From db3d0e0e5d4bc5ab4fe445b9f413d1b486508ca5 Mon Sep 17 00:00:00 2001
From: Xiang Mei <xmei5@asu.edu>
Date: Sun, 12 Jul 2026 16:42:01 -0700
Subject: netfilter: nf_conntrack_sip: widen NAT rewrite delta to s32 in
 sip_help_tcp()

sip_help_tcp() stores the size change of each NAT-rewritten SIP message
in s16 diff and accumulates it in s16 tdiff, but a single message can
grow by more than S16_MAX while the packet stays under the 65535
enlarge_skb() limit: nf_nat_sip() rewrites every matching URI, and a long
Contact list expands the message by tens of kilobytes. diff then wraps,
and "datalen = datalen + diff - msglen" yields a huge unsigned datalen,
so the next iteration's ct_sip_get_header() reads past the linearized skb
tail.

Widen diff, tdiff and the seq_adjust hook to s32. Both are bounded by the
65535 byte packet limit, and the seqadj core is already s32
(nf_ct_seqadj_set() takes s32), so no previously accepted input is
rejected.

  BUG: KASAN: use-after-free in ct_sip_get_header (net/netfilter/nf_conntrack_sip.c:464)
  Read of size 1 at addr ffff888010800000 by task ksoftirqd/1/25
   ct_sip_get_header (net/netfilter/nf_conntrack_sip.c:464)
   sip_help_tcp (net/netfilter/nf_conntrack_sip.c:1694)
   nf_confirm (net/netfilter/nf_conntrack_proto.c:183)
   nf_hook_slow (net/netfilter/core.c:619)
   ip6_output (net/ipv6/ip6_output.c:246)
   ip6_forward (net/ipv6/ip6_output.c:690)
   ipv6_rcv (net/ipv6/ip6_input.c:351)
   __netif_receive_skb_one_core (net/core/dev.c:6212)
   process_backlog (net/core/dev.c:6676)
   __napi_poll (net/core/dev.c:7735)
   net_rx_action (net/core/dev.c:7955)
   handle_softirqs (kernel/softirq.c:622)
   run_ksoftirqd (kernel/softirq.c:1076)
   ...

Fixes: f5b321bd37fb ("netfilter: nf_conntrack_sip: add TCP support")
Reported-by: Weiming Shi <bestswngs@gmail.com>
Link: https://patch.msgid.link/netfilter-devel/20260712234201.3213635-1-xmei5@asu.edu
Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nf_conntrack_sip.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h
index dbc614dfe0d5..aafa0c04f917 100644
--- a/include/linux/netfilter/nf_conntrack_sip.h
+++ b/include/linux/netfilter/nf_conntrack_sip.h
@@ -115,7 +115,7 @@ struct nf_nat_sip_hooks {
 			    unsigned int *datalen);
 
 	void (*seq_adjust)(struct sk_buff *skb,
-			   unsigned int protoff, s16 off);
+			   unsigned int protoff, s32 off);
 
 	unsigned int (*expect)(struct sk_buff *skb,
 			       unsigned int protoff,
-- 
cgit 


From 4aa63842fc92de1bce59d4709a0d32e718890bb2 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 13 Jul 2026 00:26:04 +0200
Subject: netfilter: nf_conntrack_expect: add and use
 nf_ct_expect_related_pair()

Add a new function to insert a pair of expectations, this is required by
the SIP and H323 NAT helpers. The spinlock is held to check if there is
a slot for both expectations, in such case, insert them.

This removes the need for nf_ct_unexpect_related() inside the loop to
find a pair of consecutive ports, otherwise inserting expectations whose
dead flag is already set on can happen.

Bump master_help->expecting for the expectation class after checking if
the expectation fits in the master expectation list, which is needed for
this new _pair() function variant to run the eviction routine including
the preallocated slot for the first expectation in the pair.

Fixes: b8b09dc2bf35 ("netfilter: nf_conntrack_expect: use conntrack GC to reap expectations")
Reported-by: Jaeyeong Lee <iostreampy@proton.me>
Link: https://patch.msgid.link/178377968720.33756.12204817361601593230@proton.me/
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_expect.h |  3 +++
 net/ipv4/netfilter/nf_nat_h323.c            | 22 ++++++------------
 net/netfilter/nf_conntrack_expect.c         | 35 ++++++++++++++++++++++++++++-
 net/netfilter/nf_nat_sip.c                  | 20 +++++------------
 4 files changed, 50 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index c024345c9bd8..26d6babd92fc 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -161,6 +161,9 @@ static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect,
 	return nf_ct_expect_related_report(expect, 0, 0, flags);
 }
 
+int nf_ct_expect_related_pair(struct nf_conntrack_expect *expect[],
+			      unsigned int flag);
+
 struct nf_conn_help;
 void nf_ct_expectation_gc(struct nf_conn_help *master_help);
 
diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c
index 183e8a3ff2ba..6bcd6734769b 100644
--- a/net/ipv4/netfilter/nf_nat_h323.c
+++ b/net/ipv4/netfilter/nf_nat_h323.c
@@ -182,6 +182,7 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct,
 			struct nf_conntrack_expect *rtp_exp,
 			struct nf_conntrack_expect *rtcp_exp)
 {
+	struct nf_conntrack_expect *rtp_pair[2] = { rtp_exp, rtcp_exp };
 	struct nf_ct_h323_master *info = nfct_help_data(ct);
 	int dir = CTINFO2DIR(ctinfo);
 	int i;
@@ -227,22 +228,13 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct,
 		int ret;
 
