tcp_output.c

/*
 * 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, <waltje@uWalt.NL.Mugnet.ORG>
 *		Mark Evans, <evansmp@uhura.aston.ac.uk>
 *		Corey Minyard <wf-rch!minyard@relay.EU.net>
 *		Florian La Roche, <flla@stud.uni-sb.de>
 *		Charles Hedrick, <hedrick@klinzhai.rutgers.edu>
 *		Linus Torvalds, <torvalds@cs.helsinki.fi>
 *		Alan Cox, <gw4pts@gw4pts.ampr.org>
 *		Matthew Dillon, <dillon@apollo.west.oic.com>
 *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
 *		Jorge Cwik, <jorge@laser.satlink.net>
 */

/*
 * 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) "TCP: " fmt

#include <net/tcp.h>

#include <linux/compiler.h>
#include <linux/gfp.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;

/* Default TSQ limit of two TSO segments */
int sysctl_tcp_limit_output_bytes __read_mostly = 131072;

/* 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 = TCP_BASE_MSS;

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

unsigned int sysctl_tcp_notsent_lowat __read_mostly = UINT_MAX;
EXPORT_SYMBOL(sysctl_tcp_notsent_lowat);

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, const struct sk_buff *skb)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	unsigned int prior_packets = tp->packets_out;

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

	tp->packets_out += tcp_skb_pcount(skb);
	if (!prior_packets || icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
		tcp_rearm_rto(sk);
	}
}

/* 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(const struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);

	if (!before(tcp_wnd_end(tp), tp->snd_nxt))
		return tp->snd_nxt;
	else
		return tcp_wnd_end(tp);
}

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

	if (dst) {
		unsigned int metric = dst_metric_advmss(dst);

		if (metric < mss) {
			mss = metric;
			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, const 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;
}

/* Congestion state accounting after a packet has been sent. */
static void tcp_event_data_sent(struct tcp_sock *tp,
				struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	const u32 now = tcp_time_stamp;
	const struct dst_entry *dst = __sk_dst_get(sk);

	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 &&
	    (!dst || !dst_metric(dst, RTAX_QUICKACK)))
			icsk->icsk_ack.pingpong = 1;
}

/* Account for an ACK we sent. */
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);
}


u32 tcp_default_init_rwnd(u32 mss)
{
	/* Initial receive window should be twice of TCP_INIT_CWND to
	 * enable proper sending of new unsent data during fast recovery
	 * (RFC 3517, Section 4, NextSeg() rule (2)). Further place a
	 * limit when mss is larger than 1460.
	 */
	u32 init_rwnd = TCP_INIT_CWND * 2;

	if (mss > 1460)
		init_rwnd = max((1460 * init_rwnd) / mss, 2U);
	return init_rwnd;
}

/* 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,
			       __u32 init_rcv_wnd)
{
	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)++;
		}
	}

	if (mss > (1 << *rcv_wscale)) {
		if (!init_rcv_wnd) /* Use default unless specified otherwise */
			init_rcv_wnd = tcp_default_init_rwnd(mss);
		*rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
	}

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

/* 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 = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale);
	}
	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;
}

/* Packet ECN state for a SYN-ACK */
static inline void TCP_ECN_send_synack(const struct tcp_sock *tp, struct sk_buff *skb)
{
	TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR;
	if (!(tp->ecn_flags & TCP_ECN_OK))
		TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE;
}

/* Packet ECN state for a SYN.  */
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 (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1) {
		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
		tp->ecn_flags = TCP_ECN_OK;
	}
}

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

/* Set up ECN state for a packet on a ESTABLISHED socket that is about to
 * be sent.
 */
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;
	}
}

/* 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)
{
	struct skb_shared_info *shinfo = skb_shinfo(skb);

	skb->ip_summed = CHECKSUM_PARTIAL;
	skb->csum = 0;

