/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * 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 module. * * Version: @(#)tcp.h 1.0.5 05/23/93 * * Authors: Ross Biro * Fred N. van Kempen, <[email protected]> */ #ifndef _TCP_H #define _TCP_H #define FASTRETRANS_DEBUG … #include <linux/list.h> #include <linux/tcp.h> #include <linux/bug.h> #include <linux/slab.h> #include <linux/cache.h> #include <linux/percpu.h> #include <linux/skbuff.h> #include <linux/kref.h> #include <linux/ktime.h> #include <linux/indirect_call_wrapper.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> #include <net/inet_hashtables.h> #include <net/checksum.h> #include <net/request_sock.h> #include <net/sock_reuseport.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ip.h> #include <net/tcp_states.h> #include <net/tcp_ao.h> #include <net/inet_ecn.h> #include <net/dst.h> #include <net/mptcp.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> #include <linux/bpf-cgroup.h> #include <linux/siphash.h> extern struct inet_hashinfo tcp_hashinfo; DECLARE_PER_CPU(unsigned int, tcp_orphan_count); int tcp_orphan_count_sum(void); DECLARE_PER_CPU(u32, tcp_tw_isn); void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER … #define MAX_TCP_OPTION_SPACE … #define TCP_MIN_SND_MSS … #define TCP_MIN_GSO_SIZE … /* * Never offer a window over 32767 without using window scaling. Some * poor stacks do signed 16bit maths! */ #define MAX_TCP_WINDOW … /* Minimal accepted MSS. It is (60+60+8) - (20+20). */ #define TCP_MIN_MSS … /* The initial MTU to use for probing */ #define TCP_BASE_MSS … /* probing interval, default to 10 minutes as per RFC4821 */ #define TCP_PROBE_INTERVAL … /* Specify interval when tcp mtu probing will stop */ #define TCP_PROBE_THRESHOLD … /* After receiving this amount of duplicate ACKs fast retransmit starts. */ #define TCP_FASTRETRANS_THRESH … /* Maximal number of ACKs sent quickly to accelerate slow-start. */ #define TCP_MAX_QUICKACKS … /* Maximal number of window scale according to RFC1323 */ #define TCP_MAX_WSCALE … /* urg_data states */ #define TCP_URG_VALID … #define TCP_URG_NOTYET … #define TCP_URG_READ … #define TCP_RETR1 … #define TCP_RETR2 … #define TCP_SYN_RETRIES … #define TCP_SYNACK_RETRIES … #define TCP_TIMEWAIT_LEN … #define TCP_FIN_TIMEOUT … /* BSD style FIN_WAIT2 deadlock breaker. * It used to be 3min, new value is 60sec, * to combine FIN-WAIT-2 timeout with * TIME-WAIT timer. */ #define TCP_FIN_TIMEOUT_MAX … #define TCP_DELACK_MAX … static_assert(…); #if HZ >= 100 #define TCP_DELACK_MIN … #define TCP_ATO_MIN … #else #define TCP_DELACK_MIN … #define TCP_ATO_MIN … #endif #define TCP_RTO_MAX … #define TCP_RTO_MIN … #define TCP_TIMEOUT_MIN … #define TCP_TIMEOUT_MIN_US … #define TCP_TIMEOUT_INIT … #define TCP_TIMEOUT_FALLBACK … #define TCP_RESOURCE_PROBE_INTERVAL … #define TCP_KEEPALIVE_TIME … #define TCP_KEEPALIVE_PROBES … #define TCP_KEEPALIVE_INTVL … #define MAX_TCP_KEEPIDLE … #define MAX_TCP_KEEPINTVL … #define MAX_TCP_KEEPCNT … #define MAX_TCP_SYNCNT … /* Ensure that TCP PAWS checks are relaxed after ~2147 seconds * to avoid overflows. This assumes a clock smaller than 1 Mhz. * Default clock is 1 Khz, tcp_usec_ts uses 1 Mhz. */ #define TCP_PAWS_WRAP … #define TCP_PAWS_MSL … #define TCP_PAWS_WINDOW … /* * TCP option */ #define TCPOPT_NOP … #define TCPOPT_EOL … #define TCPOPT_MSS … #define TCPOPT_WINDOW … #define TCPOPT_SACK_PERM … #define TCPOPT_SACK … #define TCPOPT_TIMESTAMP … #define TCPOPT_MD5SIG … #define TCPOPT_AO … #define TCPOPT_MPTCP … #define TCPOPT_FASTOPEN … #define TCPOPT_EXP … /* Magic number to be after the option value for sharing TCP * experimental options. See draft-ietf-tcpm-experimental-options-00.txt */ #define TCPOPT_FASTOPEN_MAGIC … #define TCPOPT_SMC_MAGIC … /* * TCP option lengths */ #define TCPOLEN_MSS … #define TCPOLEN_WINDOW … #define TCPOLEN_SACK_PERM … #define TCPOLEN_TIMESTAMP … #define TCPOLEN_MD5SIG … #define TCPOLEN_FASTOPEN_BASE … #define TCPOLEN_EXP_FASTOPEN_BASE … #define TCPOLEN_EXP_SMC_BASE … /* But this is what stacks really send out. */ #define TCPOLEN_TSTAMP_ALIGNED … #define TCPOLEN_WSCALE_ALIGNED … #define TCPOLEN_SACKPERM_ALIGNED … #define TCPOLEN_SACK_BASE … #define TCPOLEN_SACK_BASE_ALIGNED … #define TCPOLEN_SACK_PERBLOCK … #define TCPOLEN_MD5SIG_ALIGNED … #define TCPOLEN_MSS_ALIGNED … #define TCPOLEN_EXP_SMC_BASE_ALIGNED … /* Flags in tp->nonagle */ #define TCP_NAGLE_OFF … #define TCP_NAGLE_CORK … #define TCP_NAGLE_PUSH … /* TCP thin-stream limits */ #define TCP_THIN_LINEAR_RETRIES … /* TCP initial congestion window as per rfc6928 */ #define TCP_INIT_CWND … /* Bit Flags for sysctl_tcp_fastopen */ #define TFO_CLIENT_ENABLE … #define TFO_SERVER_ENABLE … #define TFO_CLIENT_NO_COOKIE … /* Accept SYN data w/o any cookie option */ #define TFO_SERVER_COOKIE_NOT_REQD … /* Force enable TFO on all listeners, i.e., not requiring the * TCP_FASTOPEN socket option. */ #define TFO_SERVER_WO_SOCKOPT1 … /* sysctl variables for tcp */ extern int sysctl_tcp_max_orphans; extern long sysctl_tcp_mem[3]; #define TCP_RACK_LOSS_DETECTION … #define TCP_RACK_STATIC_REO_WND … #define TCP_RACK_NO_DUPTHRESH … extern atomic_long_t tcp_memory_allocated; DECLARE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); extern struct percpu_counter tcp_sockets_allocated; extern unsigned long tcp_memory_pressure; /* optimized version of sk_under_memory_pressure() for TCP sockets */ static inline bool tcp_under_memory_pressure(const struct sock *sk) { … } /* * The next routines