* [PATCH net-next 3/3] Move shared tcp code to net/ipv4v6shared
2017-10-03 22:22 [PATCH net-next 0/3] A own subdirectory for shared TCP code Richard Sailer
2017-10-03 22:22 ` [PATCH net-next 1/3] net/ipv4: Move shared tcp code to own subdirectory Richard Sailer
2017-10-03 22:22 ` [PATCH net-next 2/3] tcp: Move cc algorithms " Richard Sailer
@ 2017-10-03 22:22 ` Richard Sailer
[not found] ` <CAOaVG14r2Uwm+r17Oa9jwKj50vRr8=SqwXEmmGAeW8rHj3FgXg@mail.gmail.com>
2017-10-03 22:42 ` [PATCH net-next 0/3] A own subdirectory for shared TCP code Eric Dumazet
2017-10-03 23:03 ` David Miller
4 siblings, 1 reply; 10+ messages in thread
From: Richard Sailer @ 2017-10-03 22:22 UTC (permalink / raw)
To: netdev, davem; +Cc: kuznet, yoshfuji
Currently a lot of Code shared between IPv4 and IPv6 resides in net/ipv4.
As an attempt to make things more modular and encapsulated + the source tree
more self documenting this commit:
* introduces net/ipv4v6shared
* moves the shared tcp code there
* updates the makefiles accordingly
* creates a new Kconfig file for the TCP code
* updates all other Kconfig files accordingly
Of course I left the ipv4 specific parts of tcp (tcp_ipv4.c and tcp_offload.c)
in net/ipv4.
Thanks valdis from #kernelnewbies for the hint of doing this, when already
isolating tcp code.
Signed-off-by: Richard Sailer <richard_siegfried@systemli.org>
---
net/Kconfig | 1 +
net/Makefile | 6 +-
net/ipv4/Kconfig | 321 --------------------
net/ipv4/Makefile | 4 +-
net/ipv4v6_shared/Makefile | 7 +
net/ipv4v6_shared/tcp/Kconfig | 324 +++++++++++++++++++++
net/{ipv4 => ipv4v6_shared}/tcp/Makefile | 0
net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/Makefile | 0
net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_bbr.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_bic.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_cdg.c | 0
.../tcp/cc_algos/tcp_cubic.c | 0
.../tcp/cc_algos/tcp_dctcp.c | 0
.../tcp/cc_algos/tcp_highspeed.c | 0
.../tcp/cc_algos/tcp_htcp.c | 0
.../tcp/cc_algos/tcp_hybla.c | 0
.../tcp/cc_algos/tcp_illinois.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_lp.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_nv.c | 0
.../tcp/cc_algos/tcp_scalable.c | 0
.../tcp/cc_algos/tcp_vegas.c | 0
.../tcp/cc_algos/tcp_vegas.h | 0
.../tcp/cc_algos/tcp_veno.c | 0
.../tcp/cc_algos/tcp_westwood.c | 0
.../tcp/cc_algos/tcp_yeah.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/tcp.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/tcp_cong.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/tcp_diag.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/tcp_fastopen.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/tcp_input.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/tcp_metrics.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/tcp_minisocks.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/tcp_output.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/tcp_probe.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/tcp_rate.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/tcp_recovery.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/tcp_timer.c | 0
net/{ipv4 => ipv4v6_shared}/tcp/tcp_ulp.c | 0
38 files changed, 339 insertions(+), 324 deletions(-)
create mode 100644 net/ipv4v6_shared/Makefile
create mode 100644 net/ipv4v6_shared/tcp/Kconfig
rename net/{ipv4 => ipv4v6_shared}/tcp/Makefile (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/Makefile (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_bbr.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_bic.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_cdg.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_cubic.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_dctcp.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_highspeed.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_htcp.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_hybla.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_illinois.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_lp.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_nv.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_scalable.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_vegas.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_vegas.h (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_veno.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_westwood.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/cc_algos/tcp_yeah.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/tcp.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/tcp_cong.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/tcp_diag.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/tcp_fastopen.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/tcp_input.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/tcp_metrics.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/tcp_minisocks.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/tcp_output.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/tcp_probe.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/tcp_rate.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/tcp_recovery.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/tcp_timer.c (100%)
rename net/{ipv4 => ipv4v6_shared}/tcp/tcp_ulp.c (100%)
diff --git a/net/Kconfig b/net/Kconfig
index 9dba2715919d..caa1c51c577d 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -86,6 +86,7 @@ config INET
if INET
source "net/ipv4/Kconfig"
+source "net/ipv4v6_shared/tcp/Kconfig"
source "net/ipv6/Kconfig"
source "net/netlabel/Kconfig"
diff --git a/net/Makefile b/net/Makefile
index ae2fe2283d2f..b089a88d3d5d 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -14,7 +14,11 @@ obj-$(CONFIG_NET) += $(tmp-y)
obj-$(CONFIG_LLC) += llc/
obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/ bpf/
obj-$(CONFIG_NETFILTER) += netfilter/
-obj-$(CONFIG_INET) += ipv4/
+
+# IPv6 depends on CONFIG_INET anyways, so this also includes the shared code
+# for IPv6 when needed.