	TCP_SKB_CB(skb)->tcp_flags = flags;
	TCP_SKB_CB(skb)->sacked = 0;

	shinfo->gso_segs = 1;
	shinfo->gso_size = 0;
	shinfo->gso_type = 0;

	TCP_SKB_CB(skb)->seq = seq;
	if (flags & (TCPHDR_SYN | TCPHDR_FIN))
		seq++;
	TCP_SKB_CB(skb)->end_seq = seq;
}

static inline bool tcp_urg_mode(const struct tcp_sock *tp)
{
	return tp->snd_una != tp->snd_up;
}

#define OPTION_SACK_ADVERTISE	(1 << 0)
#define OPTION_TS		(1 << 1)
#define OPTION_MD5		(1 << 2)
#define OPTION_WSCALE		(1 << 3)
#define OPTION_FAST_OPEN_COOKIE	(1 << 8)

struct tcp_out_options {
	u16 options;		/* bit field of OPTION_* */
	u16 mss;		/* 0 to disable */
	u8 ws;			/* window scale, 0 to disable */
	u8 num_sack_blocks;	/* number of SACK blocks to include */
	u8 hash_size;		/* bytes in hash_location */
	__u8 *hash_location;	/* temporary pointer, overloaded */
	__u32 tsval, tsecr;	/* need to include OPTION_TS */
	struct tcp_fastopen_cookie *fastopen_cookie;	/* Fast open cookie */
};

/* 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-operatibility 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(__be32 *ptr, struct tcp_sock *tp,
			      struct tcp_out_options *opts)
{
	u16 options = opts->options;	/* mungable copy */

	if (unlikely(OPTION_MD5 & options)) {
		*ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
			       (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG);
		/* overload cookie hash location */
		opts->hash_location = (__u8 *)ptr;
		ptr += 4;
	}

	if (unlikely(opts->mss)) {
		*ptr++ = htonl((TCPOPT_MSS << 24) |
			       (TCPOLEN_MSS << 16) |
			       opts->mss);
	}

	if (likely(OPTION_TS & options)) {
		if (unlikely(OPTION_SACK_ADVERTISE & options)) {
			*ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
				       (TCPOLEN_SACK_PERM << 16) |
				       (TCPOPT_TIMESTAMP << 8) |
				       TCPOLEN_TIMESTAMP);
			options &= ~OPTION_SACK_ADVERTISE;
		} else {
			*ptr++ = htonl((TCPOPT_NOP << 24) |
				       (TCPOPT_NOP << 16) |
				       (TCPOPT_TIMESTAMP << 8) |
				       TCPOLEN_TIMESTAMP);
		}
		*ptr++ = htonl(opts->tsval);
		*ptr++ = htonl(opts->tsecr);
	}

	if (unlikely(OPTION_SACK_ADVERTISE & options)) {
		*ptr++ = htonl((TCPOPT_NOP << 24) |
			       (TCPOPT_NOP << 16) |
			       (TCPOPT_SACK_PERM << 8) |
			       TCPOLEN_SACK_PERM);
	}

	if (unlikely(OPTION_WSCALE & options)) {
		*ptr++ = htonl((TCPOPT_NOP << 24) |
			       (TCPOPT_WINDOW << 16) |
			       (TCPOLEN_WINDOW << 8) |
			       opts->ws);
	}

	if (unlikely(opts->num_sack_blocks)) {
		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 + (opts->num_sack_blocks *
						     TCPOLEN_SACK_PERBLOCK)));

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

		tp->rx_opt.dsack = 0;
	}

	if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) {
		struct tcp_fastopen_cookie *foc = opts->fastopen_cookie;

		*ptr++ = htonl((TCPOPT_EXP << 24) |
			       ((TCPOLEN_EXP_FASTOPEN_BASE + foc->len) << 16) |
			       TCPOPT_FASTOPEN_MAGIC);

		memcpy(ptr, foc->val, foc->len);
		if ((foc->len & 3) == 2) {
			u8 *align = ((u8 *)ptr) + foc->len;
			align[0] = align[1] = TCPOPT_NOP;
		}
		ptr += (foc->len + 3) >> 2;
	}
}

