[IPV6]: Policy Routing Rules

Adds support for policy routing rules including a new
local table for routes with a local destination.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

9 files changed, 329 insertions, 12 deletions

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index facd9ee37b76..bf353538ae93 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -889,6 +889,8 @@ enum rtnetlink_groups {
         RTNLGRP_NOP4,
         RTNLGRP_IPV6_PREFIX,
 #define RTNLGRP_IPV6_PREFIX     RTNLGRP_IPV6_PREFIX
+        RTNLGRP_IPV6_RULE,
+#define RTNLGRP_IPV6_RULE       RTNLGRP_IPV6_RULE
         __RTNLGRP_MAX
 };
 #define RTNLGRP_MAX     (__RTNLGRP_MAX - 1)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 818411519c89..7b47e8d5a765 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -155,7 +155,6 @@ struct fib6_table {
 
 #define RT6_TABLE_UNSPEC        RT_TABLE_UNSPEC
 #define RT6_TABLE_MAIN          RT_TABLE_MAIN
-#define RT6_TABLE_LOCAL         RT6_TABLE_MAIN
 #define RT6_TABLE_DFLT          RT6_TABLE_MAIN
 #define RT6_TABLE_INFO          RT6_TABLE_MAIN
 #define RT6_TABLE_PREFIX        RT6_TABLE_MAIN
@@ -163,9 +162,11 @@ struct fib6_table {
 #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
 
 #define RT6_F_STRICT            1
@@ -221,5 +222,11 @@ extern void			fib6_run_gc(unsigned long dummy);
 extern void                     fib6_gc_cleanup(void);
 
 extern void                     fib6_init(void);
+
+extern void                     fib6_rules_init(void);
+extern void                     fib6_rules_cleanup(void);
+extern int                      fib6_rules_dump(struct sk_buff *,
+                                                struct netlink_callback *);
+
 #endif
 #endif
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index d49c8c90eb68..9bfa3cc6cedb 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -41,6 +41,11 @@ struct pol_chain {
 
 extern struct rt6_info  ip6_null_entry;
 
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+extern struct rt6_info  ip6_prohibit_entry;
+extern struct rt6_info  ip6_blk_hole_entry;
+#endif
+
 extern int ip6_rt_gc_interval;
 
 extern void                     ip6_route_input(struct sk_buff *skb);
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 159c63d99c81..36a6c2b79889 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -139,6 +139,7 @@ config IPV6_TUNNEL
 config IPV6_MULTIPLE_TABLES
         bool "IPv6: Multiple Routing Tables"
         depends on IPV6 && EXPERIMENTAL
+        select FIB_RULES
         ---help---
           Support multiple routing tables.
 
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 386e0a626948..9eebf6091279 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -13,6 +13,7 @@ ipv6-objs :=	af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o sit.o \
 ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \
         xfrm6_output.o
 ipv6-$(CONFIG_NETFILTER) += netfilter.o
+ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o
 ipv6-objs += $(ipv6-y)
 
 obj-$(CONFIG_INET6_AH) += ah6.o
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 318767fcefdc..ed766eebc022 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3528,6 +3528,7 @@ static struct rtnetlink_link inet6_rtnetlink_table[RTM_NR_MSGTYPES] = {
         [RTM_DELROUTE - RTM_BASE] = { .doit     = inet6_rtm_delroute, },
         [RTM_GETROUTE - RTM_BASE] = { .doit     = inet6_rtm_getroute,
                                       .dumpit   = inet6_dump_fib, },
+        [RTM_GETRULE  - RTM_BASE] = { .dumpit   = fib6_rules_dump,   },
 };
 
