microsoft
/
WSL2-Linux-Kernel
зеркало из https://github.com/microsoft/WSL2-Linux-Kernel.git
1
0
Форкнуть 0
Код Задачи Пакеты Проекты Релизы Вики Активность
WSL2-Linux-Kernel/include/uapi/linux/tcp.h

272 строки
8.1 KiB
C
Исходник Обычный вид История

License cleanup: add SPDX license identifier to uapi header files with a license Many user space API headers have licensing information, which is either incomplete, badly formatted or just a shorthand for referring to the license under which the file is supposed to be. This makes it hard for compliance tools to determine the correct license. Update these files with an SPDX license identifier. The identifier was chosen based on the license information in the file. GPL/LGPL licensed headers get the matching GPL/LGPL SPDX license identifier with the added 'WITH Linux-syscall-note' exception, which is the officially assigned exception identifier for the kernel syscall exception: NOTE! This copyright does *not* cover user programs that use kernel services by normal system calls - this is merely considered normal use of the kernel, and does *not* fall under the heading of "derived work". This exception makes it possible to include GPL headers into non GPL code, without confusing license compliance tools. Headers which have either explicit dual licensing or are just licensed under a non GPL license are updated with the corresponding SPDX identifier and the GPLv2 with syscall exception identifier. The format is: ((GPL-2.0 WITH Linux-syscall-note) OR SPDX-ID-OF-OTHER-LICENSE) SPDX license identifiers are a legally binding shorthand, which can be used instead of the full boiler plate text. The update does not remove existing license information as this has to be done on a case by case basis and the copyright holders might have to be consulted. This will happen in a separate step. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. See the previous patch in this series for the methodology of how this patch was researched. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 17:09:13 +03:00
/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
UAPI: (Scripted) Disintegrate include/linux Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Dave Jones <davej@redhat.com>
2012-10-13 13:46:48 +04:00
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Definitions for the TCP protocol.
*
* Version: @(#)tcp.h 1.0.2 04/28/93
*
* Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef _UAPI_LINUX_TCP_H
#define _UAPI_LINUX_TCP_H
#include <linux/types.h>
#include <asm/byteorder.h>
#include <linux/socket.h>
struct tcphdr {
__be16 source;
__be16 dest;
__be32 seq;
__be32 ack_seq;
#if defined(__LITTLE_ENDIAN_BITFIELD)
__u16 res1:4,
doff:4,
fin:1,
syn:1,
rst:1,
psh:1,
ack:1,
urg:1,
ece:1,
cwr:1;
#elif defined(__BIG_ENDIAN_BITFIELD)
__u16 doff:4,
res1:4,
cwr:1,
ece:1,
urg:1,
ack:1,
psh:1,
rst:1,
syn:1,
fin:1;
#else
#error "Adjust your <asm/byteorder.h> defines"
#endif
__be16 window;
__sum16 check;
__be16 urg_ptr;
};
/*
* The union cast uses a gcc extension to avoid aliasing problems
* (union is compatible to any of its members)
* This means this part of the code is -fstrict-aliasing safe now.
*/
union tcp_word_hdr {
struct tcphdr hdr;
__be32 words[5];
};
#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3])
enum {
TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000),
TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000),
TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000),
TCP_FLAG_ACK = __constant_cpu_to_be32(0x00100000),
TCP_FLAG_PSH = __constant_cpu_to_be32(0x00080000),
TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000),
TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000),
TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000),
TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000),
TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000)
};
/*
* TCP general constants
*/
#define TCP_MSS_DEFAULT 536U /* IPv4 (RFC1122, RFC2581) */
#define TCP_MSS_DESIRED 1220U /* IPv6 (tunneled), EDNS0 (RFC3226) */
/* TCP socket options */
#define TCP_NODELAY 1 /* Turn off Nagle's algorithm. */
#define TCP_MAXSEG 2 /* Limit MSS */
#define TCP_CORK 3 /* Never send partially complete segments */
#define TCP_KEEPIDLE 4 /* Start keeplives after this period */
#define TCP_KEEPINTVL 5 /* Interval between keepalives */
#define TCP_KEEPCNT 6 /* Number of keepalives before death */
#define TCP_SYNCNT 7 /* Number of SYN retransmits */
#define TCP_LINGER2 8 /* Life time of orphaned FIN-WAIT-2 state */
#define TCP_DEFER_ACCEPT 9 /* Wake up listener only when data arrive */
#define TCP_WINDOW_CLAMP 10 /* Bound advertised window */
#define TCP_INFO 11 /* Information about this connection. */
