123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567 |
- /* 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 protocol.
- *
- * Version: @(#)tcp.h 1.0.2 04/28/93
- *
- * Author: Fred N. van Kempen, <[email protected]>
- */
- #ifndef _LINUX_TCP_H
- #define _LINUX_TCP_H
- #include <linux/skbuff.h>
- #include <linux/win_minmax.h>
- #include <linux/android_kabi.h>
- #include <net/sock.h>
- #include <net/inet_connection_sock.h>
- #include <net/inet_timewait_sock.h>
- #include <uapi/linux/tcp.h>
- static inline struct tcphdr *tcp_hdr(const struct sk_buff *skb)
- {
- return (struct tcphdr *)skb_transport_header(skb);
- }
- static inline unsigned int __tcp_hdrlen(const struct tcphdr *th)
- {
- return th->doff * 4;
- }
- static inline unsigned int tcp_hdrlen(const struct sk_buff *skb)
- {
- return __tcp_hdrlen(tcp_hdr(skb));
- }
- static inline struct tcphdr *inner_tcp_hdr(const struct sk_buff *skb)
- {
- return (struct tcphdr *)skb_inner_transport_header(skb);
- }
- static inline unsigned int inner_tcp_hdrlen(const struct sk_buff *skb)
- {
- return inner_tcp_hdr(skb)->doff * 4;
- }
- /**
- * skb_tcp_all_headers - Returns size of all headers for a TCP packet
- * @skb: buffer
- *
- * Used in TX path, for a packet known to be a TCP one.
- *
- * if (skb_is_gso(skb)) {
- * int hlen = skb_tcp_all_headers(skb);
- * ...
- */
- static inline int skb_tcp_all_headers(const struct sk_buff *skb)
- {
- return skb_transport_offset(skb) + tcp_hdrlen(skb);
- }
- /**
- * skb_inner_tcp_all_headers - Returns size of all headers for an encap TCP packet
- * @skb: buffer
- *
- * Used in TX path, for a packet known to be a TCP one.
- *
- * if (skb_is_gso(skb) && skb->encapsulation) {
- * int hlen = skb_inner_tcp_all_headers(skb);
- * ...
- */
- static inline int skb_inner_tcp_all_headers(const struct sk_buff *skb)
- {
- return skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb);
- }
- static inline unsigned int tcp_optlen(const struct sk_buff *skb)
- {
- return (tcp_hdr(skb)->doff - 5) * 4;
- }
- /* TCP Fast Open */
- #define TCP_FASTOPEN_COOKIE_MIN 4 /* Min Fast Open Cookie size in bytes */
- #define TCP_FASTOPEN_COOKIE_MAX 16 /* Max Fast Open Cookie size in bytes */
- #define TCP_FASTOPEN_COOKIE_SIZE 8 /* the size employed by this impl. */
- /* TCP Fast Open Cookie as stored in memory */
- struct tcp_fastopen_cookie {
- __le64 val[DIV_ROUND_UP(TCP_FASTOPEN_COOKIE_MAX, sizeof(u64))];
- s8 len;
- bool exp; /* In RFC6994 experimental option format */
- };
- /* This defines a selective acknowledgement block. */
- struct tcp_sack_block_wire {
- __be32 start_seq;
- __be32 end_seq;
- };
- struct tcp_sack_block {
- u32 start_seq;
- u32 end_seq;
- };
- /*These are used to set the sack_ok field in struct tcp_options_received */
- #define TCP_SACK_SEEN (1 << 0) /*1 = peer is SACK capable, */
- #define TCP_DSACK_SEEN (1 << 2) /*1 = DSACK was received from peer*/
- struct tcp_options_received {
- /* PAWS/RTTM data */
- int ts_recent_stamp;/* Time we stored ts_recent (for aging) */
- u32 ts_recent; /* Time stamp to echo next */
- u32 rcv_tsval; /* Time stamp value */
- u32 rcv_tsecr; /* Time stamp echo reply */
- u16 saw_tstamp : 1, /* Saw TIMESTAMP on last packet */