 static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
new file mode 100644
index 000000000000..c3c8195744ee
--- /dev/null
+++ b/net/ipv6/fib6_rules.c
@@ -0,0 +1,251 @@
+/*
+ * net/ipv6/fib6_rules.c        IPv6 Routing Policy Rules
+ *
+ * Copyright (C)2003-2006 Helsinki University of Technology
+ * Copyright (C)2003-2006 USAGI/WIDE Project
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License as
+ *      published by the Free Software Foundation, version 2.
+ *
+ * Authors
+ *      Thomas Graf             <tgraf@suug.ch>
+ *      Ville Nuorvala          <vnuorval@tcs.hut.fi>
+ */
+
+#include <linux/config.h>
+#include <linux/netdevice.h>
+
+#include <net/fib_rules.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/netlink.h>
+
+struct fib6_rule
+{
+        struct fib_rule         common;
+        struct rt6key           src;
+        struct rt6key           dst;
+        u8                      tclass;
+};
+
+static struct fib_rules_ops fib6_rules_ops;
+
+static struct fib6_rule main_rule = {
+        .common = {
+                .refcnt =       ATOMIC_INIT(2),
+                .pref =         0x7FFE,
+                .action =       FR_ACT_TO_TBL,
+                .table =        RT6_TABLE_MAIN,
+        },
+};
+
+static struct fib6_rule local_rule = {
+        .common = {
+                .refcnt =       ATOMIC_INIT(2),
+                .pref =         0,
+                .action =       FR_ACT_TO_TBL,
+                .table =        RT6_TABLE_LOCAL,
+                .flags =        FIB_RULE_PERMANENT,
+        },
+};
+
+static LIST_HEAD(fib6_rules);
+
+struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags,
+                                   pol_lookup_t lookup)
+{
+        struct fib_lookup_arg arg = {
+                .lookup_ptr = lookup,
+        };
+
+        fib_rules_lookup(&fib6_rules_ops, fl, flags, &arg);
+        if (arg.rule)
+                fib_rule_put(arg.rule);
+
+        return (struct dst_entry *) arg.result;
+}
+
+int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
+                     int flags, struct fib_lookup_arg *arg)
+{
+        struct rt6_info *rt = NULL;
+        struct fib6_table *table;
+        pol_lookup_t lookup = arg->lookup_ptr;
+
+        switch (rule->action) {
+        case FR_ACT_TO_TBL:
+                break;
+        case FR_ACT_UNREACHABLE:
+                rt = &ip6_null_entry;
+                goto discard_pkt;
+        default:
+        case FR_ACT_BLACKHOLE:
+                rt = &ip6_blk_hole_entry;
+                goto discard_pkt;
+        case FR_ACT_PROHIBIT:
+                rt = &ip6_prohibit_entry;
+                goto discard_pkt;
+        }
+
+        table = fib6_get_table(rule->table);
+        if (table)
+                rt = lookup(table, flp, flags);
+
+        if (rt != &ip6_null_entry)
+                goto out;
+
+        dst_release(&rt->u.dst);
+discard_pkt:
+        dst_hold(&rt->u.dst);
+out:
+        arg->result = rt;
+        return rt == NULL ? -EAGAIN : 0;
+}
+
+
+static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
+{
+        struct fib6_rule *r = (struct fib6_rule *) rule;
+
+        if (!ipv6_prefix_equal(&fl->fl6_dst, &r->dst.addr, r->dst.plen))
+                return 0;
+
+        if ((flags & RT6_F_HAS_SADDR) &&
+            !ipv6_prefix_equal(&fl->fl6_src, &r->src.addr, r->src.plen))
+                return 0;
+
+        return 1;
+}
+
+static struct nla_policy fib6_rule_policy[RTA_MAX+1] __read_mostly = {
+        [FRA_IFNAME]    = { .type = NLA_STRING },
+        [FRA_PRIORITY]  = { .type = NLA_U32 },
+        [FRA_SRC]       = { .minlen = sizeof(struct in6_addr) },
+        [FRA_DST]       = { .minlen = sizeof(struct in6_addr) },
+};
+
+static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
+                               struct nlmsghdr *nlh, struct fib_rule_hdr *frh,