+obj-$(CONFIG_INET) += ipv4/ ipv4v6_shared/
+
obj-$(CONFIG_TLS) += tls/
obj-$(CONFIG_XFRM) += xfrm/
obj-$(CONFIG_UNIX) += unix/
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 91a2557942fa..aa952b0c6a8c 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -261,42 +261,6 @@ config IP_PIMSM_V2
gated-5). This routing protocol is not used widely, so say N unless
you want to play with it.
-config SYN_COOKIES
- bool "IP: TCP syncookie support"
- ---help---
- Normal TCP/IP networking is open to an attack known as "SYN
- flooding". This denial-of-service attack prevents legitimate remote
- users from being able to connect to your computer during an ongoing
- attack and requires very little work from the attacker, who can
- operate from anywhere on the Internet.
-
- SYN cookies provide protection against this type of attack. If you
- say Y here, the TCP/IP stack will use a cryptographic challenge
- protocol known as "SYN cookies" to enable legitimate users to
- continue to connect, even when your machine is under attack. There
- is no need for the legitimate users to change their TCP/IP software;
- SYN cookies work transparently to them. For technical information
- about SYN cookies, check out <http://cr.yp.to/syncookies.html>.
-
- If you are SYN flooded, the source address reported by the kernel is
- likely to have been forged by the attacker; it is only reported as
- an aid in tracing the packets to their actual source and should not
- be taken as absolute truth.
-
- SYN cookies may prevent correct error reporting on clients when the
- server is really overloaded. If this happens frequently better turn
- them off.
-
- If you say Y here, you can disable SYN cookies at run time by
- saying Y to "/proc file system support" and
- "Sysctl support" below and executing the command
-
- echo 0 > /proc/sys/net/ipv4/tcp_syncookies
-
- after the /proc file system has been mounted.
-
- If unsure, say N.
-
config NET_IPVTI
tristate "Virtual (secure) IP: tunneling"
select INET_TUNNEL
@@ -465,288 +429,3 @@ config INET_DIAG_DESTROY
had been disconnected.
If unsure, say N.
-menuconfig TCP_CONG_ADVANCED
- bool "TCP: advanced congestion control"
- ---help---
- Support for selection of various TCP congestion control
- modules.
-
- Nearly all users can safely say no here, and a safe default
- selection will be made (CUBIC with new Reno as a fallback).
-
- If unsure, say N.
-
-if TCP_CONG_ADVANCED
-
-config TCP_CONG_BIC
- tristate "Binary Increase Congestion (BIC) control"
- default m
- ---help---
- BIC-TCP is a sender-side only change that ensures a linear RTT
- fairness under large windows while offering both scalability and
- bounded TCP-friendliness. The protocol combines two schemes
- called additive increase and binary search increase. When the
- congestion window is large, additive increase with a large
- increment ensures linear RTT fairness as well as good
- scalability. Under small congestion windows, binary search
- increase provides TCP friendliness.
- See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/
-
-config TCP_CONG_CUBIC
- tristate "CUBIC TCP"
- default y
- ---help---
- This is version 2.0 of BIC-TCP which uses a cubic growth function
- among other techniques.
- See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/cubic-paper.pdf
-
-config TCP_CONG_WESTWOOD
- tristate "TCP Westwood+"
- default m
- ---help---
- TCP Westwood+ is a sender-side only modification of the TCP Reno
- protocol stack that optimizes the performance of TCP congestion
- control. It is based on end-to-end bandwidth estimation to set
- congestion window and slow start threshold after a congestion
- episode. Using this estimation, TCP Westwood+ adaptively sets a
- slow start threshold and a congestion window which takes into
- account the bandwidth used at the time congestion is experienced.
- TCP Westwood+ significantly increases fairness wrt TCP Reno in
- wired networks and throughput over wireless links.