/* 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_md5sig_key **md5)
{
	struct tcp_sock *tp = tcp_sk(sk);
	unsigned int remaining = MAX_TCP_OPTION_SPACE;
	struct tcp_fastopen_request *fastopen = tp->fastopen_req;

#ifdef CONFIG_TCP_MD5SIG
	*md5 = tp->af_specific->md5_lookup(sk, sk);
	if (*md5) {
		opts->options |= OPTION_MD5;
		remaining -= TCPOLEN_MD5SIG_ALIGNED;
	}
#else
	*md5 = NULL;
#endif

	/* 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.  */
	opts->mss = tcp_advertise_mss(sk);
	remaining -= TCPOLEN_MSS_ALIGNED;

	if (likely(sysctl_tcp_timestamps && *md5 == NULL)) {
		opts->options |= OPTION_TS;
		opts->tsval = TCP_SKB_CB(skb)->when + tp->tsoffset;
		opts->tsecr = tp->rx_opt.ts_recent;
		remaining -= TCPOLEN_TSTAMP_ALIGNED;
	}
	if (likely(sysctl_tcp_window_scaling)) {
		opts->ws = tp->rx_opt.rcv_wscale;
		opts->options |= OPTION_WSCALE;
		remaining -= TCPOLEN_WSCALE_ALIGNED;
	}
	if (likely(sysctl_tcp_sack)) {
		opts->options |= OPTION_SACK_ADVERTISE;
		if (unlikely(!(OPTION_TS & opts->options)))
			remaining -= TCPOLEN_SACKPERM_ALIGNED;
	}

	if (fastopen && fastopen->cookie.len >= 0) {
		u32 need = TCPOLEN_EXP_FASTOPEN_BASE + fastopen->cookie.len;
		need = (need + 3) & ~3U;  /* Align to 32 bits */
		if (remaining >= need) {
			opts->options |= OPTION_FAST_OPEN_COOKIE;
			opts->fastopen_cookie = &fastopen->cookie;
			remaining -= need;
			tp->syn_fastopen = 1;
		}
	}

	return MAX_TCP_OPTION_SPACE - remaining;
}

/* Set up TCP options for SYN-ACKs. */
static unsigned int tcp_synack_options(struct sock *sk,
				   struct request_sock *req,
				   unsigned int mss, struct sk_buff *skb,
				   struct tcp_out_options *opts,
				   struct tcp_md5sig_key **md5,
				   struct tcp_fastopen_cookie *foc)
{
	struct inet_request_sock *ireq = inet_rsk(req);
	unsigned int remaining = MAX_TCP_OPTION_SPACE;

#ifdef CONFIG_TCP_MD5SIG
	*md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req);
	if (*md5) {
		opts->options |= OPTION_MD5;
		remaining -= TCPOLEN_MD5SIG_ALIGNED;

		/* We can't fit any SACK blocks in a packet with MD5 + TS
		 * options. There was discussion about disabling SACK
		 * rather than TS in order to fit in better with old,
		 * buggy kernels, but that was deemed to be unnecessary.
		 */
		ireq->tstamp_ok &= !ireq->sack_ok;
	}
#else
	*md5 = NULL;
#endif