#define TCP_QUICKACK 12 /* Block/reenable quick acks */
#define TCP_CONGESTION 13 /* Congestion control algorithm */
#define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */
#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/
#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */
#define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */
#define TCP_REPAIR 19 /* TCP sock is under repair right now */
#define TCP_REPAIR_QUEUE 20
#define TCP_QUEUE_SEQ 21
#define TCP_REPAIR_OPTIONS 22
#define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */
tcp: set and get per-socket timestamp A timestamp can be set, only if a socket is in the repair mode. This patch adds a new socket option TCP_TIMESTAMP, which allows to get and set current tcp times stamp. Cc: "David S. Miller" <davem@davemloft.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Cc: James Morris <jmorris@namei.org> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: Patrick McHardy <kaber@trash.net> Cc: Eric Dumazet <edumazet@google.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrey Vagin <avagin@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-02-11 09:50:18 +04:00
#define TCP_TIMESTAMP 24
tcp: TCP_NOTSENT_LOWAT socket option Idea of this patch is to add optional limitation of number of unsent bytes in TCP sockets, to reduce usage of kernel memory. TCP receiver might announce a big window, and TCP sender autotuning might allow a large amount of bytes in write queue, but this has little performance impact if a large part of this buffering is wasted : Write queue needs to be large only to deal with large BDP, not necessarily to cope with scheduling delays (incoming ACKS make room for the application to queue more bytes) For most workloads, using a value of 128 KB or less is OK to give applications enough time to react to POLLOUT events in time (or being awaken in a blocking sendmsg()) This patch adds two ways to set the limit : 1) Per socket option TCP_NOTSENT_LOWAT 2) A sysctl (/proc/sys/net/ipv4/tcp_notsent_lowat) for sockets not using TCP_NOTSENT_LOWAT socket option (or setting a zero value) Default value being UINT_MAX (0xFFFFFFFF), meaning this has no effect. This changes poll()/select()/epoll() to report POLLOUT only if number of unsent bytes is below tp->nosent_lowat Note this might increase number of sendmsg()/sendfile() calls when using non blocking sockets, and increase number of context switches for blocking sockets. Note this is not related to SO_SNDLOWAT (as SO_SNDLOWAT is defined as : Specify the minimum number of bytes in the buffer until the socket layer will pass the data to the protocol) Tested: netperf sessions, and watching /proc/net/protocols "memory" column for TCP With 200 concurrent netperf -t TCP_STREAM sessions, amount of kernel memory used by TCP buffers shrinks by ~55 % (20567 pages instead of 45458) lpq83:~# echo -1 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# (super_netperf 200 -t TCP_STREAM -H remote -l 90 &); sleep 60 ; grep TCP /proc/net/protocols TCPv6 1880 2 45458 no 208 yes ipv6 y y y y y y y y y y y y y n y y y y y TCP 1696 508 45458 no 208 yes kernel y y y y y y y y y y y y y n y y y y y lpq83:~# echo 131072 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# (super_netperf 200 -t TCP_STREAM -H remote -l 90 &); sleep 60 ; grep TCP /proc/net/protocols TCPv6 1880 2 20567 no 208 yes ipv6 y y y y y y y y y y y y y n y y y y y TCP 1696 508 20567 no 208 yes kernel y y y y y y y y y y y y y n y y y y y Using 128KB has no bad effect on the throughput or cpu usage of a single flow, although there is an increase of context switches. A bonus is that we hold socket lock for a shorter amount of time and should improve latencies of ACK processing. lpq83:~# echo -1 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# perf stat -e context-switches ./netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3 OMNI Send TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.7.84 () port 0 AF_INET : +/-2.500% @ 99% conf. Local Remote Local Elapsed Throughput Throughput Local Local Remote Remote Local Remote Service Send Socket Recv Socket Send Time Units CPU CPU CPU CPU Service Service Demand Size Size Size (sec) Util Util Util Util Demand Demand Units Final Final % Method % Method 1651584 6291456 16384 20.00 17447.90 10^6bits/s 3.13 S -1.00 U 0.353 -1.000 usec/KB Performance counter stats for './netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3': 412,514 context-switches 200.034645535 seconds time elapsed lpq83:~# echo 131072 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# perf stat -e context-switches ./netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3 OMNI Send TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.7.84 () port 0 AF_INET : +/-2.500% @ 99% conf. Local Remote Local Elapsed Throughput Throughput Local Local Remote Remote Local Remote Service Send Socket Recv Socket Send Time Units CPU CPU CPU CPU Service Service Demand Size Size Size (sec) Util Util Util Util Demand Demand Units Final Final % Method % Method 1593240 6291456 16384 20.00 17321.16 10^6bits/s 3.35 S -1.00 U 0.381 -1.000 usec/KB Performance counter stats for './netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3': 2,675,818 context-switches 200.029651391 seconds time elapsed Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Yuchung Cheng <ycheng@google.com> Acked-By: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-07-23 07:27:07 +04:00
#define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */
tcp: add TCP_CC_INFO socket option Some Congestion Control modules can provide per flow information, but current way to get this information is to use netlink. Like TCP_INFO, let's add TCP_CC_INFO so that applications can issue a getsockopt() if they have a socket file descriptor, instead of playing complex netlink games. Sample usage would be : union tcp_cc_info info; socklen_t len = sizeof(info); if (getsockopt(fd, SOL_TCP, TCP_CC_INFO, &info, &len) == -1) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Neal Cardwell <ncardwell@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-29 02:23:49 +03:00
#define TCP_CC_INFO 26 /* Get Congestion Control (optional) info */
tcp: provide SYN headers for passive connections This patch allows a server application to get the TCP SYN headers for its passive connections. This is useful if the server is doing fingerprinting of clients based on SYN packet contents. Two socket options are added: TCP_SAVE_SYN and TCP_SAVED_SYN. The first is used on a socket to enable saving the SYN headers for child connections. This can be set before or after the listen() call. The latter is used to retrieve the SYN headers for passive connections, if the parent listener has enabled TCP_SAVE_SYN. TCP_SAVED_SYN is read once, it frees the saved SYN headers. The data returned in TCP_SAVED_SYN are network (IPv4/IPv6) and TCP headers. Original patch was written by Tom Herbert, I changed it to not hold a full skb (and associated dst and conntracking reference). We have used such patch for about 3 years at Google. Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Tested-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-04 07:34:46 +03:00
#define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */
#define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */
tcp: add an ability to dump and restore window parameters We found that sometimes a restored tcp socket doesn't work. A reason of this bug is incorrect window parameters and in this case tcp_acceptable_seq() returns tcp_wnd_end(tp) instead of tp->snd_nxt. The other side drops packets with this seq, because seq is less than tp->rcv_nxt ( tcp_sequence() ). Data from a send queue is sent only if there is enough space in a window, so when we restore unacked data, we need to expand a window to fit this data. This was in a first version of this patch: "tcp: extend window to fit all restored unacked data in a send queue" Then Alexey recommended me to restore window parameters instead of adjusted them according with data in a sent queue. This sounds resonable. rcv_wnd has to be restored, because it was reported to another side and the offered window is never shrunk. One of reasons why we need to restore snd_wnd was described above. Cc: Pavel Emelyanov <xemul@parallels.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Cc: James Morris <jmorris@namei.org> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: Patrick McHardy <kaber@trash.net> Signed-off-by: Andrey Vagin <avagin@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-28 01:33:56 +03:00
#define TCP_REPAIR_WINDOW 29 /* Get/set window parameters */
net/tcp-fastopen: Add new API support This patch adds a new socket option, TCP_FASTOPEN_CONNECT, as an alternative way to perform Fast Open on the active side (client). Prior to this patch, a client needs to replace the connect() call with sendto(MSG_FASTOPEN). This can be cumbersome for applications who want to use Fast Open: these socket operations are often done in lower layer libraries used by many other applications. Changing these libraries and/or the socket call sequences are not trivial. A more convenient approach is to perform Fast Open by simply enabling a socket option when the socket is created w/o changing other socket calls sequence: s = socket() create a new socket setsockopt(s, IPPROTO_TCP, TCP_FASTOPEN_CONNECT …); newly introduced sockopt If set, new functionality