-
-config TCP_CONG_HTCP
- tristate "H-TCP"
- default m
- ---help---
- H-TCP is a send-side only modifications of the TCP Reno
- protocol stack that optimizes the performance of TCP
- congestion control for high speed network links. It uses a
- modeswitch to change the alpha and beta parameters of TCP Reno
- based on network conditions and in a way so as to be fair with
- other Reno and H-TCP flows.
-
-config TCP_CONG_HSTCP
- tristate "High Speed TCP"
- default n
- ---help---
- Sally Floyd's High Speed TCP (RFC 3649) congestion control.
- A modification to TCP's congestion control mechanism for use
- with large congestion windows. A table indicates how much to
- increase the congestion window by when an ACK is received.
- For more detail see http://www.icir.org/floyd/hstcp.html
-
-config TCP_CONG_HYBLA
- tristate "TCP-Hybla congestion control algorithm"
- default n
- ---help---
- TCP-Hybla is a sender-side only change that eliminates penalization of
- long-RTT, large-bandwidth connections, like when satellite legs are
- involved, especially when sharing a common bottleneck with normal
- terrestrial connections.
-
-config TCP_CONG_VEGAS
- tristate "TCP Vegas"
- default n
- ---help---
- TCP Vegas is a sender-side only change to TCP that anticipates
- the onset of congestion by estimating the bandwidth. TCP Vegas
- adjusts the sending rate by modifying the congestion
- window. TCP Vegas should provide less packet loss, but it is
- not as aggressive as TCP Reno.
-
-config TCP_CONG_NV
- tristate "TCP NV"
- default n
- ---help---
- TCP NV is a follow up to TCP Vegas. It has been modified to deal with
- 10G networks, measurement noise introduced by LRO, GRO and interrupt
- coalescence. In addition, it will decrease its cwnd multiplicatively
- instead of linearly.
-
- Note that in general congestion avoidance (cwnd decreased when # packets
- queued grows) cannot coexist with congestion control (cwnd decreased only
- when there is packet loss) due to fairness issues. One scenario when they
- can coexist safely is when the CA flows have RTTs << CC flows RTTs.
-
- For further details see http://www.brakmo.org/networking/tcp-nv/
-
-config TCP_CONG_SCALABLE
- tristate "Scalable TCP"
- default n
- ---help---
- Scalable TCP is a sender-side only change to TCP which uses a
- MIMD congestion control algorithm which has some nice scaling
- properties, though is known to have fairness issues.
- See http://www.deneholme.net/tom/scalable/
-
-config TCP_CONG_LP
- tristate "TCP Low Priority"
- default n
- ---help---
- TCP Low Priority (TCP-LP), a distributed algorithm whose goal is
- to utilize only the excess network bandwidth as compared to the
- ``fair share`` of bandwidth as targeted by TCP.
- See http://www-ece.rice.edu/networks/TCP-LP/
-
-config TCP_CONG_VENO
- tristate "TCP Veno"
- default n
- ---help---
- TCP Veno is a sender-side only enhancement of TCP to obtain better
- throughput over wireless networks. TCP Veno makes use of state
- distinguishing to circumvent the difficult judgment of the packet loss
- type. TCP Veno cuts down less congestion window in response to random
- loss packets.
- See <http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1177186>
-
-config TCP_CONG_YEAH
- tristate "YeAH TCP"
- select TCP_CONG_VEGAS
- default n
- ---help---
- YeAH-TCP is a sender-side high-speed enabled TCP congestion control
- algorithm, which uses a mixed loss/delay approach to compute the
- congestion window. It's design goals target high efficiency,
- internal, RTT and Reno fairness, resilience to link loss while
- keeping network elements load as low as possible.
-
- For further details look here:
- http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf
-
-config TCP_CONG_ILLINOIS
- tristate "TCP Illinois"
- default n
- ---help---
- TCP-Illinois is a sender-side modification of TCP Reno for
- high speed long delay links. It uses round-trip-time to
- adjust the alpha and beta parameters to achieve a higher average
- throughput and maintain fairness.
-
- For further details see:
- http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html
-
-config TCP_CONG_DCTCP
- tristate "DataCenter TCP (DCTCP)"
- default n
- ---help---
- DCTCP leverages Explicit Congestion Notification (ECN) in the network to
- provide multi-bit feedback to the end hosts. It is designed to provide:
-
- - High burst tolerance (incast due to partition/aggregate),
- - Low latency (short flows, queries),
- - High throughput (continuous data updates, large file transfers) with
- commodity, shallow-buffered switches.
-
- All switches in the data center network running DCTCP must support
- ECN marking and be configured for marking when reaching defined switch
- buffer thresholds. The default ECN marking threshold heuristic for
- DCTCP on switches is 20 packets (30KB) at 1Gbps, and 65 packets
- (~100KB) at 10Gbps, but might need further careful tweaking.