 		rtp_exp->tuple.dst.u.udp.port = htons(nated_port);
-		ret = nf_ct_expect_related(rtp_exp, 0);
+		rtcp_exp->tuple.dst.u.udp.port = htons(nated_port + 1);
+		ret = nf_ct_expect_related_pair(rtp_pair, 0);
 		if (ret == 0) {
-			rtcp_exp->tuple.dst.u.udp.port =
-			    htons(nated_port + 1);
-			ret = nf_ct_expect_related(rtcp_exp, 0);
-			if (ret == 0)
-				break;
-			else if (ret == -EBUSY) {
-				nf_ct_unexpect_related(rtp_exp);
-				continue;
-			} else if (ret < 0) {
-				nf_ct_unexpect_related(rtp_exp);
-				nated_port = 0;
-				break;
-			}
-		} else if (ret != -EBUSY) {
+			break;
+		} else if (ret == -EBUSY) {
+			continue;
+		} else if (ret < 0) {
 			nated_port = 0;
 			break;
 		}
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 7ae68d60586a..8a3b9e33e94f 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -427,7 +427,6 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp,
 		exp->timeout += helper->expect_policy[exp->class].timeout * HZ;
 
 	hlist_add_head_rcu(&exp->lnode, &master_help->expectations);
-	master_help->expecting[exp->class]++;
 
 	hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]);
 	cnet = nf_ct_pernet(net);
@@ -534,6 +533,7 @@ int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
 	if (ret < 0)
 		goto out;
 
+	master_help->expecting[expect->class]++;
 	nf_ct_expect_insert(expect, master_help);
 
 	nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report);
@@ -546,6 +546,39 @@ out:
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_related_report);
 
+int nf_ct_expect_related_pair(struct nf_conntrack_expect *expect[],
+			      unsigned int flags)
+{
+	struct nf_conn_help *master_help;
+	int i, ret;
+
+	spin_lock_bh(&nf_conntrack_expect_lock);
+	master_help = nfct_help(expect[0]->master);
+	if (!master_help || master_help != nfct_help(expect[1]->master)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	for (i = 0; i < 2; i++) {
+		ret = __nf_ct_expect_check(expect[i], master_help, flags);
+		if (ret < 0) {
+			if (i == 1)
+				master_help->expecting[expect[0]->class]--;
+			goto out;
+		}
+		master_help->expecting[expect[i]->class]++;
+	}
+
+	for (i = 0; i < 2; i++) {
+		nf_ct_expect_insert(expect[i], master_help);
+		nf_ct_expect_event_report(IPEXP_NEW, expect[i], 0, 0);
+	}
+out:
+	spin_unlock_bh(&nf_conntrack_expect_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_ct_expect_related_pair);
+
 void nf_ct_expect_iterate_destroy(bool (*iter)(struct nf_conntrack_expect *e, void *data),
 				  void *data)
 {
diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c
index a93eaf0f7d30..133bd713fe0c 100644
--- a/net/netfilter/nf_nat_sip.c
+++ b/net/netfilter/nf_nat_sip.c
@@ -592,6 +592,7 @@ static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff,
 				     unsigned int medialen,
 				     union nf_inet_addr *rtp_addr)
 {
+	struct nf_conntrack_expect *rtp_pair[2] = { rtp_exp, rtcp_exp };
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
@@ -622,24 +623,15 @@ static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff,
 		int ret;
 
 		rtp_exp->tuple.dst.u.udp.port = htons(port);
-		ret = nf_ct_expect_related(rtp_exp,
-					   NF_CT_EXP_F_SKIP_MASTER);
-		if (ret == -EBUSY)
-			continue;
-		else if (ret < 0) {
-			port = 0;
-			break;
-		}
 		rtcp_exp->tuple.dst.u.udp.port = htons(port + 1);
-		ret = nf_ct_expect_related(rtcp_exp,
-					   NF_CT_EXP_F_SKIP_MASTER);
+
+		ret = nf_ct_expect_related_pair(rtp_pair,
+						NF_CT_EXP_F_SKIP_MASTER);
 		if (ret == 0)
 			break;
-		else if (ret == -EBUSY) {
-			nf_ct_unexpect_related(rtp_exp);
+		else if (ret == -EBUSY)
 			continue;
-		} else if (ret < 0) {
-			nf_ct_unexpect_related(rtp_exp);
+		else if (ret < 0) {
 			port = 0;
 			break;
 		}
-- 
cgit 


From f4f699790590bd0896c48a71e9232a65198f92f0 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 16 Jul 2026 10:13:37 +0200
Subject: netfilter: nf_tables: make nft_object rhltable per table

The nft_object rhltable is global, this allows for accessing objects
that are being dismangled from lookup path by other existing netns.
Given the nft_obj_destroy() releases the object inmediately, this might
lead to use-after-free of these objects that are being released.
Make the existing rhltable per table to address this issue to deal with
with the nft_rcv_nl_event() path too.

Update nft_obj_lookup() to take the table as non-const, otherwise,
compiler complains when passing the objname_ht to rhltable_lookup().

Fixes: 4d44175aa5bb ("netfilter: nf_tables: handle nft_object lookups via rhltable")
Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |  4 +++-
 net/netfilter/nf_tables_api.c     | 34 ++++++++++++++++------------------
 2 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 9d844354c4d9..3be612145c13 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1294,6 +1294,7 @@ static inline void nft_use_inc_restore(u32 *use)
  *	@sets: sets in the table
  *	@objects: stateful objects in the table
  *	@flowtables: flow tables in the table
+ *	@objname_ht: hashtable for objects lookup by name
  *	@hgenerator: handle generator state
  *	@handle: table handle
  *	@use: number of chain references to this table
@@ -1313,6 +1314,7 @@ struct nft_table {
 	struct list_head		sets;
 	struct list_head		objects;
 	struct list_head		flowtables;
+	struct rhltable			objname_ht;
 	u64				hgenerator;
 	u64				handle;
 	u32				use;
@@ -1400,7 +1402,7 @@ static inline void *nft_obj_data(const struct nft_object *obj)
 #define nft_expr_obj(expr)	*((struct nft_object **)nft_expr_priv(expr))
 
 struct nft_object *nft_obj_lookup(const struct net *net,
-				  const struct nft_table *table,
+				  struct nft_table *table,
 				  const struct nlattr *nla, u32 objtype,
 				  u8 genmask);
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index a9eaf9455c77..af357f6c5070 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -45,8 +45,6 @@ enum {
 	NFT_VALIDATE_DO,
 };
 
