WSL2-Linux-Kernel/include/net/inet_connection_sock.h

349 строки
11 KiB
C
Исходник Обычный вид История

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* NET Generic infrastructure for INET connection oriented protocols.
*
* Definitions for inet_connection_sock
*
* Authors: Many people, see the TCP sources
*
* From code originally in TCP
*/
#ifndef _INET_CONNECTION_SOCK_H
#define _INET_CONNECTION_SOCK_H
#include <linux/compiler.h>
#include <linux/string.h>
#include <linux/timer.h>
#include <linux/poll.h>
#include <linux/kernel.h>
#include <linux/sockptr.h>
#include <net/inet_sock.h>
#include <net/request_sock.h>
/* Cancel timers, when they are not required. */
#undef INET_CSK_CLEAR_TIMERS
struct inet_bind_bucket;
struct tcp_congestion_ops;
/*
* Pointers to address related TCP functions
* (i.e. things that depend on the address family)
*/
struct inet_connection_sock_af_ops {
int (*queue_xmit)(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
void (*send_check)(struct sock *sk, struct sk_buff *skb);
int (*rebuild_header)(struct sock *sk);
void (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb);
int (*conn_request)(struct sock *sk, struct sk_buff *skb);
struct sock *(*syn_recv_sock)(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst,
struct request_sock *req_unhash,
bool *own_req);
[INET_CONNECTION_SOCK]: Pack struct inet_connection_sock_af_ops We have a hole in: [acme@newtoy net-2.6.20]$ pahole net/ipv6/tcp_ipv6.o inet_connection_sock_af_ops /* /pub/scm/linux/kernel/git/acme/net-2.6.20/include/net/inet_connection_sock.h:38 */ struct inet_connection_sock_af_ops { int (*queue_xmit)(); /* 0 4 */ void (*send_check)(); /* 4 4 */ int (*rebuild_header)(); /* 8 4 */ int (*conn_request)(); /* 12 4 */ struct sock * (*syn_recv_sock)(); /* 16 4 */ int (*remember_stamp)(); /* 20 4 */ __u16 net_header_len; /* 24 2 */ /* XXX 2 bytes hole, try to pack */ int (*setsockopt)(); /* 28 4 */ int (*getsockopt)(); /* 32 4 */ int (*compat_setsockopt)(); /* 36 4 */ int (*compat_getsockopt)(); /* 40 4 */ void (*addr2sockaddr)(); /* 44 4 */ int sockaddr_len; /* 48 4 */ }; /* size: 52, sum members: 50, holes: 1, sum holes: 2 */ But we don't need sockaddr_len to be an int: [acme@newtoy net-2.6.20]$ find net -name "*.[ch]" | xargs grep '\.sockaddr_len.\+=' | sort -u net/dccp/ipv4.c: .sockaddr_len = sizeof(struct sockaddr_in), net/dccp/ipv6.c: .sockaddr_len = sizeof(struct sockaddr_in6), net/ipv4/tcp_ipv4.c: .sockaddr_len = sizeof(struct sockaddr_in), net/ipv6/tcp_ipv6.c: .sockaddr_len = sizeof(struct sockaddr_in6), net/sctp/ipv6.c: .sockaddr_len = sizeof(struct sockaddr_in6), net/sctp/protocol.c: .sockaddr_len = sizeof(struct sockaddr_in), [acme@newtoy net-2.6.20]$ pahole --sizes net/ipv6/tcp_ipv6.o | grep sockaddr_in struct sockaddr_in: 16 0 struct sockaddr_in6: 28 0 [acme@newtoy net-2.6.20]$ So I turned sockaddr_len a 'u16', and now: [acme@newtoy net-2.6.20]$ pahole net/ipv6/tcp_ipv6.o inet_connection_sock_af_ops /* /pub/scm/linux/kernel/git/acme/net-2.6.20/include/net/inet_connection_sock.h:38 */ struct inet_connection_sock_af_ops { int (*queue_xmit)(); /* 0 4 */ void (*send_check)(); /* 4 4 */ int (*rebuild_header)(); /* 8 4 */ int (*conn_request)(); /* 12 4 */ struct sock * (*syn_recv_sock)(); /* 16 4 */ int (*remember_stamp)(); /* 20 4 */ u16 net_header_len; /* 24 2 */ u16 sockaddr_len; /* 26 2 */ int (*setsockopt)(); /* 28 4 */ int (*getsockopt)(); /* 32 4 */ int (*compat_setsockopt)(); /* 36 4 */ int (*compat_getsockopt)(); /* 40 4 */ void (*addr2sockaddr)(); /* 44 4 */ }; /* size: 48 */ So we've saved 4 bytes: [acme@newtoy net-2.6.20]$ codiff -sV /tmp/tcp_ipv6.o.before net/ipv6/tcp_ipv6.o /pub/scm/linux/kernel/git/acme/net-2.6.20/net/ipv6/tcp_ipv6.c: struct inet_connection_sock_af_ops | -4 net_header_len; from: __u16 /* 24(0) 2(0) */ to: u16 /* 24(0) 2(0) */ sockaddr_len; from: int /* 48(0) 4(0) */ to: u16 /* 26(0) 2(0) */ 1 struct changed [acme@newtoy net-2.6.20]$ Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2006-11-27 22:56:43 +03:00
u16 net_header_len;
