@@ -337,7 +337,6 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb), *cache_dst = NULL;
- struct in6_addr orig_daddr;
struct ioam6_lwt *ilwt;
int err = -EINVAL;
u32 pkt_cnt;
@@ -352,8 +351,6 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (pkt_cnt % ilwt->freq.n >= ilwt->freq.k)
goto out;
- orig_daddr = ipv6_hdr(skb)->daddr;
-
local_bh_disable();
cache_dst = dst_cache_get(&ilwt->cache);
local_bh_enable();
@@ -422,7 +419,8 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
goto drop;
}
- if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) {
+ /* avoid a lwtunnel_input() loop when dst_entry is the same */
+ if (dst->lwtstate != cache_dst->lwtstate) {
skb_dst_drop(skb);
skb_dst_set(skb, cache_dst);
return dst_output(net, sk, skb);
@@ -247,6 +247,12 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
goto drop;
}
+ /* avoid a lwtunnel_output() loop when dst_entry is the same */
+ if (orig_dst->lwtstate == dst->lwtstate) {
+ dst_release(dst);
+ return orig_dst->lwtstate->orig_output(net, sk, skb);
+ }
+
skb_dst_drop(skb);
skb_dst_set(skb, dst);
@@ -305,6 +311,10 @@ static int rpl_input(struct sk_buff *skb)
skb_dst_set(skb, dst);
}
+ /* avoid a lwtunnel_input() loop when dst_entry is the same */
+ if (lwtst == dst->lwtstate)
+ return dst->lwtstate->orig_input(skb);
+
return dst_input(skb);
drop:
@@ -467,9 +467,16 @@ static int seg6_input_finish(struct net *net, struct sock *sk,
return dst_input(skb);
}
+static int seg6_input_redirect_finish(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ return skb_dst(skb)->lwtstate->orig_input(skb);
+}
+
static int seg6_input_core(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
+ int (*input_func)(struct net *, struct sock *, struct sk_buff *);
struct dst_entry *orig_dst = skb_dst(skb);
struct dst_entry *dst = NULL;
struct lwtunnel_state *lwtst;
@@ -515,12 +522,18 @@ static int seg6_input_core(struct net *net, struct sock *sk,
skb_dst_set(skb, dst);
}
+ /* avoid a lwtunnel_input() loop when dst_entry is the same */
+ if (lwtst == dst->lwtstate)
+ input_func = seg6_input_redirect_finish;
+ else
+ input_func = seg6_input_finish;
+
if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
dev_net(skb->dev), NULL, skb, NULL,
- skb_dst(skb)->dev, seg6_input_finish);
+ skb_dst(skb)->dev, input_func);
- return seg6_input_finish(dev_net(skb->dev), NULL, skb);
+ return input_func(dev_net(skb->dev), NULL, skb);
drop:
kfree_skb(skb);
return err;
@@ -554,6 +567,7 @@ static int seg6_input(struct sk_buff *skb)
static int seg6_output_core(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
+ int (*output_func)(struct net *, struct sock *, struct sk_buff *);
struct dst_entry *orig_dst = skb_dst(skb);
struct dst_entry *dst = NULL;
struct seg6_lwt *slwt;
@@ -598,14 +612,21 @@ static int seg6_output_core(struct net *net, struct sock *sk,
goto drop;
}
- skb_dst_drop(skb);
- skb_dst_set(skb, dst);
+ /* avoid a lwtunnel_output() loop when dst_entry is the same */
+ if (orig_dst->lwtstate == dst->lwtstate) {
+ dst_release(dst);
+ output_func = orig_dst->lwtstate->orig_output;
+ } else {
+ skb_dst_drop(skb);
+ skb_dst_set(skb, dst);
+ output_func = dst_output;
+ }
if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb,
- NULL, skb_dst(skb)->dev, dst_output);
+ NULL, skb_dst(skb)->dev, output_func);
- return dst_output(net, sk, skb);
+ return output_func(net, sk, skb);
drop:
dst_release(dst);
kfree_skb(skb);
When the destination is the same post-transformation, we enter a lwtunnel loop. This is true for ioam6_iptunnel, rpl_iptunnel, and seg6_iptunnel, in both input() and output() handlers respectively, where either dst_input() or dst_output() is called at the end. It happens for instance with the ioam6 inline mode, but can also happen for any of them as long as the post-transformation destination still matches the fib entry. Note that ioam6_iptunnel was already comparing the old and new destination address to prevent the loop, but it is not enough (e.g., other addresses can still match the same subnet). Here is an example for rpl_input(): dump_stack_lvl+0x60/0x80 rpl_input+0x9d/0x320 lwtunnel_input+0x64/0xa0 lwtunnel_input+0x64/0xa0 lwtunnel_input+0x64/0xa0 lwtunnel_input+0x64/0xa0 lwtunnel_input+0x64/0xa0 [...] lwtunnel_input+0x64/0xa0 lwtunnel_input+0x64/0xa0 lwtunnel_input+0x64/0xa0 lwtunnel_input+0x64/0xa0 lwtunnel_input+0x64/0xa0 ip6_sublist_rcv_finish+0x85/0x90 ip6_sublist_rcv+0x236/0x2f0 ... until rpl_do_srh() fails, which means skb_cow_head() failed. This patch prevents that kind of loop by redirecting to the origin input() or output() when the destination is the same post-transformation. Fixes: 8cb3bf8bff3c ("ipv6: ioam: Add support for the ip6ip6 encapsulation") Fixes: a7a29f9c361f ("net: ipv6: add rpl sr tunnel") Fixes: 6c8702c60b88 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels") Signed-off-by: Justin Iurman <justin.iurman@uliege.be> Cc: Alexander Aring <aahringo@redhat.com> Cc: David Lebrun <dlebrun@google.com> --- net/ipv6/ioam6_iptunnel.c | 6 ++---- net/ipv6/rpl_iptunnel.c | 10 ++++++++++ net/ipv6/seg6_iptunnel.c | 33 +++++++++++++++++++++++++++------ 3 files changed, 39 insertions(+), 10 deletions(-)