- tstamp_ok : 1, /* TIMESTAMP seen on SYN packet */
- dsack : 1, /* D-SACK is scheduled */
- wscale_ok : 1, /* Wscale seen on SYN packet */
- sack_ok : 3, /* SACK seen on SYN packet */
- smc_ok : 1, /* SMC seen on SYN packet */
- snd_wscale : 4, /* Window scaling received from sender */
- rcv_wscale : 4; /* Window scaling to send to receiver */
- u8 saw_unknown:1, /* Received unknown option */
- unused:7;
- u8 num_sacks; /* Number of SACK blocks */
- u16 user_mss; /* mss requested by user in ioctl */
- u16 mss_clamp; /* Maximal mss, negotiated at connection setup */
- };
- static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
- {
- rx_opt->tstamp_ok = rx_opt->sack_ok = 0;
- rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
- #if IS_ENABLED(CONFIG_SMC)
- rx_opt->smc_ok = 0;
- #endif
- }
- /* This is the max number of SACKS that we'll generate and process. It's safe
- * to increase this, although since:
- * size = TCPOLEN_SACK_BASE_ALIGNED (4) + n * TCPOLEN_SACK_PERBLOCK (8)
- * only four options will fit in a standard TCP header */
- #define TCP_NUM_SACKS 4
- struct tcp_request_sock_ops;
- struct tcp_request_sock {
- struct inet_request_sock req;
- const struct tcp_request_sock_ops *af_specific;
- u64 snt_synack; /* first SYNACK sent time */
- bool tfo_listener;
- bool is_mptcp;
- #if IS_ENABLED(CONFIG_MPTCP)
- bool drop_req;
- #endif
- u32 txhash;
- u32 rcv_isn;
- u32 snt_isn;
- u32 ts_off;
- u32 last_oow_ack_time; /* last SYNACK */
- u32 rcv_nxt; /* the ack # by SYNACK. For
- * FastOpen it's the seq#
- * after data-in-SYN.
- */
- u8 syn_tos;
- };
- static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
- {
- return (struct tcp_request_sock *)req;
- }
- struct tcp_sock {
- /* inet_connection_sock has to be the first member of tcp_sock */
- struct inet_connection_sock inet_conn;
- u16 tcp_header_len; /* Bytes of tcp header to send */
- u16 gso_segs; /* Max number of segs per GSO packet */
- /*
- * Header prediction flags
- * 0x5?10 << 16 + snd_wnd in net byte order
- */
- __be32 pred_flags;
- /*
- * RFC793 variables by their proper names. This means you can
- * read the code and the spec side by side (and laugh ...)
- * See RFC793 and RFC1122. The RFC writes these in capitals.
- */
- u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived
- * sum(delta(rcv_nxt)), or how many bytes
- * were acked.
- */
- u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn
- * total number of segments in.
- */
- u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn
- * total number of data segments in.
- */
- u32 rcv_nxt; /* What we want to receive next */
- u32 copied_seq; /* Head of yet unread data */
- u32 rcv_wup; /* rcv_nxt on last window update sent */
- u32 snd_nxt; /* Next sequence we send */
- u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut
- * The total number of segments sent.
- */
- u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut
- * total number of data segments sent.
- */
- u64 bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut
- * total number of data bytes sent.
- */
- u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked
- * sum(delta(snd_una)), or how many bytes
- * were acked.
