summaryrefslogtreecommitdiff
path: root/net/core/lwtunnel.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/lwtunnel.c')
-rw-r--r--net/core/lwtunnel.c155
1 files changed, 106 insertions, 49 deletions
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 0b171756453c..f9d76d85d04f 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -1,13 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* lwtunnel Infrastructure for light weight tunnels like mpls
*
* Authors: Roopa Prabhu, <roopa@cumulusnetworks.com>
- *
- * 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; either version
- * 2 of the License, or (at your option) any later version.
- *
*/
#include <linux/capability.h>
@@ -26,7 +21,12 @@
#include <net/lwtunnel.h>
#include <net/rtnetlink.h>
#include <net/ip6_fib.h>
-#include <net/nexthop.h>
+#include <net/rtnh.h>
+
+#include "dev.h"
+
+DEFINE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled);
+EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_enabled);
#ifdef CONFIG_MODULES
@@ -46,6 +46,13 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type)
return "BPF";
case LWTUNNEL_ENCAP_SEG6_LOCAL:
return "SEG6LOCAL";
+ case LWTUNNEL_ENCAP_RPL:
+ return "RPL";
+ case LWTUNNEL_ENCAP_IOAM6:
+ return "IOAM6";
+ case LWTUNNEL_ENCAP_XFRM:
+ /* module autoload not supported for encap type */
+ return NULL;
case LWTUNNEL_ENCAP_IP6:
case LWTUNNEL_ENCAP_IP:
case LWTUNNEL_ENCAP_NONE:
@@ -103,7 +110,7 @@ int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *ops,
}
EXPORT_SYMBOL_GPL(lwtunnel_encap_del_ops);
-int lwtunnel_build_state(u16 encap_type,
+int lwtunnel_build_state(struct net *net, u16 encap_type,
struct nlattr *encap, unsigned int family,
const void *cfg, struct lwtunnel_state **lws,
struct netlink_ext_ack *extack)
@@ -122,18 +129,18 @@ int lwtunnel_build_state(u16 encap_type,
ret = -EOPNOTSUPP;
rcu_read_lock();
ops = rcu_dereference(lwtun_encaps[encap_type]);
- if (likely(ops && ops->build_state && try_module_get(ops->owner))) {
+ if (likely(ops && ops->build_state && try_module_get(ops->owner)))
found = true;
- ret = ops->build_state(encap, family, cfg, lws, extack);
- if (ret)
- module_put(ops->owner);
- }
rcu_read_unlock();
- /* don't rely on -EOPNOTSUPP to detect match as build_state
- * handlers could return it
- */
- if (!found) {
+ if (found) {
+ ret = ops->build_state(net, encap, family, cfg, lws, extack);
+ if (ret)
+ module_put(ops->owner);
+ } else {
+ /* don't rely on -EOPNOTSUPP to detect match as build_state
+ * handlers could return it
+ */
NL_SET_ERR_MSG_ATTR(extack, encap,
"LWT encapsulation type not supported");
}
@@ -153,21 +160,14 @@ int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack)
return ret;
}
- rcu_read_lock();
- ops = rcu_dereference(lwtun_encaps[encap_type]);
- rcu_read_unlock();
+ ops = rcu_access_pointer(lwtun_encaps[encap_type]);
#ifdef CONFIG_MODULES
if (!ops) {
const char *encap_type_str = lwtunnel_encap_str(encap_type);
if (encap_type_str) {
- __rtnl_unlock();
request_module("rtnl-lwt-%s", encap_type_str);
- rtnl_lock();
-
- rcu_read_lock();
- ops = rcu_dereference(lwtun_encaps[encap_type]);
- rcu_read_unlock();
+ ops = rcu_access_pointer(lwtun_encaps[encap_type]);
}
}
#endif
@@ -195,10 +195,13 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining,
nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
if (nla_entype) {
+ if (nla_len(nla_entype) < sizeof(u16)) {
+ NL_SET_ERR_MSG(extack, "Invalid RTA_ENCAP_TYPE");
+ return -EINVAL;
+ }
encap_type = nla_get_u16(nla_entype);
- if (lwtunnel_valid_encap_type(encap_type,
- extack) != 0)
+ if (lwtunnel_valid_encap_type(encap_type, extack))
return -EOPNOTSUPP;
}
}
@@ -223,7 +226,8 @@ void lwtstate_free(struct lwtunnel_state *lws)
}
EXPORT_SYMBOL_GPL(lwtstate_free);
-int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate)
+int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate,
