tcp_output.c

Linux Kernel 2.6.9 for OMAP1710

/*
 * 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, <[e-mail]>
 *		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>
#include <linux/smp_lock.h>

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

/* 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 = 8;

static __inline__
void update_send_head(struct sock *sk, struct tcp_opt *tp, struct sk_buff *skb)
{
	sk->sk_send_head = skb->next;
	if (sk->sk_send_head == (struct sk_buff *)&sk->sk_write_queue)
		sk->sk_send_head = NULL;
	tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
	tcp_packets_out_inc(sk, tp, 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_opt *tp)
{
	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_opt *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 tcp_opt *tp, struct dst_entry *dst)
{
	s32 delta = tcp_time_stamp - tp->lsndtime;
	u32 restart_cwnd = tcp_init_cwnd(tp, dst);
	u32 cwnd = tp->snd_cwnd;

	if (tcp_is_vegas(tp)) 
		tcp_vegas_enable(tp);

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

	while ((delta -= tp->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 __inline__ void tcp_event_data_sent(struct tcp_opt *tp, struct sk_buff *skb, struct sock *sk)
{
	u32 now = tcp_time_stamp;

	if (!tcp_get_pcount(&tp->packets_out) &&
	    (s32)(now - tp->lsndtime) > tp->rto)
		tcp_cwnd_restart(tp, __sk_dst_get(sk));

	tp->lsndtime = now;

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

static __inline__ void tcp_event_ack_sent(struct sock *sk)
{
	struct tcp_opt *tp = tcp_sk(sk);

	tcp_dec_quickack_mode(tp);
	tcp_clear_xmit_timer(sk, TCP_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. We try to be nice.
	 * If we are not window scaling, then this truncates
	 * our initial window offering to 32k. There should also
	 * be a sysctl option to stop being nice.
	 */
	(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
	(*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);
		while (space > 65535 && (*rcv_wscale) < 14) {
			space >>= 1;
			(*rcv_wscale)++;
		}
	}

	/* Set initial window to value enough for senders,
	 * following RFC1414. 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_opt 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 __inline__ u16 tcp_select_window(struct sock *sk)
{
	struct tcp_opt *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->rcv_wscale)
		new_win = min(new_win, MAX_TCP_WINDOW);
	else
		new_win = min(new_win, (65535U << tp->rcv_wscale));

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

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

	return new_win;
}


/* 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)
{
	if (skb != NULL) {
		struct inet_opt *inet = inet_sk(sk);
		struct tcp_opt *tp = tcp_sk(sk);
		struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
		int tcp_header_size = tp->tcp_header_len;
		struct tcphdr *th;
		int sysctl_flags;
		int err;

		BUG_ON(!tcp_skb_pcount(skb));

#define SYSCTL_FLAG_TSTAMPS	0x1
#define SYSCTL_FLAG_WSCALE	0x2
#define SYSCTL_FLAG_SACK	0x4

		sysctl_flags = 0;
		if (tcb->flags & TCPCB_FLAG_SYN) {
			tcp_header_size = sizeof(struct tcphdr) + TCPOLEN_MSS;
			if(sysctl_tcp_timestamps) {
				tcp_header_size += TCPOLEN_TSTAMP_ALIGNED;
				sysctl_flags |= SYSCTL_FLAG_TSTAMPS;
			}
			if(sysctl_tcp_window_scaling) {
				tcp_header_size += TCPOLEN_WSCALE_ALIGNED;
				sysctl_flags |= SYSCTL_FLAG_WSCALE;
			}
			if(sysctl_tcp_sack) {
				sysctl_flags |= SYSCTL_FLAG_SACK;
				if(!(sysctl_flags & SYSCTL_FLAG_TSTAMPS))
					tcp_header_size += TCPOLEN_SACKPERM_ALIGNED;
			}
		} else if (tp->eff_sacks) {
			/* A SACK is 2 pad bytes, a 2 byte header, plus
			 * 2 32-bit sequence numbers for each SACK block.
			 */
			tcp_header_size += (TCPOLEN_SACK_BASE_ALIGNED +
					    (tp->eff_sacks * TCPOLEN_SACK_PERBLOCK));
		}
		