- */
- u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups
- * total number of DSACK blocks received
- */
- u32 snd_una; /* First byte we want an ack for */
- u32 snd_sml; /* Last byte of the most recently transmitted small packet */
- u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */
- u32 lsndtime; /* timestamp of last sent data packet (for restart window) */
- u32 last_oow_ack_time; /* timestamp of last out-of-window ACK */
- u32 compressed_ack_rcv_nxt;
- u32 tsoffset; /* timestamp offset */
- struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
- struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */
- u32 snd_wl1; /* Sequence for window update */
- u32 snd_wnd; /* The window we expect to receive */
- u32 max_window; /* Maximal window ever seen from peer */
- u32 mss_cache; /* Cached effective mss, not including SACKS */
- u32 window_clamp; /* Maximal window to advertise */
- u32 rcv_ssthresh; /* Current window clamp */
- /* Information of the most recently (s)acked skb */
- struct tcp_rack {
- u64 mstamp; /* (Re)sent time of the skb */
- u32 rtt_us; /* Associated RTT */
- u32 end_seq; /* Ending TCP sequence of the skb */
- u32 last_delivered; /* tp->delivered at last reo_wnd adj */
- u8 reo_wnd_steps; /* Allowed reordering window */
- #define TCP_RACK_RECOVERY_THRESH 16
- u8 reo_wnd_persist:5, /* No. of recovery since last adj */
- dsack_seen:1, /* Whether DSACK seen after last adj */
- advanced:1; /* mstamp advanced since last lost marking */
- } rack;
- u16 advmss; /* Advertised MSS */
- u8 compressed_ack;
- u8 dup_ack_counter:2,
- tlp_retrans:1, /* TLP is a retransmission */
- unused:5;
- u32 chrono_start; /* Start time in jiffies of a TCP chrono */
- u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */
- u8 chrono_type:2, /* current chronograph type */
- rate_app_limited:1, /* rate_{delivered,interval_us} limited? */
- fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
- fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */
- is_sack_reneg:1, /* in recovery from loss with SACK reneg? */
- fastopen_client_fail:2; /* reason why fastopen failed */
- u8 nonagle : 4,/* Disable Nagle algorithm? */
- thin_lto : 1,/* Use linear timeouts for thin streams */
- recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */
- repair : 1,
- frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */
- u8 repair_queue;
- u8 save_syn:2, /* Save headers of SYN packet */
- syn_data:1, /* SYN includes data */
- syn_fastopen:1, /* SYN includes Fast Open option */
- syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
- syn_fastopen_ch:1, /* Active TFO re-enabling probe */
- syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
- is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
- u32 tlp_high_seq; /* snd_nxt at the time of TLP */
- u32 tcp_tx_delay; /* delay (in usec) added to TX packets */
- u64 tcp_wstamp_ns; /* departure time for next sent data packet */
- u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */
- /* RTT measurement */
- u64 tcp_mstamp; /* most recent packet received/sent */
- u32 srtt_us; /* smoothed round trip time << 3 in usecs */
- u32 mdev_us; /* medium deviation */
- u32 mdev_max_us; /* maximal mdev for the last rtt period */
- u32 rttvar_us; /* smoothed mdev_max */
- u32 rtt_seq; /* sequence number to update rttvar */
- struct minmax rtt_min;
- u32 packets_out; /* Packets which are "in flight" */
- u32 retrans_out; /* Retransmitted packets out */
- u32 max_packets_out; /* max packets_out in last window */
- u32 cwnd_usage_seq; /* right edge of cwnd usage tracking flight */
- u16 urg_data; /* Saved octet of OOB data and control flags */
- u8 ecn_flags; /* ECN status bits. */
- u8 keepalive_probes; /* num of allowed keep alive probes */
- u32 reordering; /* Packet reordering metric. */
- u32 reord_seen; /* number of data packet reordering events */
- u32 snd_up; /* Urgent pointer */
- /*
- * Options received (usually on last packet, some only on SYN packets).
- */
- struct tcp_options_received rx_opt;
- /*
- * Slow start and congestion control (see also Nagle, and Karn & Partridge)
- */
- u32 snd_ssthresh; /* Slow start size threshold */
- u32 snd_cwnd; /* Sending congestion window */
- u32 snd_cwnd_cnt; /* Linear increase counter */
- u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */
- u32 snd_cwnd_used;
