Merge branch 'dccp' of git://eden-feed.erg.abdn.ac.uk/net-next-2.6

include/linux/dccp.h

@@ -462,6 +462,7 @@ 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_xmitlet - tasklet scheduled by the TX CCID to dequeue data packets
  * @dccps_xmit_timer - used by the TX CCID to delay sending (rate-based pacing)
  * @dccps_syn_rtt - RTT sample from Request/Response exchange (in usecs)
@@ -503,6 +504,7 @@ 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 tasklet_struct		dccps_xmitlet;
 	struct timer_list		dccps_xmit_timer;
 };

net/dccp/ackvec.h

@@ -29,6 +29,9 @@
 /* Estimated minimum average Ack Vector length - used for updating MPS */
 #define DCCPAV_MIN_OPTLEN	16
 
+/* Threshold for coping with large bursts of losses */
+#define DCCPAV_BURST_THRESH	(DCCPAV_MAX_ACKVEC_LEN / 8)
+
 enum dccp_ackvec_states {
 	DCCPAV_RECEIVED =	0x00,
 	DCCPAV_ECN_MARKED =	0x40,
@@ -61,7 +64,6 @@ static inline u8 dccp_ackvec_state(const u8 *cell)
  *		   %DCCP_SINGLE_OPT_MAXLEN cells in the live portion of @av_buf
  * @av_overflow:   if 1 then buf_head == buf_tail indicates buffer wraparound
  * @av_records:	   list of %dccp_ackvec_record (Ack Vectors sent previously)
- * @av_veclen:	   length of the live portion of @av_buf
  */
 struct dccp_ackvec {
 	u8			av_buf[DCCPAV_MAX_ACKVEC_LEN];
@@ -72,7 +74,6 @@ struct dccp_ackvec {
 	bool			av_buf_nonce[DCCPAV_NUM_ACKVECS];
 	u8			av_overflow:1;
 	struct list_head	av_records;
-	u16			av_vec_len;
 };
 
 /** struct dccp_ackvec_record - Records information about sent Ack Vectors
@@ -98,29 +99,38 @@ struct dccp_ackvec_record {
 	u8		 avr_ack_nonce:1;
 };
 
-struct sock;
-struct sk_buff;
-
 extern int dccp_ackvec_init(void);
 extern void dccp_ackvec_exit(void);
 
 extern struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority);
 extern void dccp_ackvec_free(struct dccp_ackvec *av);
 
-extern int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk,
-			   const u64 ackno, const u8 state);
-
-extern void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av,
-					struct sock *sk, const u64 ackno);
-extern int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb,
-			     u64 *ackno, const u8 opt,
-			     const u8 *value, const u8 len);
-
+extern void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb);
 extern int  dccp_ackvec_update_records(struct dccp_ackvec *av, u64 seq, u8 sum);
+extern void dccp_ackvec_clear_state(struct dccp_ackvec *av, const u64 ackno);
 extern u16  dccp_ackvec_buflen(const struct dccp_ackvec *av);
 
 static inline bool dccp_ackvec_is_empty(const struct dccp_ackvec *av)
 {
 	return av->av_overflow == 0 && av->av_buf_head == av->av_buf_tail;
 }
+
+/**
+ * struct dccp_ackvec_parsed  -  Record offsets of Ack Vectors in skb
+ * @vec:	start of vector (offset into skb)
+ * @len:	length of @vec
+ * @nonce:	whether @vec had an ECN nonce of 0 or 1
+ * @node:	FIFO - arranged in descending order of ack_ackno
+ * This structure is used by CCIDs to access Ack Vectors in a received skb.
+ */
+struct dccp_ackvec_parsed {
+	u8		 *vec,
+			 len,
+			 nonce:1;
+	struct list_head node;
+};
+
+extern int dccp_ackvec_parsed_add(struct list_head *head,
+				  u8 *vec, u8 len, u8 nonce);
+extern void dccp_ackvec_parsed_cleanup(struct list_head *parsed_chunks);
 #endif /* _ACKVEC_H */

net/dccp/ccids/ccid2.c

@@ -246,68 +246,6 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len)
 #endif
 }
 
