// SPDX-License-Identifier: GPL-2.0-only /* * 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. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <[email protected]> * Mark Evans, <[email protected]> * Corey Minyard <[email protected]> * Florian La Roche, <[email protected]> * Charles Hedrick, <[email protected]> * Linus Torvalds, <[email protected]> * Alan Cox, <[email protected]> * Matthew Dillon, <[email protected]> * Arnt Gulbrandsen, <[email protected]> * Jorge Cwik, <[email protected]> */ /* * Changes: Pedro Roque : Retransmit queue handled by TCP. * : Fragmentation on mtu decrease * : Segment collapse on retransmit * : AF independence * * Linus Torvalds : send_delayed_ack * David S. Miller : Charge memory using the right skb * during syn/ack processing. * David S. Miller : Output engine completely rewritten. * Andrea Arcangeli: SYNACK carry ts_recent in tsecr. * Cacophonix Gaul : draft-minshall-nagle-01 * J Hadi Salim : ECN support * */ #define pr_fmt(fmt) … #include <net/tcp.h> #include <net/mptcp.h> #include <net/proto_memory.h> #include <linux/compiler.h> #include <linux/gfp.h> #include <linux/module.h> #include <linux/static_key.h> #include <linux/skbuff_ref.h> #include <trace/events/tcp.h> /* Refresh clocks of a TCP socket, * ensuring monotically increasing values. */ void tcp_mstamp_refresh(struct tcp_sock *tp) { … } static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); /* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) { … } /* SND.NXT, if window was not shrunk or the amount of shrunk was less than one * window scaling factor due to loss of precision. * If window has been shrunk, what should we make? It is not clear at all. * Using SND.UNA we will fail to open window, SND.NXT is out of window. :-( * Anything in between SND.UNA...SND.UNA+SND.WND also can be already * invalid. OK, let's make this for now: */ static inline __u32 tcp_acceptable_seq(const struct sock *sk) { … } /* Calculate mss to advertise in SYN segment. * RFC1122, RFC1063, draft-ietf-tcpimpl-pmtud-01 state that: * * 1. It is independent of path mtu. * 2. Ideally, it is maximal possible segment size i.e. 65535-40. * 3. For IPv4 it is reasonable to calculate it from maximal MTU of * attached devices, because some buggy hosts are confused by * large MSS. * 4. We do not make 3, we advertise MSS, calculated from first * hop device mtu, but allow to raise it to ip_rt_min_advmss. * This may be overridden via information stored in routing table. * 5. Value 65535 for MSS is valid in IPv6 and means "as large as possible, * probably even Jumbo". */ static __u16 tcp_advertise_mss(struct sock *sk) { … } /* RFC2861. Reset CWND after idle period longer RTO to "restart window". * This is the first part of cwnd validation mechanism. */ void tcp_cwnd_restart(struct sock *sk, s32 delta) { … } /* Congestion state accounting after a packet has been sent. */ static void tcp_event_data_sent(struct tcp_sock *tp, struct sock *sk) { … } /* Account for an ACK we sent. */ static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt) { … } /* Determine a window scaling and initial window to offer. * Based on the assumption that the given amount of space * will be offered. Store the results in the tp structure. * NOTE: for smooth operation initial space offering should * be a multiple of mss if possible. We assume here that mss >= 1. * This MUST be enforced by all callers. */ 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) { … } EXPORT_SYMBOL(…); /* Chose a new window to advertise, update state in tcp_sock for the * socket, and return result with RFC1323 scaling applied. The return * value can be stuffed directly into th->window for an outgoing * frame. */ static u16 tcp_select_window(struct sock *sk) { … } /* Packet ECN state for a SYN-ACK */ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) { … } /* Packet ECN state for a SYN. */ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) { … } static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) { … } static void tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th) { … } /* Set up ECN state for a packet on a ESTABLISHED socket that is about to * be sent. */ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, int tcp_header_len) { … } /* Constructs common control bits of non-data skb. If SYN/FIN is present, * auto increment end seqno. */ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) { … } static inline bool tcp_urg_mode(const struct tcp_sock *tp) { … } #define OPTION_SACK_ADVERTISE … #define OPTION_TS … #define