	/* We always send an MSS option. */
	opts->mss = mss;
	remaining -= TCPOLEN_MSS_ALIGNED;

	if (likely(ireq->wscale_ok)) {
		opts->ws = ireq->rcv_wscale;
		opts->options |= OPTION_WSCALE;
		remaining -= TCPOLEN_WSCALE_ALIGNED;
	}
	if (likely(ireq->tstamp_ok)) {
		opts->options |= OPTION_TS;
		opts->tsval = TCP_SKB_CB(skb)->when;
		opts->tsecr = req->ts_recent;
		remaining -= TCPOLEN_TSTAMP_ALIGNED;
	}
	if (likely(ireq->sack_ok)) {
		opts->options |= OPTION_SACK_ADVERTISE;
		if (unlikely(!ireq->tstamp_ok))
			remaining -= TCPOLEN_SACKPERM_ALIGNED;
	}
	if (foc != NULL) {
		u32 need = TCPOLEN_EXP_FASTOPEN_BASE + foc->len;
		need = (need + 3) & ~3U;  /* Align to 32 bits */
		if (remaining >= need) {
			opts->options |= OPTION_FAST_OPEN_COOKIE;
			opts->fastopen_cookie = foc;
			remaining -= need;
		}
	}

	return MAX_TCP_OPTION_SPACE - remaining;
}

/* 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_md5sig_key **md5)
{
	struct tcp_skb_cb *tcb = skb ? TCP_SKB_CB(skb) : NULL;
	struct tcp_sock *tp = tcp_sk(sk);
	unsigned int size = 0;
	unsigned int eff_sacks;

	opts->options = 0;

#ifdef CONFIG_TCP_MD5SIG
	*md5 = tp->af_specific->md5_lookup(sk, sk);
	if (unlikely(*md5)) {
		opts->options |= OPTION_MD5;
		size += TCPOLEN_MD5SIG_ALIGNED;
	}
#else
	*md5 = NULL;
#endif

	if (likely(tp->rx_opt.tstamp_ok)) {
		opts->options |= OPTION_TS;
		opts->tsval = tcb ? tcb->when + tp->tsoffset : 0;
		opts->tsecr = tp->rx_opt.ts_recent;
		size += TCPOLEN_TSTAMP_ALIGNED;
	}

	eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack;
	if (unlikely(eff_sacks)) {
		const unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
		opts->num_sack_blocks =
			min_t(unsigned int, eff_sacks,
			      (remaining - TCPOLEN_SACK_BASE_ALIGNED) /
			      TCPOLEN_SACK_PERBLOCK);
		size += TCPOLEN_SACK_BASE_ALIGNED +
			opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
	}

	return size;
}


/* 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 substracted 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 {
	struct tasklet_struct	tasklet;
	struct list_head	head; /* queue of tcp sockets */
};
static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet);

static void tcp_tsq_handler(struct sock *sk)
{
	if ((1 << sk->sk_state) &
	    (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING |
	     TCPF_CLOSE_WAIT  | TCPF_LAST_ACK))
		tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC);
}
/*
 * One tasklest per cpu tries to send more skbs.
 * We run in tasklet context but need to disable irqs when
 * transfering tsq->head because tcp_wfree() might
 * interrupt us (non NAPI drivers)
 */
static void tcp_tasklet_func(unsigned long data)
{
	struct tsq_tasklet *tsq = (struct tsq_tasklet *)data;
	LIST_HEAD(list);
	unsigned long flags;
	struct list_head *q, *n;
	struct tcp_sock *tp;
	struct sock *sk;

	local_irq_save(flags);
	list_splice_init(&tsq->head, &list);
	local_irq_restore(flags);

	list_for_each_safe(q, n, &list) {
		tp = list_entry(q, struct tcp_sock, tsq_node);
		list_del(&tp->tsq_node);

		sk = (struct sock *)tp;
		bh_lock_sock(sk);

		if (!sock_owned_by_user(sk)) {
			tcp_tsq_handler(sk);
		} else {
			/* defer the work to tcp_release_cb() */
			set_bit(TCP_TSQ_DEFERRED, &tp->tsq_flags);
		}
		bh_unlock_sock(sk);

		clear_bit(TSQ_QUEUED, &tp->tsq_flags);
		sk_free(sk);
	}
}

#define TCP_DEFERRED_ALL ((1UL << TCP_TSQ_DEFERRED) |		\
			  (1UL << TCP_WRITE_TIMER_DEFERRED) |	\
			  (1UL << TCP_DELACK_TIMER_DEFERRED) |	\
			  (1UL << TCP_MTU_REDUCED_DEFERRED))
/**
 * 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)
{
	struct tcp_sock *tp = tcp_sk(sk);
	unsigned long flags, nflags;