-/* XXX Lame code duplication!
- * returns -1 if none was found.
- * else returns the next offset to use in the function call.
- */
-static int ccid2_ackvector(struct sock *sk, struct sk_buff *skb, int offset,
-			   unsigned char **vec, unsigned char *veclen)
-{
-	const struct dccp_hdr *dh = dccp_hdr(skb);
-	unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb);
-	unsigned char *opt_ptr;
-	const unsigned char *opt_end = (unsigned char *)dh +
-					(dh->dccph_doff * 4);
-	unsigned char opt, len;
-	unsigned char *value;
-
-	BUG_ON(offset < 0);
-	options += offset;
-	opt_ptr = options;
-	if (opt_ptr >= opt_end)
-		return -1;
-
-	while (opt_ptr != opt_end) {
-		opt   = *opt_ptr++;
-		len   = 0;
-		value = NULL;
-
-		/* Check if this isn't a single byte option */
-		if (opt > DCCPO_MAX_RESERVED) {
-			if (opt_ptr == opt_end)
-				goto out_invalid_option;
-
-			len = *opt_ptr++;
-			if (len < 3)
-				goto out_invalid_option;
-			/*
-			 * Remove the type and len fields, leaving
-			 * just the value size
-			 */
-			len     -= 2;
-			value   = opt_ptr;
-			opt_ptr += len;
-
-			if (opt_ptr > opt_end)
-				goto out_invalid_option;
-		}
-
-		switch (opt) {
-		case DCCPO_ACK_VECTOR_0:
-		case DCCPO_ACK_VECTOR_1:
-			*vec	= value;
-			*veclen = len;
-			return offset + (opt_ptr - options);
-		}
-	}
-
-	return -1;
-
-out_invalid_option:
-	DCCP_BUG("Invalid option - this should not happen (previous parsing)!");
-	return -1;
-}
-
 /**
  * ccid2_rtt_estimator - Sample RTT and compute RTO using RFC2988 algorithm
  * This code is almost identical with TCP's tcp_rtt_estimator(), since
@@ -432,16 +370,28 @@ static void ccid2_congestion_event(struct sock *sk, struct ccid2_seq *seqp)
 		ccid2_change_l_ack_ratio(sk, hc->tx_cwnd);
 }
 
+static int ccid2_hc_tx_parse_options(struct sock *sk, u8 packet_type,
+				     u8 option, u8 *optval, u8 optlen)
+{
+	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+
+	switch (option) {
+	case DCCPO_ACK_VECTOR_0:
+	case DCCPO_ACK_VECTOR_1:
+		return dccp_ackvec_parsed_add(&hc->tx_av_chunks, optval, optlen,
+					      option - DCCPO_ACK_VECTOR_0);
+	}
+	return 0;
+}
+
 static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
 	const bool sender_was_blocked = ccid2_cwnd_network_limited(hc);
+	struct dccp_ackvec_parsed *avp;
 	u64 ackno, seqno;
 	struct ccid2_seq *seqp;
-	unsigned char *vector;
-	unsigned char veclen;
-	int offset = 0;
 	int done = 0;
 	unsigned int maxincr = 0;
 
@@ -475,17 +425,12 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 	}
 
 	/* check forward path congestion */
-	/* still didn't send out new data packets */
-	if (hc->tx_seqh == hc->tx_seqt)
+	if (dccp_packet_without_ack(skb))
 		return;
 
-	switch (DCCP_SKB_CB(skb)->dccpd_type) {
-	case DCCP_PKT_ACK:
-	case DCCP_PKT_DATAACK:
-		break;
-	default:
-		return;
-	}
+	/* still didn't send out new data packets */
+	if (hc->tx_seqh == hc->tx_seqt)
+		goto done;
 
 	ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq;
 	if (after48(ackno, hc->tx_high_ack))
@@ -509,15 +454,16 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 		maxincr = DIV_ROUND_UP(dp->dccps_l_ack_ratio, 2);
 
 	/* go through all ack vectors */
-	while ((offset = ccid2_ackvector(sk, skb, offset,
-					 &vector, &veclen)) != -1) {
+	list_for_each_entry(avp, &hc->tx_av_chunks, node) {
 		/* go through this ack vector */
-		while (veclen--) {
-			u64 ackno_end_rl = SUB48(ackno, dccp_ackvec_runlen(vector));
+		for (; avp->len--; avp->vec++) {
+			u64 ackno_end_rl = SUB48(ackno,
+						 dccp_ackvec_runlen(avp->vec));
 
-			ccid2_pr_debug("ackvec start:%llu end:%llu\n",
+			ccid2_pr_debug("ackvec %llu |%u,%u|\n",
 				       (unsigned long long)ackno,
-				       (unsigned long long)ackno_end_rl);
+				       dccp_ackvec_state(avp->vec) >> 6,
+				       dccp_ackvec_runlen(avp->vec));
 			/* if the seqno we are analyzing is larger than the
 			 * current ackno, then move towards the tail of our
 			 * seqnos.
@@ -536,7 +482,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 			 * run length
 			 */
 			while (between48(seqp->ccid2s_seq,ackno_end_rl,ackno)) {
-				const u8 state = dccp_ackvec_state(vector);
+				const u8 state = dccp_ackvec_state(avp->vec);
 
