[DCCP]: Initial implementation

Development to this point was done on a subversion repository at:

http://oops.ghostprotocols.net:81/cgi-bin/viewcvs.cgi/dccp-2.6/

This repository will be kept at this site for the foreseable future,
so that interested parties can see the history of this code,
attributions, etc.

If I ever decide to take this offline I'll provide the full history at
some other suitable place.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/in.h

@@ -32,6 +32,7 @@ enum {
   IPPROTO_PUP = 12,		/* PUP protocol				*/
   IPPROTO_UDP = 17,		/* User Datagram Protocol		*/
   IPPROTO_IDP = 22,		/* XNS IDP protocol			*/
+  IPPROTO_DCCP = 33,		/* Datagram Congestion Control Protocol */
   IPPROTO_RSVP = 46,		/* RSVP protocol			*/
   IPPROTO_GRE = 47,		/* Cisco GRE tunnels (rfc 1701,1702)	*/
 

include/linux/net.h

@@ -84,6 +84,7 @@ enum sock_type {
 	SOCK_RAW	= 3,
 	SOCK_RDM	= 4,
 	SOCK_SEQPACKET	= 5,
+	SOCK_DCCP	= 6,
 	SOCK_PACKET	= 10,
 };
 

include/linux/socket.h

@@ -271,6 +271,7 @@ struct ucred {
 #define SOL_IRDA        266
 #define SOL_NETBEUI	267
 #define SOL_LLC		268
+#define SOL_DCCP	269
 
 /* IPX options */
 #define IPX_TYPE	1

net/Kconfig

@@ -147,6 +147,7 @@ source "net/bridge/netfilter/Kconfig"
 
 endif
 
+source "net/dccp/Kconfig"
 source "net/sctp/Kconfig"
 source "net/atm/Kconfig"
 source "net/bridge/Kconfig"

net/Makefile

@@ -42,6 +42,7 @@ obj-$(CONFIG_ATM)		+= atm/
 obj-$(CONFIG_DECNET)		+= decnet/
 obj-$(CONFIG_ECONET)		+= econet/
 obj-$(CONFIG_VLAN_8021Q)	+= 8021q/
+obj-$(CONFIG_IP_DCCP)		+= dccp/
 obj-$(CONFIG_IP_SCTP)		+= sctp/
 
 ifeq ($(CONFIG_NET),y)

net/dccp/Kconfig

@@ -0,0 +1,24 @@
+menu "DCCP Configuration (EXPERIMENTAL)"
+	depends on INET && EXPERIMENTAL
+
+config IP_DCCP
+	tristate "The DCCP Protocol (EXPERIMENTAL)"
+	---help---
+	  Datagram Congestion Control Protocol
+
+	  From draft-ietf-dccp-spec-11 <http://www.icir.org/kohler/dcp/draft-ietf-dccp-spec-11.txt>.
+
+	  The Datagram Congestion Control Protocol (DCCP) is a transport
+	  protocol that implements bidirectional, unicast connections of
+	  congestion-controlled, unreliable datagrams. It should be suitable
+	  for use by applications such as streaming media, Internet telephony,
+	  and on-line games
+
+	  To compile this protocol support as a module, choose M here: the
+	  module will be called dccp.
+
+	  If in doubt, say N.
+
+source "net/dccp/ccids/Kconfig"
+
+endmenu

net/dccp/Makefile

@@ -0,0 +1,5 @@
+obj-$(CONFIG_IP_DCCP) += dccp.o
+
+dccp-y := ccid.o input.o ipv4.o minisocks.o options.o output.o proto.o timer.o
+
+obj-y += ccids/

