1 files changed, 215 insertions, 88 deletions

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index a66e9de16a6..9bcb220bd4a 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -13,104 +13,210 @@
 #ifndef _IP6_FIB_H
 #define _IP6_FIB_H
 
-#ifdef __KERNEL__
-
 #include <linux/ipv6_route.h>
-
-#include <net/dst.h>
-#include <net/flow.h>
 #include <linux/rtnetlink.h>
 #include <linux/spinlock.h>
+#include <net/dst.h>
+#include <net/flow.h>
+#include <net/netlink.h>
+#include <net/inetpeer.h>
+
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+#define FIB6_TABLE_HASHSZ 256
+#else
+#define FIB6_TABLE_HASHSZ 1
+#endif
 
 struct rt6_info;
 
-struct fib6_node
-{
+struct fib6_config {
+	u32		fc_table;
+	u32		fc_metric;
+	int		fc_dst_len;
+	int		fc_src_len;
+	int		fc_ifindex;
+	u32		fc_flags;
+	u32		fc_protocol;
+	u32		fc_type;	/* only 8 bits are used */
+
+	struct in6_addr	fc_dst;
+	struct in6_addr	fc_src;
+	struct in6_addr	fc_prefsrc;
+	struct in6_addr	fc_gateway;
+
+	unsigned long	fc_expires;
+	struct nlattr	*fc_mx;
+	int		fc_mx_len;
+	int		fc_mp_len;
+	struct nlattr	*fc_mp;
+
+	struct nl_info	fc_nlinfo;
+};
+
+struct fib6_node {
 	struct fib6_node	*parent;
 	struct fib6_node	*left;
 	struct fib6_node	*right;
-
+#ifdef CONFIG_IPV6_SUBTREES
 	struct fib6_node	*subtree;
-
+#endif
 	struct rt6_info		*leaf;
 
 	__u16			fn_bit;		/* bit key */
 	__u16			fn_flags;
 	__u32			fn_sernum;
+	struct rt6_info		*rr_ptr;
 };
 
+#ifndef CONFIG_IPV6_SUBTREES
+#define FIB6_SUBTREE(fn)	NULL
+#else
+#define FIB6_SUBTREE(fn)	((fn)->subtree)
+#endif
 
 /*
  *	routing information
  *
  */
 
-struct rt6key
-{
+struct rt6key {
 	struct in6_addr	addr;
 	int		plen;
 };
 
-struct rt6_info
-{
-	union {
-		struct dst_entry	dst;
-		struct rt6_info		*next;
-	} u;
+struct fib6_table;
 
-	struct inet6_dev		*rt6i_idev;
-
-#define rt6i_dev			u.dst.dev
-#define rt6i_nexthop			u.dst.neighbour
-#define rt6i_expires			u.dst.expires
+struct rt6_info {
+	struct dst_entry		dst;
 
+	/*
+	 * Tail elements of dst_entry (__refcnt etc.)
+	 * and these elements (rarely used in hot path) are in
+	 * the same cache line.
+	 */
+	struct fib6_table		*rt6i_table;
 	struct fib6_node		*rt6i_node;
 
 	struct in6_addr			rt6i_gateway;
-	
-	u32				rt6i_flags;
-	u32				rt6i_metric;
+
+	/* Multipath routes:
+	 * siblings is a list of rt6_info that have the the same metric/weight,
+	 * destination, but not the same gateway. nsiblings is just a cache
+	 * to speed up lookup.
+	 */
+	struct list_head		rt6i_siblings;
+	unsigned int			rt6i_nsiblings;
+
 	atomic_t			rt6i_ref;
 
-	struct rt6key			rt6i_dst;
+	/* These are in a separate cache line. */
+	struct rt6key			rt6i_dst ____cacheline_aligned_in_smp;
+	u32				rt6i_flags;
 	struct rt6key			rt6i_src;
+	struct rt6key			rt6i_prefsrc;
+	u32				rt6i_metric;
+
+	struct inet6_dev		*rt6i_idev;
+	unsigned long			_rt6i_peer;
+
+	u32				rt6i_genid;
+
+	/* more non-fragment space at head required */
+	unsigned short			rt6i_nfheader_len;
 
 	u8				rt6i_protocol;
 };
 
