ipv4: Fix nexthop caching wrt. scoping.

Move the scope value out of the fib alias entries and into fib_info,
so that we always use the correct scope when recomputing the nexthop
cached source address.

Reported-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index cd92b92..e5d66ec 100644 (file)
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -51,7 +51,6 @@ struct fib_nh {
        struct fib_info         *nh_parent;
        unsigned                nh_flags;
        unsigned char           nh_scope;
-       unsigned char           nh_cfg_scope;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
        int                     nh_weight;
        int                     nh_power;
@@ -75,9 +74,10 @@ struct fib_info {
        struct net              *fib_net;
        int                     fib_treeref;
        atomic_t                fib_clntref;
-       int                     fib_dead;
        unsigned                fib_flags;
-       int                     fib_protocol;
+       unsigned char           fib_dead;
+       unsigned char           fib_protocol;
+       unsigned char           fib_scope;
        __be32                  fib_prefsrc;
        u32                     fib_priority;
        u32                     *fib_metrics;

diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index 4ec3238..af0f14a 100644 (file)
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -10,7 +10,6 @@ struct fib_alias {
        struct fib_info         *fa_info;
        u8                      fa_tos;
        u8                      fa_type;
-       u8                      fa_scope;
        u8                      fa_state;
        struct rcu_head         rcu;
 };
@@ -29,7 +28,7 @@ extern void fib_release_info(struct fib_info *);
 extern struct fib_info *fib_create_info(struct fib_config *cfg);
 extern int fib_nh_match(struct fib_config *cfg, struct fib_info *fi);
 extern int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
-                        u32 tb_id, u8 type, u8 scope, __be32 dst,
+                        u32 tb_id, u8 type, __be32 dst,
                         int dst_len, u8 tos, struct fib_info *fi,
                         unsigned int);
 extern void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 2d4bebc..641a5a2 100644 (file)
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -222,7 +222,7 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
        unsigned int mask = (fib_info_hash_size - 1);
        unsigned int val = fi->fib_nhs;
 
-       val ^= fi->fib_protocol;
+       val ^= (fi->fib_protocol << 8) | fi->fib_scope;
        val ^= (__force u32)fi->fib_prefsrc;
        val ^= fi->fib_priority;
        for_nexthops(fi) {
@@ -248,6 +248,7 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi)
                if (fi->fib_nhs != nfi->fib_nhs)
                        continue;
                if (nfi->fib_protocol == fi->fib_protocol &&
+                   nfi->fib_scope == fi->fib_scope &&
                    nfi->fib_prefsrc == fi->fib_prefsrc &&
                    nfi->fib_priority == fi->fib_priority &&
                    memcmp(nfi->fib_metrics, fi->fib_metrics,
@@ -328,7 +329,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
                goto errout;
 
        err = fib_dump_info(skb, info->pid, seq, event, tb_id,
-                           fa->fa_type, fa->fa_scope, key, dst_len,
+                           fa->fa_type, key, dst_len,
                            fa->fa_tos, fa->fa_info, nlm_flags);
        if (err < 0) {
                /* -EMSGSIZE implies BUG in fib_nlmsg_size() */
@@ -699,7 +700,7 @@ __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh)
 {
        nh->nh_saddr = inet_select_addr(nh->nh_dev,
                                        nh->nh_gw,
-                                       nh->nh_cfg_scope);
+                                       nh->nh_parent->fib_scope);
        nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid);
 
        return nh->nh_saddr;
@@ -763,6 +764,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 
        fi->fib_net = hold_net(net);
        fi->fib_protocol = cfg->fc_protocol;
+       fi->fib_scope = cfg->fc_scope;
        fi->fib_flags = cfg->fc_flags;
        fi->fib_priority = cfg->fc_priority;
        fi->fib_prefsrc = cfg->fc_prefsrc;
@@ -864,7 +866,6 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
        }
 
        change_nexthops(fi) {
-               nexthop_nh->nh_cfg_scope = cfg->fc_scope;
                fib_info_update_nh_saddr(net, nexthop_nh);
        } endfor_nexthops(fi)
 