deal with comparing 32 bit unsigned ints * and worry about wraparound (automatic with unsigned arithmetic). */ static inline bool before(__u32 seq1, __u32 seq2) { … } #define after(seq2, seq1) … /* is s2<=s1<=s3 ? */ static inline bool between(__u32 seq1, __u32 seq2, __u32 seq3) { … } static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { … } void sk_forced_mem_schedule(struct sock *sk, int size); bool tcp_check_oom(const struct sock *sk, int shift); extern struct proto tcp_prot; #define TCP_INC_STATS(net, field) … #define __TCP_INC_STATS(net, field) … #define TCP_DEC_STATS(net, field) … #define TCP_ADD_STATS(net, field, val) … void tcp_tasklet_init(void); int tcp_v4_err(struct sk_buff *skb, u32); void tcp_shutdown(struct sock *sk, int how); int tcp_v4_early_demux(struct sk_buff *skb); int tcp_v4_rcv(struct sk_buff *skb); void tcp_remove_empty_skb(struct sock *sk); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size, struct ubuf_info *uarg); void tcp_splice_eof(struct socket *sock); int tcp_send_mss(struct sock *sk, int *size_goal, int flags); int tcp_wmem_schedule(struct sock *sk, int copy); void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle, int size_goal); void tcp_release_cb(struct sock *sk); void tcp_wfree(struct sk_buff *skb); void tcp_write_timer_handler(struct sock *sk); void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, int *karg); enum skb_drop_reason tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); void tcp_twsk_purge(struct list_head *net_exit_list); ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, bool force_schedule); static inline void tcp_dec_quickack_mode(struct sock *sk) { … } #define TCP_ECN_OK … #define TCP_ECN_QUEUE_CWR … #define TCP_ECN_DEMAND_CWR … #define TCP_ECN_SEEN … enum tcp_tw_status { … }; enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th, u32 *tw_isn); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, bool fastopen, bool *lost_race); enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag); void tcp_clear_retrans(struct tcp_sock *tp); void tcp_update_metrics(struct sock *sk); void tcp_init_metrics(struct sock *sk); void tcp_metrics_init(void); bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); void __tcp_close(struct sock *sk, long timeout); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int do_tcp_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); bool tcp_bpf_bypass_getsockopt(int level, int optname); int do_tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); void tcp_syn_ack_timeout(const struct request_sock *req); int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); int tcp_set_rcvlowat(struct sock *sk, int val); int tcp_set_window_clamp(struct sock *sk, int val); void tcp_update_recv_tstamps(struct sk_buff *skb, struct scm_timestamping_internal *tss); void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping_internal *tss); void tcp_data_ready(struct sock *sk); #ifdef CONFIG_MMU int tcp_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); #endif void tcp_parse_options(const struct net *net, const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); /* * BPF SKB-less helpers */ u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss); u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct tcphdr *th); /* * TCP v4 functions exported for the inet6 API */ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); void tcp_v4_mtu_reduced(struct sock *sk); void tcp_req_err(struct sock *sk, u32 seq, bool abort); void tcp_ld_RTO_revert(struct sock *sk, u32 seq); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(const struct sock *sk, struct request_sock *req, struct sk_buff *skb); void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst); struct sock *tcp_v4_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); int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int tcp_connect(struct sock *sk); enum tcp_synack_type { … }; struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb); int tcp_disconnect(struct sock *sk, int flags); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size); void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb); /* From syncookies.c */ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk, struct sk_buff *skb, struct tcp_options_received *tcp_opt, int mss, u32 tsoff); #if IS_ENABLED(CONFIG_BPF) struct bpf_tcp_req_attrs { … }; #endif #ifdef CONFIG_SYN_COOKIES /* Syncookies use a monotonic timer which increments every 60 seconds. * This counter is used both as a hash input and partially encoded into * the cookie value. A cookie is only validated further if the delta * between the current counter value and the encoded one is less than this, * i.e. a sent cookie is valid only at most for 2*60 seconds (or less if * the counter advances immediately after a cookie is generated). */ #define MAX_SYNCOOKIE_AGE … #define TCP_SYNCOOKIE_PERIOD … #define TCP_SYNCOOKIE_VALID … /* syncookies: remember time of last synqueue overflow * But do not dirty this field too often (once per second is enough) * It is racy as we do not hold a lock, but race is very minor. */ static inline void tcp_synq_overflow(const struct sock *sk) { … } /* syncookies: no recent synqueue overflow on this listening socket? */ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) { … } static inline u32 tcp_cookie_time(void) { … } /* Convert one nsec 64bit timestamp to ts (ms or usec resolution) */ static inline u64 tcp_ns_to_ts(bool usec_ts, u64 