OPTION_MD5 … #define OPTION_WSCALE … #define OPTION_FAST_OPEN_COOKIE … #define OPTION_SMC … #define OPTION_MPTCP … #define OPTION_AO … static void smc_options_write(__be32 *ptr, u16 *options) { … } struct tcp_out_options { … }; static void mptcp_options_write(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, struct tcp_out_options *opts) { … } #ifdef CONFIG_CGROUP_BPF static int bpf_skops_write_hdr_opt_arg0(struct sk_buff *skb, enum tcp_synack_type synack_type) { … } /* req, syn_skb and synack_type are used when writing synack */ static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts, unsigned int *remaining) { … } static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts) { … } #else static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts, unsigned int *remaining) { } static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts) { } #endif static __be32 *process_tcp_ao_options(struct tcp_sock *tp, const struct tcp_request_sock *tcprsk, struct tcp_out_options *opts, struct tcp_key *key, __be32 *ptr) { … } /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of * TCP options, we learned this through the hard way, so be careful here. * Luckily we can at least blame others for their non-compliance but from * inter-operability perspective it seems that we're somewhat stuck with * the ordering which we have been using if we want to keep working with * those broken things (not that it currently hurts anybody as there isn't * particular reason why the ordering would need to be changed). * * At least SACK_PERM as the first option is known to lead to a disaster * (but it may well be that other scenarios fail similarly). */ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, const struct tcp_request_sock *tcprsk, struct tcp_out_options *opts, struct tcp_key *key) { … } static void smc_set_option(const struct tcp_sock *tp, struct tcp_out_options *opts, unsigned int *remaining) { … } static void smc_set_option_cond(const struct tcp_sock *tp, const struct inet_request_sock *ireq, struct tcp_out_options *opts, unsigned int *remaining) { … } static void mptcp_set_option_cond(const struct request_sock *req, struct tcp_out_options *opts, unsigned int *remaining) { … } /* Compute TCP options for SYN packets. This is not the final * network wire format yet. */ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_key *key) { … } /* Set up TCP options for SYN-ACKs. */ static unsigned int tcp_synack_options(const struct sock *sk, struct request_sock *req, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, const struct tcp_key *key, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { … } /* Compute TCP options for ESTABLISHED sockets. This is not the * final wire format yet. */ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_key *key) { … } /* TCP SMALL QUEUES (TSQ) * * TSQ goal is to keep small amount of skbs per tcp flow in tx queues (qdisc+dev) * to reduce RTT and bufferbloat. * We do this using a special skb destructor (tcp_wfree). * * Its important tcp_wfree() can be replaced by sock_wfree() in the event skb * needs to be reallocated in a driver. * The invariant being skb->truesize subtracted from sk->sk_wmem_alloc * * Since transmit from skb destructor is forbidden, we use a tasklet * to process all sockets that eventually need to send more skbs. * We use one tasklet per cpu, with its own queue of sockets. */ struct tsq_tasklet { … }; static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); static void tcp_tsq_write(struct sock *sk) { … } static void tcp_tsq_handler(struct sock *sk) { … } /* * One tasklet per cpu tries to send more skbs. * We run in tasklet context but need to disable irqs when * transferring tsq->head because tcp_wfree() might * interrupt us (non NAPI drivers) */ static void tcp_tasklet_func(struct tasklet_struct *t) { … } #define TCP_DEFERRED_ALL … /** * tcp_release_cb - tcp release_sock() callback * @sk: socket * * called from release_sock() to perform protocol dependent * actions before socket release. */ void tcp_release_cb(struct sock *sk) { … } EXPORT_SYMBOL(…); void __init tcp_tasklet_init(void) { … } /* * Write buffer destructor automatically called from kfree_skb. * We can't xmit new skbs from this context, as we might already * hold qdisc lock. */ void tcp_wfree(struct sk_buff *skb) { … } /* Note: Called under soft irq. * We can call TCP stack right away, unless socket is owned by user. */ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) { … } static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb, u64 