- u32 snd_cwnd_stamp;
- u32 prior_cwnd; /* cwnd right before starting loss recovery */
- u32 prr_delivered; /* Number of newly delivered packets to
- * receiver in Recovery. */
- u32 prr_out; /* Total number of pkts sent during Recovery. */
- u32 delivered; /* Total data packets delivered incl. rexmits */
- u32 delivered_ce; /* Like the above but only ECE marked packets */
- u32 lost; /* Total data packets lost incl. rexmits */
- u32 app_limited; /* limited until "delivered" reaches this val */
- u64 first_tx_mstamp; /* start of window send phase */
- u64 delivered_mstamp; /* time we reached "delivered" */
- u32 rate_delivered; /* saved rate sample: packets delivered */
- u32 rate_interval_us; /* saved rate sample: time elapsed */
- u32 rcv_wnd; /* Current receiver window */
- u32 write_seq; /* Tail(+1) of data held in tcp send buffer */
- u32 notsent_lowat; /* TCP_NOTSENT_LOWAT */
- u32 pushed_seq; /* Last pushed seq, required to talk to windows */
- u32 lost_out; /* Lost packets */
- u32 sacked_out; /* SACK'd packets */
- struct hrtimer pacing_timer;
- struct hrtimer compressed_ack_timer;
- /* from STCP, retrans queue hinting */
- struct sk_buff* lost_skb_hint;
- struct sk_buff *retransmit_skb_hint;
- /* OOO segments go in this rbtree. Socket lock must be held. */
- struct rb_root out_of_order_queue;
- struct sk_buff *ooo_last_skb; /* cache rb_last(out_of_order_queue) */
- /* SACKs data, these 2 need to be together (see tcp_options_write) */
- struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */
- struct tcp_sack_block selective_acks[4]; /* The SACKS themselves*/
- struct tcp_sack_block recv_sack_cache[4];
- struct sk_buff *highest_sack; /* skb just after the highest
- * skb with SACKed bit set
- * (validity guaranteed only if
- * sacked_out > 0)
- */
- int lost_cnt_hint;
- u32 prior_ssthresh; /* ssthresh saved at recovery start */
- u32 high_seq; /* snd_nxt at onset of congestion */
- u32 retrans_stamp; /* Timestamp of the last retransmit,
- * also used in SYN-SENT to remember stamp of
- * the first SYN. */
- u32 undo_marker; /* snd_una upon a new recovery episode. */
- int undo_retrans; /* number of undoable retransmissions. */
- u64 bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans
- * Total data bytes retransmitted
- */
- u32 total_retrans; /* Total retransmits for entire connection */
- u32 urg_seq; /* Seq of received urgent pointer */
- unsigned int keepalive_time; /* time before keep alive takes place */
- unsigned int keepalive_intvl; /* time interval between keep alive probes */
- int linger2;
- /* Sock_ops bpf program related variables */
- #ifdef CONFIG_BPF
- u8 bpf_sock_ops_cb_flags; /* Control calling BPF programs
- * values defined in uapi/linux/tcp.h
- */
- u8 bpf_chg_cc_inprogress:1; /* In the middle of
- * bpf_setsockopt(TCP_CONGESTION),
- * it is to avoid the bpf_tcp_cc->init()
- * to recur itself by calling
- * bpf_setsockopt(TCP_CONGESTION, "itself").
- */
- #define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) (TP->bpf_sock_ops_cb_flags & ARG)
- #else
- #define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0
- #endif
- u16 timeout_rehash; /* Timeout-triggered rehash attempts */
- u32 rcv_ooopack; /* Received out-of-order packets, for tcpinfo */
- /* Receiver side RTT estimation */
- u32 rcv_rtt_last_tsecr;
- struct {
- u32 rtt_us;
- u32 seq;
- u64 time;
- } rcv_rtt_est;
- /* Receiver queue space */
- struct {
- u32 space;
- u32 seq;
- u64 time;
- } rcvq_space;
- /* TCP-specific MTU probe information. */
- struct {
- u32 probe_seq_start;
- u32 probe_seq_end;
- } mtu_probe;
- u32 mtu_info; /* We received an ICMP_FRAG_NEEDED / ICMPV6_PKT_TOOBIG
- * while socket was owned by user.
- */
- #if IS_ENABLED(CONFIG_MPTCP)
- bool is_mptcp;
- #endif
- #if IS_ENABLED(CONFIG_SMC)
- bool (*smc_hs_congested)(const struct sock *sk);
- bool syn_smc; /* SYN includes SMC */
- #endif
- #ifdef CONFIG_TCP_MD5SIG
- /* TCP AF-Specific parts; only used by MD5 Signature support so far */
- const struct tcp_sock_af_ops *af_specific;
- /* TCP MD5 Signature Option information */
- struct tcp_md5sig_info __rcu *md5sig_info;
- #endif
- /* TCP fastopen related information */
- struct tcp_fastopen_request *fastopen_req;
- /* fastopen_rsk points to request_sock that resulted in this big
- * socket. Used to retransmit SYNACKs etc.
