Neal Cardwell
3625b684a2
tcp: fix tcp_cwnd_validate() to not forget is_cwnd_limited
...
[ Upstream commit f4ce91ce12a7c6ead19b128ffa8cff6e3ded2a14 ]
This commit fixes a bug in the tracking of max_packets_out and
is_cwnd_limited. This bug can cause the connection to fail to remember
that is_cwnd_limited is true, causing the connection to fail to grow
cwnd when it should, causing throughput to be lower than it should be.
The following event sequence is an example that triggers the bug:
(a) The connection is cwnd_limited, but packets_out is not at its
peak due to TSO deferral deciding not to send another skb yet.
In such cases the connection can advance max_packets_seq and set
tp->is_cwnd_limited to true and max_packets_out to a small
number.
(b) Then later in the round trip the connection is pacing-limited (not
cwnd-limited), and packets_out is larger. In such cases the
connection would raise max_packets_out to a bigger number but
(unexpectedly) flip tp->is_cwnd_limited from true to false.
This commit fixes that bug.
One straightforward fix would be to separately track (a) the next
window after max_packets_out reaches a maximum, and (b) the next
window after tp->is_cwnd_limited is set to true. But this would
require consuming an extra u32 sequence number.
Instead, to save space we track only the most important
information. Specifically, we track the strongest available signal of
the degree to which the cwnd is fully utilized:
(1) If the connection is cwnd-limited then we remember that fact for
the current window.
(2) If the connection not cwnd-limited then we track the maximum
number of outstanding packets in the current window.
In particular, note that the new logic cannot trigger the buggy
(a)/(b) sequence above because with the new logic a condition where
tp->packets_out > tp->max_packets_out can only trigger an update of
tp->is_cwnd_limited if tp->is_cwnd_limited is false.
This first showed up in a testing of a BBRv2 dev branch, but this
buggy behavior highlighted a general issue with the
tcp_cwnd_validate() logic that can cause cwnd to fail to increase at
the proper rate for any TCP congestion control, including Reno or
CUBIC.
Fixes: ca8a226343 ("tcp: make cwnd-limited checks measurement-based, and gentler")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Kevin(Yudong) Yang <yyd@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2022-10-26 13:22:26 +02:00
..
9p
bluetooth
Bluetooth: L2CAP: Fix use-after-free caused by l2cap_chan_put
2022-08-03 11:59:37 +02:00
caif
net: caif: add proper error handling
2021-06-10 13:37:09 +02:00
iucv
netfilter
netfilter: conntrack: re-fetch conntrack after insertion
2022-06-06 08:33:50 +02:00
netns
ipv4: convert fib_num_tclassid_users to atomic_t
2021-12-08 09:01:12 +01:00
nfc
NFC: add NCI_UNREG flag to eliminate the race
2021-12-01 09:23:35 +01:00
phonet
sctp
sctp: use call_rcu to free endpoint
2022-01-05 12:37:44 +01:00
tc_act
net/sched: act_pedit: really ensure the skb is writable
2022-05-18 09:47:25 +02:00
6lowpan.h
act_api.h
net: sched: fix police ext initialization
2021-03-04 10:26:53 +01:00
addrconf.h
ipv6/addrconf: fix a null-ptr-deref bug for ip6_ptr
2022-08-03 11:59:39 +02:00
af_ieee802154.h
af_rxrpc.h
rxrpc: Make rxrpc_kernel_get_srtt() indicate validity
2020-09-09 19:12:23 +02:00
af_unix.h
af_vsock.h
ah.h
arp.h
ipv4: Invalidate neighbour for broadcast address upon address addition
2022-04-15 14:18:33 +02:00
atmclip.h
ax25.h
ax25: fix reference count leaks of ax25_dev
2022-04-20 09:19:39 +02:00
ax88796.h
bond_3ad.h
bonding: fix data-races around agg_select_timer
2022-02-23 11:59:58 +01:00
bond_alb.h
bonding: make tx_rebalance_counter an atomic
2021-12-14 14:49:00 +01:00
bond_options.h
bonding.h
bonding: wait for sysfs kobject destruction before freeing struct slave
2020-12-08 10:40:24 +01:00
bpf_sk_storage.h
busy_poll.h
net: Fix a data-race around sysctl_net_busy_poll.
