aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/fib_semantics.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/fib_semantics.c')
-rw-r--r--net/ipv4/fib_semantics.c128
1 files changed, 104 insertions, 24 deletions
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index e5b7182fa09..b10cd43a472 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -140,6 +140,63 @@ const struct fib_prop fib_props[RTN_MAX + 1] = {
},
};
+static void rt_fibinfo_free(struct rtable __rcu **rtp)
+{
+ struct rtable *rt = rcu_dereference_protected(*rtp, 1);
+
+ if (!rt)
+ return;
+
+ /* Not even needed : RCU_INIT_POINTER(*rtp, NULL);
+ * because we waited an RCU grace period before calling
+ * free_fib_info_rcu()
+ */
+
+ dst_free(&rt->dst);
+}
+
+static void free_nh_exceptions(struct fib_nh *nh)
+{
+ struct fnhe_hash_bucket *hash = nh->nh_exceptions;
+ int i;
+
+ for (i = 0; i < FNHE_HASH_SIZE; i++) {
+ struct fib_nh_exception *fnhe;
+
+ fnhe = rcu_dereference_protected(hash[i].chain, 1);
+ while (fnhe) {
+ struct fib_nh_exception *next;
+
+ next = rcu_dereference_protected(fnhe->fnhe_next, 1);
+
+ rt_fibinfo_free(&fnhe->fnhe_rth_input);
+ rt_fibinfo_free(&fnhe->fnhe_rth_output);
+
+ kfree(fnhe);
+
+ fnhe = next;
+ }
+ }
+ kfree(hash);
+}
+
+static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
+{
+ int cpu;
+
+ if (!rtp)
+ return;
+
+ for_each_possible_cpu(cpu) {
+ struct rtable *rt;
+
+ rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1);
+ if (rt)
+ dst_free(&rt->dst);
+ }
+ free_percpu(rtp);
+}
+
/* Release a nexthop info record */
static void free_fib_info_rcu(struct rcu_head *head)
{
@@ -148,6 +205,10 @@ static void free_fib_info_rcu(struct rcu_head *head)
change_nexthops(fi) {
if (nexthop_nh->nh_dev)
dev_put(nexthop_nh->nh_dev);
+ if (nexthop_nh->nh_exceptions)
+ free_nh_exceptions(nexthop_nh);
+ rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output);
+ rt_fibinfo_free(&nexthop_nh->nh_rth_input);
} endfor_nexthops(fi);
release_net(fi->fib_net);
@@ -163,6 +224,12 @@ void free_fib_info(struct fib_info *fi)
return;
}
fib_info_cnt--;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ change_nexthops(fi) {
+ if (nexthop_nh->nh_tclassid)
+ fi->fib_net->ipv4.fib_num_tclassid_users--;
+ } endfor_nexthops(fi);
+#endif
call_rcu(&fi->rcu, free_fib_info_rcu);
}
@@ -232,14 +299,13 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
static struct fib_info *fib_find_info(const struct fib_info *nfi)
{
struct hlist_head *head;
- struct hlist_node *node;
struct fib_info *fi;
unsigned int hash;
hash = fib_info_hashfn(nfi);
head = &fib_info_hash[hash];
- hlist_for_each_entry(fi, node, head, fib_hash) {
+ hlist_for_each_entry(fi, head, fib_hash) {
if (!net_eq(fi->fib_net, nfi->fib_net))
continue;
if (fi->fib_nhs != nfi->fib_nhs)
@@ -248,6 +314,7 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi)
nfi->fib_scope == fi->fib_scope &&
nfi->fib_prefsrc == fi->fib_prefsrc &&
nfi->fib_priority == fi->fib_priority &&
+ nfi->fib_type == fi->fib_type &&
memcmp(nfi->fib_metrics, fi->fib_metrics,
sizeof(u32) * RTAX_MAX) == 0 &&
((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_F_DEAD) == 0 &&
@@ -264,7 +331,6 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi)
int ip_fib_check_default(__be32 gw, struct net_device *dev)