-static struct rhltable nft_objname_ht;
-
 static u32 nft_chain_hash(const void *data, u32 len, u32 seed);
 static u32 nft_chain_hash_obj(const void *data, u32 len, u32 seed);
 static int nft_chain_hash_cmp(struct rhashtable_compare_arg *, const void *);
@@ -1635,6 +1633,10 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info,
 	if (err)
 		goto err_chain_ht;
 
+	err = rhltable_init(&table->objname_ht, &nft_objname_ht_params);
+	if (err < 0)
+		goto err_obj_ht;
+
 	INIT_LIST_HEAD(&table->chains);
 	INIT_LIST_HEAD(&table->sets);
 	INIT_LIST_HEAD(&table->objects);
@@ -1653,6 +1655,8 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info,
 	list_add_tail_rcu(&table->list, &nft_net->tables);
 	return 0;
 err_trans:
+	rhltable_destroy(&table->objname_ht);
+err_obj_ht:
 	rhltable_destroy(&table->chains_ht);
 err_chain_ht:
 	kfree(table->udata);
@@ -1819,6 +1823,7 @@ static void nf_tables_table_destroy(struct nft_table *table)
 		return;
 
 	rhltable_destroy(&table->chains_ht);
+	rhltable_destroy(&table->objname_ht);
 	kfree(table->name);
 	kfree(table->udata);
 	kfree(table);
@@ -8086,7 +8091,7 @@ void nft_unregister_obj(struct nft_object_type *obj_type)
 EXPORT_SYMBOL_GPL(nft_unregister_obj);
 
 struct nft_object *nft_obj_lookup(const struct net *net,
-				  const struct nft_table *table,
+				  struct nft_table *table,
 				  const struct nlattr *nla, u32 objtype,
 				  u8 genmask)
 {
@@ -8102,7 +8107,7 @@ struct nft_object *nft_obj_lookup(const struct net *net,
 		     !lockdep_commit_lock_is_held(net));
 
 	rcu_read_lock();
-	list = rhltable_lookup(&nft_objname_ht, &k, nft_objname_ht_params);
+	list = rhltable_lookup(&table->objname_ht, &k, nft_objname_ht_params);
 	if (!list)
 		goto out;
 
@@ -8382,7 +8387,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info,
 	if (err < 0)
 		goto err_trans;
 
-	err = rhltable_insert(&nft_objname_ht, &obj->rhlhead,
+	err = rhltable_insert(&table->objname_ht, &obj->rhlhead,
 			      nft_objname_ht_params);
 	if (err < 0)
 		goto err_obj_ht;
@@ -8567,8 +8572,8 @@ nf_tables_getobj_single(u32 portid, const struct nfnl_info *info,
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_cur(info->net);
 	u8 family = info->nfmsg->nfgen_family;
-	const struct nft_table *table;
 	struct net *net = info->net;
+	struct nft_table *table;
 	struct nft_object *obj;
 	struct sk_buff *skb2;
 	u32 objtype;
@@ -10437,9 +10442,9 @@ static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain)
 		nf_tables_commit_chain_free_rules_old(g0);
 }
 
-static void nft_obj_del(struct nft_object *obj)
+static void nft_obj_del(struct nft_table *table, struct nft_object *obj)
 {
-	rhltable_remove(&nft_objname_ht, &obj->rhlhead, nft_objname_ht_params);
+	rhltable_remove(&table->objname_ht, &obj->rhlhead, nft_objname_ht_params);
 	list_del_rcu(&obj->list);
 }
 
@@ -11124,7 +11129,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 			break;
 		case NFT_MSG_DELOBJ:
 		case NFT_MSG_DESTROYOBJ:
-			nft_obj_del(nft_trans_obj(trans));
+			nft_obj_del(table, nft_trans_obj(trans));
 			nf_tables_obj_notify(&ctx, nft_trans_obj(trans),
 					     trans->msg_type);
 			break;
@@ -11416,7 +11421,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 				nft_trans_destroy(trans);
 			} else {
 				nft_use_dec_restore(&table->use);
-				nft_obj_del(nft_trans_obj(trans));
+				nft_obj_del(table, nft_trans_obj(trans));
 			}
 			break;
 		case NFT_MSG_DELOBJ:
@@ -12043,7 +12048,7 @@ static void __nft_release_table(struct net *net, struct nft_table *table)
 		nft_set_destroy(&ctx, set);
 	}
 	list_for_each_entry_safe(obj, ne, &table->objects, list) {
-		nft_obj_del(obj);
+		nft_obj_del(table, obj);
 		nft_use_dec(&table->use);
 		nft_obj_destroy(&ctx, obj);
 	}
@@ -12225,10 +12230,6 @@ static int __init nf_tables_module_init(void)
 	if (err < 0)
 		goto err_netdev_notifier;
 
-	err = rhltable_init(&nft_objname_ht, &nft_objname_ht_params);
-	if (err < 0)
-		goto err_rht_objname;
-
 	err = nft_offload_init();
 	if (err < 0)
 		goto err_offload;
@@ -12251,8 +12252,6 @@ err_nfnl_subsys:
 err_netlink_notifier:
 	nft_offload_exit();
 err_offload:
-	rhltable_destroy(&nft_objname_ht);
-err_rht_objname:
 	unregister_netdevice_notifier(&nf_tables_flowtable_notifier);
 err_netdev_notifier:
 	nf_tables_core_module_exit();
@@ -12274,7 +12273,6 @@ static void __exit nf_tables_module_exit(void)
 	unregister_pernet_subsys(&nf_tables_net_ops);
 	cancel_work_sync(&trans_gc_work);
 	rcu_barrier();
-	rhltable_destroy(&nft_objname_ht);
 	nf_tables_core_module_exit();
 }
 
