tcp_output.c

linux 内核源代码

 * 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;
	int tcp_header_size;
#ifdef CONFIG_TCP_MD5SIG
	struct tcp_md5sig_key *md5;
	__u8 *md5_hash_location;
#endif
	struct tcphdr *th;
	int sysctl_flags;
	int err;

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

	/* 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 (likely(clone_it)) {
		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);
	tcp_header_size = tp->tcp_header_len;

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

	sysctl_flags = 0;
	if (unlikely(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 (unlikely(tp->rx_opt.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->rx_opt.eff_sacks *
				     TCPOLEN_SACK_PERBLOCK));
	}

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

#ifdef CONFIG_TCP_MD5SIG
	/*
	 * Are we doing MD5 on this segment? If so - make
	 * room for it.
	 */
	md5 = tp->af_specific->md5_lookup(sk, sk);
	if (md5)
		tcp_header_size += TCPOLEN_MD5SIG_ALIGNED;
#endif

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

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

	if (unlikely(tcb->flags & TCPCB_FLAG_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;

	if (unlikely(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 (unlikely(tcb->flags & TCPCB_FLAG_SYN)) {
		tcp_syn_build_options((__be32 *)(th + 1),
				      tcp_advertise_mss(sk),
				      (sysctl_flags & SYSCTL_FLAG_TSTAMPS),
				      (sysctl_flags & SYSCTL_FLAG_SACK),
				      (sysctl_flags & SYSCTL_FLAG_WSCALE),
				      tp->rx_opt.rcv_wscale,
				      tcb->when,
				      tp->rx_opt.ts_recent,

#ifdef CONFIG_TCP_MD5SIG
				      md5 ? &md5_hash_location :
#endif
				      NULL);
	} else {
		tcp_build_and_update_options((__be32 *)(th + 1),
					     tp, tcb->when,
#ifdef CONFIG_TCP_MD5SIG
					     md5 ? &md5_hash_location :
#endif
					     NULL);
		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) {
		tp->af_specific->calc_md5_hash(md5_hash_location,
					       md5,
					       sk, NULL, NULL,
					       tcp_hdr(skb),
					       sk->sk_protocol,
					       skb->len);
	}
#endif

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

	if (likely(tcb->flags & TCPCB_FLAG_ACK))
		tcp_event_ack_sent(sk, tcp_skb_pcount(skb));

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

	if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
		TCP_INC_STATS(TCP_MIB_OUTSEGS);

	err = icsk->icsk_af_ops->queue_xmit(skb, 0);
	if (likely(err <= 0))
		return err;

	tcp_enter_cwr(sk, 1);

	return net_xmit_eval(err);

#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_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_charge_skb(sk, skb);
}

static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now)
{
	if (skb->len <= mss_now || !sk_can_gso(sk)) {
		/* Avoid the costly divide in the normal
		 * non-TSO case.
		 */
		skb_shinfo(skb)->gso_segs = 1;
		skb_shinfo(skb)->gso_size = 0;
		skb_shinfo(skb)->gso_type = 0;
	} else {
		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss_now);
		skb_shinfo(skb)->gso_size = mss_now;
		skb_shinfo(skb)->gso_type = sk->sk_gso_type;
	}
}

/* When a modification to fackets out becomes necessary, we need to check
 * skb is counted to fackets_out or not. Another important thing is to
 * tweak SACK fastpath hint too as it would overwrite all changes unless
 * hint is also changed.
 */
static void tcp_adjust_fackets_out(struct tcp_sock *tp, struct sk_buff *skb,
				   int decr)
{
	if (!tp->sacked_out || tcp_is_reno(tp))
		return;

	if (!before(tp->highest_sack, TCP_SKB_CB(skb)->seq))
		tp->fackets_out -= decr;

	/* cnt_hint is "off-by-one" compared with fackets_out (see sacktag) */
	if (tp->fastpath_skb_hint != NULL &&
	    after(TCP_SKB_CB(tp->fastpath_skb_hint)->seq, TCP_SKB_CB(skb)->seq))
		tp->fastpath_cnt_hint -= decr;
}

/* 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;
	u16 flags;

	BUG_ON(len > skb->len);

	tcp_clear_retrans_hints_partial(tp);
	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_charge_skb(sk, buff);
	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;

	if (tcp_is_sack(tp) && tp->sacked_out &&
	    (TCP_SKB_CB(skb)->seq == tp->highest_sack))
		tp->highest_sack = TCP_SKB_CB(buff)->seq;

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

	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);

		tp->packets_out -= diff;

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

		if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST)
			tp->lost_out -= diff;

		/* Adjust Reno SACK estimate. */
		if (tcp_is_reno(tp) && diff > 0) {
			tcp_dec_pcount_approx_int(&tp->sacked_out, diff);
			tcp_verify_left_out(tp);
		}
		tcp_adjust_fackets_out(tp, 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 = len;
	k = 0;
	for (i=0; i<skb_shinfo(skb)->nr_frags; i++) {
		if (skb_shinfo(skb)->frags[i].size <= eat) {
			put_page(skb_shinfo(skb)->frags[i].page);
			eat -= skb_shinfo(skb)->frags[i].size;
		} else {
			skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i];
			if (eat) {
				skb_shinfo(skb)->frags[k].page_offset += eat;
				skb_shinfo(skb)->frags[k].size -= eat;
				eat = 0;
			}
			k++;
		}
	}
	skb_shinfo(skb)->nr_frags = k;

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

int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
{
	if (skb_cloned(skb) &&
	    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
		return -ENOMEM;

	/* If len == headlen, we avoid __skb_pull to preserve alignment. */
	if (unlikely(len < skb_headlen(skb)))
		__skb_pull(skb, len);
	else
		__pskb_trim_head(skb, len - skb_headlen(skb));

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

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

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

	return 0;
}

/* Not accounting for SACKs here. */
int tcp_mtu_to_mss(struct sock *sk, int pmtu)
{
	struct tcp_sock *tp = tcp_sk(sk);
	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);

	/* 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;

	/* Now subtract TCP options size, not including SACKs */
	mss_now -= tp->tcp_header_len - sizeof(struct tcphdr);

	return mss_now;
}

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

	return mtu;
}

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;