 				/* new packet received or marked */
 				if (state != DCCPAV_NOT_RECEIVED &&
@@ -563,7 +509,6 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 				break;
 
 			ackno = SUB48(ackno_end_rl, 1);
-			vector++;
 		}
 		if (done)
 			break;
@@ -631,10 +576,11 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 		sk_stop_timer(sk, &hc->tx_rtotimer);
 	else
 		sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
-
+done:
 	/* check if incoming Acks allow pending packets to be sent */
 	if (sender_was_blocked && !ccid2_cwnd_network_limited(hc))
 		tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
+	dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
 }
 
 static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
@@ -663,6 +609,7 @@ static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
 	hc->tx_last_cong = ccid2_time_stamp;
 	setup_timer(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire,
 			(unsigned long)sk);
+	INIT_LIST_HEAD(&hc->tx_av_chunks);
 	return 0;
 }
 
@@ -696,16 +643,17 @@ static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
 }
 
 struct ccid_operations ccid2_ops = {
-	.ccid_id		= DCCPC_CCID2,
-	.ccid_name		= "TCP-like",
-	.ccid_hc_tx_obj_size	= sizeof(struct ccid2_hc_tx_sock),
-	.ccid_hc_tx_init	= ccid2_hc_tx_init,
-	.ccid_hc_tx_exit	= ccid2_hc_tx_exit,
-	.ccid_hc_tx_send_packet	= ccid2_hc_tx_send_packet,
-	.ccid_hc_tx_packet_sent	= ccid2_hc_tx_packet_sent,
-	.ccid_hc_tx_packet_recv	= ccid2_hc_tx_packet_recv,
-	.ccid_hc_rx_obj_size	= sizeof(struct ccid2_hc_rx_sock),
-	.ccid_hc_rx_packet_recv	= ccid2_hc_rx_packet_recv,
+	.ccid_id		  = DCCPC_CCID2,
+	.ccid_name		  = "TCP-like",
+	.ccid_hc_tx_obj_size	  = sizeof(struct ccid2_hc_tx_sock),
+	.ccid_hc_tx_init	  = ccid2_hc_tx_init,
+	.ccid_hc_tx_exit	  = ccid2_hc_tx_exit,
+	.ccid_hc_tx_send_packet	  = ccid2_hc_tx_send_packet,
+	.ccid_hc_tx_packet_sent	  = ccid2_hc_tx_packet_sent,
+	.ccid_hc_tx_parse_options = ccid2_hc_tx_parse_options,
+	.ccid_hc_tx_packet_recv	  = ccid2_hc_tx_packet_recv,
+	.ccid_hc_rx_obj_size	  = sizeof(struct ccid2_hc_rx_sock),
+	.ccid_hc_rx_packet_recv	  = ccid2_hc_rx_packet_recv,
 };
 
 #ifdef CONFIG_IP_DCCP_CCID2_DEBUG

net/dccp/ccids/ccid2.h

@@ -55,6 +55,7 @@ struct ccid2_seq {
  * @tx_rtt_seq:		     to decay RTTVAR at most once per flight
  * @tx_rpseq:		     last consecutive seqno
  * @tx_rpdupack:	     dupacks since rpseq
+ * @tx_av_chunks:	     list of Ack Vectors received on current skb
  */
 struct ccid2_hc_tx_sock {
 	u32			tx_cwnd;
@@ -79,6 +80,7 @@ struct ccid2_hc_tx_sock {
 	int			tx_rpdupack;
 	u32			tx_last_cong;
 	u64			tx_high_ack;
+	struct list_head	tx_av_chunks;
 };
 
 static inline bool ccid2_cwnd_network_limited(struct ccid2_hc_tx_sock *hc)

net/dccp/input.c

@@ -160,13 +160,15 @@ static void dccp_rcv_reset(struct sock *sk, struct sk_buff *skb)
 	dccp_time_wait(sk, DCCP_TIME_WAIT, 0);
 }
 
-static void dccp_event_ack_recv(struct sock *sk, struct sk_buff *skb)
+static void dccp_handle_ackvec_processing(struct sock *sk, struct sk_buff *skb)
 {
-	struct dccp_sock *dp = dccp_sk(sk);
+	struct dccp_ackvec *av = dccp_sk(sk)->dccps_hc_rx_ackvec;
 
