tcp_output.c

linux 内核源代码

/*
 * 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).
 *
 * Version:	$Id: tcp_output.c,v 1.146 2002/02/01 22:01:04 davem Exp $
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <[e-mail]>
 *		Mark Evans, <[e-mail]>
 *		Corey Minyard <wf-rch![e-mail]>
 *		Florian La Roche, <[e-mail]>
 *		Charles Hedrick, <[e-mail]>
 *		Linus Torvalds, <[e-mail]>
 *		Alan Cox, <[e-mail]>
 *		Matthew Dillon, <[e-mail]>
 *		Arnt Gulbrandsen, <[e-mail]>
 *		Jorge Cwik, <[e-mail]>
 */

/*
 * 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
 *
 */

#include <net/tcp.h>

#include <linux/compiler.h>
#include <linux/module.h>

/* People can turn this off for buggy TCP's found in printers etc. */
int sysctl_tcp_retrans_collapse __read_mostly = 1;

/* People can turn this on to  work with those rare, broken TCPs that
 * interpret the window field as a signed quantity.
 */
int sysctl_tcp_workaround_signed_windows __read_mostly = 0;

/* This limits the percentage of the congestion window which we
 * will allow a single TSO frame to consume.  Building TSO frames
 * which are too large can cause TCP streams to be bursty.
 */
int sysctl_tcp_tso_win_divisor __read_mostly = 3;

int sysctl_tcp_mtu_probing __read_mostly = 0;
int sysctl_tcp_base_mss __read_mostly = 512;

/* By default, RFC2861 behavior.  */
int sysctl_tcp_slow_start_after_idle __read_mostly = 1;

static inline void tcp_packets_out_inc(struct sock *sk,
				       const struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int orig = tp->packets_out;

	tp->packets_out += tcp_skb_pcount(skb);
	if (!orig)
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
					  inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
}

static void update_send_head(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);

	tcp_advance_send_head(sk, skb);
	tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
	tcp_packets_out_inc(sk, skb);
}

/* SND.NXT, if window was not shrunk.
 * 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(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (!before(tp->snd_una+tp->snd_wnd, tp->snd_nxt))
		return tp->snd_nxt;
	else
		return tp->snd_una+tp->snd_wnd;
}

/* 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)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct dst_entry *dst = __sk_dst_get(sk);
	int mss = tp->advmss;

	if (dst && dst_metric(dst, RTAX_ADVMSS) < mss) {
		mss = dst_metric(dst, RTAX_ADVMSS);
		tp->advmss = mss;
	}

	return (__u16)mss;
}

/* RFC2861. Reset CWND after idle period longer RTO to "restart window".
 * This is the first part of cwnd validation mechanism. */
static void tcp_cwnd_restart(struct sock *sk, struct dst_entry *dst)
{
	struct tcp_sock *tp = tcp_sk(sk);
	s32 delta = tcp_time_stamp - tp->lsndtime;
	u32 restart_cwnd = tcp_init_cwnd(tp, dst);
	u32 cwnd = tp->snd_cwnd;

	tcp_ca_event(sk, CA_EVENT_CWND_RESTART);

	tp->snd_ssthresh = tcp_current_ssthresh(sk);
	restart_cwnd = min(restart_cwnd, cwnd);

	while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd)
		cwnd >>= 1;
	tp->snd_cwnd = max(cwnd, restart_cwnd);
	tp->snd_cwnd_stamp = tcp_time_stamp;
	tp->snd_cwnd_used = 0;
}

static void tcp_event_data_sent(struct tcp_sock *tp,
				struct sk_buff *skb, struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	const u32 now = tcp_time_stamp;

	if (sysctl_tcp_slow_start_after_idle &&
	    (!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto))
		tcp_cwnd_restart(sk, __sk_dst_get(sk));

	tp->lsndtime = now;

	/* If it is a reply for ato after last received
	 * packet, enter pingpong mode.
	 */
	if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
		icsk->icsk_ack.pingpong = 1;
}

static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
{
	tcp_dec_quickack_mode(sk, pkts);
	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
}

/* 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(int __space, __u32 mss,
			       __u32 *rcv_wnd, __u32 *window_clamp,
			       int wscale_ok, __u8 *rcv_wscale)
{
	unsigned int space = (__space < 0 ? 0 : __space);

	/* If no clamp set the clamp to the max possible scaled window */
	if (*window_clamp == 0)
		(*window_clamp) = (65535 << 14);
	space = min(*window_clamp, space);