val) { … } u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); u64 cookie_init_timestamp(struct request_sock *req, u64 now); bool cookie_timestamp_decode(const struct net *net, struct tcp_options_received *opt); static inline bool cookie_ecn_ok(const struct net *net, const struct dst_entry *dst) { … } #if IS_ENABLED(CONFIG_BPF) static inline bool cookie_bpf_ok(struct sk_buff *skb) { … } struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb); #else static inline bool cookie_bpf_ok(struct sk_buff *skb) { return false; } static inline struct request_sock *cookie_bpf_check(struct net *net, struct sock *sk, struct sk_buff *skb) { return NULL; } #endif /* From net/ipv6/syncookies.c */ int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th); struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); #endif /* tcp_output.c */ void tcp_skb_entail(struct sock *sk, struct sk_buff *skb); void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb); void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle); int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); void tcp_retransmit_timer(struct sock *sk); void tcp_xmit_retransmit_queue(struct sock *); void tcp_simple_retransmit(struct sock *); void tcp_enter_recovery(struct sock *sk, bool ece_ack); int tcp_trim_head(struct sock *, struct sk_buff *, u32); enum tcp_queue { … }; int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp); void tcp_send_probe0(struct sock *); int tcp_write_wakeup(struct sock *, int mib); void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority, enum sk_rst_reason reason); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto); void tcp_skb_collapse_tstamp(struct sk_buff *skb, const struct sk_buff *next_skb); /* tcp_input.c */ void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_done_with_error(struct sock *sk, int err); void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_fin(struct sock *sk); void tcp_check_space(struct sock *sk); void tcp_sack_compress_send_ack(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); static inline void tcp_clear_xmit_timers(struct sock *sk) { … } unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu); unsigned int tcp_current_mss(struct sock *sk); u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when); /* Bound MSS / TSO packet size with the half of the window */ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) { … } /* tcp.c */ void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor); struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off); void tcp_read_done(struct sock *sk, size_t len); void tcp_initialize_rcv_mss(struct sock *sk); int tcp_mtu_to_mss(struct sock *sk, int pmtu); int tcp_mss_to_mtu(struct sock *sk, int mss); void tcp_mtup_init(struct sock *sk); static inline void tcp_bound_rto(struct sock *sk) { … } static inline u32 __tcp_set_rto(const struct tcp_sock *tp) { … } static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) { … } static inline void tcp_fast_path_on(struct tcp_sock *tp) { … } static inline void tcp_fast_path_check(struct sock *sk) { … } u32 tcp_delack_max(const struct sock *sk); /* Compute the actual rto_min value */ static inline u32 tcp_rto_min(const struct sock *sk) { … } static inline u32 tcp_rto_min_us(const struct sock *sk) { … } static inline bool tcp_ca_dst_locked(const struct dst_entry *dst) { … } /* Minimum RTT in usec. ~0 means not available. */ static inline u32 tcp_min_rtt(const struct tcp_sock *tp) { … } /* Compute the actual receive window we are currently advertising. * Rcv_nxt can be after the window if our peer push more data * than the offered window. */ static inline u32 tcp_receive_window(const struct tcp_sock *tp) { … } /* Choose a new window, without checks for shrinking, and without * scaling applied to the result. The caller does these things * if necessary. This is a "raw" window selection. */ u32 __tcp_select_window(struct sock *sk); void tcp_send_window_probe(struct sock *sk); /* TCP uses 32bit jiffies to save some space. * Note that this is different from tcp_time_stamp, which * historically has been the same until linux-4.13. */ #define tcp_jiffies32 … /* * Deliver a 32bit value for TCP timestamp option (RFC 7323) * It is no longer tied to jiffies, but to 1 ms clock. * Note: double check if you want to use tcp_jiffies32 instead of this. */ #define TCP_TS_HZ … static inline u64 tcp_clock_ns(void) { … } static inline u64 tcp_clock_us(void) { … } static inline u64 tcp_clock_ms(void) { … } /* TCP Timestamp included in TS option (RFC 1323) can either use ms * or usec resolution. Each socket carries a flag to select one or other * resolution, as the route attribute could change anytime. * Each flow must stick to initial resolution. */ static inline u32 tcp_clock_ts(bool usec_ts) { … } static inline u32 tcp_time_stamp_ms(const struct tcp_sock *tp) { … } static inline u32 tcp_time_stamp_ts(const struct tcp_sock *tp) { … } void tcp_mstamp_refresh(struct tcp_sock *tp); static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) { … } /* provide the departure time in us unit */ static inline u64 tcp_skb_timestamp_us(const struct sk_buff *skb) { … } /* Provide skb TSval in usec or ms unit */ static inline u32 tcp_skb_timestamp_ts(bool usec_ts, const struct sk_buff *skb) { … } static inline u32 tcp_tw_tsval(const struct tcp_timewait_sock *tcptw) { … } static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq) { … } #define tcp_flag_byte(th) … #define TCPHDR_FIN … #define TCPHDR_SYN … #define TCPHDR_RST … #define