	/* perform an atomic operation only if at least one flag is set */
	do {
		flags = tp->tsq_flags;
		if (!(flags & TCP_DEFERRED_ALL))
			return;
		nflags = flags & ~TCP_DEFERRED_ALL;
	} while (cmpxchg(&tp->tsq_flags, flags, nflags) != flags);

	if (flags & (1UL << TCP_TSQ_DEFERRED))
		tcp_tsq_handler(sk);

	if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) {
		tcp_write_timer_handler(sk);
		__sock_put(sk);
	}
	if (flags & (1UL << TCP_DELACK_TIMER_DEFERRED)) {
		tcp_delack_timer_handler(sk);
		__sock_put(sk);
	}
	if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) {
		sk->sk_prot->mtu_reduced(sk);
		__sock_put(sk);
	}
}
EXPORT_SYMBOL(tcp_release_cb);

void __init tcp_tasklet_init(void)
{
	int i;

	for_each_possible_cpu(i) {
		struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i);

		INIT_LIST_HEAD(&tsq->head);
		tasklet_init(&tsq->tasklet,
			     tcp_tasklet_func,
			     (unsigned long)tsq);
	}
}

/*
 * Write buffer destructor automatically called from kfree_skb.
 * We cant xmit new skbs from this context, as we might already
 * hold qdisc lock.
 */
void tcp_wfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;
	struct tcp_sock *tp = tcp_sk(sk);

	if (test_and_clear_bit(TSQ_THROTTLED, &tp->tsq_flags) &&
	    !test_and_set_bit(TSQ_QUEUED, &tp->tsq_flags)) {
		unsigned long flags;
		struct tsq_tasklet *tsq;

		/* Keep a ref on socket.
		 * This last ref will be released in tcp_tasklet_func()
		 */
		atomic_sub(skb->truesize - 1, &sk->sk_wmem_alloc);

		/* queue this socket to tasklet queue */
		local_irq_save(flags);
		tsq = &__get_cpu_var(tsq_tasklet);
		list_add(&tp->tsq_node, &tsq->head);
		tasklet_schedule(&tsq->tasklet);
		local_irq_restore(flags);
	} else {
		sock_wfree(skb);
	}
}

/* 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)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct inet_sock *inet;
	struct tcp_sock *tp;
	struct tcp_skb_cb *tcb;
	struct tcp_out_options opts;
	unsigned int tcp_options_size, tcp_header_size;
	struct tcp_md5sig_key *md5;
	struct tcphdr *th;
	int err;

	BUG_ON(!skb || !tcp_skb_pcount(skb));

	if (clone_it) {
		const struct sk_buff *fclone = skb + 1;

		/* If congestion control is doing timestamping, we must
		 * take such a timestamp before we potentially clone/copy.
		 */
		if (icsk->icsk_ca_ops->flags & TCP_CONG_RTT_STAMP)
			__net_timestamp(skb);

		if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
			     fclone->fclone == SKB_FCLONE_CLONE))
			NET_INC_STATS_BH(sock_net(sk),
					 LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);

		if (unlikely(skb_cloned(skb)))
			skb = pskb_copy(skb, gfp_mask);
		else
			skb = skb_clone(skb, gfp_mask);
		if (unlikely(!skb))
			return -ENOBUFS;
	}

	inet = inet_sk(sk);
	tp = tcp_sk(sk);
	tcb = TCP_SKB_CB(skb);
	memset(&opts, 0, sizeof(opts));

	if (unlikely(tcb->tcp_flags & TCPHDR_SYN))
		tcp_options_size = tcp_syn_options(sk, skb, &opts, &md5);
	else
		tcp_options_size = tcp_established_options(sk, skb, &opts,
							   &md5);
	tcp_header_size = tcp_options_size + sizeof(struct tcphdr);

	if (tcp_packets_in_flight(tp) == 0)
		tcp_ca_event(sk, CA_EVENT_TX_START);

