tcp_output.c

		return;

	if (after(tcp_highest_sack_seq(tp), TCP_SKB_CB(skb)->seq))
		tp->fackets_out -= decr;
}

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

	tp->packets_out -= decr;

	if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
		tp->sacked_out -= decr;
	if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
		tp->retrans_out -= decr;
	if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST)
		tp->lost_out -= decr;

	/* Reno case is special. Sigh... */
	if (tcp_is_reno(tp) && decr > 0)
		tp->sacked_out -= min_t(u32, tp->sacked_out, decr);

	tcp_adjust_fackets_out(sk, skb, decr);

	if (tp->lost_skb_hint &&
	    before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) &&
	    (tcp_is_fack(tp) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)))
		tp->lost_cnt_hint -= decr;

	tcp_verify_left_out(tp);
}

/* 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, struct sk_buff *skb, u32 len,
		 unsigned int mss_now)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *buff;
	int nsize, old_factor;
	int nlen;
	u8 flags;

	if (WARN_ON(len > skb->len))
		return -EINVAL;

	nsize = skb_headlen(skb) - len;
	if (nsize < 0)
		nsize = 0;

	if (skb_cloned(skb) &&
	    skb_is_nonlinear(skb) &&
	    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
		return -ENOMEM;

	/* Get a new skb... force flag on. */
	buff = sk_stream_alloc_skb(sk, nsize, GFP_ATOMIC);
	if (buff == NULL)
		return -ENOMEM; /* We'll just try again later. */

	sk->sk_wmem_queued += buff->truesize;
	sk_mem_charge(sk, buff->truesize);
	nlen = skb->len - len - nsize;
	buff->truesize += nlen;
	skb->truesize -= nlen;

	/* Correct the sequence numbers. */
	TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len;
	TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq;
	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq;

	/* PSH and FIN should only be set in the second packet. */
	flags = TCP_SKB_CB(skb)->tcp_flags;
	TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH);
	TCP_SKB_CB(buff)->tcp_flags = flags;
	TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked;

	if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) {
		/* Copy and checksum data tail into the new buffer. */
		buff->csum = csum_partial_copy_nocheck(skb->data + len,
						       skb_put(buff, nsize),
						       nsize, 0);

		skb_trim(skb, len);

		skb->csum = csum_block_sub(skb->csum, buff->csum, len);
	} else {
		skb->ip_summed = CHECKSUM_PARTIAL;
		skb_split(skb, buff, len);
	}

	buff->ip_summed = skb->ip_summed;

	/* Looks stupid, but our code really uses when of
	 * skbs, which it never sent before. --ANK
	 */
	TCP_SKB_CB(buff)->when = TCP_SKB_CB(skb)->when;
	buff->tstamp = skb->tstamp;

	old_factor = tcp_skb_pcount(skb);

	/* Fix up tso_factor for both original and new SKB.  */
	tcp_set_skb_tso_segs(sk, skb, mss_now);
	tcp_set_skb_tso_segs(sk, buff, mss_now);

	/* If this packet has been sent out already, we must
	 * adjust the various packet counters.
	 */
	if (!before(tp->snd_nxt, TCP_SKB_CB(buff)->end_seq)) {
		int diff = old_factor - tcp_skb_pcount(skb) -
			tcp_skb_pcount(buff);

		if (diff)
			tcp_adjust_pcount(sk, skb, diff);
	}

	/* Link BUFF into the send queue. */
	skb_header_release(buff);
	tcp_insert_write_queue_after(skb, buff, sk);

	return 0;
}

/* This is similar to __pskb_pull_head() (it will go to core/skbuff.c
 * eventually). The difference is that pulled data not copied, but
 * immediately discarded.
 */
static void __pskb_trim_head(struct sk_buff *skb, int len)
{
	int i, k, eat;

	eat = min_t(int, len, skb_headlen(skb));
	if (eat) {
		__skb_pull(skb, eat);
		len -= eat;
		if (!len)
			return;
	}
	eat = len;
	k = 0;
	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		int size = skb_frag_size(&skb_shinfo(skb)->frags[i]);

		if (size <= eat) {
			skb_frag_unref(skb, i);
			eat -= size;
		} else {
			skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i];
			if (eat) {
				skb_shinfo(skb)->frags[k].page_offset += eat;
				skb_frag_size_sub(&skb_shinfo(skb)->frags[k], eat);
				eat = 0;
			}
			k++;
		}
	}
	skb_shinfo(skb)->nr_frags = k;

	skb_reset_tail_pointer(skb);
	skb->data_len -= len;
	skb->len = skb->data_len;
}

/* Remove acked data from a packet in the transmit queue. */
int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
{
	if (skb_unclone(skb, GFP_ATOMIC))
		return -ENOMEM;