TCPHDR_PSH … #define TCPHDR_ACK … #define TCPHDR_URG … #define TCPHDR_ECE … #define TCPHDR_CWR … #define TCPHDR_SYN_ECN … /* State flags for sacked in struct tcp_skb_cb */ enum tcp_skb_cb_sacked_flags { … }; /* This is what the send packet queuing engine uses to pass * TCP per-packet control information to the transmission code. * We also store the host-order sequence numbers in here too. * This is 44 bytes if IPV6 is enabled. * If this grows please adjust skbuff.h:skbuff->cb[xxx] size appropriately. */ struct tcp_skb_cb { … }; #define TCP_SKB_CB(__skb) … extern const struct inet_connection_sock_af_ops ipv4_specific; #if IS_ENABLED(CONFIG_IPV6) /* This is the variant of inet6_iif() that must be used by TCP, * as TCP moves IP6CB into a different location in skb->cb[] */ static inline int tcp_v6_iif(const struct sk_buff *skb) { … } static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb) { … } /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v6_sdif(const struct sk_buff *skb) { … } extern const struct inet_connection_sock_af_ops ipv6_specific; INDIRECT_CALLABLE_DECLARE(…); INDIRECT_CALLABLE_DECLARE(…); void tcp_v6_early_demux(struct sk_buff *skb); #endif /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v4_sdif(struct sk_buff *skb) { … } /* Due to TSO, an SKB can be composed of multiple actual * packets. To keep these tracked properly, we use this. */ static inline int tcp_skb_pcount(const struct sk_buff *skb) { … } static inline void tcp_skb_pcount_set(struct sk_buff *skb, int segs) { … } static inline void tcp_skb_pcount_add(struct sk_buff *skb, int segs) { … } /* This is valid iff skb is in write queue and tcp_skb_pcount() > 1. */ static inline int tcp_skb_mss(const struct sk_buff *skb) { … } static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb) { … } static inline bool tcp_skb_can_collapse(const struct sk_buff *to, const struct sk_buff *from) { … } static inline bool tcp_skb_can_collapse_rx(const struct sk_buff *to, const struct sk_buff *from) { … } /* Events passed to congestion control interface */ enum tcp_ca_event { … }; /* Information about inbound ACK, passed to cong_ops->in_ack_event() */ enum tcp_ca_ack_event_flags { … }; /* * Interface for adding new TCP congestion control handlers */ #define TCP_CA_NAME_MAX … #define TCP_CA_MAX … #define TCP_CA_BUF_MAX … #define TCP_CA_UNSPEC … /* Algorithm can be set on socket without CAP_NET_ADMIN privileges */ #define TCP_CONG_NON_RESTRICTED … /* Requires ECN/ECT set on all packets */ #define TCP_CONG_NEEDS_ECN … #define TCP_CONG_MASK … tcp_cc_info; struct ack_sample { … }; /* A rate sample measures the number of (original/retransmitted) data * packets delivered "delivered" over an interval of time "interval_us". * The tcp_rate.c code fills in the rate sample, and congestion * control modules that define a cong_control function to run at the end * of ACK processing can optionally chose to consult this sample when * setting cwnd and pacing rate. * A sample is invalid if "delivered" or "interval_us" is negative. */ struct rate_sample { … }; struct tcp_congestion_ops { … } ____cacheline_aligned_in_smp; int tcp_register_congestion_control(struct tcp_congestion_ops *type); void tcp_unregister_congestion_control(struct tcp_congestion_ops *type); int tcp_update_congestion_control(struct tcp_congestion_ops *type, struct tcp_congestion_ops *old_type); int tcp_validate_congestion_control(struct tcp_congestion_ops *ca); void tcp_assign_congestion_control(struct sock *sk); void tcp_init_congestion_control(struct sock *sk); void tcp_cleanup_congestion_control(struct sock *sk); int tcp_set_default_congestion_control(struct net *net, const char *name); void tcp_get_default_congestion_control(struct net *net, char *name); void tcp_get_available_congestion_control(char *buf, size_t len); void tcp_get_allowed_congestion_control(char *buf, size_t len); int tcp_set_allowed_congestion_control(char *allowed); int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool cap_net_admin); u32 tcp_slow_start(struct tcp_sock *tp, u32 acked); void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked); u32 tcp_reno_ssthresh(struct sock *sk); u32 tcp_reno_undo_cwnd(struct sock *sk); void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked); extern struct tcp_congestion_ops tcp_reno; struct tcp_congestion_ops *tcp_ca_find(const char *name); struct tcp_congestion_ops *tcp_ca_find_key(u32 key); u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca); #ifdef CONFIG_INET char *tcp_ca_get_name_by_key(u32 key, char *buffer); #else static inline char *tcp_ca_get_name_by_key(u32 key, char *buffer) { return NULL; } #endif static inline bool tcp_ca_needs_ecn(const struct sock *sk) { … } static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { … } /* From tcp_cong.c */ void tcp_set_ca_state(struct sock *sk, const u8 ca_state); /* From tcp_rate.c */ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb); void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct rate_sample *rs); void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, bool is_sack_reneg, struct rate_sample *rs); void tcp_rate_check_app_limited(struct sock *sk); static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) { … } /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. * * tcp_is_sack - SACK enabled * tcp_is_reno - No SACK */ static inline int tcp_is_sack(const struct tcp_sock *tp) { … } static inline bool tcp_is_reno(const struct tcp_sock *tp) { … } static inline unsigned