+/* Create a new MTU probe if we are ready.
+ * 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;
+ unsigned int pif;
+ 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.eff_sacks)
+ return -1;
+
+ /* Very simple search strategy: just double the MSS. */
+ mss_now = tcp_current_mss(sk, 0);
+ probe_size = 2*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? */
+ len = 0;
+ if ((skb = sk->sk_send_head) == NULL)
+ return -1;
+ while ((len += skb->len) < probe_size && !tcp_skb_is_last(sk, skb))
+ skb = skb->next;
+ if (len < probe_size)
+ return -1;
+
+ /* Receive window check. */
+ if (after(TCP_SKB_CB(skb)->seq + probe_size, tp->snd_una + tp->snd_wnd)) {
+ if (tp->snd_wnd < probe_size)
+ return -1;
+ else
+ return 0;
+ }
+
+ /* Do we need to wait to drain cwnd? */
+ pif = tcp_packets_in_flight(tp);
+ if (pif + 2 > tp->snd_cwnd) {
+ /* With no packets in flight, don't stall. */
+ if (pif == 0)
+ 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_charge_skb(sk, nskb);
+
+ skb = sk->sk_send_head;
+ __skb_insert(nskb, skb->prev, skb, &sk->sk_write_queue);
+ sk->sk_send_head = nskb;
+
+ 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)->flags = TCPCB_FLAG_ACK;
+ TCP_SKB_CB(nskb)->sacked = 0;
+ nskb->csum = 0;
+ if (skb->ip_summed == CHECKSUM_HW)
+ nskb->ip_summed = CHECKSUM_HW;
+
+ len = 0;
+ while (len < probe_size) {
+ next = skb->next;
+
+ 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)->flags |= TCP_SKB_CB(skb)->flags;
+ __skb_unlink(skb, &sk->sk_write_queue);
+ sk_stream_free_skb(sk, skb);
+ } else {
+ TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags &
+ ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
+ if (!skb_shinfo(skb)->nr_frags) {
+ skb_pull(skb, copy);
+ if (skb->ip_summed != CHECKSUM_HW)
+ 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;
+ skb = next;
+ }
+ 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--;
+ update_send_head(sk, tp, 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;
+}
+
+