	__pskb_trim_head(skb, len);

	TCP_SKB_CB(skb)->seq += len;
	skb->ip_summed = CHECKSUM_PARTIAL;

	skb->truesize	     -= len;
	sk->sk_wmem_queued   -= len;
	sk_mem_uncharge(sk, len);
	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);

	/* Any change of skb->len requires recalculation of tso factor. */
	if (tcp_skb_pcount(skb) > 1)
		tcp_set_skb_tso_segs(sk, skb, tcp_skb_mss(skb));

	return 0;
}

/* Calculate MSS not accounting any TCP options.  */
static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);
	int mss_now;

	/* Calculate base mss without TCP options:
	   It is MMS_S - sizeof(tcphdr) of rfc1122
	 */
	mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr);

	/* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */
	if (icsk->icsk_af_ops->net_frag_header_len) {
		const struct dst_entry *dst = __sk_dst_get(sk);

		if (dst && dst_allfrag(dst))
			mss_now -= icsk->icsk_af_ops->net_frag_header_len;
	}

	/* Clamp it (mss_clamp does not include tcp options) */
	if (mss_now > tp->rx_opt.mss_clamp)
		mss_now = tp->rx_opt.mss_clamp;

	/* Now subtract optional transport overhead */
	mss_now -= icsk->icsk_ext_hdr_len;

	/* Then reserve room for full set of TCP options and 8 bytes of data */
	if (mss_now < 48)
		mss_now = 48;
	return mss_now;
}

/* Calculate MSS. Not accounting for SACKs here.  */
int tcp_mtu_to_mss(struct sock *sk, int pmtu)
{
	/* Subtract TCP options size, not including SACKs */
	return __tcp_mtu_to_mss(sk, pmtu) -
	       (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr));
}

/* Inverse of above */
int tcp_mss_to_mtu(struct sock *sk, int mss)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);
	int mtu;

	mtu = mss +
	      tp->tcp_header_len +
	      icsk->icsk_ext_hdr_len +
	      icsk->icsk_af_ops->net_header_len;

	/* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */
	if (icsk->icsk_af_ops->net_frag_header_len) {
		const struct dst_entry *dst = __sk_dst_get(sk);

		if (dst && dst_allfrag(dst))
			mtu += icsk->icsk_af_ops->net_frag_header_len;
	}
	return mtu;
}

/* MTU probing init per socket */
void tcp_mtup_init(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);

	icsk->icsk_mtup.enabled = sysctl_tcp_mtu_probing > 1;
	icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) +
			       icsk->icsk_af_ops->net_header_len;
	icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, sysctl_tcp_base_mss);
	icsk->icsk_mtup.probe_size = 0;
}
EXPORT_SYMBOL(tcp_mtup_init);

/* 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)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	int mss_now;

	if (icsk->icsk_mtup.search_high > pmtu)
		icsk->icsk_mtup.search_high = pmtu;

	mss_now = tcp_mtu_to_mss(sk, pmtu);
	mss_now = tcp_bound_to_half_wnd(tp, mss_now);

	/* And store cached results */
	icsk->icsk_pmtu_cookie = pmtu;
	if (icsk->icsk_mtup.enabled)
		mss_now = min(mss_now, tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low));
	tp->mss_cache = mss_now;

	return mss_now;
}
EXPORT_SYMBOL(tcp_sync_mss);

/* 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)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	const struct dst_entry *dst = __sk_dst_get(sk);
	u32 mss_now;
	unsigned int header_len;
	struct tcp_out_options opts;
	struct tcp_md5sig_key *md5;

	mss_now = tp->mss_cache;

	if (dst) {
		u32 mtu = dst_mtu(dst);
		if (mtu != inet_csk(sk)->icsk_pmtu_cookie)
			mss_now = tcp_sync_mss(sk, mtu);
	}

	header_len = tcp_established_options(sk, NULL, &opts, &md5) +
		     sizeof(struct tcphdr);
	/* The mss_cache is sized based on tp->tcp_header_len, which assumes
	 * some common options. If this is an odd packet (because we have SACK
	 * blocks etc) then our calculated header_len will be different, and
	 * we have to adjust mss_now correspondingly */
	if (header_len != tp->tcp_header_len) {
		int delta = (int) header_len - tp->tcp_header_len;
		mss_now -= delta;
	}