described below will be used. Return ENOTSUPP if TFO is not supported or not enabled in the kernel. connect() With cookie present, return 0 immediately. With no cookie, initiate 3WHS with TFO cookie-request option and return -1 with errno = EINPROGRESS. write()/sendmsg() With cookie present, send out SYN with data and return the number of bytes buffered. With no cookie, and 3WHS not yet completed, return -1 with errno = EINPROGRESS. No MSG_FASTOPEN flag is needed. read() Return -1 with errno = EWOULDBLOCK/EAGAIN if connect() is called but write() is not called yet. Return -1 with errno = EWOULDBLOCK/EAGAIN if connection is established but no msg is received yet. Return number of bytes read if socket is established and there is msg received. The new API simplifies life for applications that always perform a write() immediately after a successful connect(). Such applications can now take advantage of Fast Open by merely making one new setsockopt() call at the time of creating the socket. Nothing else about the application's socket call sequence needs to change. Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-23 21:59:22 +03:00
#define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */
tcp: md5: add TCP_MD5SIG_EXT socket option to set a key address prefix Replace first padding in the tcp_md5sig structure with a new flag field and address prefix length so it can be specified when configuring a new key for TCP MD5 signature. The tcpm_flags field will only be used if the socket option is TCP_MD5SIG_EXT to avoid breaking existing programs, and tcpm_prefixlen only when the TCP_MD5SIG_FLAG_PREFIX flag is set. Signed-off-by: Bob Gilligan <gilligan@arista.com> Signed-off-by: Eric Mowat <mowat@arista.com> Signed-off-by: Ivan Delalande <colona@arista.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-16 04:07:07 +03:00
#define TCP_ULP 31 /* Attach a ULP to a TCP connection */
#define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */
tcp: socket option to set TCP fast open key New socket option TCP_FASTOPEN_KEY to allow different keys per listener. The listener by default uses the global key until the socket option is set. The key is a 16 bytes long binary data. This option has no effect on regular non-listener TCP sockets. Signed-off-by: Yuchung Cheng <ycheng@google.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Christoph Paasch <cpaasch@apple.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-18 21:22:51 +03:00
#define TCP_FASTOPEN_KEY 33 /* Set the key for Fast Open (cookie) */
tcp: Configure TFO without cookie per socket and/or per route We already allow to enable TFO without a cookie by using the fastopen-sysctl and setting it to TFO_SERVER_COOKIE_NOT_REQD (or TFO_CLIENT_NO_COOKIE). This is safe to do in certain environments where we know that there isn't a malicous host (aka., data-centers) or when the application-protocol already provides an authentication mechanism in the first flight of data. A server however might be providing multiple services or talking to both sides (public Internet and data-center). So, this server would want to enable cookie-less TFO for certain services and/or for connections that go to the data-center. This patch exposes a socket-option and a per-route attribute to enable such fine-grained configurations. Signed-off-by: Christoph Paasch <cpaasch@apple.com> Reviewed-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-23 23:22:23 +03:00
#define TCP_FASTOPEN_NO_COOKIE 34 /* Enable TFO without a TFO cookie */
UAPI: (Scripted) Disintegrate include/linux Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Dave Jones <davej@redhat.com>
2012-10-13 13:46:48 +04:00
struct tcp_repair_opt {
__u32 opt_code;
__u32 opt_val;
};
tcp: add an ability to dump and restore window parameters We found that sometimes a restored tcp socket doesn't work. A reason of this bug is incorrect window parameters and in this case tcp_acceptable_seq() returns tcp_wnd_end(tp) instead of tp->snd_nxt. The other side drops packets with this seq, because seq is less than tp->rcv_nxt ( tcp_sequence() ). Data from a send queue is sent only if there is enough space in a window, so when we restore unacked data, we need to expand a window to fit this data. This was in a first version of this patch: "tcp: extend window to fit all restored unacked data in a send queue" Then Alexey recommended me to restore window parameters instead of adjusted them according with data in a sent queue. This sounds resonable. rcv_wnd has to be restored, because it was reported to another side and the offered window is never shrunk. One of reasons why we need to restore snd_wnd was described above. Cc: Pavel Emelyanov <xemul@parallels.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Cc: James Morris <jmorris@namei.org> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: Patrick McHardy <kaber@trash.net> Signed-off-by: Andrey Vagin <avagin@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-28 01:33:56 +03:00