-- 
cgit 


From e876b75b9020a97bbdc79721e7fc749024891c65 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Wed, 22 Jul 2026 13:15:15 +0300
Subject: ipvs: fix the checksum validations

ip_vs_in_icmp_v6() is missing checksum validation for ICMPv6
packets from clients. In fact, as for TCP/UDP we should
validate the checksum for ICMP packets only when we
mangle the packets on MASQ or on reply for tunnel.

Also, Sashiko points out that handle_response_icmp() being
common for IPv4 and IPv6 is missing the pseudo-header
calculation while validating ICMPv6 messages from real
servers which is a problem if checksum is not validated
by the hardware.

Fix the problems by creating ip_vs_checksum_common_check()
helper and use it for TCP/UDP/ICMP both for IPv4 and IPv6.
Rely on the nf_checksum() for validating the ICMP messages
but use it also for TCP and UDP.

Use correct IP offset for IP_VS_DBG_RL_PKT for TCP/UDP/SCTP.

IPVS packets (TCP/UDP/SCTP/ICMP) do not need checksum
validation on LOCAL_OUT (local clients or local real
servers) and on FORWARD (traffic from servers on LAN).
Do it only on LOCAL_IN, in case nf_checksum() is not
called on PRE_ROUTING.

Also, ip_vs_checksum_complete() can be marked static.

Fixes: 2a3b791e6e11 ("IPVS: Add/adjust Netfilter hook functions and helpers for v6")
Link: https://sashiko.dev/#/patchset/20260708180315.77413-1-ja%40ssi.bg
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/ip_vs.h                   | 31 ++++++++++++++++++++--
 net/netfilter/ipvs/ip_vs_core.c       | 20 +++++++++++---
 net/netfilter/ipvs/ip_vs_proto_sctp.c | 15 ++++++-----
 net/netfilter/ipvs/ip_vs_proto_tcp.c  | 44 ++++++------------------------
 net/netfilter/ipvs/ip_vs_proto_udp.c  | 50 ++++++++---------------------------
 5 files changed, 74 insertions(+), 86 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 417ff51f62fc..d8f9ddb0fb38 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -25,7 +25,9 @@
 #include <linux/netfilter.h>		/* for union nf_inet_addr */
 #include <linux/ip.h>
 #include <linux/ipv6.h>			/* for struct ipv6hdr */
+#include <net/route.h>
 #include <net/ipv6.h>
+#include <net/ip6_fib.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <net/netfilter/nf_conntrack.h>
 #endif
@@ -2066,8 +2068,6 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		       struct ip_vs_conn *cp, int dir);
 #endif
 
-__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset);
-
 static inline __wsum ip_vs_check_diff4(__be32 old, __be32 new, __wsum oldsum)
 {
 	__be32 diff[2] = { ~old, new };
@@ -2093,6 +2093,33 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum)
 	return csum_partial(diff, sizeof(diff), oldsum);
 }
 
+static inline bool ip_vs_checksum_needed(struct sk_buff *skb, int af)
+{
+	/* Checksum unnecessary or already validated? */
+	if (skb_csum_unnecessary(skb))
+		return false;
+	/* LOCAL_OUT ? */
+	if (!skb->dev || skb->dev->flags & IFF_LOOPBACK)
+		return false;
+	/* !LOCAL_IN (FORWARD) ? */
+	if (af == AF_INET6) {
+		if (!(dst_rt6_info(skb_dst(skb))->rt6i_flags & RTF_LOCAL))
+			return false;
+	} else {
+		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL))
+			return false;
+	}
+	return true;
+}
+
+static inline bool ip_vs_checksum_common_check(struct sk_buff *skb,
+					       int offset, int proto, int af)
+{
+	if (!ip_vs_checksum_needed(skb, af))
+		return true;
+	return !nf_checksum(skb, NF_INET_LOCAL_IN, offset, proto, af);
+}
+
 /* Forget current conntrack (unconfirmed) and attach notrack entry */
 static inline void ip_vs_notrack(struct sk_buff *skb)
 {
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index bafab93451d0..c8b512725e6e 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -867,7 +867,7 @@ static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; }
 
 #endif
 
-__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset)
+static __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset)
 {
 	return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0));
 }
@@ -1038,13 +1038,14 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 				unsigned int offset, unsigned int ihl,
 				unsigned int hooknum)
 {
+	int iproto = af == AF_INET6 ? IPPROTO_ICMPV6 : IPPROTO_ICMP;
 	unsigned int verdict = NF_DROP;
 
 	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
 		goto after_nat;
 
 	/* Ensure the checksum is correct */
-	if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) {
+	if (!ip_vs_checksum_common_check(skb, ihl, iproto, af)) {
 		/* Failed checksum! */
 		IP_VS_DBG_BUF(1, "Forward ICMP: failed checksum from %s!\n",
 			      IP_VS_DBG_ADDR(af, snet));
@@ -1898,7 +1899,8 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 	verdict = NF_DROP;
 
 	/* Ensure the checksum is correct */
-	if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) {
+	if ((IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ || tunnel) &&
+	    !ip_vs_checksum_common_check(skb, ihl, IPPROTO_ICMP, AF_INET)) {
 		/* Failed checksum! */
 		IP_VS_DBG(1, "Incoming ICMP: failed checksum from %pI4!\n",
 			  &iph->saddr);
@@ -2064,6 +2066,18 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
 		goto out;
 	}
 
