dccp: Per-socket initialisation of feature negotiation

This provides feature-negotiation initialisation for both DCCP sockets
and DCCP request_sockets, to support feature negotiation during
connection setup.

It also resolves a FIXME regarding the congestion control
initialisation.

Thanks to Wei Yongjun for help with the IPv6 side of this patch.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: NIan McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

include/linux/dccp.h

@@ -412,6 +412,7 @@ extern void dccp_minisock_init(struct dccp_minisock *dmsk);
  * @dreq_iss: initial sequence number sent on the Response (RFC 4340, 7.1)
  * @dreq_isr: initial sequence number received on the Request
  * @dreq_service: service code present on the Request (there is just one)
+ * @dreq_featneg: feature negotiation options for this connection
  * The following two fields are analogous to the ones in dccp_sock:
  * @dreq_timestamp_echo: last received timestamp to echo (13.1)
  * @dreq_timestamp_echo: the time of receiving the last @dreq_timestamp_echo
@@ -421,6 +422,7 @@ struct dccp_request_sock {
 	__u64			 dreq_iss;
 	__u64			 dreq_isr;
 	__be32			 dreq_service;
+	struct list_head	 dreq_featneg;
 	__u32			 dreq_timestamp_echo;
 	__u32			 dreq_timestamp_time;
 };
@@ -498,6 +500,7 @@ struct dccp_ackvec;
  * @dccps_mss_cache - current value of MSS (path MTU minus header sizes)
  * @dccps_rate_last - timestamp for rate-limiting DCCP-Sync (RFC 4340, 7.5.4)
  * @dccps_minisock - associated minisock (accessed via dccp_msk)
+ * @dccps_featneg - tracks feature-negotiation state (mostly during handshake)
  * @dccps_hc_rx_ackvec - rx half connection ack vector
  * @dccps_hc_rx_ccid - CCID used for the receiver (or receiving half-connection)
  * @dccps_hc_tx_ccid - CCID used for the sender (or sending half-connection)
@@ -535,6 +538,7 @@ struct dccp_sock {
 	__u64				dccps_ndp_count:48;
 	unsigned long			dccps_rate_last;
 	struct dccp_minisock		dccps_minisock;
+	struct list_head		dccps_featneg;
 	struct dccp_ackvec		*dccps_hc_rx_ackvec;
 	struct ccid			*dccps_hc_rx_ccid;
 	struct ccid			*dccps_hc_tx_ccid;

net/dccp/dccp.h

@@ -252,7 +252,8 @@ extern const char *dccp_state_name(const int state);
 extern void dccp_set_state(struct sock *sk, const int state);
 extern void dccp_done(struct sock *sk);
 
-extern void dccp_reqsk_init(struct request_sock *req, struct sk_buff *skb);
+extern int  dccp_reqsk_init(struct request_sock *rq, struct dccp_sock const *dp,
+			    struct sk_buff const *skb);
 
 extern int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
 

net/dccp/feat.c

@@ -90,6 +90,20 @@ static u8 dccp_feat_type(u8 feat_num)
 	return dccp_feat_table[idx].reconciliation;
 }
 
+/* copy constructor, fval must not already contain allocated memory */
+static int dccp_feat_clone_sp_val(dccp_feat_val *fval, u8 const *val, u8 len)
+{
+	fval->sp.len = len;
+	if (fval->sp.len > 0) {
+		fval->sp.vec = kmemdup(val, len, gfp_any());
+		if (fval->sp.vec == NULL) {
+			fval->sp.len = 0;
+			return -ENOBUFS;
+		}
+	}
+	return 0;
+}
+
 static void dccp_feat_val_destructor(u8 feat_num, dccp_feat_val *val)
 {
 	if (unlikely(val == NULL))
@@ -99,6 +113,28 @@ static void dccp_feat_val_destructor(u8 feat_num, dccp_feat_val *val)
 	memset(val, 0, sizeof(*val));
 }
 
+static struct dccp_feat_entry *
+	      dccp_feat_clone_entry(struct dccp_feat_entry const *original)
+{
+	struct dccp_feat_entry *new;
+	u8 type = dccp_feat_type(original->feat_num);
+
+	if (type == FEAT_UNKNOWN)
+		return NULL;
+
+	new = kmemdup(original, sizeof(struct dccp_feat_entry), gfp_any());
+	if (new == NULL)
+		return NULL;
+
+	if (type == FEAT_SP && dccp_feat_clone_sp_val(&new->val,
+						      original->val.sp.vec,
+						      original->val.sp.len)) {
+		kfree(new);
+		return NULL;
+	}
+	return new;
+}
+
 static void dccp_feat_entry_destructor(struct dccp_feat_entry *entry)
 {
 	if (entry != NULL) {
@@ -133,6 +169,25 @@ void dccp_feat_list_purge(struct list_head *fn_list)
 }
 EXPORT_SYMBOL_GPL(dccp_feat_list_purge);
 