{
struct hlist_head *head;
- struct hlist_node *node;
struct fib_nh *nh;
unsigned int hash;
@@ -272,7 +338,7 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev)
hash = fib_devindex_hashfn(dev->ifindex);
head = &fib_info_devhash[hash];
- hlist_for_each_entry(nh, node, head, nh_hash) {
+ hlist_for_each_entry(nh, head, nh_hash) {
if (nh->nh_dev == dev &&
nh->nh_gw == gw &&
!(nh->nh_flags & RTNH_F_DEAD)) {
@@ -314,7 +380,7 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi)
}
void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
- int dst_len, u32 tb_id, struct nl_info *info,
+ int dst_len, u32 tb_id, const struct nl_info *info,
unsigned int nlm_flags)
{
struct sk_buff *skb;
@@ -325,7 +391,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
if (skb == NULL)
goto errout;
- err = fib_dump_info(skb, info->pid, seq, event, tb_id,
+ err = fib_dump_info(skb, info->portid, seq, event, tb_id,
fa->fa_type, key, dst_len,
fa->fa_tos, fa->fa_info, nlm_flags);
if (err < 0) {
@@ -334,7 +400,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
kfree_skb(skb);
goto errout;
}
- rtnl_notify(skb, info->nl_net, info->pid, RTNLGRP_IPV4_ROUTE,
+ rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_IPV4_ROUTE,
info->nlh, GFP_KERNEL);
return;
errout:
@@ -360,8 +426,9 @@ struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio)
return NULL;
}
-int fib_detect_death(struct fib_info *fi, int order,
- struct fib_info **last_resort, int *last_idx, int dflt)
+static int fib_detect_death(struct fib_info *fi, int order,
+ struct fib_info **last_resort, int *last_idx,
+ int dflt)
{
struct neighbour *n;
int state = NUD_NONE;
@@ -421,6 +488,8 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
#ifdef CONFIG_IP_ROUTE_CLASSID
nla = nla_find(attrs, attrlen, RTA_FLOW);
nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
+ if (nexthop_nh->nh_tclassid)
+ fi->fib_net->ipv4.fib_num_tclassid_users++;
#endif
}
@@ -562,6 +631,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
.daddr = nh->nh_gw,
.flowi4_scope = cfg->fc_scope + 1,
.flowi4_oif = nh->nh_oif,
+ .flowi4_iif = LOOPBACK_IFINDEX,
};
/* It is not necessary, but requires a bit of thinking */
@@ -652,10 +722,10 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash,
for (i = 0; i < old_size; i++) {
struct hlist_head *head = &fib_info_hash[i];
- struct hlist_node *node, *n;
+ struct hlist_node *n;
struct fib_info *fi;
- hlist_for_each_entry_safe(fi, node, n, head, fib_hash) {
+ hlist_for_each_entry_safe(fi, n, head, fib_hash) {
struct hlist_head *dest;
unsigned int new_hash;
@@ -670,10 +740,10 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash,
for (i = 0; i < old_size; i++) {
struct hlist_head *lhead = &fib_info_laddrhash[i];
- struct hlist_node *node, *n;
+ struct hlist_node *n;
struct fib_info *fi;
- hlist_for_each_entry_safe(fi, node, n, lhead, fib_lhash) {
+ hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) {
struct hlist_head *ldest;
unsigned int new_hash;
@@ -734,7 +804,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
unsigned int bytes;
if (!new_size)
- new_size = 1;
+ new_size = 16;
bytes = new_size * sizeof(struct hlist_head *);
new_info_hash = fib_info_hash_alloc(bytes);
new_laddrhash = fib_info_hash_alloc(bytes);