+	verdict = NF_DROP;
+
+	/* Ensure the checksum is correct */
+	if (IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ &&
+	    !ip_vs_checksum_common_check(skb, iph->len, IPPROTO_ICMPV6,
+					 AF_INET6)) {
+		/* Failed checksum! */
+		IP_VS_DBG(1, "Incoming ICMPv6: failed checksum from %pI6c!\n",
+			  &iph->saddr);
+		goto out;
+	}
+
 	/* do the statistics and put it back */
 	ip_vs_in_stats(cp, skb);
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index c67317be17df..f6f732b7dfa8 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -11,7 +11,7 @@
 
 static int
 sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
-		unsigned int sctphoff);
+		struct ip_vs_iphdr *iph);
 
 static int
 sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,
@@ -109,7 +109,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		int ret;
 
 		/* Some checks before mangling */
-		if (!sctp_csum_check(cp->af, skb, pp, sctphoff))
+		if (!sctp_csum_check(cp->af, skb, pp, iph))
 			return 0;
 
 		/* Call application helper if needed */
@@ -157,7 +157,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		int ret;
 
 		/* Some checks before mangling */
-		if (!sctp_csum_check(cp->af, skb, pp, sctphoff))
+		if (!sctp_csum_check(cp->af, skb, pp, iph))
 			return 0;
 
 		/* Call application helper if needed */
@@ -187,19 +187,22 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 
 static int
 sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
-		unsigned int sctphoff)
+		struct ip_vs_iphdr *iph)
 {
+	unsigned int sctphoff = iph->len;
 	struct sctphdr *sh;
 	__le32 cmp, val;
 
+	if (!ip_vs_checksum_needed(skb, af))
+		return 1;
 	sh = (struct sctphdr *)(skb->data + sctphoff);
 	cmp = sh->checksum;
 	val = sctp_compute_cksum(skb, sctphoff);
 
 	if (val != cmp) {
 		/* CRC failure, dump it. */
-		IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
-				"Failed checksum for");
+		IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off,
+				 "Failed checksum for");
 		return 0;
 	}
 	return 1;
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index f86b763efcc4..533fce3e5e4e 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -29,7 +29,7 @@
 
 static int
 tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
-	       unsigned int tcphoff);
+	       struct ip_vs_iphdr *iph);
 
 static int
 tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,
@@ -166,7 +166,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		int ret;
 
 		/* Some checks before mangling */
-		if (!tcp_csum_check(cp->af, skb, pp, tcphoff))
+		if (!tcp_csum_check(cp->af, skb, pp, iph))
 			return 0;
 
 		/* Call application helper if needed */
@@ -244,7 +244,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		int ret;
 
 		/* Some checks before mangling */
-		if (!tcp_csum_check(cp->af, skb, pp, tcphoff))
+		if (!tcp_csum_check(cp->af, skb, pp, iph))
 			return 0;
 
 		/*
@@ -302,41 +302,13 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 
 static int
 tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
-	       unsigned int tcphoff)
+	       struct ip_vs_iphdr *iph)
 {
-	switch (skb->ip_summed) {
-	case CHECKSUM_NONE:
-		skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0);
-		fallthrough;
-	case CHECKSUM_COMPLETE:
-#ifdef CONFIG_IP_VS_IPV6
-		if (af == AF_INET6) {
-			if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-					    &ipv6_hdr(skb)->daddr,
-					    skb->len - tcphoff,
-					    IPPROTO_TCP,
-					    skb->csum)) {
-				IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
-						 "Failed checksum for");
-				return 0;
-			}
-		} else
-#endif
-			if (csum_tcpudp_magic(ip_hdr(skb)->saddr,
-					      ip_hdr(skb)->daddr,
-					      skb->len - tcphoff,
-					      ip_hdr(skb)->protocol,
-					      skb->csum)) {
-				IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
-						 "Failed checksum for");
-				return 0;
-			}
-		break;
-	default:
-		/* No need to checksum. */
-		break;
+	if (!ip_vs_checksum_common_check(skb, iph->len, IPPROTO_TCP, af)) {
+		IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off,
+				 "Failed checksum for");
+		return 0;
 	}
-
 	return 1;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 58f9e255927e..de3597347542 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -25,7 +25,7 @@
 
 static int
 udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
-	       unsigned int udphoff);
+	       struct ip_vs_iphdr *iph);
 
 static int
 udp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,
@@ -155,7 +155,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		int ret;
 
 		/* Some checks before mangling */
-		if (!udp_csum_check(cp->af, skb, pp, udphoff))
+		if (!udp_csum_check(cp->af, skb, pp, iph))
 			return 0;
 
 		/*
@@ -238,7 +238,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		int ret;
 
 		/* Some checks before mangling */
-		if (!udp_csum_check(cp->af, skb, pp, udphoff))
+		if (!udp_csum_check(cp->af, skb, pp, iph))
 			return 0;
 
 		/*
@@ -298,48 +298,20 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 
 static int
 udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
-	       unsigned int udphoff)
+	       struct ip_vs_iphdr *iph)
 {
 	struct udphdr _udph, *uh;
 
-	uh = skb_header_pointer(skb, udphoff, sizeof(_udph), &_udph);
+	uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph);
 	if (uh == NULL)
 		return 0;
 
