the
scoreboard is not kept with TCPCB_SACKED_ACKED bits in the non-SACK
case so the check for that bit won't help like it does with SACK).
Having FLAG_ORIG_SACK_ACKED set results in the spurious FRTO undo
in tcp_process_loss.

We need to use more strict condition for non-SACK case and check
that none of the cumulatively ACKed segments were retransmitted
to prove that progress is due to original transmissions. Only then
keep FLAG_ORIG_SACK_ACKED set, allowing FRTO undo to proceed in
non-SACK case.

(FLAG_ORIG_SACK_ACKED is planned to be renamed to FLAG_ORIG_PROGRESS
to better indicate its purpose but to keep this change minimal, it
will be done in another patch).

Besides burstiness and congestion control violations, this problem
can result in RTO loop: When the loss recovery is prematurely
undoed, only new data will be transmitted (if available) and
the next retransmission can occur only after a new RTO which in case
of multiple losses (that are not for consecutive packets) requires
one RTO per loss to recover.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Tested-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-07-22 14:25:53 +02:00
..
netfilter netfilter: x_tables: initialise match/target check parameter struct 2018-07-17 11:31:46 +02:00
af_inet.c net: ping: do not abuse udp_poll() 2017-06-14 13:16:19 +02:00
ah4.c ipsec: check return value of skb_to_sgvec always 2018-04-13 19:50:23 +02:00
arp.c arp: fix arp_filter on l3slave devices 2018-04-13 19:50:24 +02:00
cipso_ipv4.c tcp/dccp: fix ireq->opt races 2017-11-18 11:11:06 +01:00
datagram.c net: Set sk_txhash from a random number 2015-07-29 22:44:04 -07:00
devinet.c ipv4: igmp: guard against silly MTU values 2018-01-02 20:33:24 +01:00
esp4.c ipsec: check return value of skb_to_sgvec always 2018-04-13 19:50:23 +02:00
fib_frontend.c ipv4: Fix use-after-free when flushing FIB tables 2018-01-02 20:33:26 +01:00
fib_lookup.h ipv4: consider TOS in fib_select_default 2015-07-24 22:46:11 -07:00
fib_rules.c net: ipv6: use common fib_default_rule_pref 2015-09-09 14:19:50 -07:00
fib_semantics.c ipv4: Fix error return value in fib_convert_metrics() 2018-07-11 16:03:47 +02:00
fib_trie.c net: Improve handling of failures on link and route dumps 2017-06-07 12:05:58 +02:00
fou.c net: add recursion limit to GRO 2016-11-15 07:46:38 +01:00
gre_demux.c gre: Remove support for sharing GRE protocol hook. 2015-08-10 14:03:54 -07:00
gre_offload.c net: add recursion limit to GRO 2016-11-15 07:46:38 +01:00
icmp.c Revert "ipv4/icmp: redirect messages can use the ingress daddr as source" 2015-10-14 06:01:07 -07:00
igmp.c net: igmp: add a missing rcu locking section 2018-02-16 20:09:37 +01:00
inet_connection_sock.c tcp/dccp: fix other lockdep splats accessing ireq_opt 2017-11-18 11:11:07 +01:00
inet_diag.c tcp/dccp: install syn_recv requests into ehash table 2015-10-03 04:32:41 -07:00
inet_fragment.c net: Fix hlist corruptions in inet_evict_bucket() 2018-03-31 18:12:33 +02:00
inet_hashtables.c tcp/dccp: fix hashdance race for passive sessions 2015-10-23 05:42:21 -07:00
inet_lro.c
inet_timewait_sock.c soreuseport: initialise timewait reuseport field 2018-05-16 10:06:50 +02:00
inetpeer.c net: Add helper function to compare inetpeer addresses 2015-08-28 13:32:36 -07:00
ip_forward.c net: Pass net into dst_output and remove dst_output_okfn 2015-10-08 04:26:54 -07:00
ip_fragment.c inet: frag: release spinlock before calling icmp_send() 2017-12-25 14:22:11 +01:00
ip_gre.c vxlan, gre, geneve: Set a large MTU on ovs-created tunnel devices 2016-06-24 10:18:18 -07:00
ip_input.c ipv4: Pass struct net into ip_defrag and ip_check_defrag 2015-10-12 19:44:16 -07:00
ip_options.c ipv4: coding style: comparison for inequality with NULL 2015-04-03 12:11:15 -04:00
ip_output.c net: test tailroom before appending to linear skb 2018-05-26 08:48:57 +02:00
ip_sockglue.c ipv4: remove warning in ip_recv_error 2018-06-13 16:15:28 +02:00
ip_tunnel.c ip_tunnel: better validate user provided tunnel names 2018-04-13 19:50:26 +02:00
ip_tunnel_core.c tunnels: Remove encapsulation offloads on decap. 2016-10-31 04:13:59 -06:00
ip_vti.c Revert "vti4: Don't override MTU passed on link creation via IFLA_MTU" 2018-05-30 22:11:35 +02:00