	return mss_now;
}

/* Congestion window validation. (RFC2861) */
static void tcp_cwnd_validate(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tp->packets_out >= tp->snd_cwnd) {
		/* Network is feed fully. */
		tp->snd_cwnd_used = 0;
		tp->snd_cwnd_stamp = tcp_time_stamp;
	} else {
		/* Network starves. */
		if (tp->packets_out > tp->snd_cwnd_used)
			tp->snd_cwnd_used = tp->packets_out;

		if (sysctl_tcp_slow_start_after_idle &&
		    (s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto)
			tcp_cwnd_application_limited(sk);
	}
}

/* Returns the portion of skb which can be sent right away without
 * introducing MSS oddities to segment boundaries. In rare cases where
 * mss_now != mss_cache, we will request caller to create a small skb
 * per input skb which could be mostly avoided here (if desired).
 *
 * We explicitly want to create a request for splitting write queue tail
 * to a small skb for Nagle purposes while avoiding unnecessary modulos,
 * thus all the complexity (cwnd_len is always MSS multiple which we
 * return whenever allowed by the other factors). Basically we need the
 * modulo only when the receiver window alone is the limiting factor or
 * when we would be allowed to send the split-due-to-Nagle skb fully.
 */
static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb,
					unsigned int mss_now, unsigned int max_segs)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	u32 needed, window, max_len;

	window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
	max_len = mss_now * max_segs;

	if (likely(max_len <= window && skb != tcp_write_queue_tail(sk)))
		return max_len;

	needed = min(skb->len, window);

	if (max_len <= needed)
		return max_len;

	return needed - needed % mss_now;
}

/* 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 inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp,
					 const struct sk_buff *skb)
{
	u32 in_flight, cwnd;

	/* Don't be strict about the congestion window for the final FIN.  */
	if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) &&
	    tcp_skb_pcount(skb) == 1)
		return 1;

	in_flight = tcp_packets_in_flight(tp);
	cwnd = tp->snd_cwnd;
	if (in_flight < cwnd)
		return (cwnd - in_flight);

	return 0;
}

/* 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(const struct sock *sk, struct sk_buff *skb,
			     unsigned int mss_now)
{
	int tso_segs = tcp_skb_pcount(skb);

	if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) {
		tcp_set_skb_tso_segs(sk, skb, mss_now);
		tso_segs = tcp_skb_pcount(skb);
	}
	return tso_segs;
}

/* Minshall's variant of the Nagle send check. */
static inline bool tcp_minshall_check(const struct tcp_sock *tp)
{
	return after(tp->snd_sml, tp->snd_una) &&
		!after(tp->snd_sml, tp->snd_nxt);
}

/* Return false, if packet can be sent now without violation Nagle's rules:
 * 1. It is full sized.
 * 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 inline bool tcp_nagle_check(const struct tcp_sock *tp,
				  const struct sk_buff *skb,
				  unsigned int mss_now, int nonagle)
{
	return skb->len < mss_now &&
		((nonagle & TCP_NAGLE_CORK) ||
		 (!nonagle && tp->packets_out && tcp_minshall_check(tp)));
}

/* 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)
{
	/* Nagle rule does not apply to frames, which sit in the middle of the
	 * write_queue (they have no chances to get new data).
	 *
	 * This is implemented in the callers, where they modify the 'nonagle'
	 * argument based upon the location of SKB in the send queue.
	 */
	if (nonagle & TCP_NAGLE_PUSH)
		return true;

	/* Don't use the nagle rule for urgent data (or for the final FIN). */
	if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
		return true;

	if (!tcp_nagle_check(tp, skb, cur_mss, nonagle))
		return true;

	return false;
}

/* 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)
{
	u32 end_seq = TCP_SKB_CB(skb)->end_seq;

	if (skb->len > cur_mss)
		end_seq = TCP_SKB_CB(skb)->seq + cur_mss;

	return !after(end_seq, tcp_wnd_end(tp));
}

/* This checks if the data bearing packet SKB (usually tcp_send_head(sk))
 * should be put on the wire right now.  If so, it returns the number of
 * packets allowed by the congestion window.
 */
static unsigned int tcp_snd_test(const struct sock *sk, struct sk_buff *skb,
				 unsigned int cur_mss, int nonagle)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	unsigned int cwnd_quota;