-	if (uh->check != 0) {
-		switch (skb->ip_summed) {
-		case CHECKSUM_NONE:
-			skb->csum = skb_checksum(skb, udphoff,
-						 skb->len - udphoff, 0);
-			fallthrough;
-		case CHECKSUM_COMPLETE:
-#ifdef CONFIG_IP_VS_IPV6
-			if (af == AF_INET6) {
-				if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-						    &ipv6_hdr(skb)->daddr,
-						    skb->len - udphoff,
-						    IPPROTO_UDP,
-						    skb->csum)) {
-					IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
-							 "Failed checksum for");
-					return 0;
-				}
-			} else
-#endif
-				if (csum_tcpudp_magic(ip_hdr(skb)->saddr,
-						      ip_hdr(skb)->daddr,
-						      skb->len - udphoff,
-						      ip_hdr(skb)->protocol,
-						      skb->csum)) {
-					IP_VS_DBG_RL_PKT(0, af, pp, skb, 0,
-							 "Failed checksum for");
-					return 0;
-				}
-			break;
-		default:
-			/* No need to checksum. */
-			break;
-		}
+	if (!uh->check)
+		return 1;
+	if (!ip_vs_checksum_common_check(skb, iph->len, IPPROTO_UDP, af)) {
+		IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off,
+				 "Failed checksum for");
+		return 0;
 	}
 	return 1;
 }
-- 
cgit 


From 15cab31a3730e05f0767b922a7450e5d784b2607 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Wed, 22 Jul 2026 13:15:16 +0300
Subject: ipvs: fix places with wrong packet offsets

The offsets we use to packet headers and payloads should be
based on skb->data. We even already respect non-zero
network offset in ip_vs_fill_iph_skb() but some places
do it wrongly and support only zero offset which is expected
for the IP layer where IPVS has hooks.

Change all places that instead of skb->data use offsets based
on the network header (skb_network_header, ip_hdr, etc) because
this doubles the network offset as noted by Sashiko.

For ip_vs_nat_icmp_v6() we can even rely on the IPv6 header
parsing done by the caller.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Link: https://sashiko.dev/#/patchset/20260710143733.29741-2-fw%40strlen.de
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/ip_vs.h                   |  15 ++--
 net/netfilter/ipvs/ip_vs_app.c        |   4 +-
 net/netfilter/ipvs/ip_vs_core.c       | 133 +++++++++++++++++-----------------
 net/netfilter/ipvs/ip_vs_proto_sctp.c |   4 +-
 net/netfilter/ipvs/ip_vs_proto_tcp.c  |   4 +-
 net/netfilter/ipvs/ip_vs_proto_udp.c  |   4 +-
 net/netfilter/ipvs/ip_vs_xmit.c       |  26 ++++---
 7 files changed, 97 insertions(+), 93 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index d8f9ddb0fb38..4a10a01d6e2f 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1974,8 +1974,9 @@ int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
 int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-		    struct ip_vs_protocol *pp, int offset,
-		    unsigned int hooknum, struct ip_vs_iphdr *iph);
+		    struct ip_vs_protocol *pp, unsigned int toff,
+		    unsigned int wlen, unsigned int hooknum,
+		    struct ip_vs_iphdr *ciph);
 void ip_vs_dest_dst_rcu_free(struct rcu_head *head);
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -1988,8 +1989,9 @@ int ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 int ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		     struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
 int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-		       struct ip_vs_protocol *pp, int offset,
-		       unsigned int hooknum, struct ip_vs_iphdr *iph);
+		       struct ip_vs_protocol *pp, unsigned int toff,
+		       unsigned int wlen, unsigned int hooknum,
+		       struct ip_vs_iphdr *ciph);
 #endif
 
 #ifdef CONFIG_SYSCTL
@@ -2061,11 +2063,12 @@ static inline bool ip_vs_conn_use_hash2(struct ip_vs_conn *cp)
 }
 
 void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
-		    struct ip_vs_conn *cp, int dir);
+		    struct ip_vs_conn *cp, int dir, unsigned int toff);
 
 #ifdef CONFIG_IP_VS_IPV6
 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
-		       struct ip_vs_conn *cp, int dir);
+		       struct ip_vs_conn *cp, int dir, unsigned int toff,
+		       struct ip_vs_iphdr *ciph);
 #endif
 
 static inline __wsum ip_vs_check_diff4(__be32 old, __be32 new, __wsum oldsum)
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index b0e00be85cb1..11cbdbaf561d 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -367,7 +367,7 @@ static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb,
 	if (skb_ensure_writable(skb, ipvsh->len + sizeof(*th)))
 		return 0;
 
-	th = (struct tcphdr *)(skb_network_header(skb) + ipvsh->len);
+	th = (struct tcphdr *)(skb->data + ipvsh->len);
 
 	/*
 	 *	Remember seq number in case this pkt gets resized
@@ -443,7 +443,7 @@ static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb,
 	if (skb_ensure_writable(skb, ipvsh->len + sizeof(*th)))
 		return 0;
 
-	th = (struct tcphdr *)(skb_network_header(skb) + ipvsh->len);
+	th = (struct tcphdr *)(skb->data + ipvsh->len);
 
 	/*
 	 *	Remember seq number in case this pkt gets resized
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index c8b512725e6e..cd5eb71543ec 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -924,13 +924,12 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af,
  * - inout: 1=in->out, 0=out->in
  */
 void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
-		    struct ip_vs_conn *cp, int inout)
+		    struct ip_vs_conn *cp, int inout, unsigned int toff)
 {
 	struct iphdr *iph	 = ip_hdr(skb);
-	unsigned int icmp_offset = iph->ihl*4;
-	struct icmphdr *icmph	 = (struct icmphdr *)(skb_network_header(skb) +
-						      icmp_offset);
+	struct icmphdr *icmph	 = (struct icmphdr *)(skb->data + toff);
 	struct iphdr *ciph	 = (struct iphdr *)(icmph + 1);
+	unsigned int coff __maybe_unused = toff + sizeof(struct icmphdr);
 
 	if (inout) {
 		iph->saddr = cp->vaddr.ip;
@@ -957,48 +956,45 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
 
