Merge nuts.ninka.net:/home/davem/src/BK/network-2.5

into nuts.ninka.net:/home/davem/src/BK/net-2.5

8 files changed, 55 insertions, 161 deletions

diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 9fd7d5c05605..0fb31130009d 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -301,7 +301,8 @@ enum
 	NET_IPV4_NONLOCAL_BIND=88,
 	NET_IPV4_ICMP_RATELIMIT=89,
 	NET_IPV4_ICMP_RATEMASK=90,
-	NET_TCP_TW_REUSE=91
+	NET_TCP_TW_REUSE=91,
+	NET_TCP_FRTO=92
 };
 
 enum {
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index ce34341d6a2c..91b66d7ab004 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -366,6 +366,9 @@ struct tcp_opt {
 	unsigned int		keepalive_intvl;  /* time interval between keep alive probes */
 	int			linger2;
 
+	int                     frto_counter; /* Number of new acks after RTO */
+	__u32                   frto_highmark; /* snd_nxt when RTO occurred */
+
 	unsigned long last_synq_overflow; 
 };
 
diff --git a/include/net/flow.h b/include/net/flow.h
index e1ce1b2aea31..58fbf0e8314a 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -1,6 +1,6 @@
 /*
  *
- *	Flow based forwarding rules (usage: firewalling, etc)
+ *	Generic internet FLOW.
  *
  */
 
@@ -8,12 +8,16 @@
 #define _NET_FLOW_H
 
 struct flowi {
-	int	proto;		/*	{TCP, UDP, ICMP}	*/
+	int	oif;
+	int	iif;
 
 	union {
 		struct {
 			__u32			daddr;
 			__u32			saddr;
+			__u32			fwmark;
+			__u8			tos;
+			__u8			scope;
 		} ip4_u;
 		
 		struct {
@@ -27,9 +31,12 @@ struct flowi {
 #define fl6_flowlabel	nl_u.ip6_u.flowlabel
 #define fl4_dst		nl_u.ip4_u.daddr
 #define fl4_src		nl_u.ip4_u.saddr
+#define fl4_fwmark	nl_u.ip4_u.fwmark
+#define fl4_tos		nl_u.ip4_u.tos
+#define fl4_scope	nl_u.ip4_u.scope
 
-	int	oif;
-
+	__u8	proto;
+	__u8	flags;
 	union {
 		struct {
 			__u16	sport;
@@ -41,61 +48,8 @@ struct flowi {
 			__u8	code;
 		} icmpt;
 
-		unsigned long	data;
+		__u32		spi;
 	} uli_u;
 };
 
-#define FLOWR_NODECISION	0	/* rule not appliable to flow	*/
-#define FLOWR_SELECT		1	/* flow must follow this rule	*/
-#define FLOWR_CLEAR		2	/* priority level clears flow	*/
-#define FLOWR_ERROR		3
-
-struct fl_acc_args {
-	int	type;
-
-
-#define FL_ARG_FORWARD	1
-#define FL_ARG_ORIGIN	2
-
-	union {
-		struct sk_buff		*skb;
-		struct {
-			struct sock	*sk;
-			struct flowi	*flow;
-		} fl_o;
-	} fl_u;
-};
-
-
-struct pkt_filter {
-	atomic_t		refcnt;
-	unsigned int		offset;
-	__u32			value;
-	__u32			mask;
-	struct pkt_filter	*next;
-};
-
-#define FLR_INPUT		1
-#define FLR_OUTPUT		2
-
-struct flow_filter {
-	int				type;
-	union {
-		struct pkt_filter	*filter;
-		struct sock		*sk;
-	} u;
-};
-
-struct flow_rule {
-	struct flow_rule_ops		*ops;
-	unsigned char			private[0];
-};
-
-struct flow_rule_ops {
-	int			(*accept)(struct rt6_info *rt,
-					  struct rt6_info *rule,
-					  struct fl_acc_args *args,
-					  struct rt6_info **nrt);
-};
-
 #endif
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index f8d382f4e7d8..4fb406133dbb 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -70,14 +70,6 @@ struct rt6_info
 	u8				rt6i_hoplimit;
 	atomic_t			rt6i_ref;
 