ipcomp.c ipv4: coding style: comparison for equality with NULL 2015-04-03 12:11:15 -04:00
ipconfig.c ipv4: ipconfig: avoid unused ic_proto_used symbol 2018-02-25 11:03:47 +01:00
ipip.c ipip: only increase err_count for some certain type icmp in ipip_err 2017-11-18 11:11:06 +01:00
ipmr.c ipmr, ip6mr: fix scheduling while atomic and a deadlock with ipmr_get_route 2016-11-15 07:46:37 +01:00
Kconfig ip_tunnel: replace dst_cache with generic implementation 2018-02-28 10:17:21 +01:00
Makefile tcp: track the packet timings in RACK 2015-10-21 07:00:48 -07:00
netfilter.c netfilter: use skb_to_full_sk in ip_route_me_harder 2018-03-18 11:17:51 +01:00
ping.c ipv4: fix memory leaks in udp_sendmsg, ping_v4_sendmsg 2018-05-26 08:48:46 +02:00
proc.c net: track success and failure of TCP PMTU probing 2015-07-21 22:36:33 -07:00
protocol.c
raw.c net: ipv4: fix for a race condition in raw_sendmsg 2018-01-02 20:33:25 +01:00
route.c ipv4: lock mtu in fnhe when received PMTU < net.ipv4.route.min_pmtu 2018-05-30 07:49:04 +02:00
syncookies.c tcp/dccp: fix ireq->opt races 2017-11-18 11:11:06 +01:00
sysctl_net_ipv4.c tcp: fix Fast Open key endianness 2018-07-22 14:25:53 +02:00
tcp.c tcp: ignore Fast Open on repair mode 2018-05-26 08:48:48 +02:00
tcp_bic.c tcp: add tcp_in_slow_start helper 2015-07-09 14:22:52 -07:00
tcp_cdg.c tcp: do not slow start when cwnd equals ssthresh 2015-07-09 14:22:52 -07:00
tcp_cong.c tcp: disallow cwnd undo when switching congestion control 2017-06-14 13:16:19 +02:00
tcp_cubic.c tcp_cubic: do not set epoch_start in the future 2015-09-17 22:35:07 -07:00
tcp_dctcp.c dctcp: avoid bogus doubling of cwnd after loss 2016-11-21 10:06:39 +01:00
tcp_diag.c tcp: ensure proper barriers in lockless contexts 2015-11-15 18:36:38 -05:00
tcp_fastopen.c tcp: initialize max window for a new fastopen socket 2017-02-04 09:45:09 +01:00
tcp_highspeed.c tcp: add tcp_in_slow_start helper 2015-07-09 14:22:52 -07:00
tcp_htcp.c tcp: add tcp_in_slow_start helper 2015-07-09 14:22:52 -07:00
tcp_hybla.c tcp: do not slow start when cwnd equals ssthresh 2015-07-09 14:22:52 -07:00
tcp_illinois.c net/tcp/illinois: replace broken algorithm reference link 2018-05-30 07:49:02 +02:00
tcp_input.c tcp: prevent bogus FRTO undos with non-SACK flows 2018-07-22 14:25:53 +02:00
tcp_ipv4.c tcp: verify the checksum of the first data segment in a new connection 2018-07-03 11:21:25 +02:00
tcp_lp.c tcp: fix wraparound issue in tcp_lp 2017-05-14 13:32:58 +02:00
tcp_memcontrol.c
tcp_metrics.c tcp: convert cached rtt from usec to jiffies when feeding initial rto 2016-04-20 15:41:56 +09:00
tcp_minisocks.c tcp: do not inherit fastopen_req from parent 2017-05-14 13:32:58 +02:00
tcp_offload.c tcp: reserve tcp_skb_mss() to tcp stack 2015-06-11 16:33:10 -07:00
tcp_output.c tcp: purge write queue in tcp_connect_init() 2018-05-26 08:48:58 +02:00
tcp_probe.c
tcp_recovery.c tcp: use RACK to detect losses 2015-10-21 07:00:53 -07:00
tcp_scalable.c tcp: add tcp_in_slow_start helper 2015-07-09 14:22:52 -07:00
tcp_timer.c net: tcp: close sock if net namespace is exiting 2018-01-31 12:06:14 +01:00
tcp_vegas.c tcp: fix under-evaluated ssthresh in TCP Vegas 2017-12-25 14:22:15 +01:00
tcp_vegas.h tcp: prepare CC get_info() access from getsockopt() 2015-04-29 17:10:38 -04:00
tcp_veno.c tcp: add tcp_in_slow_start helper 2015-07-09 14:22:52 -07:00
tcp_westwood.c tcp_westwood: fix tcp_westwood_info() 2015-05-05 19:50:09 -04:00
tcp_yeah.c tcp: cwnd does not increase in TCP YeAH 2016-09-30 10:18:34 +02:00
tunnel4.c
udp.c ipv4: fix memory leaks in udp_sendmsg, ping_v4_sendmsg 2018-05-26 08:48:46 +02:00
udp_diag.c sock_diag: specify info_size per inet protocol 2015-06-15 19:49:22 -07:00
udp_impl.h
udp_offload.c net: avoid skb_warn_bad_offload false positives on UFO 2017-08-12 19:29:08 -07:00
udp_tunnel.c tunnel: Clear IPCB(skb)->opt before dst_link_failure called 2016-04-20 15:41:56 +09:00
udplite.c
xfrm4_input.c netfilter: Pass net into okfn 2015-09-17 17:18:37 -07:00
xfrm4_mode_beet.c
xfrm4_mode_transport.c
xfrm4_mode_tunnel.c
xfrm4_output.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2015-10-24 06:54:12 -07:00
xfrm4_policy.c ipv4: lock mtu in fnhe when received PMTU < net.ipv4.route.min_pmtu 2018-05-30 07:49:04 +02:00
xfrm4_protocol.c
xfrm4_state.c
xfrm4_tunnel.c