[TCP]: MTU probing

Implementation of packetization layer path mtu discovery for TCP, based on
the internet-draft currently found at
<http://www.ietf.org/internet-drafts/draft-ietf-pmtud-method-05.txt>.

Signed-off-by: John Heffner <jheffner@psc.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/sysctl.h

@@ -397,6 +397,8 @@ enum
 	NET_TCP_CONG_CONTROL=110,
 	NET_TCP_ABC=111,
 	NET_IPV4_IPFRAG_MAX_DIST=112,
+ 	NET_TCP_MTU_PROBING=113,
+	NET_TCP_BASE_MSS=114,
 };
 
 enum {

include/net/inet_connection_sock.h

@@ -72,6 +72,7 @@ struct inet_connection_sock_af_ops {
  * @icsk_probes_out:	   unanswered 0 window probes
  * @icsk_ext_hdr_len:	   Network protocol overhead (IP/IPv6 options)
  * @icsk_ack:		   Delayed ACK control data
+ * @icsk_mtup;		   MTU probing control data
  */
 struct inet_connection_sock {
 	/* inet_sock has to be the first member! */
@@ -104,6 +105,18 @@ struct inet_connection_sock {
 		__u16		  last_seg_size; /* Size of last incoming segment	   */
 		__u16		  rcv_mss;	 /* MSS used for delayed ACK decisions	   */ 
 	} icsk_ack;
+	struct {
+		int		  enabled;
+
+		/* Range of MTUs to search */
+		int		  search_high;
+		int		  search_low;
+
+		/* Information on the current probe. */
+		int		  probe_size;
+		__u32		  probe_seq_start;
+		__u32		  probe_seq_end;
+	} icsk_mtup;
 	u32			  icsk_ca_priv[16];
 #define ICSK_CA_PRIV_SIZE	(16 * sizeof(u32))
 };

include/net/tcp.h

@@ -60,6 +60,9 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 /* Minimal RCV_MSS. */
 #define TCP_MIN_RCVMSS		536U
 
+/* The least MTU to use for probing */
+#define TCP_BASE_MSS		512
+
 /* After receiving this amount of duplicate ACKs fast retransmit starts. */
 #define TCP_FASTRETRANS_THRESH 3
 
@@ -219,6 +222,8 @@ extern int sysctl_tcp_nometrics_save;
 extern int sysctl_tcp_moderate_rcvbuf;
 extern int sysctl_tcp_tso_win_divisor;
 extern int sysctl_tcp_abc;
+extern int sysctl_tcp_mtu_probing;
+extern int sysctl_tcp_base_mss;
 
 extern atomic_t tcp_memory_allocated;
 extern atomic_t tcp_sockets_allocated;
@@ -447,6 +452,10 @@ extern int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 
 extern void tcp_initialize_rcv_mss(struct sock *sk);
 
+extern int tcp_mtu_to_mss(struct sock *sk, int pmtu);
+extern int tcp_mss_to_mtu(struct sock *sk, int mss);
+extern void tcp_mtup_init(struct sock *sk);
+
 static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
 {
 	tp->pred_flags = htonl((tp->tcp_header_len << 26) |

net/ipv4/sysctl_net_ipv4.c

@@ -664,6 +664,22 @@ ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name	= NET_TCP_MTU_PROBING,
+		.procname	= "tcp_mtu_probing",
+		.data		= &sysctl_tcp_mtu_probing,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= NET_TCP_BASE_MSS,
+		.procname	= "tcp_base_mss",
+		.data		= &sysctl_tcp_base_mss,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 
 	{ .ctl_name = 0 }
 };

net/ipv4/tcp_input.c

@@ -1891,6 +1891,34 @@ static void tcp_try_to_open(struct sock *sk, struct tcp_sock *tp, int flag)
 	}
 }
 
+static void tcp_mtup_probe_failed(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	icsk->icsk_mtup.search_high = icsk->icsk_mtup.probe_size - 1;
+	icsk->icsk_mtup.probe_size = 0;
+}
+
+static void tcp_mtup_probe_success(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	/* FIXME: breaks with very large cwnd */
+	tp->prior_ssthresh = tcp_current_ssthresh(sk);
+	tp->snd_cwnd = tp->snd_cwnd *
+		       tcp_mss_to_mtu(sk, tp->mss_cache) /
+		       icsk->icsk_mtup.probe_size;
+	tp->snd_cwnd_cnt = 0;
+	tp->snd_cwnd_stamp = tcp_time_stamp;
+	tp->rcv_ssthresh = tcp_current_ssthresh(sk);
+
+	icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size;
+	icsk->icsk_mtup.probe_size = 0;
+	tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
+}
+
+
 /* Process an event, which can update packets-in-flight not trivially.
  * Main goal of this function is to calculate new estimate for left_out,
  * taking into account both packets sitting in receiver's buffer and
@@ -2023,6 +2051,17 @@ tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
 			return;
 		}
 
+		/* MTU probe failure: don't reduce cwnd */
+		if (icsk->icsk_ca_state < TCP_CA_CWR &&
+		    icsk->icsk_mtup.probe_size &&
+		    tp->snd_una == icsk->icsk_mtup.probe_seq_start) {
+			tcp_mtup_probe_failed(sk);
+			/* Restores the reduction we did in tcp_mtup_probe() */
+			tp->snd_cwnd++;
+			tcp_simple_retransmit(sk);
+			return;
+		}
+
 		/* Otherwise enter Recovery state */
 
 		if (IsReno(tp))
@@ -2243,6 +2282,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p)
 			tp->retrans_stamp = 0;
 		}
 
+		/* MTU probing checks */
+		if (icsk->icsk_mtup.probe_size) {
+			if (!after(icsk->icsk_mtup.probe_seq_end, TCP_SKB_CB(skb)->end_seq)) {
+				tcp_mtup_probe_success(sk, skb);
+			}
+		}
+
 		if (sacked) {
 			if (sacked & TCPCB_RETRANS) {
 				if(sacked & TCPCB_SACKED_RETRANS)
@@ -4101,6 +4147,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		if (tp->rx_opt.sack_ok && sysctl_tcp_fack)
 			tp->rx_opt.sack_ok |= 2;
 
+		tcp_mtup_init(sk);
 		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		tcp_initialize_rcv_mss(sk);
 
@@ -4211,6 +4258,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		if (tp->ecn_flags&TCP_ECN_OK)
 			sock_set_flag(sk, SOCK_NO_LARGESEND);
 
+		tcp_mtup_init(sk);
 		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		tcp_initialize_rcv_mss(sk);
 
@@ -4399,6 +4447,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 				 */
 				tp->lsndtime = tcp_time_stamp;
 
+				tcp_mtup_init(sk);
 				tcp_initialize_rcv_mss(sk);
 				tcp_init_buffer_space(sk);
 				tcp_fast_path_on(tp);

net/ipv4/tcp_ipv4.c

@@ -900,6 +900,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen;
 	newinet->id = newtp->write_seq ^ jiffies;
 
+	tcp_mtup_init(newsk);
 	tcp_sync_mss(newsk, dst_mtu(dst));
 	newtp->advmss = dst_metric(dst, RTAX_ADVMSS);
 	tcp_initialize_rcv_mss(newsk);