diff mbox series

[net,2/3] net: ipv6: fix lwtunnel loops in ioam6, rpl and seg6

Message ID 20250209193840.20509-3-justin.iurman@uliege.be (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series several fixes for ioam6, rpl and seg6 lwtunnels | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag present in non-next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers fail 1 blamed authors not CCed: alex.aring@gmail.com; 1 maintainers not CCed: alex.aring@gmail.com
netdev/build_clang success Errors and warnings before: 4 this patch: 4
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success Fixes tag looks correct
netdev/build_allmodconfig_warn success Errors and warnings before: 2 this patch: 2
netdev/checkpatch warning WARNING: function definition argument 'struct net *' should also have an identifier name WARNING: function definition argument 'struct sk_buff *' should also have an identifier name WARNING: function definition argument 'struct sock *' should also have an identifier name
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2025-02-11--00-00 (tests: 889)

Commit Message

Justin Iurman Feb. 9, 2025, 7:38 p.m. UTC
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(-)
diff mbox series

Patch

diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index 2c383c12a431..6c61b306f2e9 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -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);
diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index c26bf284459f..dc004e9aa649 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -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:
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 6045e850b4bf..9fce6b2dbd54 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -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);