int tcp_left_out(const struct tcp_sock *tp) { … } /* This determines how many packets are "in the network" to the best * of our knowledge. In many cases it is conservative, but where * detailed information is available from the receiver (via SACK * blocks etc.) we can make more aggressive calculations. * * Use this for decisions involving congestion control, use just * tp->packets_out to determine if the send queue is empty or not. * * Read this equation as: * * "Packets sent once on transmission queue" MINUS * "Packets left network, but not honestly ACKed yet" PLUS * "Packets fast retransmitted" */ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) { … } #define TCP_INFINITE_SSTHRESH … static inline u32 tcp_snd_cwnd(const struct tcp_sock *tp) { … } static inline void tcp_snd_cwnd_set(struct tcp_sock *tp, u32 val) { … } static inline bool tcp_in_slow_start(const struct tcp_sock *tp) { … } static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp) { … } static inline bool tcp_in_cwnd_reduction(const struct sock *sk) { … } /* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd. * The exception is cwnd reduction phase, when cwnd is decreasing towards * ssthresh. */ static inline __u32 tcp_current_ssthresh(const struct sock *sk) { … } /* Use define here intentionally to get WARN_ON location shown at the caller */ #define tcp_verify_left_out(tp) … void tcp_enter_cwr(struct sock *sk); __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst); /* The maximum number of MSS of available cwnd for which TSO defers * sending if not using sysctl_tcp_tso_win_divisor. */ static inline __u32 tcp_max_tso_deferred_mss(const struct tcp_sock *tp) { … } /* Returns end sequence number of the receiver's advertised window */ static inline u32 tcp_wnd_end(const struct tcp_sock *tp) { … } /* We follow the spirit of RFC2861 to validate cwnd but implement a more * flexible approach. The RFC suggests cwnd should not be raised unless * it was fully used previously. And that's exactly what we do in * congestion avoidance mode. But in slow start we allow cwnd to grow * as long as the application has used half the cwnd. * Example : * cwnd is 10 (IW10), but application sends 9 frames. * We allow cwnd to reach 18 when all frames are ACKed. * This check is safe because it's as aggressive as slow start which already * risks 100% overshoot. The advantage is that we discourage application to * either send more filler packets or data to artificially blow up the cwnd * usage, and allow application-limited process to probe bw more aggressively. */ static inline bool tcp_is_cwnd_limited(const struct sock *sk) { … } /* BBR congestion control needs pacing. * Same remark for SO_MAX_PACING_RATE. * sch_fq packet scheduler is efficiently handling pacing, * but is not always installed/used. * Return true if TCP stack should pace packets itself. */ static inline bool tcp_needs_internal_pacing(const struct sock *sk) { … } /* Estimates in how many jiffies next packet for this flow can be sent. * Scheduling a retransmit timer too early would be silly. */ static inline unsigned long tcp_pacing_delay(const struct sock *sk) { … } static inline void tcp_reset_xmit_timer(struct sock *sk, const int what, unsigned long when, const unsigned long max_when) { … } /* Something is really bad, we could not queue an additional packet, * because qdisc is full or receiver sent a 0 window, or we are paced. * We do not want to add fuel to the fire, or abort too early, * so make sure the timer we arm now is at least 200ms in the future, * regardless of current icsk_rto value (as it could be ~2ms) */ static inline unsigned long tcp_probe0_base(const struct sock *sk) { … } /* Variant of inet_csk_rto_backoff() used for zero window probes */ static inline unsigned long tcp_probe0_when(const struct sock *sk, unsigned long max_when) { … } static inline void tcp_check_probe_timer(struct sock *sk) { … } static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) { … } static inline void tcp_update_wl(struct tcp_sock *tp, u32 seq) { … } /* * Calculate(/check) TCP checksum */ static inline __sum16 tcp_v4_check(int len, __be32 saddr, __be32 daddr, __wsum base) { … } static inline bool tcp_checksum_complete(struct sk_buff *skb) { … } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason); int tcp_filter(struct sock *sk, struct sk_buff *skb); void tcp_set_state(struct sock *sk, int state); void tcp_done(struct sock *sk); int tcp_abort(struct sock *sk, int err); static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) { … } void tcp_cwnd_restart(struct sock *sk, s32 delta); static inline void tcp_slow_start_after_idle_check(struct sock *sk) { … } /* Determine a window scaling and initial window to offer. */ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd); static inline int __tcp_win_from_space(u8 scaling_ratio, int space) { … } static inline int tcp_win_from_space(const struct sock *sk, int space) { … } /* inverse of __tcp_win_from_space() */ static inline int __tcp_space_from_win(u8 scaling_ratio, int win) { … } static inline int tcp_space_from_win(const struct sock *sk, int win) { … } /* Assume a 50% default for skb->len/skb->truesize ratio. * This may be adjusted later in tcp_measure_rcv_mss(). */ #define TCP_DEFAULT_SCALING_RATIO … static inline void tcp_scaling_ratio_init(struct sock *sk) { … } /* Note: caller must be prepared to deal with negative returns */ static inline int tcp_space(const struct sock *sk) { … } static inline int tcp_full_space(const