linux_dsm_epyc7002/net/ipv4
Yuchung Cheng 98e36d449c tcp: check undo conditions before detecting losses
Currently RACK would mark loss before the undo operations in TCP
loss recovery. This could incorrectly identify real losses as
spurious. For example a sender first experiences a delay spike and
then eventually some packets were lost due to buffer overrun.
In this case, the sender should perform fast recovery b/c not all
the packets were lost.

But the sender may first trigger a (spurious) RTO and reset
cwnd to 1. The following ACKs may used to mark real losses by
tcp_rack_mark_lost. Then in tcp_process_loss this ACK could trigger
F-RTO undo condition and unmark real losses and revert the cwnd
reduction. If there are no more ACKs coming back, eventually the
sender would timeout again instead of performing fast recovery.

The patch fixes this incorrect process by always performing
the undo checks before detecting losses.

Fixes: 4f41b1c58a ("tcp: use RACK to detect losses")
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-13 22:37:16 -05:00
..
netfilter Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf 2017-01-05 11:49:57 -05:00
af_inet.c ipv4: Namespaceify tcp_tw_recycle and tcp_max_tw_buckets knob 2016-12-29 11:38:31 -05:00
ah4.c
arp.c
cipso_ipv4.c
datagram.c
devinet.c Replace <asm/uaccess.h> with <linux/uaccess.h> globally 2016-12-24 11:46:01 -08:00
esp4.c esp4: Fix integrity verification when ESN are used 2016-11-30 11:09:39 +01:00
fib_frontend.c ipv4: Do not allow MAIN to be alias for new LOCAL w/ custom rules 2017-01-03 09:38:34 -05:00
fib_lookup.h
fib_rules.c switchdev: remove FIB offload infrastructure 2016-09-28 04:48:00 -04:00
fib_semantics.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2017-01-11 14:43:39 -05:00
fib_trie.c Replace <asm/uaccess.h> with <linux/uaccess.h> globally 2016-12-24 11:46:01 -08:00
fou.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2016-10-30 12:42:58 -04:00
gre_demux.c
gre_offload.c net: add recursion limit to GRO 2016-10-20 14:32:22 -04:00
icmp.c net: for rate-limited ICMP replies save one atomic operation 2017-01-09 15:49:12 -05:00
igmp.c igmp: Make igmp group member RFC 3376 compliant 2017-01-02 13:01:03 -05:00
inet_connection_sock.c inet: Fix get port to handle zero port number with soreuseport set 2016-12-17 11:13:19 -05:00
inet_diag.c tcp: add reordering timer in RACK loss detection 2017-01-13 22:37:16 -05:00
inet_fragment.c
inet_hashtables.c net: Require exact match for TCP socket lookups if dif is l3mdev 2016-10-17 10:17:05 -04:00
inet_timewait_sock.c ipv4: Namespaceify tcp_tw_recycle and tcp_max_tw_buckets knob 2016-12-29 11:38:31 -05:00
inetpeer.c
ip_forward.c ipv4: allow local fragmentation in ip_finish_output_gso() 2016-11-03 16:10:26 -04:00
ip_fragment.c
ip_gre.c Replace <asm/uaccess.h> with <linux/uaccess.h> globally 2016-12-24 11:46:01 -08:00
ip_input.c net: VRF: Pass original iif to ip_route_input() 2016-09-16 04:24:07 -04:00
ip_options.c Replace <asm/uaccess.h> with <linux/uaccess.h> globally 2016-12-24 11:46:01 -08:00
ip_output.c Replace <asm/uaccess.h> with <linux/uaccess.h> globally 2016-12-24 11:46:01 -08:00
ip_sockglue.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2017-01-05 11:03:07 -05:00
ip_tunnel_core.c net: make ndo_get_stats64 a void function 2017-01-08 17:51:44 -05:00
ip_tunnel.c netns: make struct pernet_operations::id unsigned int 2016-11-18 10:59:15 -05:00
ip_vti.c netns: make struct pernet_operations::id unsigned int 2016-11-18 10:59:15 -05:00
ipcomp.c
ipconfig.c Replace <asm/uaccess.h> with <linux/uaccess.h> globally 2016-12-24 11:46:01 -08:00