prior_wstamp) { … } INDIRECT_CALLABLE_DECLARE(…); INDIRECT_CALLABLE_DECLARE(…); INDIRECT_CALLABLE_DECLARE(…); /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. * All SKB's seen here are completely headerless. It is our * job to build the TCP header, and pass the packet down to * IP so it can do the same plus pass the packet off to the * device. * * We are working here with either a clone of the original * SKB, or a fresh unique copy made by the retransmit engine. */ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, gfp_t gfp_mask, u32 rcv_nxt) { … } static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, gfp_t gfp_mask) { … } /* This routine just queues the buffer for sending. * * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames, * otherwise socket can stall. */ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) { … } /* Initialize TSO segments for a packet. */ static int tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) { … } /* Pcount in the middle of the write queue got changed, we need to do various * tweaks to fix counters */ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int decr) { … } static bool tcp_has_tx_tstamp(const struct sk_buff *skb) { … } static void tcp_fragment_tstamp(struct sk_buff *skb, struct sk_buff *skb2) { … } static void tcp_skb_fragment_eor(struct sk_buff *skb, struct sk_buff *skb2) { … } /* Insert buff after skb on the write or rtx queue of sk. */ static void tcp_insert_write_queue_after(struct sk_buff *skb, struct sk_buff *buff, struct sock *sk, enum tcp_queue tcp_queue) { … } /* Function to create two new TCP segments. Shrinks the given segment * to the specified size and appends a new segment with the rest of the * packet to the list. This won't be called frequently, I hope. * Remember, these are still headerless SKBs at this point. */ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp) { … } /* This is similar to __pskb_pull_tail(). The difference is that pulled * data is not copied, but immediately discarded. */ static int __pskb_trim_head(struct sk_buff *skb, int len) { … } /* Remove acked data from a packet in the transmit queue. */ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) { … } /* Calculate MSS not accounting any TCP options. */ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) { … } /* Calculate MSS. Not accounting for SACKs here. */ int tcp_mtu_to_mss(struct sock *sk, int pmtu) { … } EXPORT_SYMBOL(…); /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) { … } EXPORT_SYMBOL(…); /* MTU probing init per socket */ void tcp_mtup_init(struct sock *sk) { … } EXPORT_SYMBOL(…); /* This function synchronize snd mss to current pmtu/exthdr set. tp->rx_opt.user_mss is mss set by user by TCP_MAXSEG. It does NOT counts for TCP options, but includes only bare TCP header. tp->rx_opt.mss_clamp is mss negotiated at connection setup. It is minimum of user_mss and mss received with SYN. It also does not include TCP options. inet_csk(sk)->icsk_pmtu_cookie is last pmtu, seen by this function. tp->mss_cache is current effective sending mss, including all tcp options except for SACKs. It is evaluated, taking into account current pmtu, but never exceeds tp->rx_opt.mss_clamp. NOTE1. rfc1122 clearly states that advertised MSS DOES NOT include either tcp or ip options. NOTE2. inet_csk(sk)->icsk_pmtu_cookie and tp->mss_cache are READ ONLY outside this function. --ANK (980731) */ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) { … } EXPORT_SYMBOL(…); /* Compute the current effective MSS, taking SACKs and IP options, * and even PMTU discovery events into account. */ unsigned int tcp_current_mss(struct sock *sk) { … } /* RFC2861, slow part. Adjust cwnd, after it was not full during one rto. * As additional protections, we do not touch cwnd in retransmission phases, * and if application hit its sndbuf limit recently. */ static void tcp_cwnd_application_limited(struct sock *sk) { … } static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) { … } /* Minshall's variant of the Nagle send check. */ static bool tcp_minshall_check(const struct tcp_sock *tp) { … } /* Update snd_sml if this skb is under mss * Note that a TSO packet might end with a sub-mss segment * The test is really : * if ((skb->len % mss) != 0) * tp->snd_sml = TCP_SKB_CB(skb)->end_seq; * But we can avoid doing the divide again given we already have * skb_pcount = skb->len / mss_now */ static void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss_now, const struct sk_buff *skb) { … } /* Return false, if packet can