struct tcp_repair_window {
__u32 snd_wl1;
__u32 snd_wnd;
__u32 max_window;
__u32 rcv_wnd;
__u32 rcv_wup;
};
UAPI: (Scripted) Disintegrate include/linux Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Dave Jones <davej@redhat.com>
2012-10-13 13:46:48 +04:00
enum {
TCP_NO_QUEUE,
TCP_RECV_QUEUE,
TCP_SEND_QUEUE,
TCP_QUEUES_NR,
};
/* for TCP_INFO socket option */
#define TCPI_OPT_TIMESTAMPS 1
#define TCPI_OPT_SACK 2
#define TCPI_OPT_WSCALE 4
#define TCPI_OPT_ECN 8 /* ECN was negociated at TCP session init */
#define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */
tcp: add SYN/data info to TCP_INFO Add a bit TCPI_OPT_SYN_DATA (32) to the socket option TCP_INFO:tcpi_options. It's set if the data in SYN (sent or received) is acked by SYN-ACK. Server or client application can use this information to check Fast Open success rate. Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-19 19:14:44 +04:00
#define TCPI_OPT_SYN_DATA 32 /* SYN-ACK acked data in SYN sent or rcvd */
UAPI: (Scripted) Disintegrate include/linux Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Dave Jones <davej@redhat.com>
2012-10-13 13:46:48 +04:00
enum tcp_ca_state {
TCP_CA_Open = 0,
#define TCPF_CA_Open (1<<TCP_CA_Open)
TCP_CA_Disorder = 1,
#define TCPF_CA_Disorder (1<<TCP_CA_Disorder)
TCP_CA_CWR = 2,
#define TCPF_CA_CWR (1<<TCP_CA_CWR)
TCP_CA_Recovery = 3,
#define TCPF_CA_Recovery (1<<TCP_CA_Recovery)
TCP_CA_Loss = 4
#define TCPF_CA_Loss (1<<TCP_CA_Loss)
};
struct tcp_info {
__u8 tcpi_state;
__u8 tcpi_ca_state;
__u8 tcpi_retransmits;
__u8 tcpi_probes;
__u8 tcpi_backoff;
__u8 tcpi_options;
__u8 tcpi_snd_wscale : 4, tcpi_rcv_wscale : 4;
tcp: export data delivery rate This commit export two new fields in struct tcp_info: tcpi_delivery_rate: The most recent goodput, as measured by tcp_rate_gen(). If the socket is limited by the sending application (e.g., no data to send), it reports the highest measurement instead of the most recent. The unit is bytes per second (like other rate fields in tcp_info). tcpi_delivery_rate_app_limited: A boolean indicating if the goodput was measured when the socket's throughput was limited by the sending application. This delivery rate information can be useful for applications that want to know the current throughput the TCP connection is seeing, e.g. adaptive bitrate video streaming. It can also be very useful for debugging or troubleshooting. Signed-off-by: Van Jacobson <vanj@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Nandita Dukkipati <nanditad@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-20 06:39:16 +03:00
__u8 tcpi_delivery_rate_app_limited:1;
UAPI: (Scripted) Disintegrate include/linux Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Dave Jones <davej@redhat.com>
2012-10-13 13:46:48 +04:00
__u32 tcpi_rto;
__u32 tcpi_ato;
__u32 tcpi_snd_mss;
__u32 tcpi_rcv_mss;
__u32 tcpi_unacked;
__u32 tcpi_sacked;
__u32 tcpi_lost;
__u32 tcpi_retrans;
__u32 tcpi_fackets;
/* Times. */
__u32 tcpi_last_data_sent;
__u32 tcpi_last_ack_sent; /* Not remembered, sorry. */
__u32 tcpi_last_data_recv;
__u32 tcpi_last_ack_recv;
/* Metrics. */
__u32 tcpi_pmtu;
__u32 tcpi_rcv_ssthresh;
__u32 tcpi_rtt;
__u32 tcpi_rttvar;
__u32 tcpi_snd_ssthresh;
__u32 tcpi_snd_cwnd;
__u32 tcpi_advmss;
__u32 tcpi_reordering;
__u32 tcpi_rcv_rtt;
__u32 tcpi_rcv_space;
__u32 tcpi_total_retrans;
tcp: add pacing_rate information into tcp_info Add two new fields to struct tcp_info, to report sk_pacing_rate and sk_max_pacing_rate to monitoring applications, as ss from iproute2. User exported fields are 64bit, even if kernel is currently using 32bit fields. lpaa5:~# ss -i .. skmem:(r0,rb357120,t0,tb2097152,f1584,w1980880,o0,bl0) ts sack cubic wscale:6,6 rto:400 rtt:0.875/0.75 mss:1448 cwnd:1 ssthresh:12 send 13.2Mbps pacing_rate 3336.2Mbps unacked:15 retrans:1/5448 lost:15 rcv_space:29200 Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-02-14 02:27:40 +04:00
__u64 tcpi_pacing_rate;
__u64 tcpi_max_pacing_rate;
tcp: add tcpi_segs_in and tcpi_segs_out to tcp_info This patch tracks the total number of inbound and outbound segments on a TCP socket. One may use this number to have an idea on connection quality when compared against the retransmissions. RFC4898 named these : tcpEStatsPerfSegsIn and tcpEStatsPerfSegsOut These are a 32bit field each and can be fetched both from TCP_INFO getsockopt() if one has a handle on a TCP socket, or from inet_diag netlink facility (iproute2/ss patch will follow) Note that tp->segs_out was placed near tp->snd_nxt for good data locality and minimal performance impact, while tp->segs_in was placed near tp->bytes_received for the same reason. Join work with Eric Dumazet. Note that received SYN are accounted on the listener, but sent SYNACK are not accounted. Signed-off-by: Marcelo Ricardo Leitner <mleitner@redhat.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-21 02:35:41 +03:00