-
- For further details see:
- http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
-
-config TCP_CONG_CDG
- tristate "CAIA Delay-Gradient (CDG)"
- default n
- ---help---
- CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies
- the TCP sender in order to:
-
- o Use the delay gradient as a congestion signal.
- o Back off with an average probability that is independent of the RTT.
- o Coexist with flows that use loss-based congestion control.
- o Tolerate packet loss unrelated to congestion.
-
- For further details see:
- D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using
- delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg
-
-config TCP_CONG_BBR
- tristate "BBR TCP"
- default n
- ---help---
-
- BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to
- maximize network utilization and minimize queues. It builds an explicit
- model of the the bottleneck delivery rate and path round-trip
- propagation delay. It tolerates packet loss and delay unrelated to
- congestion. It can operate over LAN, WAN, cellular, wifi, or cable
- modem links. It can coexist with flows that use loss-based congestion
- control, and can operate with shallow buffers, deep buffers,
- bufferbloat, policers, or AQM schemes that do not provide a delay
- signal. It requires the fq ("Fair Queue") pacing packet scheduler.
-
-choice
- prompt "Default TCP congestion control"
- default DEFAULT_CUBIC
- help
- Select the TCP congestion control that will be used by default
- for all connections.
-
- config DEFAULT_BIC
- bool "Bic" if TCP_CONG_BIC=y
-
- config DEFAULT_CUBIC
- bool "Cubic" if TCP_CONG_CUBIC=y
-
- config DEFAULT_HTCP
- bool "Htcp" if TCP_CONG_HTCP=y
-
- config DEFAULT_HYBLA
- bool "Hybla" if TCP_CONG_HYBLA=y
-
- config DEFAULT_VEGAS
- bool "Vegas" if TCP_CONG_VEGAS=y
-
- config DEFAULT_VENO
- bool "Veno" if TCP_CONG_VENO=y
-
- config DEFAULT_WESTWOOD
- bool "Westwood" if TCP_CONG_WESTWOOD=y
-
- config DEFAULT_DCTCP
- bool "DCTCP" if TCP_CONG_DCTCP=y
-
- config DEFAULT_CDG
- bool "CDG" if TCP_CONG_CDG=y
-
- config DEFAULT_BBR
- bool "BBR" if TCP_CONG_BBR=y
-
- config DEFAULT_RENO
- bool "Reno"
-endchoice
-
-endif
-
-config TCP_CONG_CUBIC
- tristate
- depends on !TCP_CONG_ADVANCED
- default y
-
-config DEFAULT_TCP_CONG
- string
- default "bic" if DEFAULT_BIC
- default "cubic" if DEFAULT_CUBIC
- default "htcp" if DEFAULT_HTCP
- default "hybla" if DEFAULT_HYBLA
- default "vegas" if DEFAULT_VEGAS
- default "westwood" if DEFAULT_WESTWOOD
- default "veno" if DEFAULT_VENO
- default "reno" if DEFAULT_RENO
- default "dctcp" if DEFAULT_DCTCP
- default "cdg" if DEFAULT_CDG
- default "bbr" if DEFAULT_BBR
- default "cubic"
-
-config TCP_MD5SIG
- bool "TCP: MD5 Signature Option support (RFC2385)"
- select CRYPTO
- select CRYPTO_MD5
- ---help---
- RFC2385 specifies a method of giving MD5 protection to TCP sessions.
- Its main (only?) use is to protect BGP sessions between core routers
- on the Internet.
-
- If unsure, say N.
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index a106a1cf0e11..d170d6e1417c 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -1,8 +1,8 @@
#
-# Makefile for the Linux TCP/IP (INET) layer.
+# Makefile for the Linux IP layer.