@@ -751,13 +821,13 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
if (fi == NULL)
goto failure;
+ fib_info_cnt++;
if (cfg->fc_mx) {
fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
if (!fi->fib_metrics)
goto failure;
} else
fi->fib_metrics = (u32 *) dst_default_metrics;
- fib_info_cnt++;
fi->fib_net = hold_net(net);
fi->fib_protocol = cfg->fc_protocol;
@@ -765,10 +835,14 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
fi->fib_flags = cfg->fc_flags;
fi->fib_priority = cfg->fc_priority;
fi->fib_prefsrc = cfg->fc_prefsrc;
+ fi->fib_type = cfg->fc_type;
fi->fib_nhs = nhs;
change_nexthops(fi) {
nexthop_nh->nh_parent = fi;
+ nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
+ if (!nexthop_nh->nh_pcpu_rth_output)
+ goto failure;
} endfor_nexthops(fi)
if (cfg->fc_mx) {
@@ -779,9 +853,16 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
int type = nla_type(nla);
if (type) {
+ u32 val;
+
if (type > RTAX_MAX)
goto err_inval;
- fi->fib_metrics[type - 1] = nla_get_u32(nla);
+ val = nla_get_u32(nla);
+ if (type == RTAX_ADVMSS && val > 65535 - 40)
+ val = 65535 - 40;
+ if (type == RTAX_MTU && val > 65535 - 15)
+ val = 65535 - 15;
+ fi->fib_metrics[type - 1] = val;
}
}
}
@@ -810,6 +891,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
nh->nh_flags = cfg->fc_flags;
#ifdef CONFIG_IP_ROUTE_CLASSID
nh->nh_tclassid = cfg->fc_flow;
+ if (nh->nh_tclassid)
+ fi->fib_net->ipv4.fib_num_tclassid_users++;
#endif
#ifdef CONFIG_IP_ROUTE_MULTIPATH
nh->nh_weight = 1;
@@ -911,14 +994,14 @@ failure:
return ERR_PTR(err);
}
-int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
+int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos,
struct fib_info *fi, unsigned int flags)
{
struct nlmsghdr *nlh;
struct rtmsg *rtm;
- nlh = nlmsg_put(skb, pid, seq, event, sizeof(*rtm), flags);
+ nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags);
if (nlh == NULL)
return -EMSGSIZE;
@@ -1014,13 +1097,12 @@ int fib_sync_down_addr(struct net *net, __be32 local)
int ret = 0;
unsigned int hash = fib_laddr_hashfn(local);
struct hlist_head *head = &fib_info_laddrhash[hash];
- struct hlist_node *node;
struct fib_info *fi;
if (fib_info_laddrhash == NULL || local == 0)
return 0;
- hlist_for_each_entry(fi, node, head, fib_lhash) {
+ hlist_for_each_entry(fi, head, fib_lhash) {
if (!net_eq(fi->fib_net, net))
continue;
if (fi->fib_prefsrc == local) {
@@ -1038,13 +1120,12 @@ int fib_sync_down_dev(struct net_device *dev, int force)
struct fib_info *prev_fi = NULL;
unsigned int hash = fib_devindex_hashfn(dev->ifindex);
struct hlist_head *head = &fib_info_devhash[hash];
- struct hlist_node *node;
struct fib_nh *nh;
if (force)
scope = -1;
- hlist_for_each_entry(nh, node, head, nh_hash) {
+ hlist_for_each_entry(nh, head, nh_hash) {
struct fib_info *fi = nh->nh_parent;
int dead;
@@ -1150,7 +1231,6 @@ int fib_sync_up(struct net_device *dev)
struct fib_info *prev_fi;
unsigned int hash;
struct hlist_head *head;
- struct hlist_node *node;
struct fib_nh *nh;
int ret;
@@ -1162,7 +1242,7 @@ int fib_sync_up(struct net_device *dev)
head = &fib_info_devhash[hash];
ret = 0;
- hlist_for_each_entry(nh, node, head, nh_hash) {
+ hlist_for_each_entry(nh, head, nh_hash) {
struct fib_info *fi = nh->nh_parent;
int alive;