[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>

3 files changed, 24 insertions, 0 deletions

diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 8ad4beab2888..6e8880ea49e7 100644
--- a/include/linux/sysctl.h
+++ b/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 {
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index fa587c94e9d0..b3abe33f4e5f 100644
--- a/include/net/inet_connection_sock.h
+++ b/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))
 };
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 77f21c65bbca..16879fa560de 100644
--- a/include/net/tcp.h
+++ b/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) |