// SPDX-License-Identifier: GPL-2.0-only /* * Pluggable TCP congestion control support and newReno * congestion control. * Based on ideas from I/O scheduler support and Web100. * * Copyright (C) 2005 Stephen Hemminger <[email protected]> */ #define pr_fmt(fmt) … #include <linux/module.h> #include <linux/mm.h> #include <linux/types.h> #include <linux/list.h> #include <linux/gfp.h> #include <linux/jhash.h> #include <net/tcp.h> #include <trace/events/tcp.h> static DEFINE_SPINLOCK(tcp_cong_list_lock); static LIST_HEAD(tcp_cong_list); /* Simple linear search, don't expect many entries! */ struct tcp_congestion_ops *tcp_ca_find(const char *name) { … } void tcp_set_ca_state(struct sock *sk, const u8 ca_state) { … } /* Must be called with rcu lock held */ static struct tcp_congestion_ops *tcp_ca_find_autoload(const char *name) { … } /* Simple linear search, not much in here. */ struct tcp_congestion_ops *tcp_ca_find_key(u32 key) { … } int tcp_validate_congestion_control(struct tcp_congestion_ops *ca) { … } /* Attach new congestion control algorithm to the list * of available options. */ int tcp_register_congestion_control(struct tcp_congestion_ops *ca) { … } EXPORT_SYMBOL_GPL(…); /* * Remove congestion control algorithm, called from * the module's remove function. Module ref counts are used * to ensure that this can't be done till all sockets using * that method are closed. */ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca) { … } EXPORT_SYMBOL_GPL(…); /* Replace a registered old ca with a new one. * * The new ca must have the same name as the old one, that has been * registered. */ int tcp_update_congestion_control(struct tcp_congestion_ops *ca, struct tcp_congestion_ops *old_ca) { … } u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca) { … } char *tcp_ca_get_name_by_key(u32 key, char *buffer) { … } /* Assign choice of congestion control. */ void tcp_assign_congestion_control(struct sock *sk) { … } void tcp_init_congestion_control(struct sock *sk) { … } static void tcp_reinit_congestion_control(struct sock *sk, const struct tcp_congestion_ops *ca) { … } /* Manage refcounts on socket close. */ void tcp_cleanup_congestion_control(struct sock *sk) { … } /* Used by sysctl to change default congestion control */ int tcp_set_default_congestion_control(struct net *net, const char *name) { … } /* Set default value from kernel configuration at bootup */ static int __init tcp_congestion_default(void) { … } late_initcall(tcp_congestion_default); /* Build string with list of available congestion control values */ void tcp_get_available_congestion_control(char *buf, size_t maxlen) { … } /* Get current default congestion control */ void tcp_get_default_congestion_control(struct net *net, char *name) { … } /* Built list of non-restricted congestion control values */ void tcp_get_allowed_congestion_control(char *buf, size_t maxlen) { … } /* Change list of non-restricted congestion control */ int tcp_set_allowed_congestion_control(char *val) { … } /* Change congestion control for socket. If load is false, then it is the * responsibility of the caller to call tcp_init_congestion_control or * tcp_reinit_congestion_control (if the current congestion control was * already initialized. */ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool cap_net_admin) { … } /* Slow start is used when congestion window is no greater than the slow start * threshold. We base on RFC2581 and also handle stretch ACKs properly. * We do not implement RFC3465 Appropriate Byte Counting (ABC) per se but * something better;) a packet is only considered (s)acked in its entirety to * defend the ACK attacks described in the RFC. Slow start processes a stretch * ACK of degree N as if N acks of degree 1 are received back to back except * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and * returns the leftover acks to adjust cwnd in congestion avoidance mode. */ __bpf_kfunc u32 tcp_slow_start(struct tcp_sock *tp, u32 acked) { … } EXPORT_SYMBOL_GPL(…); /* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w), * for every packet that was ACKed. */ __bpf_kfunc void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked) { … } EXPORT_SYMBOL_GPL(…); /* * TCP Reno congestion control * This is special case used for fallback as well. */ /* This is Jacobson's slow start and congestion avoidance. * SIGCOMM '88, p. 328. */ __bpf_kfunc void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) { … } EXPORT_SYMBOL_GPL(…); /* Slow start threshold is half the congestion window (min 2) */ __bpf_kfunc u32 tcp_reno_ssthresh(struct sock *sk) { … } EXPORT_SYMBOL_GPL(…); __bpf_kfunc u32 tcp_reno_undo_cwnd(struct sock *sk) { … } EXPORT_SYMBOL_GPL(…); struct tcp_congestion_ops tcp_reno = …;