ipv6: RTAX_FEATURE_ALLFRAG causes inefficient TCP segment sizing Quoting Tore Anderson from : https://bugzilla.kernel.org/show_bug.cgi?id=42572 When RTAX_FEATURE_ALLFRAG is set on a route, the effective TCP segment size does not take into account the size of the IPv6 Fragmentation header that needs to be included in outbound packets, causing every transmitted TCP segment to be fragmented across two IPv6 packets, the latter of which will only contain 8 bytes of actual payload. RTAX_FEATURE_ALLFRAG is typically set on a route in response to receving a ICMPv6 Packet Too Big message indicating a Path MTU of less than 1280 bytes. 1280 bytes is the minimum IPv6 MTU, however ICMPv6 PTBs with MTU < 1280 are still valid, in particular when an IPv6 packet is sent to an IPv4 destination through a stateless translator. Any ICMPv4 Need To Fragment packets originated from the IPv4 part of the path will be translated to ICMPv6 PTB which may then indicate an MTU of less than 1280. The Linux kernel refuses to reduce the effective MTU to anything below 1280 bytes, instead it sets it to exactly 1280 bytes, and RTAX_FEATURE_ALLFRAG is also set. However, the TCP segment size appears to be set to 1240 bytes (1280 Path MTU - 40 bytes of IPv6 header), instead of 1232 (additionally taking into account the 8 bytes required by the IPv6 Fragmentation extension header). This in turn results in rather inefficient transmission, as every transmitted TCP segment now is split in two fragments containing 1232+8 bytes of payload. After this patch, all the outgoing packets that includes a Fragmentation header all are "atomic" or "non-fragmented" fragments, i.e., they both have Offset=0 and More Fragments=0. With help from David S. Miller Reported-by: Tore Anderson <tore@fud.no> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Maciej Żenczykowski <maze@google.com> Cc: Tom Herbert <therbert@google.com> Tested-by: Tore Anderson <tore@fud.no> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-24 11:37:38 +04:00
u16 net_frag_header_len;
[INET_CONNECTION_SOCK]: Pack struct inet_connection_sock_af_ops We have a hole in: [acme@newtoy net-2.6.20]$ pahole net/ipv6/tcp_ipv6.o inet_connection_sock_af_ops /* /pub/scm/linux/kernel/git/acme/net-2.6.20/include/net/inet_connection_sock.h:38 */ struct inet_connection_sock_af_ops { int (*queue_xmit)(); /* 0 4 */ void (*send_check)(); /* 4 4 */ int (*rebuild_header)(); /* 8 4 */ int (*conn_request)(); /* 12 4 */ struct sock * (*syn_recv_sock)(); /* 16 4 */ int (*remember_stamp)(); /* 20 4 */ __u16 net_header_len; /* 24 2 */ /* XXX 2 bytes hole, try to pack */ int (*setsockopt)(); /* 28 4 */ int (*getsockopt)(); /* 32 4 */ int (*compat_setsockopt)(); /* 36 4 */ int (*compat_getsockopt)(); /* 40 4 */ void (*addr2sockaddr)(); /* 44 4 */ int sockaddr_len; /* 48 4 */ }; /* size: 52, sum members: 50, holes: 1, sum holes: 2 */ But we don't need sockaddr_len to be an int: [acme@newtoy net-2.6.20]$ find net -name "*.[ch]" | xargs grep '\.sockaddr_len.\+=' | sort -u net/dccp/ipv4.c: .sockaddr_len = sizeof(struct sockaddr_in), net/dccp/ipv6.c: .sockaddr_len = sizeof(struct sockaddr_in6), net/ipv4/tcp_ipv4.c: .sockaddr_len = sizeof(struct sockaddr_in), net/ipv6/tcp_ipv6.c: .sockaddr_len = sizeof(struct sockaddr_in6), net/sctp/ipv6.c: .sockaddr_len = sizeof(struct sockaddr_in6), net/sctp/protocol.c: .sockaddr_len = sizeof(struct sockaddr_in), [acme@newtoy net-2.6.20]$ pahole --sizes net/ipv6/tcp_ipv6.o | grep sockaddr_in struct sockaddr_in: 16 0 struct sockaddr_in6: 28 0 [acme@newtoy net-2.6.20]$ So I turned sockaddr_len a 'u16', and now: [acme@newtoy net-2.6.20]$ pahole net/ipv6/tcp_ipv6.o inet_connection_sock_af_ops /* /pub/scm/linux/kernel/git/acme/net-2.6.20/include/net/inet_connection_sock.h:38 */ struct inet_connection_sock_af_ops { int (*queue_xmit)(); /* 0 4 */ void (*send_check)(); /* 4 4 */ int (*rebuild_header)(); /* 8 4 */ int (*conn_request)(); /* 12 4 */ struct sock * (*syn_recv_sock)(); /* 16 4 */ int (*remember_stamp)(); /* 20 4 */ u16 net_header_len; /* 24 2 */ u16 sockaddr_len; /* 26 2 */ int (*setsockopt)(); /* 28 4 */ int (*getsockopt)(); /* 32 4 */ int (*compat_setsockopt)(); /* 36 4 */ int (*compat_getsockopt)(); /* 40 4 */ void (*addr2sockaddr)(); /* 44 4 */ }; /* size: 48 */ So we've saved 4 bytes: [acme@newtoy net-2.6.20]$ codiff -sV /tmp/tcp_ipv6.o.before net/ipv6/tcp_ipv6.o /pub/scm/linux/kernel/git/acme/net-2.6.20/net/ipv6/tcp_ipv6.c: struct inet_connection_sock_af_ops | -4 net_header_len; from: __u16 /* 24(0) 2(0) */ to: u16 /* 24(0) 2(0) */ sockaddr_len; from: int /* 48(0) 4(0) */ to: u16 /* 26(0) 2(0) */ 1 struct changed [acme@newtoy net-2.6.20]$ Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2006-11-27 22:56:43 +03:00