	tcp_init_tso_segs(sk, skb, cur_mss);

	if (!tcp_nagle_test(tp, skb, cur_mss, nonagle))
		return 0;

	cwnd_quota = tcp_cwnd_test(tp, skb);
	if (cwnd_quota && !tcp_snd_wnd_test(tp, skb, cur_mss))
		cwnd_quota = 0;

	return cwnd_quota;
}

/* Test if sending is allowed right now. */
bool tcp_may_send_now(struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb = tcp_send_head(sk);

	return skb &&
		tcp_snd_test(sk, skb, tcp_current_mss(sk),
			     (tcp_skb_is_last(sk, skb) ?
			      tp->nonagle : TCP_NAGLE_PUSH));
}

/* 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)
{
	struct sk_buff *buff;
	int nlen = skb->len - len;
	u8 flags;

	/* All of a TSO frame must be composed of paged data.  */
	if (skb->len != skb->data_len)
		return tcp_fragment(sk, skb, len, mss_now);

	buff = sk_stream_alloc_skb(sk, 0, gfp);
	if (unlikely(buff == NULL))
		return -ENOMEM;

	sk->sk_wmem_queued += buff->truesize;
	sk_mem_charge(sk, buff->truesize);
	buff->truesize += nlen;
	skb->truesize -= nlen;

	/* Correct the sequence numbers. */
	TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len;
	TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq;
	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq;

	/* PSH and FIN should only be set in the second packet. */
	flags = TCP_SKB_CB(skb)->tcp_flags;
	TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH);
	TCP_SKB_CB(buff)->tcp_flags = flags;

	/* This packet was never sent out yet, so no SACK bits. */
	TCP_SKB_CB(buff)->sacked = 0;

	buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL;
	skb_split(skb, buff, len);

	/* Fix up tso_factor for both original and new SKB.  */
	tcp_set_skb_tso_segs(sk, skb, mss_now);
	tcp_set_skb_tso_segs(sk, buff, mss_now);

	/* Link BUFF into the send queue. */
	skb_header_release(buff);
	tcp_insert_write_queue_after(skb, buff, sk);

	return 0;
}

/* 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)
{
	struct tcp_sock *tp = tcp_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);
	u32 send_win, cong_win, limit, in_flight;
	int win_divisor;

	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
		goto send_now;

	if (icsk->icsk_ca_state != TCP_CA_Open)
		goto send_now;

	/* Defer for less than two clock ticks. */
	if (tp->tso_deferred &&
	    (((u32)jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1)
		goto send_now;

	in_flight = tcp_packets_in_flight(tp);

	BUG_ON(tcp_skb_pcount(skb) <= 1 || (tp->snd_cwnd <= in_flight));

	send_win = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;

	/* From in_flight test above, we know that cwnd > in_flight.  */
	cong_win = (tp->snd_cwnd - in_flight) * tp->mss_cache;

	limit = min(send_win, cong_win);

	/* If a full-sized TSO skb can be sent, do it. */
	if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
			   sk->sk_gso_max_segs * tp->mss_cache))
		goto send_now;

	/* Middle in queue won't get any more data, full sendable already? */
	if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len))
		goto send_now;

	win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor);
	if (win_divisor) {
		u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);

		/* If at least some fraction of a window is available,
		 * just use it.
		 */
		chunk /= win_divisor;
		if (limit >= chunk)
			goto send_now;
	} else {
		/* Different approach, try not to defer past a single
		 * ACK.  Receiver should ACK every other full sized
		 * frame, so if we have space for more than 3 frames
		 * then send now.
		 */
		if (limit > tcp_max_tso_deferred_mss(tp) * tp->mss_cache)
			goto send_now;
	}

	/* Ok, it looks like it is advisable to defer.
	 * Do not rearm the timer if already set to not break TCP ACK clocking.
	 */
	if (!tp->tso_deferred)
		tp->tso_deferred = 1 | (jiffies << 1);

	return true;

send_now:
	tp->tso_deferred = 0;
	return false;
}

/* 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)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct sk_buff *skb, *nskb, *next;
	int len;
	int probe_size;
	int size_needed;
	int copy;
	int mss_now;