+                               struct nlattr **tb)
+{
+        int err = -EINVAL;
+        struct fib6_rule *rule6 = (struct fib6_rule *) rule;
+
+        if (frh->src_len > 128 || frh->dst_len > 128 ||
+            (frh->tos & ~IPV6_FLOWINFO_MASK))
+                goto errout;
+
+        if (rule->action == FR_ACT_TO_TBL) {
+                if (rule->table == RT6_TABLE_UNSPEC)
+                        goto errout;
+
+                if (fib6_new_table(rule->table) == NULL) {
+                        err = -ENOBUFS;
+                        goto errout;
+                }
+        }
+
+        if (tb[FRA_SRC])
+                nla_memcpy(&rule6->src.addr, tb[FRA_SRC],
+                           sizeof(struct in6_addr));
+
+        if (tb[FRA_DST])
+                nla_memcpy(&rule6->dst.addr, tb[FRA_DST],
+                           sizeof(struct in6_addr));
+
+        rule6->src.plen = frh->src_len;
+        rule6->dst.plen = frh->dst_len;
+        rule6->tclass = frh->tos;
+
+        err = 0;
+errout:
+        return err;
+}
+
+static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
+                             struct nlattr **tb)
+{
+        struct fib6_rule *rule6 = (struct fib6_rule *) rule;
+
+        if (frh->src_len && (rule6->src.plen != frh->src_len))
+                return 0;
+
+        if (frh->dst_len && (rule6->dst.plen != frh->dst_len))
+                return 0;
+
+        if (frh->tos && (rule6->tclass != frh->tos))
+                return 0;
+
+        if (tb[FRA_SRC] &&
+            nla_memcmp(tb[FRA_SRC], &rule6->src.addr, sizeof(struct in6_addr)))
+                return 0;
+
+        if (tb[FRA_DST] &&
+            nla_memcmp(tb[FRA_DST], &rule6->dst.addr, sizeof(struct in6_addr)))
+                return 0;
+
+        return 1;
+}
+
+static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
+                          struct nlmsghdr *nlh, struct fib_rule_hdr *frh)
+{
+        struct fib6_rule *rule6 = (struct fib6_rule *) rule;
+
+        frh->family = AF_INET6;
+        frh->dst_len = rule6->dst.plen;
+        frh->src_len = rule6->src.plen;
+        frh->tos = rule6->tclass;
+
+        if (rule6->dst.plen)
+                NLA_PUT(skb, FRA_DST, sizeof(struct in6_addr),
+                        &rule6->dst.addr);
+
+        if (rule6->src.plen)
+                NLA_PUT(skb, FRA_SRC, sizeof(struct in6_addr),
+                        &rule6->src.addr);
+
+        return 0;
+
+nla_put_failure:
+        return -ENOBUFS;
+}
+
+int fib6_rules_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+        return fib_rules_dump(skb, cb, AF_INET6);
+}
+
+static u32 fib6_rule_default_pref(void)
+{
+        return 0x3FFF;
+}
+
+static struct fib_rules_ops fib6_rules_ops = {
+        .family                 = AF_INET6,
+        .rule_size              = sizeof(struct fib6_rule),
+        .action                 = fib6_rule_action,
+        .match                  = fib6_rule_match,
+        .configure              = fib6_rule_configure,
+        .compare                = fib6_rule_compare,
+        .fill                   = fib6_rule_fill,
+        .default_pref           = fib6_rule_default_pref,
+        .nlgroup                = RTNLGRP_IPV6_RULE,
+        .policy                 = fib6_rule_policy,
+        .rules_list             = &fib6_rules,
+        .owner                  = THIS_MODULE,
+};
+
+void __init fib6_rules_init(void)
+{
+        list_add_tail(&local_rule.common.list, &fib6_rules);
+        list_add_tail(&main_rule.common.list, &fib6_rules);
+
+        fib_rules_register(&fib6_rules_ops);
+}
+
+void fib6_rules_cleanup(void)
+{
+        fib_rules_unregister(&fib6_rules_ops);
+}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index fcd7da830aca..ce226c14bef5 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -159,6 +159,15 @@ static struct fib6_table fib6_main_tbl = {
 