u16 sockaddr_len;
int (*setsockopt)(struct sock *sk, int level, int optname,
sockptr_t optval, unsigned int optlen);
int (*getsockopt)(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
void (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
void (*mtu_reduced)(struct sock *sk);
};
/** inet_connection_sock - INET connection oriented sock
*
* @icsk_accept_queue: FIFO of established children
* @icsk_bind_hash: Bind node
* @icsk_timeout: Timeout
* @icsk_retransmit_timer: Resend (no ack)
* @icsk_rto: Retransmit timeout
* @icsk_pmtu_cookie Last pmtu seen by socket
* @icsk_ca_ops Pluggable congestion control hook
* @icsk_af_ops Operations which are AF_INET{4,6} specific
* @icsk_ulp_ops Pluggable ULP control hook
* @icsk_ulp_data ULP private data
* @icsk_clean_acked Clean acked data hook
* @icsk_listen_portaddr_node hash to the portaddr listener hashtable
* @icsk_ca_state: Congestion control state
* @icsk_retransmits: Number of unrecovered [RTO] timeouts
* @icsk_pending: Scheduled timer event
* @icsk_backoff: Backoff
* @icsk_syn_retries: Number of allowed SYN (or equivalent) retries
* @icsk_probes_out: unanswered 0 window probes
* @icsk_ext_hdr_len: Network protocol overhead (IP/IPv6 options)
* @icsk_ack: Delayed ACK control data
* @icsk_mtup; MTU probing control data
* @icsk_probes_tstamp: Probe timestamp (cleared by non-zero window ack)
* @icsk_user_timeout: TCP_USER_TIMEOUT value
*/
struct inet_connection_sock {
/* inet_sock has to be the first member! */
struct inet_sock icsk_inet;
struct request_sock_queue icsk_accept_queue;
struct inet_bind_bucket *icsk_bind_hash;
unsigned long icsk_timeout;
struct timer_list icsk_retransmit_timer;
struct timer_list icsk_delack_timer;
__u32 icsk_rto;
__u32 icsk_rto_min;
__u32 icsk_delack_max;
__u32 icsk_pmtu_cookie;
const struct tcp_congestion_ops *icsk_ca_ops;
const struct inet_connection_sock_af_ops *icsk_af_ops;
const struct tcp_ulp_ops *icsk_ulp_ops;
void __rcu *icsk_ulp_data;
void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq);
struct hlist_node icsk_listen_portaddr_node;
unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
__u8 icsk_ca_state:5,
icsk_ca_initialized:1,
tcp: fix child sockets to use system default congestion control if not set Linux 3.17 and earlier are explicitly engineered so that if the app doesn't specifically request a CC module on a listener before the SYN arrives, then the child gets the system default CC when the connection is established. See tcp_init_congestion_control() in 3.17 or earlier, which says "if no choice made yet assign the current value set as default". The change ("net: tcp: assign tcp cong_ops when tcp sk is created") altered these semantics, so that children got their parent listener's congestion control even if the system default had changed after the listener was created. This commit returns to those original semantics from 3.17 and earlier, since they are the original semantics from 2007 in 4d4d3d1e8 ("[TCP]: Congestion control initialization."), and some Linux congestion control workflows depend on that. In summary, if a listener socket specifically sets TCP_CONGESTION to "x", or the route locks the CC module to "x", then the child gets "x". Otherwise the child gets current system default from net.ipv4.tcp_congestion_control. That's the behavior in 3.17 and earlier, and this commit restores that. Fixes: 55d8694fa82c ("net: tcp: assign tcp cong_ops when tcp sk is created") Cc: Florian Westphal <fw@strlen.de> Cc: Daniel Borkmann <dborkman@redhat.com> Cc: Glenn Judd <glenn.judd@morganstanley.com> Cc: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-29 20:47:07 +03:00
icsk_ca_setsockopt:1,
