: Fix Ack Vector MPS Minimum Value

@@ -21,6 +21,9 @@
 /* We can spread an ack vector across multiple options */
 #define DCCP_MAX_ACKVEC_LEN (DCCP_SINGLE_OPT_MAXLEN * 2)
 
+/* Estimated minimum average Ack Vector length - used for updating MPS */
+#define DCCPAV_MIN_OPTLEN	16
+
 #define DCCP_ACKVEC_STATE_RECEIVED	0
 #define DCCP_ACKVEC_STATE_ECN_MARKED	(1 << 6)
 #define DCCP_ACKVEC_STATE_NOT_RECEIVED	(3 << 6)

@@ -153,21 +153,27 @@ unsigned int dccp_sync_mss(struct sock *
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct dccp_sock *dp = dccp_sk(sk);
 	u32 ccmps = dccp_determine_ccmps(dp);
-	int cur_mps = ccmps ? min(pmtu, ccmps) : pmtu;
+	u32 cur_mps = ccmps ? min(pmtu, ccmps) : pmtu;
 
 	/* Account for header lengths and IPv4/v6 option overhead */
 	cur_mps -= (icsk->icsk_af_ops->net_header_len + icsk->icsk_ext_hdr_len +
 		    sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext));
 
 	/*
-	 * FIXME: this should come from the CCID infrastructure, where, say,
-	 * TFRC will say it wants TIMESTAMPS, ELAPSED time, etc, for now lets
-	 * put a rough estimate for NDP + TIMESTAMP + TIMESTAMP_ECHO + ELAPSED
-	 * TIME + TFRC_OPT_LOSS_EVENT_RATE + TFRC_OPT_RECEIVE_RATE + padding to
-	 * make it a multiple of 4
+	 * Leave enough headroom for common DCCP header options.
+	 * This only considers options which may appear on DCCP-Data packets, as
+	 * per table 3 in RFC 4340, 5.8. When running out of space for other
+	 * options (eg. Ack Vector which can take up to 255 bytes), it is better
+	 * to schedule a separate Ack. Thus we leave headroom for the following:
+	 *  - 1 byte for Slow Receiver (11.6)
+	 *  - 6 bytes for Timestamp (13.1)
+	 *  - 10 bytes for Timestamp Echo (13.3)
+	 *  - 8 bytes for NDP count (7.7, when activated)
+	 *  - 6 bytes for Data Checksum (9.3)
+	 *  - %DCCPAV_MIN_OPTLEN bytes for Ack Vector size (11.4, when enabled)
 	 */
-
-	cur_mps -= ((5 + 6 + 10 + 6 + 6 + 6 + 3) / 4) * 4;
+	cur_mps -= roundup(1 + 6 + 10 + dp->dccps_send_ndp_count * 8 + 6 +
+			   (dp->dccps_hc_rx_ackvec ? DCCPAV_MIN_OPTLEN : 0), 4);
 
 	/* And store cached results */
 	icsk->icsk_pmtu_cookie = pmtu;

@@ -475,6 +475,7 @@ struct dccp_ackvec;
  * @dccps_hc_rx_insert_options - receiver wants to add options when acking
  * @dccps_hc_tx_insert_options - sender wants to add options when sending
  * @dccps_server_timewait - server holds timewait state on close (RFC 4340, 8.3)
+ * @dccps_sync_scheduled - flag which signals "send out-of-band message soon"
  * @dccps_xmit_timer - timer for when CCID is not ready to send
  * @dccps_syn_rtt - RTT sample from Request/Response exchange (in usecs)
  */

@@ -515,6 +516,7 @@ struct dccp_sock {
 	__u8				dccps_hc_rx_insert_options:1;
 	__u8				dccps_hc_tx_insert_options:1;
 	__u8				dccps_server_timewait:1;
+	__u8				dccps_sync_scheduled:1;
 	struct timer_list		dccps_xmit_timer;
 };
 

@@ -428,6 +428,7 @@ int dccp_insert_option_ackvec(struct soc
 {
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec;
+	struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
 	const u16 buflen = dccp_ackvec_buflen(av);
 	/* Figure out how many options do we need to represent the ackvec */
 	const u16 nr_opts = DIV_ROUND_UP(buflen, DCCP_SINGLE_OPT_MAXLEN);

@@ -436,10 +437,25 @@ int dccp_insert_option_ackvec(struct soc
 	const unsigned char *tail, *from;
 	unsigned char *to;
 
-	if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN)
+	if (dcb->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) {
+		DCCP_WARN("Lacking space for %u bytes on %s packet\n", len,
+			  dccp_packet_name(dcb->dccpd_type));
 		return -1;
-
-	DCCP_SKB_CB(skb)->dccpd_opt_len += len;
+	}
+	/*
+	 * Since Ack Vectors are variable-length, we can not always predict
+	 * their size. To catch exception cases where the space is running out
+	 * on the skb, a separate Sync is scheduled to carry the Ack Vector.
+	 */
+	if (len > DCCPAV_MIN_OPTLEN &&
+	    len + dcb->dccpd_opt_len + skb->len > dp->dccps_mss_cache) {
+		DCCP_WARN("No space left for Ack Vector (%u) on skb (%u+%u), "
+			  "MPS=%u => reduce payload size?\n", len, skb->len,
+			  dcb->dccpd_opt_len, dp->dccps_mss_cache);
+		dp->dccps_sync_scheduled = 1;
+		return 0;
+	}
+	dcb->dccpd_opt_len += len;
 
 	to   = skb_push(skb, len);
 	len  = buflen;

@@ -480,7 +496,7 @@ int dccp_insert_option_ackvec(struct soc
 	/*
 	 * Each sent Ack Vector is recorded in the list, as per A.2 of RFC 4340.
 	 */
-	if (dccp_ackvec_update_records(av, DCCP_SKB_CB(skb)->dccpd_seq, nonce))
+	if (dccp_ackvec_update_records(av, dcb->dccpd_seq, nonce))
 		return -ENOBUFS;
 	return 0;
 }

@@ -292,6 +292,8 @@ void dccp_write_xmit(struct sock *sk, in
 			if (err)
 				DCCP_BUG("err=%d after ccid_hc_tx_packet_sent",
 					 err);
+			if (dp->dccps_sync_scheduled)
+				dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC);
 		} else {
 			dccp_pr_debug("packet discarded due to err=%d\n", err);
 			kfree_skb(skb);

@@ -564,6 +566,12 @@ void dccp_send_sync(struct sock *sk, con
 	DCCP_SKB_CB(skb)->dccpd_type = pkt_type;
 	DCCP_SKB_CB(skb)->dccpd_ack_seq = ackno;
 
+	/*
+	 * Clear the flag in case the Sync was scheduled for out-of-band data,
+	 * such as carrying a long Ack Vector.
+	 */
+	dccp_sk(sk)->dccps_sync_scheduled = 0;
+
 	dccp_transmit_skb(sk, skb);
 }