#
-obj-y := tcp/ route.o inetpeer.o protocol.o \
+obj-y := route.o inetpeer.o protocol.o \
ip_input.o ip_fragment.o ip_forward.o ip_options.o \
ip_output.o ip_sockglue.o inet_hashtables.o \
inet_timewait_sock.o inet_connection_sock.o \
diff --git a/net/ipv4v6_shared/Makefile b/net/ipv4v6_shared/Makefile
new file mode 100644
index 000000000000..41a67a0cf210
--- /dev/null
+++ b/net/ipv4v6_shared/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for shared networking code called/used by IPv4 and IPv6
+#
+# Note: Currently this only contains the shared part of the TCP Implementation
+# a lot of the shared code still resides in net/ipv4/
+
+obj-y := tcp/
diff --git a/net/ipv4v6_shared/tcp/Kconfig b/net/ipv4v6_shared/tcp/Kconfig
new file mode 100644
index 000000000000..dff4d046a42b
--- /dev/null
+++ b/net/ipv4v6_shared/tcp/Kconfig
@@ -0,0 +1,324 @@
+#
+# TCP configuration
+#
+config SYN_COOKIES
+ bool "IP: TCP syncookie support"
+ ---help---
+ Normal TCP/IP networking is open to an attack known as "SYN
+ flooding". This denial-of-service attack prevents legitimate remote
+ users from being able to connect to your computer during an ongoing
+ attack and requires very little work from the attacker, who can
+ operate from anywhere on the Internet.
+
+ SYN cookies provide protection against this type of attack. If you
+ say Y here, the TCP/IP stack will use a cryptographic challenge
+ protocol known as "SYN cookies" to enable legitimate users to
+ continue to connect, even when your machine is under attack. There
+ is no need for the legitimate users to change their TCP/IP software;
+ SYN cookies work transparently to them. For technical information
+ about SYN cookies, check out <http://cr.yp.to/syncookies.html>.
+
+ If you are SYN flooded, the source address reported by the kernel is
+ likely to have been forged by the attacker; it is only reported as
+ an aid in tracing the packets to their actual source and should not
+ be taken as absolute truth.
+
+ SYN cookies may prevent correct error reporting on clients when the
+ server is really overloaded. If this happens frequently better turn
+ them off.
+
+ If you say Y here, you can disable SYN cookies at run time by
+ saying Y to "/proc file system support" and
+ "Sysctl support" below and executing the command
+
+ echo 0 > /proc/sys/net/ipv4/tcp_syncookies
+
+ after the /proc file system has been mounted.
+
+ If unsure, say N.
+
+menuconfig TCP_CONG_ADVANCED
+ bool "TCP: advanced congestion control"
+ ---help---
+ Support for selection of various TCP congestion control
+ modules.
+
+ Nearly all users can safely say no here, and a safe default
+ selection will be made (CUBIC with new Reno as a fallback).
+
+ If unsure, say N.
+
+if TCP_CONG_ADVANCED
+
+config TCP_CONG_BIC
+ tristate "Binary Increase Congestion (BIC) control"
+ default m
+ ---help---
+ BIC-TCP is a sender-side only change that ensures a linear RTT
+ fairness under large windows while offering both scalability and
+ bounded TCP-friendliness. The protocol combines two schemes
+ called additive increase and binary search increase. When the
+ congestion window is large, additive increase with a large
+ increment ensures linear RTT fairness as well as good
+ scalability. Under small congestion windows, binary search
+ increase provides TCP friendliness.
+ See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/
+
+config TCP_CONG_CUBIC
+ tristate "CUBIC TCP"
+ default y
+ ---help---
+ This is version 2.0 of BIC-TCP which uses a cubic growth function
+ among other techniques.
+ See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/cubic-paper.pdf
+
+config TCP_CONG_WESTWOOD
+ tristate "TCP Westwood+"
+ default m
+ ---help---
+ TCP Westwood+ is a sender-side only modification of the TCP Reno
+ protocol stack that optimizes the performance of TCP congestion
+ control. It is based on end-to-end bandwidth estimation to set
+ congestion window and slow start threshold after a congestion
+ episode. Using this estimation, TCP Westwood+ adaptively sets a
+ slow start threshold and a congestion window which takes into
+ account the bandwidth used at the time congestion is experienced.
+ TCP Westwood+ significantly increases fairness wrt TCP Reno in
+ wired networks and throughput over wireless links.
+
+config TCP_CONG_HTCP
+ tristate "H-TCP"
+ default m
+ ---help---
+ H-TCP is a send-side only modifications of the TCP Reno
+ protocol stack that optimizes the performance of TCP
+ congestion control for high speed network links. It uses a
+ modeswitch to change the alpha and beta parameters of TCP Reno
+ based on network conditions and in a way so as to be fair with
+ other Reno and H-TCP flows.
+
+config TCP_CONG_HSTCP
+ tristate "High Speed TCP"
+ default n
+ ---help---
+ Sally Floyd's High Speed TCP (RFC 3649) congestion control.
+ A modification to TCP's congestion control mechanism for use
+ with large congestion windows. A table indicates how much to
+ increase the congestion window by when an ACK is received.