__u64 tcpi_bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked */
tcp: add tcpi_bytes_received to tcp_info This patch tracks total number of payload bytes received on a TCP socket. This is the sum of all changes done to tp->rcv_nxt RFC4898 named this : tcpEStatsAppHCThruOctetsReceived This is a 64bit field, and can be fetched both from TCP_INFO getsockopt() if one has a handle on a TCP socket, or from inet_diag netlink facility (iproute2/ss patch will follow) Note that tp->bytes_received was placed near tp->rcv_nxt for best data locality and minimal performance impact. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Matt Mathis <mattmathis@google.com> Cc: Eric Salo <salo@google.com> Cc: Martin Lau <kafai@fb.com> Cc: Chris Rapier <rapier@psc.edu> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-29 01:28:18 +03:00
__u64 tcpi_bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived */
tcp: add tcpi_segs_in and tcpi_segs_out to tcp_info This patch tracks the total number of inbound and outbound segments on a TCP socket. One may use this number to have an idea on connection quality when compared against the retransmissions. RFC4898 named these : tcpEStatsPerfSegsIn and tcpEStatsPerfSegsOut These are a 32bit field each and can be fetched both from TCP_INFO getsockopt() if one has a handle on a TCP socket, or from inet_diag netlink facility (iproute2/ss patch will follow) Note that tp->segs_out was placed near tp->snd_nxt for good data locality and minimal performance impact, while tp->segs_in was placed near tp->bytes_received for the same reason. Join work with Eric Dumazet. Note that received SYN are accounted on the listener, but sent SYNACK are not accounted. Signed-off-by: Marcelo Ricardo Leitner <mleitner@redhat.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-21 02:35:41 +03:00
__u32 tcpi_segs_out; /* RFC4898 tcpEStatsPerfSegsOut */
__u32 tcpi_segs_in; /* RFC4898 tcpEStatsPerfSegsIn */
tcp: add tcpi_min_rtt and tcpi_notsent_bytes to tcp_info tcpi_min_rtt reports the minimal rtt observed by TCP stack for the flow, in usec unit. Might be ~0U if not yet known. tcpi_notsent_bytes reports the amount of bytes in the write queue that were not yet sent. This is done in a single patch to not add a temporary 32bit padding hole in tcp_info. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-12 09:02:53 +03:00
__u32 tcpi_notsent_bytes;
__u32 tcpi_min_rtt;
tcp: Add RFC4898 tcpEStatsPerfDataSegsOut/In Per RFC4898, they count segments sent/received containing a positive length data segment (that includes retransmission segments carrying data). Unlike tcpi_segs_out/in, tcpi_data_segs_out/in excludes segments carrying no data (e.g. pure ack). The patch also updates the segs_in in tcp_fastopen_add_skb() so that segs_in >= data_segs_in property is kept. Together with retransmission data, tcpi_data_segs_out gives a better signal on the rxmit rate. v6: Rebase on the latest net-next v5: Eric pointed out that checking skb->len is still needed in tcp_fastopen_add_skb() because skb can carry a FIN without data. Hence, instead of open coding segs_in and data_segs_in, tcp_segs_in() helper is used. Comment is added to the fastopen case to explain why segs_in has to be reset and tcp_segs_in() has to be called before __skb_pull(). v4: Add comment to the changes in tcp_fastopen_add_skb() and also add remark on this case in the commit message. v3: Add const modifier to the skb parameter in tcp_segs_in() v2: Rework based on recent fix by Eric: commit a9d99ce28ed3 ("tcp: fix tcpi_segs_in after connection establishment") Signed-off-by: Martin KaFai Lau <kafai@fb.com> Cc: Chris Rapier <rapier@psc.edu> Cc: Eric Dumazet <edumazet@google.com> Cc: Marcelo Ricardo Leitner <mleitner@redhat.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Yuchung Cheng <ycheng@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-03-14 20:52:15 +03:00
