summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorJulian Anastasov <ja@ssi.bg>2015-07-22 10:43:23 +0300
committerDavid S. Miller <davem@davemloft.net>2015-07-25 08:46:11 +0300
commit2392debc2be721a7d5b907cbcbc0ebb858dead01 (patch)
treedbcfe5697a5f9bab9752efe6c76aa74fbe8d493d /net
parent18a912e9a832dcfc7db9e055c7e41701ff5f9e69 (diff)
downloadlinux-2392debc2be721a7d5b907cbcbc0ebb858dead01.tar.xz
ipv4: consider TOS in fib_select_default
fib_select_default considers alternative routes only when res->fi is for the first alias in res->fa_head. In the common case this can happen only when the initial lookup matches the first alias with highest TOS value. This prevents the alternative routes to require specific TOS. This patch solves the problem as follows: - routes that require specific TOS should be returned by fib_select_default only when TOS matches, as already done in fib_table_lookup. This rule implies that depending on the TOS we can have many different lists of alternative gateways and we have to keep the last used gateway (fa_default) in first alias for the TOS instead of using single tb_default value. - as the aliases are ordered by many keys (TOS desc, fib_priority asc), we restrict the possible results to routes with matching TOS and lowest metric (fib_priority) and routes that match any TOS, again with lowest metric. For example, packet with TOS 8 can not use gw3 (not lowest metric), gw4 (different TOS) and gw6 (not lowest metric), all other gateways can be used: tos 8 via gw1 metric 2 <--- res->fa_head and res->fi tos 8 via gw2 metric 2 tos 8 via gw3 metric 3 tos 4 via gw4 tos 0 via gw5 tos 0 via gw6 metric 1 Reported-by: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/ipv4/fib_lookup.h1
-rw-r--r--net/ipv4/fib_semantics.c36
-rw-r--r--net/ipv4/fib_trie.c3
-rw-r--r--net/ipv4/route.c2
4 files changed, 29 insertions, 13 deletions
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index c6211ed60b03..9c02920725db 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -13,6 +13,7 @@ struct fib_alias {
u8 fa_state;
u8 fa_slen;
u32 tb_id;
+ s16 fa_default;
struct rcu_head rcu;
};
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index e1079583b8b7..3a06586b170c 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1202,28 +1202,40 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event)
}
/* Must be invoked inside of an RCU protected region. */
-void fib_select_default(struct fib_result *res)
+void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
{
struct fib_info *fi = NULL, *last_resort = NULL;
struct hlist_head *fa_head = res->fa_head;
struct fib_table *tb = res->table;
u8 slen = 32 - res->prefixlen;
int order = -1, last_idx = -1;
- struct fib_alias *fa;
+ struct fib_alias *fa, *fa1 = NULL;
+ u32 last_prio = res->fi->fib_priority;
+ u8 last_tos = 0;
hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
struct fib_info *next_fi = fa->fa_info;
if (fa->fa_slen != slen)
continue;
+ if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
+ continue;
if (fa->tb_id != tb->tb_id)
continue;
+ if (next_fi->fib_priority > last_prio &&
+ fa->fa_tos == last_tos) {
+ if (last_tos)
+ continue;
+ break;
+ }
+ if (next_fi->fib_flags & RTNH_F_DEAD)
+ continue;
+ last_tos = fa->fa_tos;
+ last_prio = next_fi->fib_priority;
+
if (next_fi->fib_scope != res->scope ||
fa->fa_type != RTN_UNICAST)
continue;
-
- if (next_fi->fib_priority > res->fi->fib_priority)
- break;
if (!next_fi->fib_nh[0].nh_gw ||
next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
continue;
@@ -1233,10 +1245,11 @@ void fib_select_default(struct fib_result *res)
if (!fi) {
if (next_fi != res->fi)
break;
+ fa1 = fa;
} else if (!fib_detect_death(fi, order, &last_resort,
- &last_idx, tb->tb_default)) {
+ &last_idx, fa1->fa_default)) {
fib_result_assign(res, fi);
- tb->tb_default = order;
+ fa1->fa_default = order;
goto out;
}
fi = next_fi;
@@ -1244,20 +1257,21 @@ void fib_select_default(struct fib_result *res)
}
if (order <= 0 || !fi) {
- tb->tb_default = -1;
+ if (fa1)
+ fa1->fa_default = -1;
goto out;
}
if (!fib_detect_death(fi, order, &last_resort, &last_idx,
- tb->tb_default)) {
+ fa1->fa_default)) {
fib_result_assign(res, fi);
- tb->tb_default = order;
+ fa1->fa_default = order;
goto out;
}
if (last_idx >= 0)
fib_result_assign(res, last_resort);
- tb->tb_default = last_idx;
+ fa1->fa_default = last_idx;
out:
return;
}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 15d32612e3c6..81797e065b21 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1171,6 +1171,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
new_fa->fa_state = state & ~FA_S_ACCESSED;
new_fa->fa_slen = fa->fa_slen;
new_fa->tb_id = tb->tb_id;
+ new_fa->fa_default = -1;
err = switchdev_fib_ipv4_add(key, plen, fi,
new_fa->fa_tos,
@@ -1222,6 +1223,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
new_fa->fa_state = 0;
new_fa->fa_slen = slen;
new_fa->tb_id = tb->tb_id;
+ new_fa->fa_default = -1;
/* (Optionally) offload fib entry to switch hardware. */
err = switchdev_fib_ipv4_add(key, plen, fi, tos, cfg->fc_type,
@@ -1990,7 +1992,6 @@ struct fib_table *fib_trie_table(u32 id, struct fib_table *alias)
return NULL;
tb->tb_id = id;
- tb->tb_default = -1;
tb->tb_num_default = 0;
tb->tb_data = (alias ? alias->__data : tb->__data);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d0362a2de3d3..e681b852ced1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2176,7 +2176,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
if (!res.prefixlen &&
res.table->tb_num_default > 1 &&
res.type == RTN_UNICAST && !fl4->flowi4_oif)
- fib_select_default(&res);
+ fib_select_default(fl4, &res);
if (!fl4->saddr)
fl4->saddr = FIB_RES_PREFSRC(net, res);