net: tcp: add key management to congestion control This patch adds necessary infrastructure to the congestion control framework for later per route congestion control support. For a per route congestion control possibility, our aim is to store a unique u32 key identifier into dst metrics, which can then be mapped into a tcp_congestion_ops struct. We argue that having a RTAX key entry is the most simple, generic and easy way to manage, and also keeps the memory footprint of dst entries lower on 64 bit than with storing a pointer directly, for example. Having a unique key id also allows for decoupling actual TCP congestion control module management from the FIB layer, i.e. we don't have to care about expensive module refcounting inside the FIB at this point. We first thought of using an IDR store for the realization, which takes over dynamic assignment of unused key space and also performs the key to pointer mapping in RCU. While doing so, we stumbled upon the issue that due to the nature of dynamic key distribution, it just so happens, arguably in very rare occasions, that excessive module loads and unloads can lead to a possible reuse of previously used key space. Thus, previously stale keys in the dst metric are now being reassigned to a different congestion control algorithm, which might lead to unexpected behaviour. One way to resolve this would have been to walk FIBs on the actually rare occasion of a module unload and reset the metric keys for each FIB in each netns, but that's just very costly. Therefore, we argue a better solution is to reuse the unique congestion control algorithm name member and map that into u32 key space through jhash. For that, we split the flags attribute (as it currently uses 2 bits only anyway) into two u32 attributes, flags and key, so that we can keep the cacheline boundary of 2 cachelines on x86_64 and cache the precalculated key at registration time for the fast path. On average we might expect 2 - 4 modules being loaded worst case perhaps 15, so a key collision possibility is extremely low, and guaranteed collision-free on LE/BE for all in-tree modules. Overall this results in much simpler code, and all without the overhead of an IDR. Due to the deterministic nature, modules can now be unloaded, the congestion control algorithm for a specific but unloaded key will fall back to the default one, and on module reload time it will switch back to the expected algorithm transparently. Joint work with Florian Westphal. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-06 01:57:46 +03:00
icsk_ca_dst_locked:1;
__u8 icsk_retransmits;
__u8 icsk_pending;
__u8 icsk_backoff;
__u8 icsk_syn_retries;
__u8 icsk_probes_out;
__u16 icsk_ext_hdr_len;
struct {
__u8 pending; /* ACK is pending */
__u8 quick; /* Scheduled number of quick acks */
__u8 pingpong; /* The session is interactive */
__u8 retry; /* Number of attempts */
__u32 ato; /* Predicted tick of soft clock */
unsigned long timeout; /* Currently scheduled timeout */
__u32 lrcvtime; /* timestamp of last received data packet */
__u16 last_seg_size; /* Size of last incoming segment */
__u16 rcv_mss; /* MSS used for delayed ACK decisions */
} icsk_ack;
struct {
/* Range of MTUs to search */
int search_high;
int search_low;
/* Information on the current probe. */
u32 probe_size:31,
/* Is the MTUP feature enabled for this connection? */
enabled:1;
u32 probe_timestamp;
} icsk_mtup;
u32 icsk_probes_tstamp;
tcp: Add TCP_USER_TIMEOUT socket option. This patch provides a "user timeout" support as described in RFC793. The socket option is also needed for the the local half of RFC5482 "TCP User Timeout Option". TCP_USER_TIMEOUT is a TCP level socket option that takes an unsigned int, when > 0, to specify the maximum amount of time in ms that transmitted data may remain unacknowledged before TCP will forcefully close the corresponding connection and return ETIMEDOUT to the application. If 0 is given, TCP will continue to use the system default. Increasing the user timeouts allows a TCP connection to survive extended periods without end-to-end connectivity. Decreasing the user timeouts allows applications to "fail fast" if so desired. Otherwise it may take upto 20 minutes with the current system defaults in a normal WAN environment. The socket option can be made during any state of a TCP connection, but is only effective during the synchronized states of a connection (ESTABLISHED, FIN-WAIT-1, FIN-WAIT-2, CLOSE-WAIT, CLOSING, or LAST-ACK). Moreover, when used with the TCP keepalive (SO_KEEPALIVE) option, TCP_USER_TIMEOUT will overtake keepalive to determine when to close a connection due to keepalive failure. The option does not change in anyway when TCP retransmits a packet, nor when a keepalive probe will be sent. This option, like many others, will be inherited by an acceptor from its listener. Signed-off-by: H.K. Jerry Chu <hkchu@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-08-27 23:13:28 +04:00