__u32 tcpi_data_segs_in; /* RFC4898 tcpEStatsDataSegsIn */
__u32 tcpi_data_segs_out; /* RFC4898 tcpEStatsDataSegsOut */
tcp: export data delivery rate This commit export two new fields in struct tcp_info: tcpi_delivery_rate: The most recent goodput, as measured by tcp_rate_gen(). If the socket is limited by the sending application (e.g., no data to send), it reports the highest measurement instead of the most recent. The unit is bytes per second (like other rate fields in tcp_info). tcpi_delivery_rate_app_limited: A boolean indicating if the goodput was measured when the socket's throughput was limited by the sending application. This delivery rate information can be useful for applications that want to know the current throughput the TCP connection is seeing, e.g. adaptive bitrate video streaming. It can also be very useful for debugging or troubleshooting. Signed-off-by: Van Jacobson <vanj@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Nandita Dukkipati <nanditad@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-20 06:39:16 +03:00
__u64 tcpi_delivery_rate;
tcp: export sender limits chronographs to TCP_INFO This patch exports all the sender chronograph measurements collected in the previous patches to TCP_INFO interface. Note that busy time exported includes all the other sending limits (rwnd-limited, sndbuf-limited). Internally the time unit is jiffy but externally the measurements are in microseconds for future extensions. Signed-off-by: Francis Yan <francisyyan@gmail.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-28 10:07:17 +03:00
__u64 tcpi_busy_time; /* Time (usec) busy sending data */
__u64 tcpi_rwnd_limited; /* Time (usec) limited by receive window */
__u64 tcpi_sndbuf_limited; /* Time (usec) limited by send buffer */
UAPI: (Scripted) Disintegrate include/linux Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Dave Jones <davej@redhat.com>
2012-10-13 13:46:48 +04:00
};
tcp: SOF_TIMESTAMPING_OPT_STATS option for SO_TIMESTAMPING This patch exports the sender chronograph stats via the socket SO_TIMESTAMPING channel. Currently we can instrument how long a particular application unit of data was queued in TCP by tracking SOF_TIMESTAMPING_TX_SOFTWARE and SOF_TIMESTAMPING_TX_SCHED. Having these sender chronograph stats exported simultaneously along with these timestamps allow further breaking down the various sender limitation. For example, a video server can tell if a particular chunk of video on a connection takes a long time to deliver because TCP was experiencing small receive window. It is not possible to tell before this patch without packet traces. To prepare these stats, the user needs to set SOF_TIMESTAMPING_OPT_STATS and SOF_TIMESTAMPING_OPT_TSONLY flags while requesting other SOF_TIMESTAMPING TX timestamps. When the timestamps are available in the error queue, the stats are returned in a separate control message of type SCM_TIMESTAMPING_OPT_STATS, in a list of TLVs (struct nlattr) of types: TCP_NLA_BUSY_TIME, TCP_NLA_RWND_LIMITED, TCP_NLA_SNDBUF_LIMITED. Unit is microsecond. Signed-off-by: Francis Yan <francisyyan@gmail.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-28 10:07:18 +03:00
/* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
enum {
TCP_NLA_PAD,
TCP_NLA_BUSY, /* Time (usec) busy sending data */
TCP_NLA_RWND_LIMITED, /* Time (usec) limited by receive window */
TCP_NLA_SNDBUF_LIMITED, /* Time (usec) limited by send buffer */
tcp: record pkts sent and retransmistted Add two stats in SCM_TIMESTAMPING_OPT_STATS: TCP_NLA_DATA_SEGS_OUT: total data packets sent including retransmission TCP_NLA_TOTAL_RETRANS: total data packets retransmitted The names are picked to be consistent with corresponding fields in TCP_INFO. This allows applications that are using the timestamping API to measure latency stats to also retrive retransmission rate of application write. Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-28 03:24:38 +03:00
TCP_NLA_DATA_SEGS_OUT, /* Data pkts sent including retransmission */
TCP_NLA_TOTAL_RETRANS, /* Data pkts retransmitted */
tcp: add related fields into SCM_TIMESTAMPING_OPT_STATS Add the following stats into SCM_TIMESTAMPING_OPT_STATS control msg: TCP_NLA_PACING_RATE TCP_NLA_DELIVERY_RATE TCP_NLA_SND_CWND TCP_NLA_REORDERING TCP_NLA_MIN_RTT TCP_NLA_RECUR_RETRANS TCP_NLA_DELIVERY_RATE_APP_LMT Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-28 20:28:21 +03:00
TCP_NLA_PACING_RATE, /* Pacing rate in bytes per second */
TCP_NLA_DELIVERY_RATE, /* Delivery rate in bytes per second */
TCP_NLA_SND_CWND, /* Sending congestion window */
TCP_NLA_REORDERING, /* Reordering metric */
TCP_NLA_MIN_RTT, /* minimum RTT */
TCP_NLA_RECUR_RETRANS, /* Recurring retransmits for the current pkt */
TCP_NLA_DELIVERY_RATE_APP_LMT, /* delivery rate application limited ? */