-	union {
-		struct flow_rule	*rt6iu_flowr;
-		struct flow_filter	*rt6iu_filter;
-	} flow_u;
-
-#define rt6i_flowr			flow_u.rt6iu_flowr
-#define rt6i_filter			flow_u.rt6iu_filter
-
 	struct rt6key			rt6i_dst;
 	struct rt6key			rt6i_src;
 };
diff --git a/include/net/ip6_fw.h b/include/net/ip6_fw.h
deleted file mode 100644
index 7866273d3d56..000000000000
--- a/include/net/ip6_fw.h
+++ /dev/null
@@ -1,54 +0,0 @@
-#ifndef __NET_IP6_FW_H
-#define __NET_IP6_FW_H
-
-#define IP6_FW_LISTHEAD		0x1000
-#define IP6_FW_ACCEPT		0x0001
-#define IP6_FW_REJECT		0x0002
-
-#define IP6_FW_DEBUG	2
-
-#define IP6_FW_MSG_ADD		1
-#define IP6_FW_MSG_DEL		2
-#define IP6_FW_MSG_REPORT	3
-
-
-/*
- *	Fast "hack" user interface
- */
-struct ip6_fw_msg {
-	struct in6_addr		dst;
-	struct in6_addr		src;
-	int			dst_len;
-	int			src_len;
-	int			action;
-	int			policy;
-	int			proto;
-	union {
-		struct {
-			__u16	sport;
-			__u16	dport;
-		} transp;
-
-		unsigned long	data;
-
-		int		icmp_type;
-	} u;
-
-	int			msg_len;
-};
-
-#ifdef __KERNEL__
-
-#include <net/flow.h>
-
-struct ip6_fw_rule {
-	struct flow_rule	flowr;
-	struct ip6_fw_rule	*next;
-	struct ip6_fw_rule	*prev;
-	struct flowi		info;
-	unsigned long		policy;
-};
-
-#endif
-
-#endif
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 3b84c5bff809..236641e5bc51 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -17,6 +17,7 @@
 #define _NET_IP_FIB_H
 
 #include <linux/config.h>
+#include <net/flow.h>
 
 struct kern_rta
 {
@@ -117,7 +118,7 @@ struct fib_table
 {
 	unsigned char	tb_id;
 	unsigned	tb_stamp;
-	int		(*tb_lookup)(struct fib_table *tb, const struct rt_key *key, struct fib_result *res);
+	int		(*tb_lookup)(struct fib_table *tb, const struct flowi *flp, struct fib_result *res);
 	int		(*tb_insert)(struct fib_table *table, struct rtmsg *r,
 				     struct kern_rta *rta, struct nlmsghdr *n,
 				     struct netlink_skb_parms *req);
@@ -130,7 +131,7 @@ struct fib_table
 	int		(*tb_get_info)(struct fib_table *table, char *buf,
 				       int first, int count);
 	void		(*tb_select_default)(struct fib_table *table,
-					     const struct rt_key *key, struct fib_result *res);
+					     const struct flowi *flp, struct fib_result *res);
 
 	unsigned char	tb_data[0];
 };
@@ -152,18 +153,18 @@ static inline struct fib_table *fib_new_table(int id)
 	return fib_get_table(id);
 }
 
-static inline int fib_lookup(const struct rt_key *key, struct fib_result *res)
+static inline int fib_lookup(const struct flowi *flp, struct fib_result *res)
 {
-	if (local_table->tb_lookup(local_table, key, res) &&
-	    main_table->tb_lookup(main_table, key, res))
+	if (local_table->tb_lookup(local_table, flp, res) &&
+	    main_table->tb_lookup(main_table, flp, res))
 		return -ENETUNREACH;
 	return 0;
 }
 
-static inline void fib_select_default(const struct rt_key *key, struct fib_result *res)
+static inline void fib_select_default(const struct flowi *flp, struct fib_result *res)
 {
 	if (FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
-		main_table->tb_select_default(main_table, key, res);
+		main_table->tb_select_default(main_table, flp, res);
 }
 
 #else /* CONFIG_IP_MULTIPLE_TABLES */
@@ -171,7 +172,7 @@ static inline void fib_select_default(const struct rt_key *key, struct fib_resul
 #define main_table (fib_tables[RT_TABLE_MAIN])
 
 extern struct fib_table * fib_tables[RT_TABLE_MAX+1];
-extern int fib_lookup(const struct rt_key *key, struct fib_result *res);
+extern int fib_lookup(const struct flowi *flp, struct fib_result *res);
 extern struct fib_table *__fib_new_table(int id);
 extern void fib_rule_put(struct fib_rule *r);
 
@@ -191,7 +192,7 @@ static inline struct fib_table *fib_new_table(int id)
 	return fib_tables[id] ? : __fib_new_table(id);
 }
 
-extern void fib_select_default(const struct rt_key *key, struct fib_result *res);
+extern void fib_select_default(const struct flowi *flp, struct fib_result *res);
 
 #endif /* CONFIG_IP_MULTIPLE_TABLES */
 
@@ -204,13 +205,13 @@ extern int inet_rtm_getroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *ar
 extern int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb);
 extern int fib_validate_source(u32 src, u32 dst, u8 tos, int oif,
 			       struct net_device *dev, u32 *spec_dst, u32 *itag);
-extern void fib_select_multipath(const struct rt_key *key, struct fib_result *res);
+extern void fib_select_multipath(const struct flowi *flp, struct fib_result *res);
 