@@ -914,7 +915,7 @@ failure:
 }
 
 int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
-                 u32 tb_id, u8 type, u8 scope, __be32 dst, int dst_len, u8 tos,
+                 u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos,
                  struct fib_info *fi, unsigned int flags)
 {
        struct nlmsghdr *nlh;
@@ -936,7 +937,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
        NLA_PUT_U32(skb, RTA_TABLE, tb_id);
        rtm->rtm_type = type;
        rtm->rtm_flags = fi->fib_flags;
-       rtm->rtm_scope = scope;
+       rtm->rtm_scope = fi->fib_scope;
        rtm->rtm_protocol = fi->fib_protocol;
 
        if (rtm->rtm_dst_len)
@@ -1092,7 +1093,7 @@ void fib_select_default(struct fib_result *res)
        list_for_each_entry_rcu(fa, fa_head, fa_list) {
                struct fib_info *next_fi = fa->fa_info;
 
-               if (fa->fa_scope != res->scope ||
+               if (next_fi->fib_scope != res->scope ||
                    fa->fa_type != RTN_UNICAST)
                        continue;
 

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index ac87a49..90a3ff6 100644 (file)
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1245,7 +1245,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
                        if (fa->fa_info->fib_priority != fi->fib_priority)
                                break;
                        if (fa->fa_type == cfg->fc_type &&
-                           fa->fa_scope == cfg->fc_scope &&
                            fa->fa_info == fi) {
                                fa_match = fa;
                                break;
@@ -1271,7 +1270,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
                        new_fa->fa_tos = fa->fa_tos;
                        new_fa->fa_info = fi;
                        new_fa->fa_type = cfg->fc_type;
-                       new_fa->fa_scope = cfg->fc_scope;
                        state = fa->fa_state;
                        new_fa->fa_state = state & ~FA_S_ACCESSED;
 
@@ -1308,7 +1306,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
        new_fa->fa_info = fi;
        new_fa->fa_tos = tos;
        new_fa->fa_type = cfg->fc_type;
-       new_fa->fa_scope = cfg->fc_scope;
        new_fa->fa_state = 0;
        /*
         * Insert new entry to the list.
@@ -1362,7 +1359,7 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
 
                        if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
                                continue;
-                       if (fa->fa_scope < flp->flowi4_scope)
+                       if (fa->fa_info->fib_scope < flp->flowi4_scope)
                                continue;
                        fib_alias_accessed(fa);
                        err = fib_props[fa->fa_type].error;
@@ -1388,7 +1385,7 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
                                res->prefixlen = plen;
                                res->nh_sel = nhsel;
                                res->type = fa->fa_type;
-                               res->scope = fa->fa_scope;
+                               res->scope = fa->fa_info->fib_scope;
                                res->fi = fi;
                                res->table = tb;
                                res->fa_head = &li->falh;
@@ -1664,7 +1661,7 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
 
                if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) &&
                    (cfg->fc_scope == RT_SCOPE_NOWHERE ||
-                    fa->fa_scope == cfg->fc_scope) &&
+                    fa->fa_info->fib_scope == cfg->fc_scope) &&
                    (!cfg->fc_prefsrc ||
                     fi->fib_prefsrc == cfg->fc_prefsrc) &&
                    (!cfg->fc_protocol ||
@@ -1863,7 +1860,6 @@ static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah,
                                  RTM_NEWROUTE,
                                  tb->tb_id,
                                  fa->fa_type,
-                                 fa->fa_scope,
                                  xkey,
                                  plen,
                                  fa->fa_tos,
@@ -2384,7 +2380,7 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v)
                                seq_indent(seq, iter->depth+1);
                                seq_printf(seq, "  /%d %s %s", li->plen,
                                           rtn_scope(buf1, sizeof(buf1),
-                                                    fa->fa_scope),
+                                                    fa->fa_info->fib_scope),
                                           rtn_type(buf2, sizeof(buf2),
                                                    fa->fa_type));
                                if (fa->fa_tos)