+ For more detail see http://www.icir.org/floyd/hstcp.html
+
+config TCP_CONG_HYBLA
+ tristate "TCP-Hybla congestion control algorithm"
+ default n
+ ---help---
+ TCP-Hybla is a sender-side only change that eliminates penalization of
+ long-RTT, large-bandwidth connections, like when satellite legs are
+ involved, especially when sharing a common bottleneck with normal
+ terrestrial connections.
+
+config TCP_CONG_VEGAS
+ tristate "TCP Vegas"
+ default n
+ ---help---
+ TCP Vegas is a sender-side only change to TCP that anticipates
+ the onset of congestion by estimating the bandwidth. TCP Vegas
+ adjusts the sending rate by modifying the congestion
+ window. TCP Vegas should provide less packet loss, but it is
+ not as aggressive as TCP Reno.
+
+config TCP_CONG_NV
+ tristate "TCP NV"
+ default n
+ ---help---
+ TCP NV is a follow up to TCP Vegas. It has been modified to deal with
+ 10G networks, measurement noise introduced by LRO, GRO and interrupt
+ coalescence. In addition, it will decrease its cwnd multiplicatively
+ instead of linearly.
+
+ Note that in general congestion avoidance (cwnd decreased when # packets
+ queued grows) cannot coexist with congestion control (cwnd decreased only
+ when there is packet loss) due to fairness issues. One scenario when they
+ can coexist safely is when the CA flows have RTTs << CC flows RTTs.
+
+ For further details see http://www.brakmo.org/networking/tcp-nv/
+
+config TCP_CONG_SCALABLE
+ tristate "Scalable TCP"
+ default n
+ ---help---
+ Scalable TCP is a sender-side only change to TCP which uses a
+ MIMD congestion control algorithm which has some nice scaling
+ properties, though is known to have fairness issues.
+ See http://www.deneholme.net/tom/scalable/
+
+config TCP_CONG_LP
+ tristate "TCP Low Priority"
+ default n
+ ---help---
+ TCP Low Priority (TCP-LP), a distributed algorithm whose goal is
+ to utilize only the excess network bandwidth as compared to the
+ ``fair share`` of bandwidth as targeted by TCP.
+ See http://www-ece.rice.edu/networks/TCP-LP/
+
+config TCP_CONG_VENO
+ tristate "TCP Veno"
+ default n
+ ---help---
+ TCP Veno is a sender-side only enhancement of TCP to obtain better
+ throughput over wireless networks. TCP Veno makes use of state
+ distinguishing to circumvent the difficult judgment of the packet loss
+ type. TCP Veno cuts down less congestion window in response to random
+ loss packets.
+ See <http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1177186>
+
+config TCP_CONG_YEAH
+ tristate "YeAH TCP"
+ select TCP_CONG_VEGAS
+ default n
+ ---help---
+ YeAH-TCP is a sender-side high-speed enabled TCP congestion control
+ algorithm, which uses a mixed loss/delay approach to compute the
+ congestion window. It's design goals target high efficiency,
+ internal, RTT and Reno fairness, resilience to link loss while
+ keeping network elements load as low as possible.
+
+ For further details look here:
+ http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf
+
+config TCP_CONG_ILLINOIS
+ tristate "TCP Illinois"
+ default n
+ ---help---
+ TCP-Illinois is a sender-side modification of TCP Reno for
+ high speed long delay links. It uses round-trip-time to
+ adjust the alpha and beta parameters to achieve a higher average
+ throughput and maintain fairness.
+
+ For further details see:
+ http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html
+
+config TCP_CONG_DCTCP
+ tristate "DataCenter TCP (DCTCP)"
+ default n
+ ---help---
+ DCTCP leverages Explicit Congestion Notification (ECN) in the network to
+ provide multi-bit feedback to the end hosts. It is designed to provide:
+
+ - High burst tolerance (incast due to partition/aggregate),
+ - Low latency (short flows, queries),
+ - High throughput (continuous data updates, large file transfers) with
+ commodity, shallow-buffered switches.
+
+ All switches in the data center network running DCTCP must support
+ ECN marking and be configured for marking when reaching defined switch
+ buffer thresholds. The default ECN marking threshold heuristic for
+ DCTCP on switches is 20 packets (30KB) at 1Gbps, and 65 packets
+ (~100KB) at 10Gbps, but might need further careful tweaking.
+
+ For further details see:
+ http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
+
+config TCP_CONG_CDG
+ tristate "CAIA Delay-Gradient (CDG)"
+ default n
+ ---help---
+ CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies
+ the TCP sender in order to:
+
+ o Use the delay gradient as a congestion signal.
+ o Back off with an average probability that is independent of the RTT.