be sent now without violation Nagle's rules: * 1. It is full sized. (provided by caller in %partial bool) * 2. Or it contains FIN. (already checked by caller) * 3. Or TCP_CORK is not set, and TCP_NODELAY is set. * 4. Or TCP_CORK is not set, and all sent packets are ACKed. * With Minshall's modification: all sent small packets are ACKed. */ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp, int nonagle) { … } /* Return how many segs we'd like on a TSO packet, * depending on current pacing rate, and how close the peer is. * * Rationale is: * - For close peers, we rather send bigger packets to reduce * cpu costs, because occasional losses will be repaired fast. * - For long distance/rtt flows, we would like to get ACK clocking * with 1 ACK per ms. * * Use min_rtt to help adapt TSO burst size, with smaller min_rtt resulting * in bigger TSO bursts. We we cut the RTT-based allowance in half * for every 2^9 usec (aka 512 us) of RTT, so that the RTT-based allowance * is below 1500 bytes after 6 * ~500 usec = 3ms. */ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, int min_tso_segs) { … } /* Return the number of segments we want in the skb we are transmitting. * See if congestion control module wants to decide; otherwise, autosize. */ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now) { … } /* Returns the portion of skb which can be sent right away */ static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb, unsigned int mss_now, unsigned int max_segs, int nonagle) { … } /* Can at least one segment of SKB be sent right now, according to the * congestion window rules? If so, return how many segments are allowed. */ static u32 tcp_cwnd_test(const struct tcp_sock *tp) { … } /* Initialize TSO state of a skb. * This must be invoked the first time we consider transmitting * SKB onto the wire. */ static int tcp_init_tso_segs(struct sk_buff *skb, unsigned int mss_now) { … } /* Return true if the Nagle test allows this packet to be * sent now. */ static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb, unsigned int cur_mss, int nonagle) { … } /* Does at least the first segment of SKB fit into the send window? */ static bool tcp_snd_wnd_test(const struct tcp_sock *tp, const struct sk_buff *skb, unsigned int cur_mss) { … } /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet * which is put after SKB on the list. It is very much like * tcp_fragment() except that it may make several kinds of assumptions * in order to speed up the splitting operation. In particular, we * know that all the data is in scatter-gather pages, and that the * packet has never been sent out before (and thus is not cloned). */ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, unsigned int mss_now, gfp_t gfp) { … } /* Try to defer sending, if possible, in order to minimize the amount * of TSO splitting we do. View it as a kind of TSO Nagle test. * * This algorithm is from John Heffner. */ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, bool *is_cwnd_limited, bool *is_rwnd_limited, u32 max_segs) { … } static inline void tcp_mtu_check_reprobe(struct sock *sk) { … } static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) { … } static int tcp_clone_payload(struct sock *sk, struct sk_buff *to, int probe_size) { … } /* tcp_mtu_probe() and tcp_grow_skb() can both eat an skb (src) if * all its payload was moved to another one (dst). * Make sure to transfer tcp_flags, eor, and tstamp. */ static void tcp_eat_one_skb(struct sock *sk, struct sk_buff *dst, struct sk_buff *src) { … } /* Create a new MTU probe if we are ready. * MTU probe is regularly attempting to increase the path MTU by * deliberately sending larger packets. This discovers routing * changes resulting in larger path MTUs. * * Returns 0 if we should wait to probe (no cwnd available), * 1 if a probe was sent, * -1 otherwise */ static int tcp_mtu_probe(struct sock *sk) { … } static bool tcp_pacing_check(struct sock *sk) { … } static bool tcp_rtx_queue_empty_or_single_skb(const struct sock *sk) { … } /* TCP Small Queues : * Control number of packets in qdisc/devices to two packets / or ~1 ms. * (These limits are doubled for retransmits) * This allows for : * - better RTT estimation and ACK scheduling * - faster recovery * - high rates * Alas, some drivers / subsystems require a fair amount * of queued bytes to ensure line rate. * One example is wifi aggregation (802.11 AMPDU) */ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, unsigned int factor) { … } static