 /* Exported by fib_semantics.c */
 extern int 		ip_fib_check_default(u32 gw, struct net_device *dev);
 extern void		fib_release_info(struct fib_info *);
 extern int		fib_semantic_match(int type, struct fib_info *,
-					   const struct rt_key *, struct fib_result*);
+					   const struct flowi *, struct fib_result*);
 extern struct fib_info	*fib_create_info(const struct rtmsg *r, struct kern_rta *rta,
 					 const struct nlmsghdr *, int *err);
 extern int fib_nh_match(struct rtmsg *r, struct nlmsghdr *, struct kern_rta *rta, struct fib_info *fi);
diff --git a/include/net/route.h b/include/net/route.h
index 7ddc79e4d07e..621b0c44b250 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -27,6 +27,7 @@
 #include <linux/config.h>
 #include <net/dst.h>
 #include <net/inetpeer.h>
+#include <net/flow.h>
 #include <linux/in_route.h>
 #include <linux/rtnetlink.h>
 #include <linux/route.h>
@@ -45,19 +46,6 @@
 
 #define RT_CONN_FLAGS(sk)   (RT_TOS(inet_sk(sk)->tos) | sk->localroute)
 
-struct rt_key
-{
-	__u32			dst;
-	__u32			src;
-	int			iif;
-	int			oif;
-#ifdef CONFIG_IP_ROUTE_FWMARK
-	__u32			fwmark;
-#endif
-	__u8			tos;
-	__u8			scope;
-};
-
 struct inet_peer;
 struct rtable
 {
@@ -78,7 +66,7 @@ struct rtable
 	__u32			rt_gateway;
 
 	/* Cache lookup keys */
-	struct rt_key		key;
+	struct flowi		fl;
 
 	/* Miscellaneous cached information */
 	__u32			rt_spec_dst; /* RFC1122 specific destination */
@@ -124,7 +112,7 @@ extern void		ip_rt_redirect(u32 old_gw, u32 dst, u32 new_gw,
 				       u32 src, u8 tos, struct net_device *dev);
 extern void		ip_rt_advice(struct rtable **rp, int advice);
 extern void		rt_cache_flush(int how);
-extern int		ip_route_output_key(struct rtable **, const struct rt_key *key);
+extern int		ip_route_output_key(struct rtable **, const struct flowi *flp);
 extern int		ip_route_input(struct sk_buff*, u32 dst, u32 src, u8 tos, struct net_device *devin);
 extern unsigned short	ip_rt_frag_needed(struct iphdr *iph, unsigned short new_mtu);
 extern void		ip_rt_update_pmtu(struct dst_entry *dst, unsigned mtu);
@@ -136,16 +124,6 @@ extern int		ip_rt_ioctl(unsigned int cmd, void *arg);
 extern void		ip_rt_get_source(u8 *src, struct rtable *rt);
 extern int		ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb);
 
-/* Deprecated: use ip_route_output_key directly */
-static inline int ip_route_output(struct rtable **rp,
-				      u32 daddr, u32 saddr, u32 tos, int oif)
-{
-	struct rt_key key = { dst:daddr, src:saddr, oif:oif, tos:tos };
-
-	return ip_route_output_key(rp, &key);
-}
-
-
 static inline void ip_rt_put(struct rtable * rt)
 {
 	if (rt)
@@ -163,15 +141,20 @@ static inline char rt_tos2priority(u8 tos)
 
 static inline int ip_route_connect(struct rtable **rp, u32 dst, u32 src, u32 tos, int oif)
 {
+	struct flowi fl = { .nl_u = { .ip4_u = { .daddr = dst,
+						 .saddr = src,
+						 .tos   = tos } },
+			    .oif = oif };
+
 	int err;
-	err = ip_route_output(rp, dst, src, tos, oif);
+	err = ip_route_output_key(rp, &fl);
 	if (err || (dst && src))
 		return err;
-	dst = (*rp)->rt_dst;
-	src = (*rp)->rt_src;
+	fl.fl4_dst = (*rp)->rt_dst;
+	fl.fl4_src = (*rp)->rt_src;
 	ip_rt_put(*rp);
 	*rp = NULL;
-	return ip_route_output(rp, dst, src, tos, oif);
+	return ip_route_output_key(rp, &fl);
 }
 
 extern void rt_bind_peer(struct rtable *rt, int create);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0a58d80e7794..f5aa33e5b15e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -472,6 +472,7 @@ extern int sysctl_tcp_rmem[3];
 extern int sysctl_tcp_app_win;
 extern int sysctl_tcp_adv_win_scale;
 extern int sysctl_tcp_tw_reuse;
+extern int sysctl_tcp_frto;
 
 extern atomic_t tcp_memory_allocated;
 extern atomic_t tcp_sockets_allocated;
@@ -1855,4 +1856,17 @@ static inline void tcp_v4_setup_caps(struct sock *sk, struct dst_entry *dst)
 
 #define TCP_CHECK_TIMER(sk) do { } while (0)
 
+static inline int tcp_use_frto(const struct sock *sk)
+{
+	const struct tcp_opt *tp = tcp_sk(sk);
+	
+	/* F-RTO must be activated in sysctl and there must be some
+	 * unsent new data, and the advertised window should allow
+	 * sending it.
+	 */
+	return (sysctl_tcp_frto && tp->send_head &&
+		!after(TCP_SKB_CB(tp->send_head)->end_seq,
+		       tp->snd_una + tp->snd_wnd));
+}
+
 #endif	/* _TCP_H */