+ o Coexist with flows that use loss-based congestion control.
+ o Tolerate packet loss unrelated to congestion.
+
+ For further details see:
+ D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using
+ delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg
+
+config TCP_CONG_BBR
+ tristate "BBR TCP"
+ default n
+ ---help---
+
+ BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to
+ maximize network utilization and minimize queues. It builds an explicit
+ model of the the bottleneck delivery rate and path round-trip
+ propagation delay. It tolerates packet loss and delay unrelated to
+ congestion. It can operate over LAN, WAN, cellular, wifi, or cable
+ modem links. It can coexist with flows that use loss-based congestion
+ control, and can operate with shallow buffers, deep buffers,
+ bufferbloat, policers, or AQM schemes that do not provide a delay
+ signal. It requires the fq ("Fair Queue") pacing packet scheduler.
+
+choice
+ prompt "Default TCP congestion control"
+ default DEFAULT_CUBIC
+ help
+ Select the TCP congestion control that will be used by default
+ for all connections.
+
+ config DEFAULT_BIC
+ bool "Bic" if TCP_CONG_BIC=y
+
+ config DEFAULT_CUBIC
+ bool "Cubic" if TCP_CONG_CUBIC=y
+
+ config DEFAULT_HTCP
+ bool "Htcp" if TCP_CONG_HTCP=y
+
+ config DEFAULT_HYBLA
+ bool "Hybla" if TCP_CONG_HYBLA=y
+
+ config DEFAULT_VEGAS
+ bool "Vegas" if TCP_CONG_VEGAS=y
+
+ config DEFAULT_VENO
+ bool "Veno" if TCP_CONG_VENO=y
+
+ config DEFAULT_WESTWOOD
+ bool "Westwood" if TCP_CONG_WESTWOOD=y
+
+ config DEFAULT_DCTCP
+ bool "DCTCP" if TCP_CONG_DCTCP=y
+
+ config DEFAULT_CDG
+ bool "CDG" if TCP_CONG_CDG=y
+
+ config DEFAULT_BBR
+ bool "BBR" if TCP_CONG_BBR=y
+
+ config DEFAULT_RENO
+ bool "Reno"
+endchoice
+
+endif
+
+config TCP_CONG_CUBIC
+ tristate
+ depends on !TCP_CONG_ADVANCED
+ default y
+
+config DEFAULT_TCP_CONG
+ string
+ default "bic" if DEFAULT_BIC
+ default "cubic" if DEFAULT_CUBIC
+ default "htcp" if DEFAULT_HTCP
+ default "hybla" if DEFAULT_HYBLA
+ default "vegas" if DEFAULT_VEGAS
+ default "westwood" if DEFAULT_WESTWOOD
+ default "veno" if DEFAULT_VENO
+ default "reno" if DEFAULT_RENO
+ default "dctcp" if DEFAULT_DCTCP
+ default "cdg" if DEFAULT_CDG
+ default "bbr" if DEFAULT_BBR
+ default "cubic"
+
+config TCP_MD5SIG
+ bool "TCP: MD5 Signature Option support (RFC2385)"
+ select CRYPTO
+ select CRYPTO_MD5
+ ---help---
+ RFC2385 specifies a method of giving MD5 protection to TCP sessions.
+ Its main (only?) use is to protect BGP sessions between core routers
+ on the Internet.
+
+ If unsure, say N.