	/* if no packet is in qdisc/device queue, then allow XPS to select
	 * another queue.
	 */
	skb->ooo_okay = sk_wmem_alloc_get(sk) == 0;

	skb_push(skb, tcp_header_size);
	skb_reset_transport_header(skb);

	skb_orphan(skb);
	skb->sk = sk;
	skb->destructor = tcp_wfree;
	atomic_add(skb->truesize, &sk->sk_wmem_alloc);

	/* Build TCP header and checksum it. */
	th = tcp_hdr(skb);
	th->source		= inet->inet_sport;
	th->dest		= inet->inet_dport;
	th->seq			= htonl(tcb->seq);
	th->ack_seq		= htonl(tp->rcv_nxt);
	*(((__be16 *)th) + 6)	= htons(((tcp_header_size >> 2) << 12) |
					tcb->tcp_flags);

	if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) {
		/* RFC1323: The window in SYN & SYN/ACK segments
		 * is never scaled.
		 */
		th->window	= htons(min(tp->rcv_wnd, 65535U));
	} else {
		th->window	= htons(tcp_select_window(sk));
	}
	th->check		= 0;
	th->urg_ptr		= 0;

	/* The urg_mode check is necessary during a below snd_una win probe */
	if (unlikely(tcp_urg_mode(tp) && before(tcb->seq, tp->snd_up))) {
		if (before(tp->snd_up, tcb->seq + 0x10000)) {
			th->urg_ptr = htons(tp->snd_up - tcb->seq);
			th->urg = 1;
		} else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) {
			th->urg_ptr = htons(0xFFFF);
			th->urg = 1;
		}
	}

	tcp_options_write((__be32 *)(th + 1), tp, &opts);
	if (likely((tcb->tcp_flags & TCPHDR_SYN) == 0))
		TCP_ECN_send(sk, skb, tcp_header_size);

#ifdef CONFIG_TCP_MD5SIG
	/* Calculate the MD5 hash, as we have all we need now */
	if (md5) {
		sk_nocaps_add(sk, NETIF_F_GSO_MASK);
		tp->af_specific->calc_md5_hash(opts.hash_location,
					       md5, sk, NULL, skb);
	}
#endif

	icsk->icsk_af_ops->send_check(sk, skb);

	if (likely(tcb->tcp_flags & TCPHDR_ACK))
		tcp_event_ack_sent(sk, tcp_skb_pcount(skb));

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

	if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
		TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
			      tcp_skb_pcount(skb));

	err = icsk->icsk_af_ops->queue_xmit(skb, &inet->cork.fl);
	if (likely(err <= 0))
		return err;

	tcp_enter_cwr(sk, 1);

	return net_xmit_eval(err);
}

/* 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)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* Advance write_seq and place onto the write_queue. */
	tp->write_seq = TCP_SKB_CB(skb)->end_seq;
	skb_header_release(skb);
	tcp_add_write_queue_tail(sk, skb);
	sk->sk_wmem_queued += skb->truesize;
	sk_mem_charge(sk, skb->truesize);
}

/* Initialize TSO segments for a packet. */
static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
				 unsigned int mss_now)
{
	struct skb_shared_info *shinfo = skb_shinfo(skb);

	/* Make sure we own this skb before messing gso_size/gso_segs */
	WARN_ON_ONCE(skb_cloned(skb));

	if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) {
		/* Avoid the costly divide in the normal
		 * non-TSO case.
		 */
		shinfo->gso_segs = 1;