	/* Quantize space offering to a multiple of mss if possible. */
	if (space > mss)
		space = (space / mss) * mss;

	/* NOTE: offering an initial window larger than 32767
	 * will break some buggy TCP stacks. If the admin tells us
	 * it is likely we could be speaking with such a buggy stack
	 * we will truncate our initial window offering to 32K-1
	 * unless the remote has sent us a window scaling option,
	 * which we interpret as a sign the remote TCP is not
	 * misinterpreting the window field as a signed quantity.
	 */
	if (sysctl_tcp_workaround_signed_windows)
		(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
	else
		(*rcv_wnd) = space;

	(*rcv_wscale) = 0;
	if (wscale_ok) {
		/* Set window scaling on max possible window
		 * See RFC1323 for an explanation of the limit to 14
		 */
		space = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max);
		space = min_t(u32, space, *window_clamp);
		while (space > 65535 && (*rcv_wscale) < 14) {
			space >>= 1;
			(*rcv_wscale)++;
		}
	}

	/* Set initial window to value enough for senders,
	 * following RFC2414. Senders, not following this RFC,
	 * will be satisfied with 2.
	 */
	if (mss > (1<<*rcv_wscale)) {
		int init_cwnd = 4;
		if (mss > 1460*3)
			init_cwnd = 2;
		else if (mss > 1460)
			init_cwnd = 3;
		if (*rcv_wnd > init_cwnd*mss)
			*rcv_wnd = init_cwnd*mss;
	}

	/* Set the clamp no higher than max representable value */
	(*window_clamp) = min(65535U << (*rcv_wscale), *window_clamp);
}

/* 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)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 cur_win = tcp_receive_window(tp);
	u32 new_win = __tcp_select_window(sk);

	/* Never shrink the offered window */
	if (new_win < cur_win) {
		/* Danger Will Robinson!
		 * Don't update rcv_wup/rcv_wnd here or else
		 * we will not be able to advertise a zero
		 * window in time.  --DaveM
		 *
		 * Relax Will Robinson.
		 */
		new_win = cur_win;
	}
	tp->rcv_wnd = new_win;
	tp->rcv_wup = tp->rcv_nxt;

	/* Make sure we do not exceed the maximum possible
	 * scaled window.
	 */
	if (!tp->rx_opt.rcv_wscale && sysctl_tcp_workaround_signed_windows)
		new_win = min(new_win, MAX_TCP_WINDOW);
	else
		new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));

	/* RFC1323 scaling applied */
	new_win >>= tp->rx_opt.rcv_wscale;

	/* If we advertise zero window, disable fast path. */
	if (new_win == 0)
		tp->pred_flags = 0;

	return new_win;
}

static inline void TCP_ECN_send_synack(struct tcp_sock *tp,
				       struct sk_buff *skb)
{
	TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_CWR;
	if (!(tp->ecn_flags&TCP_ECN_OK))
		TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_ECE;
}

static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);

	tp->ecn_flags = 0;
	if (sysctl_tcp_ecn) {
		TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_ECE|TCPCB_FLAG_CWR;
		tp->ecn_flags = TCP_ECN_OK;
	}
}

static __inline__ void
TCP_ECN_make_synack(struct request_sock *req, struct tcphdr *th)
{
	if (inet_rsk(req)->ecn_ok)
		th->ece = 1;
}

static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb,
				int tcp_header_len)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tp->ecn_flags & TCP_ECN_OK) {
		/* Not-retransmitted data segment: set ECT and inject CWR. */
		if (skb->len != tcp_header_len &&
		    !before(TCP_SKB_CB(skb)->seq, tp->snd_nxt)) {
			INET_ECN_xmit(sk);
			if (tp->ecn_flags&TCP_ECN_QUEUE_CWR) {
				tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR;
				tcp_hdr(skb)->cwr = 1;
				skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
			}
		} else {
			/* ACK or retransmitted segment: clear ECT|CE */
			INET_ECN_dontxmit(sk);
		}
		if (tp->ecn_flags & TCP_ECN_DEMAND_CWR)
			tcp_hdr(skb)->ece = 1;
	}
}

static void tcp_build_and_update_options(__be32 *ptr, struct tcp_sock *tp,
					 __u32 tstamp, __u8 **md5_hash)
{
	if (tp->rx_opt.tstamp_ok) {
		*ptr++ = htonl((TCPOPT_NOP << 24) |
			       (TCPOPT_NOP << 16) |
			       (TCPOPT_TIMESTAMP << 8) |
			       TCPOLEN_TIMESTAMP);
		*ptr++ = htonl(tstamp);
		*ptr++ = htonl(tp->rx_opt.ts_recent);
	}
	if (tp->rx_opt.eff_sacks) {
		struct tcp_sack_block *sp = tp->rx_opt.dsack ? tp->duplicate_sack : tp->selective_acks;
		int this_sack;