net/dccp/ccid.c

@@ -0,0 +1,139 @@
+/*
+ *  net/dccp/ccid.c
+ *
+ *  An implementation of the DCCP protocol
+ *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+ *
+ *  CCID infrastructure
+ *
+ *	This program is free software; you can redistribute it and/or modify it
+ *	under the terms of the GNU General Public License version 2 as
+ *	published by the Free Software Foundation.
+ */
+
+#include "ccid.h"
+
+static struct ccid *ccids[CCID_MAX];
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
+static atomic_t ccids_lockct = ATOMIC_INIT(0);
+static DEFINE_SPINLOCK(ccids_lock);
+
+/*
+ * The strategy is: modifications ccids vector are short, do not sleep and
+ * veeery rare, but read access should be free of any exclusive locks.
+ */
+static void ccids_write_lock(void)
+{
+	spin_lock(&ccids_lock);
+	while (atomic_read(&ccids_lockct) != 0) {
+		spin_unlock(&ccids_lock);
+		yield();
+		spin_lock(&ccids_lock);
+	}
+}
+
+static inline void ccids_write_unlock(void)
+{
+	spin_unlock(&ccids_lock);
+}
+
+static inline void ccids_read_lock(void)
+{
+	atomic_inc(&ccids_lockct);
+	spin_unlock_wait(&ccids_lock);
+}
+
+static inline void ccids_read_unlock(void)
+{
+	atomic_dec(&ccids_lockct);
+}
+
+#else
+#define ccids_write_lock() do { } while(0)
+#define ccids_write_unlock() do { } while(0)
+#define ccids_read_lock() do { } while(0)
+#define ccids_read_unlock() do { } while(0)
+#endif
+
+int ccid_register(struct ccid *ccid)
+{
+	int err;
+
+	if (ccid->ccid_init == NULL)
+		return -1;
+
+	ccids_write_lock();
+	err = -EEXIST;
+	if (ccids[ccid->ccid_id] == NULL) {
+		ccids[ccid->ccid_id] = ccid;
+		err = 0;
+	}
+	ccids_write_unlock();
+	if (err == 0)
+		pr_info("CCID: Registered CCID %d (%s)\n",
+			ccid->ccid_id, ccid->ccid_name);
+	return err;
+}
+
+EXPORT_SYMBOL_GPL(ccid_register);
+
+int ccid_unregister(struct ccid *ccid)
+{
+	ccids_write_lock();
+	ccids[ccid->ccid_id] = NULL;
+	ccids_write_unlock();
+	pr_info("CCID: Unregistered CCID %d (%s)\n",
+		ccid->ccid_id, ccid->ccid_name);
+	return 0;
+}
+
+EXPORT_SYMBOL_GPL(ccid_unregister);
+
+struct ccid *ccid_init(unsigned char id, struct sock *sk)
+{
+	struct ccid *ccid;
+
+#ifdef CONFIG_KMOD
+	if (ccids[id] == NULL)
+		request_module("net-dccp-ccid-%d", id);
+#endif
+	ccids_read_lock();
+
+	ccid = ccids[id];
+	if (ccid == NULL)
+		goto out;
+
+	if (!try_module_get(ccid->ccid_owner))
+		goto out_err;
+
+	if (ccid->ccid_init(sk) != 0)
+		goto out_module_put;
+out:
+	ccids_read_unlock();
+	return ccid;
+out_module_put:
+	module_put(ccid->ccid_owner);
+out_err:
+	ccid = NULL;
+	goto out;
+}
+
+EXPORT_SYMBOL_GPL(ccid_init);
+
+void ccid_exit(struct ccid *ccid, struct sock *sk)
+{
+	if (ccid == NULL)
+		return;
+
+	ccids_read_lock();
+
+	if (ccids[ccid->ccid_id] != NULL) {
+		if (ccid->ccid_exit != NULL)
+			ccid->ccid_exit(sk);
+		module_put(ccid->ccid_owner);
+	}
+
+	ccids_read_unlock();
+}
+
+EXPORT_SYMBOL_GPL(ccid_exit);