 	/* And finally the ICMP checksum */
 	icmph->checksum = 0;
-	icmph->checksum = ip_vs_checksum_complete(skb, icmp_offset);
+	icmph->checksum = ip_vs_checksum_complete(skb, toff);
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 	if (inout)
-		IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph,
-			"Forwarding altered outgoing ICMP");
+		IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff,
+			      "Forwarding altered outgoing ICMP");
 	else
-		IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph,
-			"Forwarding altered incoming ICMP");
+		IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff,
+			      "Forwarding altered incoming ICMP");
 }
 
 #ifdef CONFIG_IP_VS_IPV6
 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
-		    struct ip_vs_conn *cp, int inout)
+		       struct ip_vs_conn *cp, int inout, unsigned int toff,
+		       struct ip_vs_iphdr *ciph)
 {
 	struct ipv6hdr *iph	 = ipv6_hdr(skb);
-	unsigned int icmp_offset = 0;
-	unsigned int offs	 = 0; /* header offset*/
 	int protocol;
 	struct icmp6hdr *icmph;
-	struct ipv6hdr *ciph;
-	unsigned short fragoffs;
+	struct ipv6hdr *cih;
 
-	ipv6_find_hdr(skb, &icmp_offset, IPPROTO_ICMPV6, &fragoffs, NULL);
-	icmph = (struct icmp6hdr *)(skb_network_header(skb) + icmp_offset);
-	offs = icmp_offset + sizeof(struct icmp6hdr);
-	ciph = (struct ipv6hdr *)(skb_network_header(skb) + offs);
+	icmph = (struct icmp6hdr *)(skb->data + toff);
+	cih = (struct ipv6hdr *)(skb->data + ciph->off);
 
-	protocol = ipv6_find_hdr(skb, &offs, -1, &fragoffs, NULL);
+	protocol = ciph->protocol;
 
 	if (inout) {
 		iph->saddr = cp->vaddr.in6;
-		ciph->daddr = cp->vaddr.in6;
+		cih->daddr = cp->vaddr.in6;
 	} else {
 		iph->daddr = cp->daddr.in6;
-		ciph->saddr = cp->daddr.in6;
+		cih->saddr = cp->daddr.in6;
 	}
 
 	/* the TCP/UDP/SCTP port */
-	if (!fragoffs && (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol ||
-			  IPPROTO_SCTP == protocol)) {
-		__be16 *ports = (void *)(skb_network_header(skb) + offs);
+	if (!ciph->fragoffs &&
+	    (protocol == IPPROTO_TCP  || protocol == IPPROTO_UDP ||
+	     protocol == IPPROTO_SCTP)) {
+		__be16 *ports = (void *)(skb->data + ciph->len);
 
 		IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__,
 			      ntohs(inout ? ports[1] : ports[0]),
@@ -1011,19 +1007,17 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
 
 	/* And finally the ICMP checksum */
 	icmph->icmp6_cksum = ~csum_ipv6_magic(&iph->saddr, &iph->daddr,
-					      skb->len - icmp_offset,
+					      skb->len - toff,
 					      IPPROTO_ICMPV6, 0);
-	skb->csum_start = skb_network_header(skb) - skb->head + icmp_offset;
+	skb->csum_start = skb_headroom(skb) + toff;
 	skb->csum_offset = offsetof(struct icmp6hdr, icmp6_cksum);
 	skb->ip_summed = CHECKSUM_PARTIAL;
 
 	if (inout)
-		IP_VS_DBG_PKT(11, AF_INET6, pp, skb,
-			      (void *)ciph - (void *)iph,
+		IP_VS_DBG_PKT(11, AF_INET6, pp, skb, ciph->off,
 			      "Forwarding altered outgoing ICMPv6");
 	else
-		IP_VS_DBG_PKT(11, AF_INET6, pp, skb,
-			      (void *)ciph - (void *)iph,
+		IP_VS_DBG_PKT(11, AF_INET6, pp, skb, ciph->off,
 			      "Forwarding altered incoming ICMPv6");
 }
 #endif
@@ -1033,37 +1027,38 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
  */
 static int handle_response_icmp(int af, struct sk_buff *skb,
 				union nf_inet_addr *snet,
-				__u8 protocol, struct ip_vs_conn *cp,
+				struct ip_vs_conn *cp,
 				struct ip_vs_protocol *pp,
-				unsigned int offset, unsigned int ihl,
-				unsigned int hooknum)
+				struct ip_vs_iphdr *ciph,
+				unsigned int toff, unsigned int hooknum)
 {
 	int iproto = af == AF_INET6 ? IPPROTO_ICMPV6 : IPPROTO_ICMP;
 	unsigned int verdict = NF_DROP;
+	unsigned int ctoff = ciph->len;
 
 	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
 		goto after_nat;
 
 	/* Ensure the checksum is correct */
-	if (!ip_vs_checksum_common_check(skb, ihl, iproto, af)) {
+	if (!ip_vs_checksum_common_check(skb, toff, iproto, af)) {
 		/* Failed checksum! */
 		IP_VS_DBG_BUF(1, "Forward ICMP: failed checksum from %s!\n",
 			      IP_VS_DBG_ADDR(af, snet));
 		goto out;
 	}
 