ipip.c Replace <asm/uaccess.h> with <linux/uaccess.h> globally 2016-12-24 11:46:01 -08:00
ipmr.c ipmr: improve hash scalability 2017-01-12 16:48:26 -05:00
Kconfig Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2016-12-03 12:29:53 -05:00
Makefile net: ip, diag -- Add diag interface for raw sockets 2016-10-23 19:35:24 -04:00
netfilter.c netfilter: Update ip_route_me_harder to consider L3 domain 2016-11-24 12:44:36 +01:00
ping.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2016-12-16 10:24:44 -08:00
proc.c ipv4: Namespaceify tcp_tw_recycle and tcp_max_tw_buckets knob 2016-12-29 11:38:31 -05:00
protocol.c
raw_diag.c net: ip, raw_diag -- Use jump for exiting from nested loop 2016-11-03 15:25:26 -04:00
raw.c Replace <asm/uaccess.h> with <linux/uaccess.h> globally 2016-12-24 11:46:01 -08:00
route.c net: ipv4: remove disable of bottom half in inet_rtm_getroute 2017-01-09 13:54:44 -05:00
syncookies.c syncookies: use SipHash in place of SHA1 2017-01-09 13:58:57 -05:00
sysctl_net_ipv4.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2017-01-11 14:43:39 -05:00
tcp_bbr.c tcp_bbr: add a state transition diagram and accompanying comment 2016-10-29 17:12:43 -04:00
tcp_bic.c
tcp_cdg.c tcp: cdg: rename struct minmax in tcp_cdg.c to avoid a naming conflict 2016-09-21 00:22:59 -04:00
tcp_cong.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2016-11-22 13:27:16 -05:00
tcp_cubic.c
tcp_dctcp.c Revert "dctcp: update cwnd on congestion event" 2016-12-06 11:34:24 -05:00
tcp_diag.c
tcp_fastopen.c
tcp_highspeed.c tcp: add cwnd_undo functions to various tcp cc algorithms 2016-11-21 13:20:17 -05:00
tcp_htcp.c
tcp_hybla.c tcp: make undo_cwnd mandatory for congestion modules 2016-11-21 13:20:17 -05:00
tcp_illinois.c tcp: add cwnd_undo functions to various tcp cc algorithms 2016-11-21 13:20:17 -05:00
tcp_input.c tcp: check undo conditions before detecting losses 2017-01-13 22:37:16 -05:00
tcp_ipv4.c tcp: add reordering timer in RACK loss detection 2017-01-13 22:37:16 -05:00
tcp_lp.c tcp: make undo_cwnd mandatory for congestion modules 2016-11-21 13:20:17 -05:00
tcp_metrics.c tcp: do not export tcp_peer_is_proven() 2017-01-09 16:34:39 -05:00
tcp_minisocks.c ipv4: Namespaceify tcp_tw_recycle and tcp_max_tw_buckets knob 2016-12-29 11:38:31 -05:00
tcp_nv.c
tcp_offload.c gso: Support partial splitting at the frag_list pointer 2016-09-19 20:59:34 -04:00
tcp_output.c tcp: add reordering timer in RACK loss detection 2017-01-13 22:37:16 -05:00
tcp_probe.c
tcp_rate.c tcp: export data delivery rate 2016-09-21 00:23:00 -04:00
tcp_recovery.c tcp: use sequence to break TS ties for RACK loss detection 2017-01-13 22:37:16 -05:00
tcp_scalable.c tcp: add cwnd_undo functions to various tcp cc algorithms 2016-11-21 13:20:17 -05:00
tcp_timer.c tcp: add reordering timer in RACK loss detection 2017-01-13 22:37:16 -05:00
tcp_vegas.c tcp: make undo_cwnd mandatory for congestion modules 2016-11-21 13:20:17 -05:00
tcp_vegas.h
tcp_veno.c tcp: add cwnd_undo functions to various tcp cc algorithms 2016-11-21 13:20:17 -05:00
tcp_westwood.c tcp: make undo_cwnd mandatory for congestion modules 2016-11-21 13:20:17 -05:00
tcp_yeah.c tcp: add cwnd_undo functions to various tcp cc algorithms 2016-11-21 13:20:17 -05:00
tcp.c tcp: make TCP_INFO more consistent 2017-01-09 17:07:54 -05:00
tunnel4.c
udp_diag.c
udp_impl.h udplite: call proper backlog handlers 2016-11-24 15:32:14 -05:00
udp_offload.c net: add recursion limit to GRO 2016-10-20 14:32:22 -04:00
udp_tunnel.c
udp.c udp: inuse checks can quit early for reuseport 2017-01-06 20:56:48 -05:00
udplite.c udplite: call proper backlog handlers 2016-11-24 15:32:14 -05:00
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