diff --git a/net/ipv4/tcp/Makefile b/net/ipv4v6_shared/tcp/Makefile
similarity index 100%
rename from net/ipv4/tcp/Makefile
rename to net/ipv4v6_shared/tcp/Makefile
diff --git a/net/ipv4/tcp/cc_algos/Makefile b/net/ipv4v6_shared/tcp/cc_algos/Makefile
similarity index 100%
rename from net/ipv4/tcp/cc_algos/Makefile
rename to net/ipv4v6_shared/tcp/cc_algos/Makefile
diff --git a/net/ipv4/tcp/cc_algos/tcp_bbr.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_bbr.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_bbr.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_bbr.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_bic.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_bic.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_bic.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_bic.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_cdg.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_cdg.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_cdg.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_cdg.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_cubic.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_cubic.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_cubic.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_cubic.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_dctcp.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_dctcp.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_dctcp.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_dctcp.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_highspeed.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_highspeed.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_highspeed.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_highspeed.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_htcp.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_htcp.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_htcp.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_htcp.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_hybla.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_hybla.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_hybla.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_hybla.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_illinois.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_illinois.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_illinois.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_illinois.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_lp.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_lp.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_lp.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_lp.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_nv.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_nv.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_nv.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_nv.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_scalable.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_scalable.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_scalable.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_scalable.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_vegas.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_vegas.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_vegas.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_vegas.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_vegas.h b/net/ipv4v6_shared/tcp/cc_algos/tcp_vegas.h
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_vegas.h
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_vegas.h
diff --git a/net/ipv4/tcp/cc_algos/tcp_veno.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_veno.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_veno.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_veno.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_westwood.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_westwood.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_westwood.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_westwood.c
diff --git a/net/ipv4/tcp/cc_algos/tcp_yeah.c b/net/ipv4v6_shared/tcp/cc_algos/tcp_yeah.c
similarity index 100%
rename from net/ipv4/tcp/cc_algos/tcp_yeah.c
rename to net/ipv4v6_shared/tcp/cc_algos/tcp_yeah.c
diff --git a/net/ipv4/tcp/tcp.c b/net/ipv4v6_shared/tcp/tcp.c
similarity index 100%
rename from net/ipv4/tcp/tcp.c
rename to net/ipv4v6_shared/tcp/tcp.c
diff --git a/net/ipv4/tcp/tcp_cong.c b/net/ipv4v6_shared/tcp/tcp_cong.c
similarity index 100%
rename from net/ipv4/tcp/tcp_cong.c
rename to net/ipv4v6_shared/tcp/tcp_cong.c
diff --git a/net/ipv4/tcp/tcp_diag.c b/net/ipv4v6_shared/tcp/tcp_diag.c
similarity index 100%
rename from net/ipv4/tcp/tcp_diag.c
rename to net/ipv4v6_shared/tcp/tcp_diag.c
diff --git a/net/ipv4/tcp/tcp_fastopen.c b/net/ipv4v6_shared/tcp/tcp_fastopen.c
similarity index 100%
rename from net/ipv4/tcp/tcp_fastopen.c
rename to net/ipv4v6_shared/tcp/tcp_fastopen.c
diff --git a/net/ipv4/tcp/tcp_input.c b/net/ipv4v6_shared/tcp/tcp_input.c
similarity index 100%
rename from net/ipv4/tcp/tcp_input.c
rename to net/ipv4v6_shared/tcp/tcp_input.c
diff --git a/net/ipv4/tcp/tcp_metrics.c b/net/ipv4v6_shared/tcp/tcp_metrics.c
similarity index 100%
rename from net/ipv4/tcp/tcp_metrics.c
rename to net/ipv4v6_shared/tcp/tcp_metrics.c
diff --git a/net/ipv4/tcp/tcp_minisocks.c b/net/ipv4v6_shared/tcp/tcp_minisocks.c
similarity index 100%
rename from net/ipv4/tcp/tcp_minisocks.c
rename to net/ipv4v6_shared/tcp/tcp_minisocks.c
diff --git a/net/ipv4/tcp/tcp_output.c b/net/ipv4v6_shared/tcp/tcp_output.c
similarity index 100%
rename from net/ipv4/tcp/tcp_output.c
rename to net/ipv4v6_shared/tcp/tcp_output.c
diff --git a/net/ipv4/tcp/tcp_probe.c b/net/ipv4v6_shared/tcp/tcp_probe.c
similarity index 100%
rename from net/ipv4/tcp/tcp_probe.c
rename to net/ipv4v6_shared/tcp/tcp_probe.c
diff --git a/net/ipv4/tcp/tcp_rate.c b/net/ipv4v6_shared/tcp/tcp_rate.c
similarity index 100%
rename from net/ipv4/tcp/tcp_rate.c
rename to net/ipv4v6_shared/tcp/tcp_rate.c
diff --git a/net/ipv4/tcp/tcp_recovery.c b/net/ipv4v6_shared/tcp/tcp_recovery.c
similarity index 100%
rename from net/ipv4/tcp/tcp_recovery.c
rename to net/ipv4v6_shared/tcp/tcp_recovery.c
diff --git a/net/ipv4/tcp/tcp_timer.c b/net/ipv4v6_shared/tcp/tcp_timer.c
similarity index 100%
rename from net/ipv4/tcp/tcp_timer.c
rename to net/ipv4v6_shared/tcp/tcp_timer.c
diff --git a/net/ipv4/tcp/tcp_ulp.c b/net/ipv4v6_shared/tcp/tcp_ulp.c
similarity index 100%
rename from net/ipv4/tcp/tcp_ulp.c
rename to net/ipv4v6_shared/tcp/tcp_ulp.c
--
2.14.1
^ permalink raw reply related [flat|nested] 10+ messages in thread