net/dccp/ccid.h

@@ -0,0 +1,156 @@
+#ifndef _CCID_H
+#define _CCID_H
+/*
+ *  net/dccp/ccid.h
+ *
+ *  An implementation of the DCCP protocol
+ *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+ *
+ *  CCID infrastructure
+ *
+ *	This program is free software; you can redistribute it and/or modify it
+ *	under the terms of the GNU General Public License version 2 as
+ *	published by the Free Software Foundation.
+ */
+
+#include <net/sock.h>
+#include <linux/dccp.h>
+#include <linux/list.h>
+#include <linux/module.h>
+
+#define CCID_MAX 255
+
+struct ccid {
+	unsigned char	ccid_id;
+	const char	*ccid_name;
+	struct module	*ccid_owner;
+	int		(*ccid_init)(struct sock *sk);
+	void		(*ccid_exit)(struct sock *sk);
+	int		(*ccid_hc_rx_init)(struct sock *sk);
+	int		(*ccid_hc_tx_init)(struct sock *sk);
+	void		(*ccid_hc_rx_exit)(struct sock *sk);
+	void		(*ccid_hc_tx_exit)(struct sock *sk);
+	void		(*ccid_hc_rx_packet_recv)(struct sock *sk, struct sk_buff *skb);
+	int		(*ccid_hc_rx_parse_options)(struct sock *sk,
+						    unsigned char option,
+						    unsigned char len, u16 idx,
+						    unsigned char* value);
+	void		(*ccid_hc_rx_insert_options)(struct sock *sk, struct sk_buff *skb);
+	void		(*ccid_hc_tx_insert_options)(struct sock *sk, struct sk_buff *skb);
+	void		(*ccid_hc_tx_packet_recv)(struct sock *sk, struct sk_buff *skb);
+	int		(*ccid_hc_tx_parse_options)(struct sock *sk,
+						    unsigned char option,
+						    unsigned char len, u16 idx,
+						    unsigned char* value);
+	int		(*ccid_hc_tx_send_packet)(struct sock *sk,
+						  struct sk_buff *skb, int len,
+						  long *delay);
+	void		(*ccid_hc_tx_packet_sent)(struct sock *sk, int more, int len);
+};
+
+extern int	   ccid_register(struct ccid *ccid);
+extern int	   ccid_unregister(struct ccid *ccid);
+
+extern struct ccid *ccid_init(unsigned char id, struct sock *sk);
+extern void	   ccid_exit(struct ccid *ccid, struct sock *sk);
+
+static inline void __ccid_get(struct ccid *ccid)
+{
+	__module_get(ccid->ccid_owner);
+}
+
+static inline int ccid_hc_tx_send_packet(struct ccid *ccid, struct sock *sk,
+					 struct sk_buff *skb, int len,
+					 long *delay)
+{
+	int rc = 0;
+	if (ccid->ccid_hc_tx_send_packet != NULL)
+		rc = ccid->ccid_hc_tx_send_packet(sk, skb, len, delay);
+	return rc;
+}
+
+static inline void ccid_hc_tx_packet_sent(struct ccid *ccid, struct sock *sk,
+					  int more, int len)
+{
+	if (ccid->ccid_hc_tx_packet_sent != NULL)
+		ccid->ccid_hc_tx_packet_sent(sk, more, len);
+}
+
+static inline int ccid_hc_rx_init(struct ccid *ccid, struct sock *sk)
+{
+	int rc = 0;
+	if (ccid->ccid_hc_rx_init != NULL)
+		rc = ccid->ccid_hc_rx_init(sk);
+	return rc;
+}
+
+static inline int ccid_hc_tx_init(struct ccid *ccid, struct sock *sk)
+{
+	int rc = 0;
+	if (ccid->ccid_hc_tx_init != NULL)
+		rc = ccid->ccid_hc_tx_init(sk);
+	return rc;
+}
+
+static inline void ccid_hc_rx_exit(struct ccid *ccid, struct sock *sk)
+{
+	if (ccid->ccid_hc_rx_exit != NULL)
+		ccid->ccid_hc_rx_exit(sk);
+}
+
+static inline void ccid_hc_tx_exit(struct ccid *ccid, struct sock *sk)
+{
+	if (ccid->ccid_hc_tx_exit != NULL)
+		ccid->ccid_hc_tx_exit(sk);
+}
+
+static inline void ccid_hc_rx_packet_recv(struct ccid *ccid, struct sock *sk,
+					  struct sk_buff *skb)
+{
+	if (ccid->ccid_hc_rx_packet_recv != NULL)
+		ccid->ccid_hc_rx_packet_recv(sk, skb);
+}
+
+static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk,
+					  struct sk_buff *skb)
+{
+	if (ccid->ccid_hc_tx_packet_recv != NULL)
+		ccid->ccid_hc_tx_packet_recv(sk, skb);
+}
+
+static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk,
+					   unsigned char option,
+					   unsigned char len, u16 idx,
+					   unsigned char* value)
+{
+	int rc = 0;
+	if (ccid->ccid_hc_tx_parse_options != NULL)
+		rc = ccid->ccid_hc_tx_parse_options(sk, option, len, idx, value);
+	return rc;
+}
+
+static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk,
+					   unsigned char option,
+					   unsigned char len, u16 idx,
+					   unsigned char* value)
+{
+	int rc = 0;
+	if (ccid->ccid_hc_rx_parse_options != NULL)
+		rc = ccid->ccid_hc_rx_parse_options(sk, option, len, idx, value);
+	return rc;
+}
+
+static inline void ccid_hc_tx_insert_options(struct ccid *ccid, struct sock *sk,
+					     struct sk_buff *skb)
+{
+	if (ccid->ccid_hc_tx_insert_options != NULL)
+		ccid->ccid_hc_tx_insert_options(sk, skb);
+}
+
+static inline void ccid_hc_rx_insert_options(struct ccid *ccid, struct sock *sk,
+					     struct sk_buff *skb)
+{
+	if (ccid->ccid_hc_rx_insert_options != NULL)
+		ccid->ccid_hc_rx_insert_options(sk, skb);
+}
+#endif /* _CCID_H */

net/dccp/ccids/Kconfig

@@ -0,0 +1,25 @@
+menu "DCCP CCIDs Configuration (EXPERIMENTAL)"
+	depends on IP_DCCP && EXPERIMENTAL
+
+config IP_DCCP_CCID3
+	tristate "CCID3 (TFRC) (EXPERIMENTAL)"
+	depends on IP_DCCP
+	---help---
+	  CCID 3 denotes TCP-Friendly Rate Control (TFRC), an equation-based
+	  rate-controlled congestion control mechanism.  TFRC is designed to
+	  be reasonably fair when competing for bandwidth with TCP-like flows,
+	  where a flow is "reasonably fair" if its sending rate is generally
+	  within a factor of two of the sending rate of a TCP flow under the
+	  same conditions.  However, TFRC has a much lower variation of
+	  throughput over time compared with TCP, which makes CCID 3 more
+	  suitable than CCID 2 for applications such streaming media where a
+	  relatively smooth sending rate is of importance.
+
+	  CCID 3 is further described in [CCID 3 PROFILE]. The TFRC
+	  congestion control algorithms were initially described in RFC 3448.
+
+	  This text was extracted from draft-ietf-dccp-spec-11.txt.
+
+	  If in doubt, say M.
+
+endmenu

net/dccp/ccids/Makefile

@@ -0,0 +1,3 @@
+obj-$(CONFIG_IP_DCCP_CCID3) += dccp_ccid3.o
+
+dccp_ccid3-y := ccid3.o