void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new) { … } void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type) { … } void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type) { … } /* First skb in the write queue is smaller than ideal packet size. * Check if we can move payload from the second skb in the queue. */ static void tcp_grow_skb(struct sock *sk, struct sk_buff *skb, int amount) { … } /* This routine writes packets to the network. It advances the * send_head. This happens as incoming acks open up the remote * window for us. * * LARGESEND note: !tcp_urg_mode is overkill, only frames between * snd_up-64k-mss .. snd_up cannot be large. However, taking into * account rare use of URG, this is not a big flaw. * * Send at most one packet when push_one > 0. Temporarily ignore * cwnd limit to force at most one packet out when push_one == 2. * Returns true, if no segments are in flight and we have queued segments, * but cannot send anything now because of SWS or another problem. */ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp) { … } bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) { … } /* Thanks to skb fast clones, we can detect if a prior transmit of * a packet is still in a qdisc or driver queue. * In this case, there is very little point doing a retransmit ! */ static bool skb_still_in_host_queue(struct sock *sk, const struct sk_buff *skb) { … } /* When probe timeout (PTO) fires, try send a new segment if possible, else * retransmit the last segment. */ void tcp_send_loss_probe(struct sock *sk) { … } /* Push out any pending frames which were held back due to * TCP_CORK or attempt at coalescing tiny packets. * The socket must be locked by the caller. */ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle) { … } /* Send _single_ skb sitting at the send head. This function requires * true push pending frames to setup probe timer etc. */ void tcp_push_one(struct sock *sk, unsigned int mss_now) { … } /* This function returns the amount that we can raise the * usable window based on the following constraints * * 1. The window can never be shrunk once it is offered (RFC 793) * 2. We limit memory per socket * * RFC 1122: * "the suggested [SWS] avoidance algorithm for the receiver is to keep * RECV.NEXT + RCV.WIN fixed until: * RCV.BUFF - RCV.USER - RCV.WINDOW >= min(1/2 RCV.BUFF, MSS)" * * i.e. don't raise the right edge of the window until you can raise * it at least MSS bytes. * * Unfortunately, the recommended algorithm breaks header prediction, * since header prediction assumes th->window stays fixed. * * Strictly speaking, keeping th->window fixed violates the receiver * side SWS prevention criteria. The problem is that under this rule * a stream of single byte packets will cause the right side of the * window to always advance by a single byte. * * Of course, if the sender implements sender side SWS prevention * then this will not be a problem. * * BSD seems to make the following compromise: * * If the free space is less than the 1/4 of the maximum * space available and the free space is less than 1/2 mss, * then set the window to 0. * [ Actually, bsd uses MSS and 1/4 of maximal _window_ ] * Otherwise, just prevent the window from shrinking * and from being larger than the largest representable value. * * This prevents incremental opening of the window in the regime * where TCP is limited by the speed of the reader side taking * data out of the TCP receive queue. It does nothing about * those cases where the window is constrained on the sender side * because the pipeline is full. * * BSD also seems to "accidentally" limit itself to windows that are a * multiple of MSS, at least until the free space gets quite small. * This would appear to be a side effect of the mbuf implementation. * Combining these two algorithms results in the observed behavior * of having a fixed window size at almost all times. * * Below we obtain similar behavior by forcing the offered window to * a multiple of the mss when it is feasible to do so. * * Note, we don't "adjust" for TIMESTAMP or SACK option bytes. * Regular options like TIMESTAMP are taken into account. */ u32 __tcp_select_window(struct sock *sk) { … } void tcp_skb_collapse_tstamp(struct sk_buff *skb, const struct sk_buff *next_skb) { … } /* Collapses two adjacent SKB's during retransmission. */ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) { … } /* Check if coalescing SKBs is legal. */ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) { … } /* Collapse packets in the retransmit queue to make to create * less packets