		/*
		 * If the connection is idle and we are restarting,
		 * then we don't want to do any Vegas calculations
		 * until we get fresh RTT samples.  So when we
		 * restart, we reset our Vegas state to a clean
		 * slate. After we get acks for this flight of
		 * packets, _then_ we can make Vegas calculations
		 * again.
		 */
		if (tcp_is_vegas(tp) && tcp_packets_in_flight(tp) == 0)
			tcp_vegas_enable(tp);

		th = (struct tcphdr *) skb_push(skb, tcp_header_size);
		skb->h.th = th;
		skb_set_owner_w(skb, sk);

		/* Build TCP header and checksum it. */
		th->source		= inet->sport;
		th->dest		= inet->dport;
		th->seq			= htonl(tcb->seq);
		th->ack_seq		= htonl(tp->rcv_nxt);
		*(((__u16 *)th) + 6)	= htons(((tcp_header_size >> 2) << 12) | tcb->flags);
		if (tcb->flags & TCPCB_FLAG_SYN) {
			/* RFC1323: The window in SYN & SYN/ACK segments
			 * is never scaled.
			 */
			th->window	= htons(tp->rcv_wnd);
		} else {
			th->window	= htons(tcp_select_window(sk));
		}
		th->check		= 0;
		th->urg_ptr		= 0;

		if (tp->urg_mode &&
		    between(tp->snd_up, tcb->seq+1, tcb->seq+0xFFFF)) {
			th->urg_ptr		= htons(tp->snd_up-tcb->seq);
			th->urg			= 1;
		}

		if (tcb->flags & TCPCB_FLAG_SYN) {
			tcp_syn_build_options((__u32 *)(th + 1),
					      tcp_advertise_mss(sk),
					      (sysctl_flags & SYSCTL_FLAG_TSTAMPS),
					      (sysctl_flags & SYSCTL_FLAG_SACK),
					      (sysctl_flags & SYSCTL_FLAG_WSCALE),
					      tp->rcv_wscale,
					      tcb->when,
		      			      tp->ts_recent);
		} else {
			tcp_build_and_update_options((__u32 *)(th + 1),
						     tp, tcb->when);

			TCP_ECN_send(sk, tp, skb, tcp_header_size);
		}
		tp->af_specific->send_check(sk, th, skb->len, skb);

		if (tcb->flags & TCPCB_FLAG_ACK)
			tcp_event_ack_sent(sk);

		if (skb->len != tcp_header_size)
			tcp_event_data_sent(tp, skb, sk);

		TCP_INC_STATS(TCP_MIB_OUTSEGS);

		err = tp->af_specific->queue_xmit(skb, 0);
		if (err <= 0)
			return err;

		tcp_enter_cwr(tp);

		/* NET_XMIT_CN is special. It does not guarantee,
		 * that this packet is lost. It tells that device
		 * is about to start to drop packets or already
		 * drops some packets of the same priority and
		 * invokes us to send less aggressively.
		 */
		return err == NET_XMIT_CN ? 0 : err;
	}
	return -ENOBUFS;
#undef SYSCTL_FLAG_TSTAMPS
#undef SYSCTL_FLAG_WSCALE
#undef SYSCTL_FLAG_SACK
}


/* This routine just queue's the buffer 
 *
 * 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)
{
	struct tcp_opt *tp = tcp_sk(sk);

	/* Advance write_seq and place onto the write_queue. */
	tp->write_seq = TCP_SKB_CB(skb)->end_seq;
	__skb_queue_tail(&sk->sk_write_queue, skb);
	sk_charge_skb(sk, skb);

	/* Queue it, remembering where we must start sending. */
	if (sk->sk_send_head == NULL)
		sk->sk_send_head = skb;
}

/* 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 cur_mss)
{
	struct tcp_opt *tp = tcp_sk(sk);
	struct sk_buff *skb = sk->sk_send_head;

	if (tcp_snd_test(tp, skb, cur_mss, TCP_NAGLE_PUSH)) {
		/* Send it out now. */
		TCP_SKB_CB(skb)->when = tcp_time_stamp;
		if (!tcp_transmit_skb(sk, skb_clone(skb, sk->sk_allocation))) {
			sk->sk_send_head = NULL;
			tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
			tcp_packets_out_inc(sk, tp, skb);
			return;
		}
	}
}

void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_std)
{