-	if (dp->dccps_hc_rx_ackvec != NULL)
-		dccp_ackvec_check_rcv_ackno(dp->dccps_hc_rx_ackvec, sk,
-					    DCCP_SKB_CB(skb)->dccpd_ack_seq);
+	if (av == NULL)
+		return;
+	if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
+		dccp_ackvec_clear_state(av, DCCP_SKB_CB(skb)->dccpd_ack_seq);
+	dccp_ackvec_input(av, skb);
 }
 
 static void dccp_deliver_input_to_ccids(struct sock *sk, struct sk_buff *skb)
@@ -365,21 +367,13 @@ static int __dccp_rcv_established(struct sock *sk, struct sk_buff *skb,
 int dccp_rcv_established(struct sock *sk, struct sk_buff *skb,
 			 const struct dccp_hdr *dh, const unsigned len)
 {
-	struct dccp_sock *dp = dccp_sk(sk);
-
 	if (dccp_check_seqno(sk, skb))
 		goto discard;
 
 	if (dccp_parse_options(sk, NULL, skb))
 		return 1;
 
-	if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
-		dccp_event_ack_recv(sk, skb);
-
-	if (dp->dccps_hc_rx_ackvec != NULL &&
-	    dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
-			    DCCP_SKB_CB(skb)->dccpd_seq, DCCPAV_RECEIVED))
-		goto discard;
+	dccp_handle_ackvec_processing(sk, skb);
 	dccp_deliver_input_to_ccids(sk, skb);
 
 	return __dccp_rcv_established(sk, skb, dh, len);
@@ -631,14 +625,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 		if (dccp_parse_options(sk, NULL, skb))
 			return 1;
 
-		if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
-			dccp_event_ack_recv(sk, skb);
-
-		if (dp->dccps_hc_rx_ackvec != NULL &&
-		    dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
-				    DCCP_SKB_CB(skb)->dccpd_seq, DCCPAV_RECEIVED))
-			goto discard;
-
+		dccp_handle_ackvec_processing(sk, skb);
 		dccp_deliver_input_to_ccids(sk, skb);
 	}
 

net/dccp/options.c

@@ -54,7 +54,6 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
 	struct dccp_sock *dp = dccp_sk(sk);
 	const struct dccp_hdr *dh = dccp_hdr(skb);
 	const u8 pkt_type = DCCP_SKB_CB(skb)->dccpd_type;
-	u64 ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq;
 	unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb);
 	unsigned char *opt_ptr = options;
 	const unsigned char *opt_end = (unsigned char *)dh +
@@ -129,14 +128,6 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
 			if (rc)
 				goto out_featneg_failed;
 			break;
-		case DCCPO_ACK_VECTOR_0:
-		case DCCPO_ACK_VECTOR_1:
-			if (dccp_packet_without_ack(skb))   /* RFC 4340, 11.4 */
-				break;
-			if (dp->dccps_hc_rx_ackvec != NULL &&
-			    dccp_ackvec_parse(sk, skb, &ackno, opt, value, len))
-				goto out_invalid_option;
-			break;
 		case DCCPO_TIMESTAMP:
 			if (len != 4)
 				goto out_invalid_option;
@@ -226,6 +217,16 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
 						     pkt_type, opt, value, len))
 				goto out_invalid_option;
 			break;
+		case DCCPO_ACK_VECTOR_0:
+		case DCCPO_ACK_VECTOR_1:
+			if (dccp_packet_without_ack(skb))   /* RFC 4340, 11.4 */
+				break;
+			/*
+			 * Ack vectors are processed by the TX CCID if it is
+			 * interested. The RX CCID need not parse Ack Vectors,
+			 * since it is only interested in clearing old state.
+			 * Fall through.
+			 */
 		case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC:
 			if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk,
 						     pkt_type, opt, value, len))
@@ -429,6 +430,7 @@ static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb)
 {
 	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 u8 nr_opts = DIV_ROUND_UP(buflen, DCCP_SINGLE_OPT_MAXLEN);
@@ -437,10 +439,25 @@ static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb)
 	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;
@@ -481,7 +498,7 @@ static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb)
 	/*
 	 * 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;
 }

net/dccp/output.c

@@ -283,6 +283,15 @@ static void dccp_xmit_packet(struct sock *sk)
 	 * any local drop will eventually be reported via receiver feedback.
 	 */
 	ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, len);
+
+	/*
+	 * If the CCID needs to transfer additional header options out-of-band
+	 * (e.g. Ack Vectors or feature-negotiation options), it activates this
+	 * flag to schedule a Sync. The Sync will automatically incorporate all
+	 * currently pending header options, thus clearing the backlog.
+	 */
+	if (dp->dccps_sync_scheduled)
+		dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC);
 }
 
 /**
@@ -636,6 +645,12 @@ void dccp_send_sync(struct sock *sk, const u64 ackno,
 	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);
 }