+ int encap_attr, int encap_type_attr)
{
const struct lwtunnel_encap_ops *ops;
struct nlattr *nest;
@@ -236,7 +240,7 @@ int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate)
lwtstate->type > LWTUNNEL_ENCAP_MAX)
return 0;
- nest = nla_nest_start(skb, RTA_ENCAP);
+ nest = nla_nest_start_noflag(skb, encap_attr);
if (!nest)
return -EMSGSIZE;
@@ -250,7 +254,7 @@ int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate)
if (ret)
goto nla_put_failure;
nla_nest_end(skb, nest);
- ret = nla_put_u16(skb, RTA_ENCAP_TYPE, lwtstate->type);
+ ret = nla_put_u16(skb, encap_type_attr, lwtstate->type);
if (ret)
goto nla_put_failure;
@@ -315,82 +319,132 @@ EXPORT_SYMBOL_GPL(lwtunnel_cmp_encap);
int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct dst_entry *dst = skb_dst(skb);
const struct lwtunnel_encap_ops *ops;
struct lwtunnel_state *lwtstate;
- int ret = -EINVAL;
+ struct dst_entry *dst;
+ int ret;
+
+ local_bh_disable();
- if (!dst)
+ if (dev_xmit_recursion()) {
+ net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
+ __func__);
+ ret = -ENETDOWN;
goto drop;
+ }
+
+ dst = skb_dst(skb);
+ if (!dst) {
+ ret = -EINVAL;
+ goto drop;
+ }
lwtstate = dst->lwtstate;
if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
- lwtstate->type > LWTUNNEL_ENCAP_MAX)
- return 0;
+ lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+ ret = 0;
+ goto out;
+ }
ret = -EOPNOTSUPP;
rcu_read_lock();
ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
- if (likely(ops && ops->output))
+ if (likely(ops && ops->output)) {
+ dev_xmit_recursion_inc();
ret = ops->output(net, sk, skb);
+ dev_xmit_recursion_dec();
+ }
rcu_read_unlock();
if (ret == -EOPNOTSUPP)
goto drop;
- return ret;
+ goto out;
drop:
kfree_skb(skb);
+out:
+ local_bh_enable();
return ret;
}
EXPORT_SYMBOL_GPL(lwtunnel_output);
int lwtunnel_xmit(struct sk_buff *skb)
{
- struct dst_entry *dst = skb_dst(skb);
const struct lwtunnel_encap_ops *ops;
struct lwtunnel_state *lwtstate;
- int ret = -EINVAL;
+ struct dst_entry *dst;
+ int ret;
+
+ local_bh_disable();
- if (!dst)
+ if (dev_xmit_recursion()) {
+ net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
+ __func__);
+ ret = -ENETDOWN;
goto drop;
+ }
+
+ dst = skb_dst(skb);
+ if (!dst) {
+ ret = -EINVAL;
+ goto drop;
+ }
lwtstate = dst->lwtstate;
if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
- lwtstate->type > LWTUNNEL_ENCAP_MAX)
- return 0;
+ lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+ ret = 0;
+ goto out;
+ }
ret = -EOPNOTSUPP;
rcu_read_lock();
ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
- if (likely(ops && ops->xmit))
+ if (likely(ops && ops->xmit)) {
+ dev_xmit_recursion_inc();
ret = ops->xmit(skb);
+ dev_xmit_recursion_dec();
+ }
rcu_read_unlock();
if (ret == -EOPNOTSUPP)
goto drop;
- return ret;
+ goto out;
drop:
kfree_skb(skb);
+out:
+ local_bh_enable();
return ret;
}
EXPORT_SYMBOL_GPL(lwtunnel_xmit);
int lwtunnel_input(struct sk_buff *skb)
{
- struct dst_entry *dst = skb_dst(skb);
const struct lwtunnel_encap_ops *ops;
struct lwtunnel_state *lwtstate;
- int ret = -EINVAL;
+ struct dst_entry *dst;
+ int ret;
+
+ DEBUG_NET_WARN_ON_ONCE(!in_softirq());
- if (!dst)
+ if (dev_xmit_recursion()) {
+ net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
+ __func__);
+ ret = -ENETDOWN;
goto drop;
+ }
+
+ dst = skb_dst(skb);
+ if (!dst) {
+ ret = -EINVAL;
+ goto drop;
+ }
lwtstate = dst->lwtstate;
if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
@@ -400,8 +454,11 @@ int lwtunnel_input(struct sk_buff *skb)
ret = -EOPNOTSUPP;
rcu_read_lock();
ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
- if (likely(ops && ops->input))
+ if (likely(ops && ops->input)) {
+ dev_xmit_recursion_inc();
ret = ops->input(skb);
+ dev_xmit_recursion_dec();
+ }
rcu_read_unlock();
if (ret == -EOPNOTSUPP)
generated by cgit (git 2.34.1) at 2025-12-24 22:51:07 +0000