- */
- struct request_sock __rcu *fastopen_rsk;
- struct saved_syn *saved_syn;
- ANDROID_KABI_RESERVE(1);
- };
- enum tsq_enum {
- TSQ_THROTTLED,
- TSQ_QUEUED,
- TCP_TSQ_DEFERRED, /* tcp_tasklet_func() found socket was owned */
- TCP_WRITE_TIMER_DEFERRED, /* tcp_write_timer() found socket was owned */
- TCP_DELACK_TIMER_DEFERRED, /* tcp_delack_timer() found socket was owned */
- TCP_MTU_REDUCED_DEFERRED, /* tcp_v{4|6}_err() could not call
- * tcp_v{4|6}_mtu_reduced()
- */
- };
- enum tsq_flags {
- TSQF_THROTTLED = (1UL << TSQ_THROTTLED),
- TSQF_QUEUED = (1UL << TSQ_QUEUED),
- TCPF_TSQ_DEFERRED = (1UL << TCP_TSQ_DEFERRED),
- TCPF_WRITE_TIMER_DEFERRED = (1UL << TCP_WRITE_TIMER_DEFERRED),
- TCPF_DELACK_TIMER_DEFERRED = (1UL << TCP_DELACK_TIMER_DEFERRED),
- TCPF_MTU_REDUCED_DEFERRED = (1UL << TCP_MTU_REDUCED_DEFERRED),
- };
- static inline struct tcp_sock *tcp_sk(const struct sock *sk)
- {
- return (struct tcp_sock *)sk;
- }
- struct tcp_timewait_sock {
- struct inet_timewait_sock tw_sk;
- #define tw_rcv_nxt tw_sk.__tw_common.skc_tw_rcv_nxt
- #define tw_snd_nxt tw_sk.__tw_common.skc_tw_snd_nxt
- u32 tw_rcv_wnd;
- u32 tw_ts_offset;
- u32 tw_ts_recent;
- /* The time we sent the last out-of-window ACK: */
- u32 tw_last_oow_ack_time;
- int tw_ts_recent_stamp;
- u32 tw_tx_delay;
- #ifdef CONFIG_TCP_MD5SIG
- struct tcp_md5sig_key *tw_md5_key;
- #endif
- };
- static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)
- {
- return (struct tcp_timewait_sock *)sk;
- }
- static inline bool tcp_passive_fastopen(const struct sock *sk)
- {
- return sk->sk_state == TCP_SYN_RECV &&
- rcu_access_pointer(tcp_sk(sk)->fastopen_rsk) != NULL;
- }
- static inline void fastopen_queue_tune(struct sock *sk, int backlog)
- {
- struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
- int somaxconn = READ_ONCE(sock_net(sk)->core.sysctl_somaxconn);
- WRITE_ONCE(queue->fastopenq.max_qlen, min_t(unsigned int, backlog, somaxconn));
- }
- static inline void tcp_move_syn(struct tcp_sock *tp,
- struct request_sock *req)
- {
- tp->saved_syn = req->saved_syn;
- req->saved_syn = NULL;
- }
- static inline void tcp_saved_syn_free(struct tcp_sock *tp)
- {
- kfree(tp->saved_syn);
- tp->saved_syn = NULL;
- }
- static inline u32 tcp_saved_syn_len(const struct saved_syn *saved_syn)
- {
- return saved_syn->mac_hdrlen + saved_syn->network_hdrlen +
- saved_syn->tcp_hdrlen;
- }
- struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk,
- const struct sk_buff *orig_skb,
- const struct sk_buff *ack_skb);
- static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss)
- {
- /* We use READ_ONCE() here because socket might not be locked.
- * This happens for listeners.
- */
- u16 user_mss = READ_ONCE(tp->rx_opt.user_mss);
- return (user_mss && user_mss < mss) ? user_mss : mss;
- }
- int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,
- int shiftlen);
- void __tcp_sock_set_cork(struct sock *sk, bool on);
- void tcp_sock_set_cork(struct sock *sk, bool on);
- int tcp_sock_set_keepcnt(struct sock *sk, int val);
- int tcp_sock_set_keepidle_locked(struct sock *sk, int val);
- int tcp_sock_set_keepidle(struct sock *sk, int val);
- int tcp_sock_set_keepintvl(struct sock *sk, int val);
- void __tcp_sock_set_nodelay(struct sock *sk, bool on);
- void tcp_sock_set_nodelay(struct sock *sk);
- void tcp_sock_set_quickack(struct sock *sk, int val);
- int tcp_sock_set_syncnt(struct sock *sk, int val);
- void tcp_sock_set_user_timeout(struct sock *sk, u32 val);
- #endif /* _LINUX_TCP_H */
|