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 
+static struct fib6_table fib6_local_tbl = {
+        .tb6_id         = RT6_TABLE_LOCAL,
+        .tb6_lock       = RW_LOCK_UNLOCKED,
+        .tb6_root       = {
+                .leaf           = &ip6_null_entry,
+                .fn_flags       = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO,
+        },
+};
+
 #define FIB_TABLE_HASHSZ 256
 static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ];
 
@@ -228,20 +237,10 @@ struct fib6_table *fib6_get_table(u32 id)
         return NULL;
 }
 
-struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags,
-                                   pol_lookup_t lookup)
-{
-        /*
-         * TODO: Add rule lookup
-         */
-        struct fib6_table *table = fib6_get_table(RT6_TABLE_MAIN);
-
-        return (struct dst_entry *) lookup(table, fl, flags);
-}
-
 static void __init fib6_tables_init(void)
 {
         fib6_link_table(&fib6_main_tbl);
+        fib6_link_table(&fib6_local_tbl);
 }
 
 #else
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 73efdadb9ab8..438977e2085d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -140,6 +140,50 @@ struct rt6_info ip6_null_entry = {
         .rt6i_ref       = ATOMIC_INIT(1),
 };
 
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+
+struct rt6_info ip6_prohibit_entry = {
+        .u = {
+                .dst = {
+                        .__refcnt       = ATOMIC_INIT(1),
+                        .__use          = 1,
+                        .dev            = &loopback_dev,
+                        .obsolete       = -1,
+                        .error          = -EACCES,
+                        .metrics        = { [RTAX_HOPLIMIT - 1] = 255, },
+                        .input          = ip6_pkt_discard,
+                        .output         = ip6_pkt_discard_out,
+                        .ops            = &ip6_dst_ops,
+                        .path           = (struct dst_entry*)&ip6_prohibit_entry,
+                }
+        },
+        .rt6i_flags     = (RTF_REJECT | RTF_NONEXTHOP),
+        .rt6i_metric    = ~(u32) 0,
+        .rt6i_ref       = ATOMIC_INIT(1),
+};
+
+struct rt6_info ip6_blk_hole_entry = {
+        .u = {
+                .dst = {
+                        .__refcnt       = ATOMIC_INIT(1),
+                        .__use          = 1,
+                        .dev            = &loopback_dev,
+                        .obsolete       = -1,
+                        .error          = -EINVAL,
+                        .metrics        = { [RTAX_HOPLIMIT - 1] = 255, },
+                        .input          = ip6_pkt_discard,
+                        .output         = ip6_pkt_discard_out,
+                        .ops            = &ip6_dst_ops,
+                        .path           = (struct dst_entry*)&ip6_blk_hole_entry,
+                }
+        },
+        .rt6i_flags     = (RTF_REJECT | RTF_NONEXTHOP),
+        .rt6i_metric    = ~(u32) 0,
+        .rt6i_ref       = ATOMIC_INIT(1),
+};
+
+#endif
+
 /* allocate dst with ip6_dst_ops */
 static __inline__ struct rt6_info *ip6_dst_alloc(void)
 {
@@ -2408,10 +2452,16 @@ void __init ip6_route_init(void)
 #ifdef CONFIG_XFRM
         xfrm6_init();
 #endif
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+        fib6_rules_init();
+#endif
 }
 
 void ip6_route_cleanup(void)
 {
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+        fib6_rules_cleanup();
+#endif
 #ifdef CONFIG_PROC_FS
         proc_net_remove("ipv6_route");
         proc_net_remove("rt6_stats");