tcp: SOF_TIMESTAMPING_OPT_STATS option for SO_TIMESTAMPING This patch exports the sender chronograph stats via the socket SO_TIMESTAMPING channel. Currently we can instrument how long a particular application unit of data was queued in TCP by tracking SOF_TIMESTAMPING_TX_SOFTWARE and SOF_TIMESTAMPING_TX_SCHED. Having these sender chronograph stats exported simultaneously along with these timestamps allow further breaking down the various sender limitation. For example, a video server can tell if a particular chunk of video on a connection takes a long time to deliver because TCP was experiencing small receive window. It is not possible to tell before this patch without packet traces. To prepare these stats, the user needs to set SOF_TIMESTAMPING_OPT_STATS and SOF_TIMESTAMPING_OPT_TSONLY flags while requesting other SOF_TIMESTAMPING TX timestamps. When the timestamps are available in the error queue, the stats are returned in a separate control message of type SCM_TIMESTAMPING_OPT_STATS, in a list of TLVs (struct nlattr) of types: TCP_NLA_BUSY_TIME, TCP_NLA_RWND_LIMITED, TCP_NLA_SNDBUF_LIMITED. Unit is microsecond. Signed-off-by: Francis Yan <francisyyan@gmail.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-28 10:07:18 +03:00
};
UAPI: (Scripted) Disintegrate include/linux Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Dave Jones <davej@redhat.com>
2012-10-13 13:46:48 +04:00
/* for TCP_MD5SIG socket option */
#define TCP_MD5SIG_MAXKEYLEN 80
tcp: md5: add TCP_MD5SIG_EXT socket option to set a key address prefix Replace first padding in the tcp_md5sig structure with a new flag field and address prefix length so it can be specified when configuring a new key for TCP MD5 signature. The tcpm_flags field will only be used if the socket option is TCP_MD5SIG_EXT to avoid breaking existing programs, and tcpm_prefixlen only when the TCP_MD5SIG_FLAG_PREFIX flag is set. Signed-off-by: Bob Gilligan <gilligan@arista.com> Signed-off-by: Eric Mowat <mowat@arista.com> Signed-off-by: Ivan Delalande <colona@arista.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-16 04:07:07 +03:00
/* tcp_md5sig extension flags for TCP_MD5SIG_EXT */
#define TCP_MD5SIG_FLAG_PREFIX 1 /* address prefix length */
UAPI: (Scripted) Disintegrate include/linux Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Dave Jones <davej@redhat.com>
2012-10-13 13:46:48 +04:00
struct tcp_md5sig {
struct __kernel_sockaddr_storage tcpm_addr; /* address associated */
tcp: md5: add TCP_MD5SIG_EXT socket option to set a key address prefix Replace first padding in the tcp_md5sig structure with a new flag field and address prefix length so it can be specified when configuring a new key for TCP MD5 signature. The tcpm_flags field will only be used if the socket option is TCP_MD5SIG_EXT to avoid breaking existing programs, and tcpm_prefixlen only when the TCP_MD5SIG_FLAG_PREFIX flag is set. Signed-off-by: Bob Gilligan <gilligan@arista.com> Signed-off-by: Eric Mowat <mowat@arista.com> Signed-off-by: Ivan Delalande <colona@arista.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-16 04:07:07 +03:00
__u8 tcpm_flags; /* extension flags */
__u8 tcpm_prefixlen; /* address prefix */
UAPI: (Scripted) Disintegrate include/linux Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Dave Jones <davej@redhat.com>
2012-10-13 13:46:48 +04:00
__u16 tcpm_keylen; /* key length */
tcp: md5: add TCP_MD5SIG_EXT socket option to set a key address prefix Replace first padding in the tcp_md5sig structure with a new flag field and address prefix length so it can be specified when configuring a new key for TCP MD5 signature. The tcpm_flags field will only be used if the socket option is TCP_MD5SIG_EXT to avoid breaking existing programs, and tcpm_prefixlen only when the TCP_MD5SIG_FLAG_PREFIX flag is set. Signed-off-by: Bob Gilligan <gilligan@arista.com> Signed-off-by: Eric Mowat <mowat@arista.com> Signed-off-by: Ivan Delalande <colona@arista.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-16 04:07:07 +03:00
__u32 __tcpm_pad; /* zero */
UAPI: (Scripted) Disintegrate include/linux Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Dave Jones <davej@redhat.com>
2012-10-13 13:46:48 +04:00
__u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */
};
tcp_diag: report TCP MD5 signing keys and addresses Report TCP MD5 (RFC2385) signing keys, addresses and address prefixes to processes with CAP_NET_ADMIN requesting INET_DIAG_INFO. Currently it is not possible to retrieve these from the kernel once they have been configured on sockets. Signed-off-by: Ivan Delalande <colona@arista.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-31 19:59:39 +03:00
/* INET_DIAG_MD5SIG */
struct tcp_diag_md5sig {
__u8 tcpm_family;
__u8 tcpm_prefixlen;
__u16 tcpm_keylen;
__be32 tcpm_addr[4];
__u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN];
};
UAPI: (Scripted) Disintegrate include/linux Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Dave Jones <davej@redhat.com>
2012-10-13 13:46:48 +04:00
#endif /* _UAPI_LINUX_TCP_H */