struct sock *sk) { … } static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh) { … } static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) { … } void tcp_cleanup_rbuf(struct sock *sk, int copied); void __tcp_cleanup_rbuf(struct sock *sk, int copied); /* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override * SO_RCVLOWAT constraint, since we are receiving skbs with too small * len/truesize ratio. */ static inline bool tcp_rmem_pressure(const struct sock *sk) { … } static inline bool tcp_epollin_ready(const struct sock *sk, int target) { … } extern void tcp_openreq_init_rwin(struct request_sock *req, const struct sock *sk_listener, const struct dst_entry *dst); void tcp_enter_memory_pressure(struct sock *sk); void tcp_leave_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { … } static inline int keepalive_time_when(const struct tcp_sock *tp) { … } static inline int keepalive_probes(const struct tcp_sock *tp) { … } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) { … } static inline int tcp_fin_time(const struct sock *sk) { … } static inline bool tcp_paws_check(const struct tcp_options_received *rx_opt, int paws_win) { … } static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt, int rst) { … } bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, int mib_idx, u32 *last_oow_ack_time); static inline void tcp_mib_init(struct net *net) { … } /* from STCP */ static inline void tcp_clear_retrans_hints_partial(struct tcp_sock *tp) { … } static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp) { … } #define tcp_md5_addr … /* - key database */ struct tcp_md5sig_key { … }; /* - sock block */ struct tcp_md5sig_info { … }; /* - pseudo header */ struct tcp4_pseudohdr { … }; struct tcp6_pseudohdr { … }; tcp_md5sum_block; /* * struct tcp_sigpool - per-CPU pool of ahash_requests * @scratch: per-CPU temporary area, that can be used between * tcp_sigpool_start() and tcp_sigpool_end() to perform * crypto request * @req: pre-allocated ahash request */ struct tcp_sigpool { … }; int tcp_sigpool_alloc_ahash(const char *alg, size_t scratch_size); void tcp_sigpool_get(unsigned int id); void tcp_sigpool_release(unsigned int id); int tcp_sigpool_hash_skb_data(struct tcp_sigpool *hp, const struct sk_buff *skb, unsigned int header_len); /** * tcp_sigpool_start - disable bh and start using tcp_sigpool_ahash * @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash() * @c: returned tcp_sigpool for usage (uninitialized on failure) * * Returns 0 on success, error otherwise. */ int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c); /** * tcp_sigpool_end - enable bh and stop using tcp_sigpool * @c: tcp_sigpool context that was returned by tcp_sigpool_start() */ void tcp_sigpool_end(struct tcp_sigpool *c); size_t tcp_sigpool_algo(unsigned int id, char *buf, size_t buf_len); /* - functions */ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags, const u8 *newkey, u8 newkeylen); int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, struct tcp_md5sig_key *key); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags); void tcp_clear_md5_list(struct sock *sk); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family, bool any_l3index); static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { … } static inline struct tcp_md5sig_key * tcp_md5_do_lookup_any_l3index(const struct sock *sk, const union tcp_md5_addr *addr, int family) { … } #define tcp_twsk_md5_key(twsk) … #else static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { return NULL; } static inline struct tcp_md5sig_key * tcp_md5_do_lookup_any_l3index(const struct sock *sk, const union tcp_md5_addr *addr, int family) { return NULL; } #define tcp_twsk_md5_key … #endif int tcp_md5_alloc_sigpool(void); void tcp_md5_release_sigpool(void); void tcp_md5_add_sigpool(void); extern int tcp_md5_sigpool_id; int tcp_md5_hash_key(struct tcp_sigpool *hp, const struct tcp_md5sig_key *key); /* From tcp_fastopen.c */ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); void tcp_fastopen_cache_set(struct sock *sk, u16 mss, struct tcp_fastopen_cookie *cookie, bool syn_lost, u16 try_exp); struct tcp_fastopen_request { … }; void tcp_free_fastopen_req(struct tcp_sock *tp); void tcp_fastopen_destroy_cipher(struct sock *sk); void tcp_fastopen_ctx_destroy(struct net *net); int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, void *primary_key, void *backup_key); int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk, u64 *key); void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc, const struct dst_entry *dst); void tcp_fastopen_init_key_once(struct net *net); bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); bool tcp_fastopen_defer_connect(struct sock *sk, int *err); #define TCP_FASTOPEN_KEY_LENGTH … #define TCP_FASTOPEN_KEY_MAX … #define TCP_FASTOPEN_KEY_BUF_LENGTH … /* Fastopen key context */ struct tcp_fastopen_context { … }; void tcp_fastopen_active_disable(struct sock *sk); bool tcp_fastopen_active_should_disable(struct sock *sk); void tcp_fastopen_active_disable_ofo_check(struct sock *sk); void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired); /* Caller needs to wrap with rcu_read_(un)lock() */ static inline struct tcp_fastopen_context *tcp_fastopen_get_ctx(const struct sock *sk) { … } static inline bool tcp_fastopen_cookie_match(const struct tcp_fastopen_cookie *foc, const struct tcp_fastopen_cookie *orig) { … } static inline int tcp_fastopen_context_len(const struct tcp_fastopen_context *ctx) { … } /* Latencies incurred by various limits for a sender. They are * chronograph-like stats that are mutually exclusive. */ enum tcp_chrono { … }; void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type); void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type); /* This helper is needed, because skb->tcp_tsorted_anchor uses * the same memory storage than skb->destructor/_skb_refdst */ static inline void tcp_skb_tsorted_anchor_cleanup(struct sk_buff *skb) { … } #define tcp_skb_tsorted_save(skb) … #define tcp_skb_tsorted_restore(skb) … void tcp_write_queue_purge(struct sock *sk); static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk) { … } static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk) { … } static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk) { … } #define tcp_for_write_queue_from_safe(skb, tmp, sk) … static inline struct sk_buff *tcp_send_head(const struct sock *sk) { … } static inline bool tcp_skb_is_last(const struct sock *sk, const struct sk_buff *skb) { … } /** * tcp_write_queue_empty - test if any payload (or FIN) is available in write queue * @sk: socket * * Since the write queue can have a temporary empty skb in it, * we must not use "return skb_queue_empty(&sk->sk_write_queue)" */ static inline bool tcp_write_queue_empty(const struct sock *sk) { … } static inline bool tcp_rtx_queue_empty(const struct sock *sk) { … } static inline bool tcp_rtx_and_write_queues_empty(const struct sock *sk) { … } static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb) { … } /* Insert new before skb on the write queue of sk. */ static inline void tcp_insert_write_queue_before(struct sk_buff *new, struct sk_buff *skb, struct sock *sk) { … } static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk) { … } void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb); static inline void tcp_rtx_queue_unlink(struct sk_buff *skb, struct sock *sk) { … } static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct sock *sk) { … } static inline void tcp_write_collapse_fence(struct sock *sk) { … } static inline void tcp_push_pending_frames(struct sock *sk) { … } /* Start sequence of the skb just after the highest skb with SACKed * bit, valid only if sacked_out > 0 or when the caller has ensured * validity by itself. */ static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp) { … } static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb) { … } static inline struct sk_buff *tcp_highest_sack(struct sock *sk) { … } static inline void tcp_highest_sack_reset(struct sock *sk) { … } /* Called when old skb is about to be deleted and replaced by new skb */ static inline void tcp_highest_sack_replace(struct sock *sk, struct sk_buff *old, struct sk_buff *new) { … } /* This helper checks if socket has IP_TRANSPARENT set */ static inline bool inet_sk_transparent(const struct sock *sk) { … } /* Determines whether this is a thin stream (which may suffer from * increased latency). Used to trigger latency-reducing mechanisms. */ static inline bool tcp_stream_is_thin(struct tcp_sock *tp) { … } /* /proc */ enum tcp_seq_states { … }; void *tcp_seq_start(struct seq_file *seq, loff_t *pos); void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos); void tcp_seq_stop(struct seq_file *seq, void *v); struct tcp_seq_afinfo { … }; struct tcp_iter_state { … }; extern struct request_sock_ops tcp_request_sock_ops; extern struct request_sock_ops tcp6_request_sock_ops; void tcp_v4_destroy_sock(struct sock *sk); struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features); struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb); struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th); struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, struct tcphdr *th); INDIRECT_CALLABLE_DECLARE(…); INDIRECT_CALLABLE_DECLARE(…); INDIRECT_CALLABLE_DECLARE(…); INDIRECT_CALLABLE_DECLARE(…); #ifdef CONFIG_INET void tcp_gro_complete(struct sk_buff *skb); #else static inline void tcp_gro_complete(struct sk_buff *skb) { } #endif void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { … } bool tcp_stream_memory_free(const struct sock *sk, int wake); #ifdef CONFIG_PROC_FS int tcp4_proc_init(void); void tcp4_proc_exit(void); #endif int tcp_rtx_synack(const struct sock *sk, struct request_sock *req); int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); /* TCP af-specific functions */ struct tcp_sock_af_ops { … }; struct tcp_request_sock_ops { … }; extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops; #if IS_ENABLED(CONFIG_IPV6) extern const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops; #endif #ifdef CONFIG_SYN_COOKIES static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, const struct sock *sk, struct sk_buff *skb, __u16 *mss) { … } #else static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, const struct sock *sk, struct sk_buff *skb, __u16 *mss) { return 0; } #endif struct tcp_key { … }; static inline void tcp_get_current_key(const struct sock *sk, struct tcp_key *out) { … } static inline bool tcp_key_is_md5(const struct tcp_key *key) { … } static inline bool tcp_key_is_ao(const struct tcp_key *key) { … } int tcpv4_offload_init(void); void tcp_v4_init(void); void tcp_init(void); /* tcp_recovery.c */ void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb); void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced); extern s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd); extern bool tcp_rack_mark_lost(struct sock *sk); extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, u64 xmit_time); extern void tcp_rack_reo_timeout(struct sock *sk); extern void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs); /* tcp_plb.c */ /* * Scaling factor for fractions in PLB. For example, tcp_plb_update_state * expects cong_ratio which represents fraction of traffic that experienced * congestion over a single RTT. In order to avoid floating point operations, * this fraction should be mapped to (1 << TCP_PLB_SCALE) and passed in. */ #define TCP_PLB_SCALE … /* State for PLB (Protective Load Balancing) for a single TCP connection. */ struct tcp_plb_state { … }; static inline void tcp_plb_init(const struct sock *sk, struct tcp_plb_state *plb) { … } void tcp_plb_update_state(const struct sock *sk, struct tcp_plb_state *plb, const int cong_ratio); void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb); void tcp_plb_update_state_upon_rto(struct sock *sk, struct tcp_plb_state *plb); /* At how many usecs into the future should the RTO fire? */ static inline s64 tcp_rto_delta_us(const struct sock *sk) { … } /* * Save and compile IPv4 options, return a pointer to it */ static inline struct ip_options_rcu *tcp_v4_save_options(struct net *net, struct sk_buff *skb) { … } /* locally generated TCP pure ACKs have skb->truesize == 2 * (check tcp_send_ack() in net/ipv4/tcp_output.c ) * This is much faster than dissecting the packet to find out. * (Think of GRE encapsulations, IPv4, IPv6, ...) */ static inline bool skb_is_tcp_pure_ack(const struct sk_buff *skb) { … } static inline void skb_set_tcp_pure_ack(struct sk_buff *skb) { … } static inline int tcp_inq(struct sock *sk) { … } int tcp_peek_len(struct socket *sock); static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb) { … } /* * TCP listen path runs lockless. * We forced "struct sock" to be const qualified to make sure * we don't modify one of its field by mistake. * Here, we increment sk_drops which is an atomic_t, so we can safely * make sock writable again. */ static inline void tcp_listendrop(const struct sock *sk) { … } enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer); /* * Interface for adding Upper Level Protocols over TCP */ #define TCP_ULP_NAME_MAX … #define TCP_ULP_MAX … #define TCP_ULP_BUF_MAX … struct tcp_ulp_ops { … }; int tcp_register_ulp(struct tcp_ulp_ops *type); void tcp_unregister_ulp(struct tcp_ulp_ops *type); int tcp_set_ulp(struct sock *sk, const char *name); void tcp_get_available_ulp(char *buf, size_t len); void tcp_cleanup_ulp(struct sock *sk); void tcp_update_ulp(struct sock *sk, struct proto *p, void (*write_space)(struct sock *sk)); #define MODULE_ALIAS_TCP_ULP(name) … #ifdef CONFIG_NET_SOCK_MSG struct sk_msg; struct sk_psock; #ifdef CONFIG_BPF_SYSCALL int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); #endif /* CONFIG_BPF_SYSCALL */ #ifdef CONFIG_INET void tcp_eat_skb(struct sock *sk, struct sk_buff *skb); #else static inline void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) { } #endif int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, struct sk_msg *msg, u32 bytes, int flags); #endif /* CONFIG_NET_SOCK_MSG */ #if !defined(CONFIG_BPF_SYSCALL) || !defined(CONFIG_NET_SOCK_MSG) static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) { } #endif #ifdef CONFIG_CGROUP_BPF static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, unsigned int end_offset) { … } #else static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, unsigned int end_offset) { } #endif /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF * program does not support the chosen operation or there is no BPF * program loaded). */ #ifdef CONFIG_BPF static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { … } static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2) { … } static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, u32 arg3) { … } #else static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { return -EPERM; } static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2) { return -EPERM; } static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, u32 arg3) { return -EPERM; } #endif static inline u32 tcp_timeout_init(struct sock *sk) { … } static inline u32 tcp_rwnd_init_bpf(struct sock *sk) { … } static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) { … } static inline void tcp_bpf_rtt(struct sock *sk, long mrtt, u32 srtt) { … } #if IS_ENABLED(CONFIG_SMC) extern struct static_key_false tcp_have_smc; #endif #if IS_ENABLED(CONFIG_TLS_DEVICE) void clean_acked_data_enable(struct inet_connection_sock *icsk, void (*cad)(struct sock *sk, u32 ack_seq)); void clean_acked_data_disable(struct inet_connection_sock *icsk); void clean_acked_data_flush(void); #endif DECLARE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); static inline void tcp_add_tx_delay(struct sk_buff *skb, const struct tcp_sock *tp) { … } /* Compute Earliest Departure Time for some control packets * like ACK or RST for TIME_WAIT or non ESTABLISHED sockets. */ static inline u64 tcp_transmit_time(const struct sock *sk) { … } static inline int tcp_parse_auth_options(const struct tcphdr *th, const u8 **md5_hash, const struct tcp_ao_hdr **aoh) { … } static inline bool tcp_ao_required(struct sock *sk, const void *saddr, int family, int l3index, bool stat_inc) { … } enum skb_drop_reason tcp_inbound_hash(struct sock *sk, const struct request_sock *req, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int dif, int sdif); #endif /* _TCP_H */
Codebase Browser
linux