2022-09-05 10:27:42 +02:00
calipso.h
cfg80211-wext.h
cfg80211.h
mac80211: properly handle A-MSDUs that start with an RFC 1042 header
2021-06-03 08:59:01 +02:00
cfg802154.h
checksum.h
net: Force inlining of checksum functions in net/checksum.h
2022-03-02 11:41:08 +01:00
cipso_ipv4.h
cls_cgroup.h
codel.h
codel_impl.h
codel_qdisc.h
compat.h
datalink.h
dcbevent.h
dcbnl.h
devlink.h
dn.h
dn_dev.h
dn_fib.h
dn_neigh.h
dn_nsp.h
dn_route.h
drop_monitor.h
net: drop_monitor: use IS_REACHABLE() to guard net_dm_hw_report()
2020-05-27 17:46:24 +02:00
dsa.h
dsfield.h
dst.h
net: Added pointer check for dst->ops->neigh_lookup in dst_neigh_lookup_skb
2020-07-22 09:32:47 +02:00
dst_cache.h
dst_metadata.h
net: fix a memleak when uncloning an skb dst and its metadata
2022-02-16 12:52:51 +01:00
dst_ops.h
erspan.h
esp.h
esp: limit skb_page_frag_refill use to a single page
2022-07-12 16:30:45 +02:00
ethoc.h
failover.h
fib_notifier.h
fib_rules.h
ipv6: fix memory leak in fib6_rule_suppress
2021-12-08 09:01:13 +01:00
firewire.h
flow.h
ipv4: Initialize flowi4_multipath_hash in data path
2020-09-26 18:03:12 +02:00
flow_dissector.h
net/sched: flower: fix parsing of ethertype following VLAN header
2022-04-20 09:19:34 +02:00
flow_offload.h
fou.h
fq.h
fq_impl.h
garp.h
gen_stats.h
genetlink.h
genetlink: remove genl_bind
2020-07-22 09:32:46 +02:00
geneve.h
gre.h
gro_cells.h
gtp.h
gue.h
hwbm.h
icmp.h
net: icmp: pass zeroed opts from icmp{,v6}_ndo_send before sending
2021-03-04 10:26:53 +01:00
ieee80211_radiotap.h
ieee802154_netdev.h
net/ieee802154: fix uninit value bug in dgram_sendmsg
2022-10-15 07:54:37 +02:00
if_inet6.h
ipv6: fix locking issues with loops over idev->addr_list
2022-06-14 18:11:25 +02:00
ife.h
ila.h
inet6_connection_sock.h
inet6_hashtables.h
inet_common.h
inet_connection_sock.h
tcp: relookup sock for RST+ACK packets handled by obsolete req sock
2021-03-30 14:35:26 +02:00
inet_ecn.h
inet_ecn: Fix endianness of checksum update when setting ECT(1)
2020-12-08 10:40:25 +01:00
inet_frag.h
inet: frags: annotate races around fqdir->dead and fqdir->high_thresh
2022-01-27 09:19:54 +01:00
inet_hashtables.h
secure_seq: use the 64 bits of the siphash for port offset calculation
2022-06-06 08:33:49 +02:00
inet_sock.h
tcp/dccp: Fix a data-race around sysctl_tcp_fwmark_accept.
2022-07-29 17:14:11 +02:00
inet_timewait_sock.h
inetpeer.h
ip.h
ip: Fix a data-race around sysctl_fwmark_reflect.