	/* Not currently probing/verifying,
	 * not in recovery,
	 * have enough cwnd, and
	 * not SACKing (the variable headers throw things off) */
	if (!icsk->icsk_mtup.enabled ||
	    icsk->icsk_mtup.probe_size ||
	    inet_csk(sk)->icsk_ca_state != TCP_CA_Open ||
	    tp->snd_cwnd < 11 ||
	    tp->rx_opt.num_sacks || tp->rx_opt.dsack)
		return -1;

	/* Very simple search strategy: just double the MSS. */
	mss_now = tcp_current_mss(sk);
	probe_size = 2 * tp->mss_cache;
	size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
	if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high)) {
		/* TODO: set timer for probe_converge_event */
		return -1;
	}

	/* Have enough data in the send queue to probe? */
	if (tp->write_seq - tp->snd_nxt < size_needed)
		return -1;

	if (tp->snd_wnd < size_needed)
		return -1;
	if (after(tp->snd_nxt + size_needed, tcp_wnd_end(tp)))
		return 0;

	/* Do we need to wait to drain cwnd? With none in flight, don't stall */
	if (tcp_packets_in_flight(tp) + 2 > tp->snd_cwnd) {
		if (!tcp_packets_in_flight(tp))
			return -1;
		else
			return 0;
	}

	/* We're allowed to probe.  Build it now. */
	if ((nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC)) == NULL)
		return -1;
	sk->sk_wmem_queued += nskb->truesize;
	sk_mem_charge(sk, nskb->truesize);

	skb = tcp_send_head(sk);

	TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
	TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
	TCP_SKB_CB(nskb)->tcp_flags = TCPHDR_ACK;
	TCP_SKB_CB(nskb)->sacked = 0;
	nskb->csum = 0;
	nskb->ip_summed = skb->ip_summed;

	tcp_insert_write_queue_before(nskb, skb, sk);

	len = 0;
	tcp_for_write_queue_from_safe(skb, next, sk) {
		copy = min_t(int, skb->len, probe_size - len);
		if (nskb->ip_summed)
			skb_copy_bits(skb, 0, skb_put(nskb, copy), copy);
		else
			nskb->csum = skb_copy_and_csum_bits(skb, 0,
							    skb_put(nskb, copy),
							    copy, nskb->csum);

		if (skb->len <= copy) {
			/* We've eaten all the data from this skb.
			 * Throw it away. */
			TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
			tcp_unlink_write_queue(skb, sk);
			sk_wmem_free_skb(sk, skb);
		} else {
			TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags &
						   ~(TCPHDR_FIN|TCPHDR_PSH);
			if (!skb_shinfo(skb)->nr_frags) {
				skb_pull(skb, copy);
				if (skb->ip_summed != CHECKSUM_PARTIAL)
					skb->csum = csum_partial(skb->data,
								 skb->len, 0);
			} else {
				__pskb_trim_head(skb, copy);
				tcp_set_skb_tso_segs(sk, skb, mss_now);
			}
			TCP_SKB_CB(skb)->seq += copy;
		}

		len += copy;

		if (len >= probe_size)
			break;
	}
	tcp_init_tso_segs(sk, nskb, nskb->len);

	/* We're ready to send.  If this fails, the probe will
	 * be resegmented into mss-sized pieces by tcp_write_xmit(). */
	TCP_SKB_CB(nskb)->when = tcp_time_stamp;
	if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) {
		/* Decrement cwnd here because we are sending
		 * effectively two packets. */
		tp->snd_cwnd--;
		tcp_event_new_data_sent(sk, nskb);

		icsk->icsk_mtup.probe_size = tcp_mss_to_mtu(sk, nskb->len);
		tp->mtu_probe.probe_seq_start = TCP_SKB_CB(nskb)->seq;
		tp->mtu_probe.probe_seq_end = TCP_SKB_CB(nskb)->end_seq;

		return 1;
	}

	return -1;
}

/* 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)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	unsigned int tso_segs, sent_pkts;
	int cwnd_quota;
	int result;

	sent_pkts = 0;

	if (!push_one) {
		/* Do MTU probing. */
		result = tcp_mtu_probe(sk);
		if (!result) {
			return false;
		} else if (result > 0) {
			sent_pkts = 1;
		}
	}

	while ((skb = tcp_send_head(sk))) {
		unsigned int limit;


		tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
		BUG_ON(!tso_segs);

		if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE)
			goto repair; /* Skip network transmission */

		cwnd_quota = tcp_cwnd_test(tp, skb);
		if (!cwnd_quota) {
			if (push_one == 2)
				/* Force out a loss probe pkt. */
				cwnd_quota = 1;
			else
				break;
		}

		if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now)))
			break;

		if (tso_segs == 1) {
			if (unlikely(!tcp_nagle_test(tp, skb, mss_now,
						     (tcp_skb_is_last(sk, skb) ?
						      nonagle : TCP_NAGLE_PUSH))))
				break;
		} else {
			if (!push_one && tcp_tso_should_defer(sk, skb))
				break;
		}