+/* generate @to as full clone of @from - @to must not contain any nodes */
+int dccp_feat_clone_list(struct list_head const *from, struct list_head *to)
+{
+	struct dccp_feat_entry *entry, *new;
+
+	INIT_LIST_HEAD(to);
+	list_for_each_entry(entry, from, node) {
+		new = dccp_feat_clone_entry(entry);
+		if (new == NULL)
+			goto cloning_failed;
+		list_add_tail(&new->node, to);
+	}
+	return 0;
+
+cloning_failed:
+	dccp_feat_list_purge(to);
+	return -ENOMEM;
+}
+
 int dccp_feat_change(struct dccp_minisock *dmsk, u8 type, u8 feature,
 		     u8 *val, u8 len, gfp_t gfp)
 {

net/dccp/feat.h

@@ -96,6 +96,7 @@ extern int  dccp_feat_confirm_recv(struct sock *sk, u8 type, u8 feature,
 				   u8 *val, u8 len);
 extern void dccp_feat_clean(struct dccp_minisock *dmsk);
 extern int  dccp_feat_clone(struct sock *oldsk, struct sock *newsk);
+extern int  dccp_feat_clone_list(struct list_head const *, struct list_head *);
 extern int  dccp_feat_init(struct dccp_minisock *dmsk);
 
 #endif /* _DCCP_FEAT_H */

net/dccp/input.c

@@ -590,8 +590,6 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 			if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
 								    skb) < 0)
 				return 1;
-
-			/* FIXME: do congestion control initialization */
 			goto discard;
 		}
 		if (dh->dccph_type == DCCP_PKT_RESET)

net/dccp/ipv4.c

@@ -595,7 +595,8 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (req == NULL)
 		goto drop;
 
-	dccp_reqsk_init(req, skb);
+	if (dccp_reqsk_init(req, dccp_sk(sk), skb))
+		goto drop_and_free;
 
 	dreq = dccp_rsk(req);
 	if (dccp_parse_options(sk, dreq, skb))

net/dccp/ipv6.c

@@ -426,7 +426,8 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (req == NULL)
 		goto drop;
 
-	dccp_reqsk_init(req, skb);
+	if (dccp_reqsk_init(req, dccp_sk(sk), skb))
+		goto drop_and_free;
 
 	dreq = dccp_rsk(req);
 	if (dccp_parse_options(sk, dreq, skb))

net/dccp/minisocks.c

@@ -125,6 +125,7 @@ struct sock *dccp_create_openreq_child(struct sock *sk,
 		newdp->dccps_timestamp_time = dreq->dreq_timestamp_time;
 		newicsk->icsk_rto	    = DCCP_TIMEOUT_INIT;
 
+		INIT_LIST_HEAD(&newdp->dccps_featneg);
 		if (dccp_feat_clone(sk, newsk))
 			goto out_free;
 
@@ -304,7 +305,8 @@ void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 
 EXPORT_SYMBOL_GPL(dccp_reqsk_send_ack);
 
-void dccp_reqsk_init(struct request_sock *req, struct sk_buff *skb)
+int dccp_reqsk_init(struct request_sock *req,
+		    struct dccp_sock const *dp, struct sk_buff const *skb)
 {
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 
@@ -313,6 +315,9 @@ void dccp_reqsk_init(struct request_sock *req, struct sk_buff *skb)
 	inet_rsk(req)->acked	  = 0;
 	req->rcv_wnd		  = sysctl_dccp_feat_sequence_window;
 	dreq->dreq_timestamp_echo = 0;
+
+	/* inherit feature negotiation options from listening socket */
+	return dccp_feat_clone_list(&dp->dccps_featneg, &dreq->dreq_featneg);
 }
 
 EXPORT_SYMBOL_GPL(dccp_reqsk_init);

net/dccp/proto.c

@@ -193,6 +193,7 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
 
 	dccp_init_xmit_timers(sk);
 
+	INIT_LIST_HEAD(&dp->dccps_featneg);
 	/*
 	 * FIXME: We're hardcoding the CCID, and doing this at this point makes
 	 * the listening (master) sock get CCID control blocks, which is not