on the wire. This is only done on retransmission. */ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, int space) { … } /* This retransmits one SKB. Policy decisions and retransmit queue * state updates are done by the caller. Returns non-zero if an * error occurred which prevented the send. */ 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) { … } /* This gets called after a retransmit timeout, and the initially * retransmitted data is acknowledged. It tries to continue * resending the rest of the retransmit queue, until either * we've sent it all or the congestion window limit is reached. */ void tcp_xmit_retransmit_queue(struct sock *sk) { … } /* We allow to exceed memory limits for FIN packets to expedite * connection tear down and (memory) recovery. * Otherwise tcp_send_fin() could be tempted to either delay FIN * or even be forced to close flow without any FIN. * In general, we want to allow one skb per socket to avoid hangs * with edge trigger epoll() */ void sk_forced_mem_schedule(struct sock *sk, int size) { … } /* Send a FIN. The caller locks the socket for us. * We should try to send a FIN packet really hard, but eventually give up. */ void tcp_send_fin(struct sock *sk) { … } /* We get here when a process closes a file descriptor (either due to * an explicit close() or as a byproduct of exit()'ing) and there * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ void tcp_send_active_reset(struct sock *sk, gfp_t priority, enum sk_rst_reason reason) { … } /* Send a crossed SYN-ACK during socket establishment. * WARNING: This routine must only be called when we have already sent * a SYN packet that crossed the incoming SYN that caused this routine * to get called. If this assumption fails then the initial rcv_wnd * and rcv_wscale values will not be correct. */ int tcp_send_synack(struct sock *sk) { … } /** * tcp_make_synack - Allocate one skb and build a SYNACK packet. * @sk: listener socket * @dst: dst entry attached to the SYNACK. It is consumed and caller * should not use it again. * @req: request_sock pointer * @foc: cookie for tcp fast open * @synack_type: Type of synack to prepare * @syn_skb: SYN packet just received. It could be NULL for rtx case. */ 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) { … } EXPORT_SYMBOL(…); static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) { … } /* Do all connect socket setups that can be done AF independent. */ static void tcp_connect_init(struct sock *sk) { … } static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) { … } /* Build and send a SYN with data and (cached) Fast Open cookie. However, * queue a data-only packet after the regular SYN, such that regular SYNs * are retransmitted on timeouts. Also if the remote SYN-ACK acknowledges * only the SYN sequence, the data are retransmitted in the first ACK. * If cookie is not cached or other error occurs, falls back to send a * regular SYN with Fast Open cookie request option. */ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { … } /* Build a SYN and send it off. */ int tcp_connect(struct sock *sk) { … } EXPORT_SYMBOL(…); u32 tcp_delack_max(const struct sock *sk) { … } /* Send out a delayed ack, the caller does the policy checking * to see if we should even be here. See tcp_input.c:tcp_ack_snd_check() * for details. */ void tcp_send_delayed_ack(struct sock *sk) { … } /* This routine sends an ack and also updates the window. */ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) { … } EXPORT_SYMBOL_GPL(…); void tcp_send_ack(struct sock *sk) { … } /* This routine sends a packet with an out of date sequence * number. It assumes the other end will try to ack it. * * Question: what should we make while urgent mode? * 4.4BSD forces sending single byte of data. We cannot send * out of window data, because we have SND.NXT==SND.MAX... * * Current solution: to send TWO zero-length segments in urgent mode: * one is with SEG.SEQ=SND.UNA to deliver urgent pointer, another is * out-of-date with SND.UNA-1 to probe window. */ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) { … } /* Called from setsockopt( ... TCP_REPAIR ) */ void tcp_send_window_probe(struct sock *sk) { … } /* Initiate keepalive or window probe from timer. */ int tcp_write_wakeup(struct sock *sk, int mib) { … } /* A window probe timeout has occurred. If window is not closed send * a partial packet else a zero probe. */ void tcp_send_probe0(struct sock *sk) { … } int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) { … } EXPORT_SYMBOL(…);
Codebase Browser
linux