-struct fib6_walker_t
+static inline struct inet_peer *rt6_peer_ptr(struct rt6_info *rt)
 {
-	struct fib6_walker_t *prev, *next;
-	struct fib6_node *root, *node;
-	struct rt6_info *leaf;
-	unsigned char state;
-	unsigned char prune;
-	int (*func)(struct fib6_walker_t *);
-	void *args;
-};
+	return inetpeer_ptr(rt->_rt6i_peer);
+}
+
+static inline bool rt6_has_peer(struct rt6_info *rt)
+{
+	return inetpeer_ptr_is_peer(rt->_rt6i_peer);
+}
 
-extern struct fib6_walker_t fib6_walker_list;
-extern rwlock_t fib6_walker_lock;
+static inline void __rt6_set_peer(struct rt6_info *rt, struct inet_peer *peer)
+{
+	__inetpeer_ptr_set_peer(&rt->_rt6i_peer, peer);
+}
 
-static inline void fib6_walker_link(struct fib6_walker_t *w)
+static inline bool rt6_set_peer(struct rt6_info *rt, struct inet_peer *peer)
 {
-	write_lock_bh(&fib6_walker_lock);
-	w->next = fib6_walker_list.next;
-	w->prev = &fib6_walker_list;
-	w->next->prev = w;
-	w->prev->next = w;
-	write_unlock_bh(&fib6_walker_lock);
+	return inetpeer_ptr_set_peer(&rt->_rt6i_peer, peer);
 }
 
-static inline void fib6_walker_unlink(struct fib6_walker_t *w)
+static inline void rt6_init_peer(struct rt6_info *rt, struct inet_peer_base *base)
 {
-	write_lock_bh(&fib6_walker_lock);
-	w->next->prev = w->prev;
-	w->prev->next = w->next;
-	w->prev = w->next = w;
-	write_unlock_bh(&fib6_walker_lock);
+	inetpeer_init_ptr(&rt->_rt6i_peer, base);
 }
 
+static inline void rt6_transfer_peer(struct rt6_info *rt, struct rt6_info *ort)
+{
+	inetpeer_transfer_peer(&rt->_rt6i_peer, &ort->_rt6i_peer);
+}
+
+static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
+{
+	return ((struct rt6_info *)dst)->rt6i_idev;
+}
+
+static inline void rt6_clean_expires(struct rt6_info *rt)
+{
+	rt->rt6i_flags &= ~RTF_EXPIRES;
+	rt->dst.expires = 0;
+}
+
+static inline void rt6_set_expires(struct rt6_info *rt, unsigned long expires)
+{
+	rt->dst.expires = expires;
+	rt->rt6i_flags |= RTF_EXPIRES;
+}
+
+static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
+{
+	struct rt6_info *rt;
+
+	for (rt = rt0; rt && !(rt->rt6i_flags & RTF_EXPIRES);
+	     rt = (struct rt6_info *)rt->dst.from);
+	if (rt && rt != rt0)
+		rt0->dst.expires = rt->dst.expires;
+
+	dst_set_expires(&rt0->dst, timeout);
+	rt0->rt6i_flags |= RTF_EXPIRES;
+}
+
+static inline void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
+{
+	struct dst_entry *new = (struct dst_entry *) from;
+
+	rt->rt6i_flags &= ~RTF_EXPIRES;
+	dst_hold(new);
+	rt->dst.from = new;
+}
+
+static inline void ip6_rt_put(struct rt6_info *rt)
+{
+	/* dst_release() accepts a NULL parameter.
+	 * We rely on dst being first structure in struct rt6_info
+	 */
+	BUILD_BUG_ON(offsetof(struct rt6_info, dst) != 0);
+	dst_release(&rt->dst);
+}
+
+struct fib6_walker_t {
+	struct list_head lh;
+	struct fib6_node *root, *node;
+	struct rt6_info *leaf;
+	unsigned char state;
+	unsigned char prune;
+	unsigned int skip;
+	unsigned int count;
+	int (*func)(struct fib6_walker_t *);
+	void *args;
+};
+
 struct rt6_statistics {
 	__u32		fib_nodes;
 	__u32		fib_route_nodes;
@@ -129,60 +235,81 @@ struct rt6_statistics {
  *
  */
 