u32 icsk_user_timeout;
tcp_bbr: adapt cwnd based on ack aggregation estimation Aggregation effects are extremely common with wifi, cellular, and cable modem link technologies, ACK decimation in middleboxes, and LRO and GRO in receiving hosts. The aggregation can happen in either direction, data or ACKs, but in either case the aggregation effect is visible to the sender in the ACK stream. Previously BBR's sending was often limited by cwnd under severe ACK aggregation/decimation because BBR sized the cwnd at 2*BDP. If packets were acked in bursts after long delays (e.g. one ACK acking 5*BDP after 5*RTT), BBR's sending was halted after sending 2*BDP over 2*RTT, leaving the bottleneck idle for potentially long periods. Note that loss-based congestion control does not have this issue because when facing aggregation it continues increasing cwnd after bursts of ACKs, growing cwnd until the buffer is full. To achieve good throughput in the presence of aggregation effects, this algorithm allows the BBR sender to put extra data in flight to keep the bottleneck utilized during silences in the ACK stream that it has evidence to suggest were caused by aggregation. A summary of the algorithm: when a burst of packets are acked by a stretched ACK or a burst of ACKs or both, BBR first estimates the expected amount of data that should have been acked, based on its estimated bandwidth. Then the surplus ("extra_acked") is recorded in a windowed-max filter to estimate the recent level of observed ACK aggregation. Then cwnd is increased by the ACK aggregation estimate. The larger cwnd avoids BBR being cwnd-limited in the face of ACK silences that recent history suggests were caused by aggregation. As a sanity check, the ACK aggregation degree is upper-bounded by the cwnd (at the time of measurement) and a global max of BW * 100ms. The algorithm is further described by the following presentation: https://datatracker.ietf.org/meeting/101/materials/slides-101-iccrg-an-update-on-bbr-work-at-google-00 In our internal testing, we observed a significant increase in BBR throughput (measured using netperf), in a basic wifi setup. - Host1 (sender on ethernet) -> AP -> Host2 (receiver on wifi) - 2.4 GHz -> BBR before: ~73 Mbps; BBR after: ~102 Mbps; CUBIC: ~100 Mbps - 5.0 GHz -> BBR before: ~362 Mbps; BBR after: ~593 Mbps; CUBIC: ~601 Mbps Also, this code is running globally on YouTube TCP connections and produced significant bandwidth increases for YouTube traffic. This is based on Ian Swett's max_ack_height_ algorithm from the QUIC BBR implementation. Signed-off-by: Priyaranjan Jha <priyarjha@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-23 23:04:54 +03:00
u64 icsk_ca_priv[104 / sizeof(u64)];
#define ICSK_CA_PRIV_SIZE sizeof_field(struct inet_connection_sock, icsk_ca_priv)
};
#define ICSK_TIME_RETRANS 1 /* Retransmit timer */
#define ICSK_TIME_DACK 2 /* Delayed ack timer */
#define ICSK_TIME_PROBE0 3 /* Zero window probe timer */
tcp: Tail loss probe (TLP) This patch series implement the Tail loss probe (TLP) algorithm described in http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01. The first patch implements the basic algorithm. TLP's goal is to reduce tail latency of short transactions. It achieves this by converting retransmission timeouts (RTOs) occuring due to tail losses (losses at end of transactions) into fast recovery. TLP transmits one packet in two round-trips when a connection is in Open state and isn't receiving any ACKs. The transmitted packet, aka loss probe, can be either new or a retransmission. When there is tail loss, the ACK from a loss probe triggers FACK/early-retransmit based fast recovery, thus avoiding a costly RTO. In the absence of loss, there is no change in the connection state. PTO stands for probe timeout. It is a timer event indicating that an ACK is overdue and triggers a loss probe packet. The PTO value is set to max(2*SRTT, 10ms) and is adjusted to account for delayed ACK timer when there is only one oustanding packet. TLP Algorithm On transmission of new data in Open state: -> packets_out > 1: schedule PTO in max(2*SRTT, 10ms). -> packets_out == 1: schedule PTO in max(2*RTT, 1.5*RTT + 200ms) -> PTO = min(PTO, RTO) Conditions for scheduling PTO: -> Connection is in Open state. -> Connection