2022-07-29 17:14:11 +02:00
ip6_checksum.h
ip6_fib.h
ipv6: annotate accesses to fn->fn_sernum
2022-02-01 17:24:38 +01:00
ip6_route.h
net: ipv6: fix returned variable type in ip6_skb_dst_mtu
2021-08-12 13:20:57 +02:00
ip6_tunnel.h
ip_fib.h
ipv4: convert fib_num_tclassid_users to atomic_t
2021-12-08 09:01:12 +01:00
ip_tunnels.h
ip_tunnels: Set tunnel option flag when tunnel metadata is present
2020-11-24 13:29:05 +01:00
ip_vs.h
ipvs: allow connection reuse for unconfirmed conntrack
2020-08-19 08:16:10 +02:00
ipcomp.h
ipconfig.h
ipv6.h
ipv6_frag.h
inet: frags: annotate races around fqdir->dead and fqdir->high_thresh
2022-01-27 09:19:54 +01:00
ipv6_stubs.h
net: ipv6: add fib6_nh_release_dsts stub
2021-12-01 09:23:33 +01:00
ipx.h
bonding/alb: properly access headers in bond_alb_xmit()
2020-02-11 04:35:48 -08:00
iw_handler.h
kcm.h
l3mdev.h
lag.h
lapb.h
lib80211.h
llc.h
llc: fix out-of-bound array index in llc_sk_dev_hash()
2021-11-17 09:48:47 +01:00
llc_c_ac.h
llc_c_ev.h
llc_c_st.h
llc_conn.h
llc_if.h
llc_pdu.h
net: llc: fix skb_over_panic
2021-08-04 12:27:39 +02:00
llc_s_ac.h
llc_s_ev.h
llc_s_st.h
llc_sap.h
lwtunnel.h
mac80211.h
mac80211: populate debugfs only after cfg80211 init
2020-04-29 16:33:18 +02:00
mac802154.h
mip6.h
mld.h
mpls.h
mpls_iptunnel.h
mrp.h
ncsi.h
ndisc.h
neighbour.h
net, neigh: Enable state migration between NUD_PERMANENT and NTF_USE
2021-11-17 09:48:49 +01:00
net_failover.h
net_namespace.h
net: make get_net_ns return error if NET_NS is disabled
2021-06-23 14:41:25 +02:00
net_ratelimit.h
netevent.h
netlabel.h
netlink.h
netprio_cgroup.h
netrom.h
nexthop.h
net: ipv4: Fix rtnexthop len when RTA_FLOW is present
2021-10-06 15:42:33 +02:00
nl802154.h
net: ieee802154: handle iftypes as u32
2021-12-01 09:23:32 +01:00
nsh.h
p8022.h
page_pool.h
mm: fix struct page layout on 32-bit systems
2021-05-19 10:08:31 +02:00
ping.h
pkt_cls.h
net_sched: fix ops->bind_class() implementations
2020-02-01 09:34:38 +00:00
pkt_sched.h
net: prevent user from passing illegal stab size
2021-10-17 10:42:34 +02:00
pptp.h
protocol.h
psample.h
psample: Add a fwd declaration for skbuff
2021-08-18 08:56:59 +02:00
psnap.h
raw.h
raw: Fix a data-race around sysctl_raw_l3mdev_accept.
2022-07-21 20:59:22 +02:00
rawv6.h
red.h
sch_red: fix off-by-one checks in red_check_params()
2021-04-14 08:24:14 +02:00
regulatory.h
request_sock.h
rose.h
route.h
ipv4: remove sparse error in ip_neigh_gw4()
2022-02-01 17:24:39 +01:00
rsi_91x.h
rtnetlink.h
can: dev: Move device back to init netns on owning netns delete
2021-03-30 14:35:29 +02:00
rtnh.h
sch_generic.h
net: sched: add barrier to fix packet stuck problem for lockless qdisc
2022-06-14 18:11:55 +02:00
scm.h
secure_seq.h
secure_seq: use the 64 bits of the siphash for port offset calculation
2022-06-06 08:33:49 +02:00
seg6.h
seg6_hmac.h
seg6_local.h
slhc_vj.h
smc.h
snmp.h
sock.h
net: Fix data-races around sysctl_mem.
2022-07-21 20:59:20 +02:00
sock_reuseport.h
Space.h
stp.h
strparser.h
bpf: sockmap, strparser, and tls are reusing qdisc_skb_cb and colliding
2021-11-17 09:48:48 +01:00
switchdev.h
tcp.h
tcp: fix tcp_cwnd_validate() to not forget is_cwnd_limited
2022-10-26 13:22:26 +02:00
tcp_states.h
timewait_sock.h
tipc.h
tls.h
net/tls: Fix flipped sign in tls_err_abort() calls
2021-11-02 19:46:12 +01:00
transp_v6.h
tso.h
tun_proto.h
udp.h
udp: Fix a data-race around sysctl_udp_l3mdev_accept.
2022-07-29 17:14:14 +02:00
udp_tunnel.h
udp: call udp_encap_enable for v6 sockets when enabling encap
2022-04-15 14:18:01 +02:00
udplite.h
vsock_addr.h
vxlan.h
wext.h
wimax.h
x25.h
x25device.h
xdp.h
xdp_priv.h
xdp_sock.h
xfrm.h
xfrm: Check if_id in xfrm_migrate
2022-03-19 13:40:16 +01:00