-#define RTPRI_FIREWALL	8		/* Firewall control information	*/
-#define RTPRI_FLOW	16		/* Flow based forwarding rules	*/
-#define RTPRI_KERN_CTL	32		/* Kernel control routes	*/
-
-#define RTPRI_USER_MIN	256		/* Mimimum user priority	*/
-#define RTPRI_USER_MAX	1024		/* Maximum user priority	*/
-
-#define RTPRI_KERN_DFLT	4096		/* Kernel default routes	*/
-
-#define	MAX_FLOW_BACKTRACE	32
 
+struct fib6_table {
+	struct hlist_node	tb6_hlist;
+	u32			tb6_id;
+	rwlock_t		tb6_lock;
+	struct fib6_node	tb6_root;
+	struct inet_peer_base	tb6_peers;
+};
 
-typedef void			(*f_pnode)(struct fib6_node *fn, void *);
+#define RT6_TABLE_UNSPEC	RT_TABLE_UNSPEC
+#define RT6_TABLE_MAIN		RT_TABLE_MAIN
+#define RT6_TABLE_DFLT		RT6_TABLE_MAIN
+#define RT6_TABLE_INFO		RT6_TABLE_MAIN
+#define RT6_TABLE_PREFIX	RT6_TABLE_MAIN
+
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+#define FIB6_TABLE_MIN		1
+#define FIB6_TABLE_MAX		RT_TABLE_MAX
+#define RT6_TABLE_LOCAL		RT_TABLE_LOCAL
+#else
+#define FIB6_TABLE_MIN		RT_TABLE_MAIN
+#define FIB6_TABLE_MAX		FIB6_TABLE_MIN
+#define RT6_TABLE_LOCAL		RT6_TABLE_MAIN
+#endif
 
-extern struct fib6_node		ip6_routing_table;
+typedef struct rt6_info *(*pol_lookup_t)(struct net *,
+					 struct fib6_table *,
+					 struct flowi6 *, int);
 
 /*
  *	exported functions
  */
 
-extern struct fib6_node		*fib6_lookup(struct fib6_node *root,
-					     struct in6_addr *daddr,
-					     struct in6_addr *saddr);
+struct fib6_table *fib6_get_table(struct net *net, u32 id);
+struct fib6_table *fib6_new_table(struct net *net, u32 id);
+struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
+				   int flags, pol_lookup_t lookup);
+
+struct fib6_node *fib6_lookup(struct fib6_node *root,
+			      const struct in6_addr *daddr,
+			      const struct in6_addr *saddr);
 
-struct fib6_node		*fib6_locate(struct fib6_node *root,
-					     struct in6_addr *daddr, int dst_len,
-					     struct in6_addr *saddr, int src_len);
+struct fib6_node *fib6_locate(struct fib6_node *root,
+			      const struct in6_addr *daddr, int dst_len,
+			      const struct in6_addr *saddr, int src_len);
 
-extern void			fib6_clean_tree(struct fib6_node *root,
-						int (*func)(struct rt6_info *, void *arg),
-						int prune, void *arg);
+void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
+		    void *arg);
 
-extern int			fib6_walk(struct fib6_walker_t *w);
-extern int			fib6_walk_continue(struct fib6_walker_t *w);
+int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
+	     struct nlattr *mx, int mx_len);
 
-extern int			fib6_add(struct fib6_node *root,
-					 struct rt6_info *rt,
-					 struct nlmsghdr *nlh,
-					 void *rtattr,
-					 struct netlink_skb_parms *req);
+int fib6_del(struct rt6_info *rt, struct nl_info *info);
 
-extern int			fib6_del(struct rt6_info *rt,
-					 struct nlmsghdr *nlh,
-					 void *rtattr,
-					 struct netlink_skb_parms *req);
+void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info);
 
-extern void			inet6_rt_notify(int event, struct rt6_info *rt,
-						struct nlmsghdr *nlh,
-						struct netlink_skb_parms *req);
+void fib6_run_gc(unsigned long expires, struct net *net, bool force);
 
-extern void			fib6_run_gc(unsigned long dummy);
+void fib6_gc_cleanup(void);
 
-extern void			fib6_gc_cleanup(void);
+int fib6_init(void);
 
-extern void			fib6_init(void);
+int ipv6_route_open(struct inode *inode, struct file *file);
+
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+int fib6_rules_init(void);
+void fib6_rules_cleanup(void);
+#else
+static inline int               fib6_rules_init(void)
+{
+	return 0;
+}
+static inline void              fib6_rules_cleanup(void)
+{
+	return ;
+}
 #endif
 #endif