is either cwnd limited or no new data to send. -> Number of probes per tail loss episode is limited to one. -> Connection is SACK enabled. When PTO fires: new_segment_exists: -> transmit new segment. -> packets_out++. cwnd remains same. no_new_packet: -> retransmit the last segment. Its ACK triggers FACK or early retransmit based recovery. ACK path: -> rearm RTO at start of ACK processing. -> reschedule PTO if need be. In addition, the patch includes a small variation to the Early Retransmit (ER) algorithm, such that ER and TLP together can in principle recover any N-degree of tail loss through fast recovery. TLP is controlled by the same sysctl as ER, tcp_early_retrans sysctl. tcp_early_retrans==0; disables TLP and ER. ==1; enables RFC5827 ER. ==2; delayed ER. ==3; TLP and delayed ER. [DEFAULT] ==4; TLP only. The TLP patch series have been extensively tested on Google Web servers. It is most effective for short Web trasactions, where it reduced RTOs by 15% and improved HTTP response time (average by 6%, 99th percentile by 10%). The transmitted probes account for <0.5% of the overall transmissions. Signed-off-by: Nandita Dukkipati <nanditad@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-11 14:00:43 +04:00
#define ICSK_TIME_LOSS_PROBE 5 /* Tail loss probe timer */
tcp: add reordering timer in RACK loss detection This patch makes RACK install a reordering timer when it suspects some packets might be lost, but wants to delay the decision a little bit to accomodate reordering. It does not create a new timer but instead repurposes the existing RTO timer, because both are meant to retransmit packets. Specifically it arms a timer ICSK_TIME_REO_TIMEOUT when the RACK timing check fails. The wait time is set to RACK.RTT + RACK.reo_wnd - (NOW - Packet.xmit_time) + fudge This translates to expecting a packet (Packet) should take (RACK.RTT + RACK.reo_wnd + fudge) to deliver after it was sent. When there are multiple packets that need a timer, we use one timer with the maximum timeout. Therefore the timer conservatively uses the maximum window to expire N packets by one timeout, instead of N timeouts to expire N packets sent at different times. The fudge factor is 2 jiffies to ensure when the timer fires, all the suspected packets would exceed the deadline and be marked lost by tcp_rack_detect_loss(). It has to be at least 1 jiffy because the clock may tick between calling icsk_reset_xmit_timer(timeout) and actually hang the timer. The next jiffy is to lower-bound the timeout to 2 jiffies when reo_wnd is < 1ms. When the reordering timer fires (tcp_rack_reo_timeout): If we aren't in Recovery we'll enter fast recovery and force fast retransmit. This is very similar to the early retransmit (RFC5827) except RACK is not constrained to only enter recovery for small outstanding flights. 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 09:11:33 +03:00
#define ICSK_TIME_REO_TIMEOUT 6 /* Reordering timer */
static inline struct inet_connection_sock *inet_csk(const struct sock *sk)
{
return (struct inet_connection_sock *)sk;
}
static inline void *inet_csk_ca(const struct sock *sk)
{
return (void *)inet_csk(sk)->icsk_ca_priv;
}
struct sock *inet_csk_clone_lock(const struct sock *sk,
const struct request_sock *req,
const gfp_t priority);
enum inet_csk_ack_state_t {
ICSK_ACK_SCHED = 1,
ICSK_ACK_TIMER = 2,
ICSK_ACK_PUSHED = 4,
ICSK_ACK_PUSHED2 = 8,
ICSK_ACK_NOW = 16 /* Send the next ACK immediately (once) */
};
void inet_csk_init_xmit_timers(struct sock *sk,
void (*retransmit_handler)(struct timer_list *),
void (*delack_handler)(struct timer_list *),
void (*keepalive_handler)(struct timer_list *));
void inet_csk_clear_xmit_timers(struct sock *sk);
static inline void inet_csk_schedule_ack(struct sock *sk)
{
inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_SCHED;
}
static inline int inet_csk_ack_scheduled(const struct sock *sk)
{
return inet_csk(sk)->icsk_ack.pending & ICSK_ACK_SCHED;
}
static inline void inet_csk_delack_init(struct sock *sk)
{
memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack));
}
void inet_csk_delete_keepalive_timer(struct sock *sk);
void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
{
struct inet_connection_sock *icsk = inet_csk(sk);
if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
icsk->icsk_pending = 0;