		*ptr++ = htonl((TCPOPT_NOP  << 24) |
			       (TCPOPT_NOP  << 16) |
			       (TCPOPT_SACK <<  8) |
			       (TCPOLEN_SACK_BASE + (tp->rx_opt.eff_sacks *
						     TCPOLEN_SACK_PERBLOCK)));

		for (this_sack = 0; this_sack < tp->rx_opt.eff_sacks; this_sack++) {
			*ptr++ = htonl(sp[this_sack].start_seq);
			*ptr++ = htonl(sp[this_sack].end_seq);
		}

		if (tp->rx_opt.dsack) {
			tp->rx_opt.dsack = 0;
			tp->rx_opt.eff_sacks--;
		}
	}
#ifdef CONFIG_TCP_MD5SIG
	if (md5_hash) {
		*ptr++ = htonl((TCPOPT_NOP << 24) |
			       (TCPOPT_NOP << 16) |
			       (TCPOPT_MD5SIG << 8) |
			       TCPOLEN_MD5SIG);
		*md5_hash = (__u8 *)ptr;
	}
#endif
}

/* Construct a tcp options header for a SYN or SYN_ACK packet.
 * If this is every changed make sure to change the definition of
 * MAX_SYN_SIZE to match the new maximum number of options that you
 * can generate.
 *
 * Note - that with the RFC2385 TCP option, we make room for the
 * 16 byte MD5 hash. This will be filled in later, so the pointer for the
 * location to be filled is passed back up.
 */
static void tcp_syn_build_options(__be32 *ptr, int mss, int ts, int sack,
				  int offer_wscale, int wscale, __u32 tstamp,
				  __u32 ts_recent, __u8 **md5_hash)
{
	/* We always get an MSS option.
	 * The option bytes which will be seen in normal data
	 * packets should timestamps be used, must be in the MSS
	 * advertised.  But we subtract them from tp->mss_cache so
	 * that calculations in tcp_sendmsg are simpler etc.
	 * So account for this fact here if necessary.  If we
	 * don't do this correctly, as a receiver we won't
	 * recognize data packets as being full sized when we
	 * should, and thus we won't abide by the delayed ACK
	 * rules correctly.
	 * SACKs don't matter, we never delay an ACK when we
	 * have any of those going out.
	 */
	*ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss);
	if (ts) {
		if (sack)
			*ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
				       (TCPOLEN_SACK_PERM << 16) |
				       (TCPOPT_TIMESTAMP << 8) |
				       TCPOLEN_TIMESTAMP);
		else
			*ptr++ = htonl((TCPOPT_NOP << 24) |
				       (TCPOPT_NOP << 16) |
				       (TCPOPT_TIMESTAMP << 8) |
				       TCPOLEN_TIMESTAMP);
		*ptr++ = htonl(tstamp);		/* TSVAL */
		*ptr++ = htonl(ts_recent);	/* TSECR */
	} else if (sack)
		*ptr++ = htonl((TCPOPT_NOP << 24) |
			       (TCPOPT_NOP << 16) |
			       (TCPOPT_SACK_PERM << 8) |
			       TCPOLEN_SACK_PERM);
	if (offer_wscale)
		*ptr++ = htonl((TCPOPT_NOP << 24) |
			       (TCPOPT_WINDOW << 16) |
			       (TCPOLEN_WINDOW << 8) |
			       (wscale));
#ifdef CONFIG_TCP_MD5SIG
	/*
	 * If MD5 is enabled, then we set the option, and include the size
	 * (always 18). The actual MD5 hash is added just before the
	 * packet is sent.
	 */
	if (md5_hash) {
		*ptr++ = htonl((TCPOPT_NOP << 24) |
			       (TCPOPT_NOP << 16) |
			       (TCPOPT_MD5SIG << 8) |
			       TCPOLEN_MD5SIG);
		*md5_hash = (__u8 *) ptr;
	}
#endif
}

/* 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.
 *