		/* TSQ : sk_wmem_alloc accounts skb truesize,
		 * including skb overhead. But thats OK.
		 */
		if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) {
			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
			break;
		}
		limit = mss_now;
		if (tso_segs > 1 && !tcp_urg_mode(tp))
			limit = tcp_mss_split_point(sk, skb, mss_now,
						    min_t(unsigned int,
							  cwnd_quota,
							  sk->sk_gso_max_segs));

		if (skb->len > limit &&
		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
			break;

		TCP_SKB_CB(skb)->when = tcp_time_stamp;

		if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
			break;

repair:
		/* Advance the send_head.  This one is sent out.
		 * This call will increment packets_out.
		 */
		tcp_event_new_data_sent(sk, skb);

		tcp_minshall_update(tp, mss_now, skb);
		sent_pkts += tcp_skb_pcount(skb);

		if (push_one)
			break;
	}

	if (likely(sent_pkts)) {
		if (tcp_in_cwnd_reduction(sk))
			tp->prr_out += sent_pkts;

		/* Send one loss probe per tail loss episode. */
		if (push_one != 2)
			tcp_schedule_loss_probe(sk);
		tcp_cwnd_validate(sk);
		return false;
	}
	return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk));
}

bool tcp_schedule_loss_probe(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	u32 timeout, tlp_time_stamp, rto_time_stamp;
	u32 rtt = tp->srtt >> 3;

	if (WARN_ON(icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS))
		return false;
	/* No consecutive loss probes. */
	if (WARN_ON(icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)) {
		tcp_rearm_rto(sk);
		return false;
	}
	/* Don't do any loss probe on a Fast Open connection before 3WHS
	 * finishes.
	 */
	if (sk->sk_state == TCP_SYN_RECV)
		return false;

	/* TLP is only scheduled when next timer event is RTO. */
	if (icsk->icsk_pending != ICSK_TIME_RETRANS)
		return false;

	/* Schedule a loss probe in 2*RTT for SACK capable connections
	 * in Open state, that are either limited by cwnd or application.
	 */
	if (sysctl_tcp_early_retrans < 3 || !rtt || !tp->packets_out ||
	    !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
		return false;

	if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) &&
	     tcp_send_head(sk))
		return false;

	/* Probe timeout is at least 1.5*rtt + TCP_DELACK_MAX to account
	 * for delayed ack when there's one outstanding packet.
	 */
	timeout = rtt << 1;
	if (tp->packets_out == 1)
		timeout = max_t(u32, timeout,
				(rtt + (rtt >> 1) + TCP_DELACK_MAX));
	timeout = max_t(u32, timeout, msecs_to_jiffies(10));

	/* If RTO is shorter, just schedule TLP in its place. */
	tlp_time_stamp = tcp_time_stamp + timeout;
	rto_time_stamp = (u32)inet_csk(sk)->icsk_timeout;
	if ((s32)(tlp_time_stamp - rto_time_stamp) > 0) {
		s32 delta = rto_time_stamp - tcp_time_stamp;
		if (delta > 0)
			timeout = delta;
	}

	inet_csk_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout,
				  TCP_RTO_MAX);
	return true;
}

/* When probe timeout (PTO) fires, send a new segment if one exists, else
 * retransmit the last segment.
 */
void tcp_send_loss_probe(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	int pcount;
	int mss = tcp_current_mss(sk);
	int err = -1;

	if (tcp_send_head(sk) != NULL) {
		err = tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
		goto rearm_timer;
	}

	/* At most one outstanding TLP retransmission. */
	if (tp->tlp_high_seq)
		goto rearm_timer;

	/* Retransmit last segment. */
	skb = tcp_write_queue_tail(sk);
	if (WARN_ON(!skb))
		goto rearm_timer;

	pcount = tcp_skb_pcount(skb);
	if (WARN_ON(!pcount))
		goto rearm_timer;

	if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) {
		if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss)))
			goto rearm_timer;
		skb = tcp_write_queue_tail(sk);