#ifdef INET_CSK_CLEAR_TIMERS
sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
#endif
} else if (what == ICSK_TIME_DACK) {
icsk->icsk_ack.pending = 0;
icsk->icsk_ack.retry = 0;
#ifdef INET_CSK_CLEAR_TIMERS
sk_stop_timer(sk, &icsk->icsk_delack_timer);
#endif
} else {
pr_debug("inet_csk BUG: unknown timer value\n");
}
}
/*
* Reset the retransmission timer
*/
static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
unsigned long when,
const unsigned long max_when)
{
struct inet_connection_sock *icsk = inet_csk(sk);
if (when > max_when) {
pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n",
sk, what, when, (void *)_THIS_IP_);
when = max_when;
}
tcp: Tail loss probe (TLP) This patch series implement the Tail loss probe (TLP) algorithm described in http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01. The first patch implements the basic algorithm. TLP's goal is to reduce tail latency of short transactions. It achieves this by converting retransmission timeouts (RTOs) occuring due to tail losses (losses at end of transactions) into fast recovery. TLP transmits one packet in two round-trips when a connection is in Open state and isn't receiving any ACKs. The transmitted packet, aka loss probe, can be either new or a retransmission. When there is tail loss, the ACK from a loss probe triggers FACK/early-retransmit based fast recovery, thus avoiding a costly RTO. In the absence of loss, there is no change in the connection state. PTO stands for probe timeout. It is a timer event indicating that an ACK is overdue and triggers a loss probe packet. The PTO value is set to max(2*SRTT, 10ms) and is adjusted to account for delayed ACK timer when there is only one oustanding packet. TLP Algorithm On transmission of new data in Open state: -> packets_out > 1: schedule PTO in max(2*SRTT, 10ms). -> packets_out == 1: schedule PTO in max(2*RTT, 1.5*RTT + 200ms) -> PTO = min(PTO, RTO) Conditions for scheduling PTO: -> Connection is in Open state. -> Connection is either cwnd limited or no new data to send. -> Number of probes per tail loss episode is limited to one. -> Connection is SACK enabled. When PTO fires: new_segment_exists: -> transmit new segment. -> packets_out++. cwnd remains same. no_new_packet: -> retransmit the last segment. Its ACK triggers FACK or early retransmit based recovery. ACK path: -> rearm RTO at start of ACK processing. -> reschedule PTO if need be. In addition, the patch includes a small variation to the Early Retransmit (ER) algorithm, such that ER and TLP together can in principle recover any N-degree of tail loss through fast recovery. TLP is controlled by the same sysctl as ER, tcp_early_retrans sysctl. tcp_early_retrans==0; disables TLP and ER. ==1; enables RFC5827 ER. ==2; delayed ER. ==3; TLP and delayed ER. [DEFAULT] ==4; TLP only. The TLP patch series have been extensively tested on Google Web servers. It is most effective for short Web trasactions, where it reduced RTOs by 15% and improved HTTP response time (average by 6%, 99th percentile by 10%). The transmitted probes account for <0.5% of the overall transmissions. Signed-off-by: Nandita Dukkipati <nanditad@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-11 14:00:43 +04:00
if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 ||
what == ICSK_TIME_LOSS_PROBE || what == ICSK_TIME_REO_TIMEOUT) {
icsk->icsk_pending = what;
icsk->icsk_timeout = jiffies + when;
sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
} else if (what == ICSK_TIME_DACK) {
icsk->icsk_ack.pending |= ICSK_ACK_TIMER;
icsk->icsk_ack.timeout = jiffies + when;
sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
} else {
pr_debug("inet_csk BUG: unknown timer value\n");
}
}
static inline unsigned long
inet_csk_rto_backoff(const struct inet_connection_sock *icsk,
unsigned long max_when)
{
u64 when = (u64)icsk->icsk_rto << icsk->icsk_backoff;
return (unsigned long)min_t(u64, when, max_when);
}
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 11:09:05 +03:00
struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern);
int inet_csk_get_port(struct sock *sk, unsigned short snum);
struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4,
const struct request_sock *req);
struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
struct sock *newsk,
const struct request_sock *req);
struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
struct request_sock *req,
struct sock *child);
void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
unsigned long timeout);
struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
struct request_sock *req,
bool own_req);
static inline void inet_csk_reqsk_queue_added(struct sock *sk)
{
reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue);
}
static inline int inet_csk_reqsk_queue_len(const struct sock *sk)
{
return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue);
}
static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
{
return inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog;
}
bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req);
static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk)
{
/* The below has to be done to allow calling inet_csk_destroy_sock */
sock_set_flag(sk, SOCK_DEAD);
tcp: switch orphan_count to bare per-cpu counters Use of percpu_counter structure to track count of orphaned sockets is causing problems on modern hosts with 256 cpus or more. Stefan Bach reported a serious spinlock contention in real workloads, that I was able to reproduce with a netfilter rule dropping incoming FIN packets. 53.56% server [kernel.kallsyms] [k] queued_spin_lock_slowpath | ---queued_spin_lock_slowpath | --53.51%--_raw_spin_lock_irqsave | --53.51%--__percpu_counter_sum tcp_check_oom | |--39.03%--__tcp_close | tcp_close | inet_release | inet6_release | sock_close | __fput | ____fput | task_work_run | exit_to_usermode_loop | do_syscall_64 | entry_SYSCALL_64_after_hwframe | __GI___libc_close | --14.48%--tcp_out_of_resources tcp_write_timeout tcp_retransmit_timer tcp_write_timer_handler tcp_write_timer call_timer_fn expire_timers __run_timers run_timer_softirq __softirqentry_text_start As explained in commit cf86a086a180 ("net/dst: use a smaller percpu_counter batch for dst entries accounting"), default batch size is too big for the default value of tcp_max_orphans (262144). But even if we reduce batch sizes, there would still be cases where the estimated count of orphans is beyond the limit, and where tcp_too_many_orphans() has to call the expensive percpu_counter_sum_positive(). One solution is to use plain per-cpu counters, and have a timer to periodically refresh this cache. Updating this cache every 100ms seems about right, tcp pressure state is not radically changing over shorter periods. percpu_counter was nice 15 years ago while hosts had less than 16 cpus, not anymore by current standards. v2: Fix the build issue for CONFIG_CRYPTO_DEV_CHELSIO_TLS=m, reported by kernel test robot <lkp@intel.com> Remove unused socket argument from tcp_too_many_orphans() Fixes: dd24c00191d5 ("net: Use a percpu_counter for orphan_count") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Stefan Bach <sfb@google.com> Cc: Neal Cardwell <ncardwell@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-10-14 16:41:26 +03:00
this_cpu_inc(*sk->sk_prot->orphan_count);
}
void inet_csk_destroy_sock(struct sock *sk);
void inet_csk_prepare_forced_close(struct sock *sk);
/*
* LISTEN is a special case for poll..
*/
static inline __poll_t inet_csk_listen_poll(const struct sock *sk)
{
return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ?
(EPOLLIN | EPOLLRDNORM) : 0;
}
int inet_csk_listen_start(struct sock *sk, int backlog);
void inet_csk_listen_stop(struct sock *sk);
void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
/* update the fast reuse flag when adding a socket */
void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
struct sock *sk);
struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
#define TCP_PINGPONG_THRESH 3
static inline void inet_csk_enter_pingpong_mode(struct sock *sk)
{
inet_csk(sk)->icsk_ack.pingpong = TCP_PINGPONG_THRESH;
}
static inline void inet_csk_exit_pingpong_mode(struct sock *sk)
{
inet_csk(sk)->icsk_ack.pingpong = 0;
}
static inline bool inet_csk_in_pingpong_mode(struct sock *sk)
{
return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH;
}
static inline void inet_csk_inc_pingpong_cnt(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_ack.pingpong < U8_MAX)
icsk->icsk_ack.pingpong++;
}
static inline bool inet_csk_has_ulp(struct sock *sk)
{
return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops;
}
#endif /* _INET_CONNECTION_SOCK_H */