-	if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol ||
-	    IPPROTO_SCTP == protocol)
-		offset += 2 * sizeof(__u16);
-	if (skb_ensure_writable(skb, offset))
+	if (ciph->protocol == IPPROTO_TCP || ciph->protocol == IPPROTO_UDP ||
+	    ciph->protocol == IPPROTO_SCTP)
+		ctoff += 2 * sizeof(__u16);
+	if (skb_ensure_writable(skb, ctoff))
 		goto out;
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6)
-		ip_vs_nat_icmp_v6(skb, pp, cp, 1);
+		ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, ciph);
 	else
 #endif
-		ip_vs_nat_icmp(skb, pp, cp, 1);
+		ip_vs_nat_icmp(skb, pp, cp, 1, toff);
 
 	if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum))
 		goto out;
@@ -1091,9 +1086,9 @@ out:
  *	Currently handles error types - unreachable, quench, ttl exceeded.
  */
 static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb,
-			  int *related, unsigned int hooknum)
+			  int *related, unsigned int hooknum,
+			  struct ip_vs_iphdr *ipvsh)
 {
-	struct iphdr *iph;
 	struct icmphdr	_icmph, *ic;
 	struct iphdr	_ciph, *cih;	/* The ip header contained within the ICMP */
 	struct ip_vs_iphdr ciph;
@@ -1108,17 +1103,19 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb,
 	if (ip_is_fragment(ip_hdr(skb))) {
 		if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum)))
 			return NF_STOLEN;
+		if (!ip_vs_fill_iph_skb(AF_INET, skb, false, ipvsh))
+			return NF_ACCEPT;
 	}
 
-	iph = ip_hdr(skb);
-	offset = ihl = iph->ihl * 4;
+	ihl = ipvsh->len;
+	offset = ipvsh->len;
 	ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph);
 	if (ic == NULL)
 		return NF_DROP;
 
 	IP_VS_DBG(12, "Outgoing ICMP (%d,%d) %pI4->%pI4\n",
 		  ic->type, ntohs(icmp_id(ic)),
-		  &iph->saddr, &iph->daddr);
+		  &ipvsh->saddr.ip, &ipvsh->daddr.ip);
 
 	/*
 	 * Work through seeing if this is for us.
@@ -1137,7 +1134,7 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb,
 	/* Now find the contained IP header */
 	offset += sizeof(_icmph);
 	cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
-	if (cih == NULL)
+	if (!(cih && cih->version == 4 && cih->ihl >= 5))
 		return NF_ACCEPT; /* The packet looks wrong, ignore */
 
 	pp = ip_vs_proto_get(cih->protocol);
@@ -1160,9 +1157,9 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb,
 	if (!cp)
 		return NF_ACCEPT;
 
-	snet.ip = iph->saddr;
-	return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp,
-				    pp, ciph.len, ihl, hooknum);
+	snet.ip = ipvsh->saddr.ip;
+	return handle_response_icmp(AF_INET, skb, &snet, cp, pp, &ciph, ihl,
+				    hooknum);
 }
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -1175,7 +1172,6 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
 	union nf_inet_addr snet;
-	unsigned int offset;
 
 	*related = 1;
 	ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph);
@@ -1218,9 +1214,8 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
 		return NF_ACCEPT;
 
 	snet.in6 = ciph.saddr.in6;
-	offset = ciph.len;
-	return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp,
-				    pp, offset, ipvsh->len, hooknum);
+	return handle_response_icmp(AF_INET6, skb, &snet, cp, pp, &ciph,
+				    ipvsh->len, hooknum);
 }
 #endif
 
@@ -1546,7 +1541,8 @@ ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *stat
 #endif
 		if (unlikely(iph.protocol == IPPROTO_ICMP)) {
 			int related;
-			int verdict = ip_vs_out_icmp(ipvs, skb, &related, hooknum);
+			int verdict = ip_vs_out_icmp(ipvs, skb, &related,
+						     hooknum, &iph);
 
 			if (related)
 				return verdict;
@@ -1754,9 +1750,8 @@ unk:
  */
 static int
 ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
-	      unsigned int hooknum)
+	      unsigned int hooknum, struct ip_vs_iphdr *iph)
 {
-	struct iphdr *iph;
 	struct icmphdr	_icmph, *ic;
 	struct iphdr	_ciph, *cih;	/* The ip header contained within the ICMP */
 	struct ip_vs_iphdr ciph;
@@ -1766,7 +1761,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 	unsigned int offset, offset2, ihl, verdict;
 	bool tunnel, new_cp = false;
 	union nf_inet_addr *raddr;
-	char *outer_proto = "IPIP";
+	char *outer_proto __maybe_unused = "IPIP";
 	unsigned int hlen_ipip;
 	int ulen = 0;
 
@@ -1776,17 +1771,19 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 	if (ip_is_fragment(ip_hdr(skb))) {
 		if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum)))
 			return NF_STOLEN;
+		if (!ip_vs_fill_iph_skb(AF_INET, skb, false, iph))
+			return NF_ACCEPT;
 	}
 
-	iph = ip_hdr(skb);
-	offset = ihl = iph->ihl * 4;
+	ihl = iph->len;
+	offset = iph->len;
 	ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph);
 	if (ic == NULL)
 		return NF_DROP;
 
 	IP_VS_DBG(12, "Incoming ICMP (%d,%d) %pI4->%pI4\n",
 		  ic->type, ntohs(icmp_id(ic)),
-		  &iph->saddr, &iph->daddr);
+		  &iph->saddr.ip, &iph->daddr.ip);
 
 	/*
 	 * Work through seeing if this is for us.
@@ -1903,7 +1900,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 	    !ip_vs_checksum_common_check(skb, ihl, IPPROTO_ICMP, AF_INET)) {
 		/* Failed checksum! */
 		IP_VS_DBG(1, "Incoming ICMP: failed checksum from %pI4!\n",
-			  &iph->saddr);
+			  &iph->saddr.ip);
 		goto out;
 	}
 
@@ -1974,7 +1971,8 @@ ignore_tunnel:
 	if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol ||
 	    IPPROTO_SCTP == cih->protocol)
 		offset += 2 * sizeof(__u16);
-	verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph);
+	verdict = ip_vs_icmp_xmit(skb, cp, pp, iph->len, offset, hooknum,
+				  &ciph);
 
 out:
 	if (likely(!new_cp))
@@ -2087,7 +2085,8 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
 	    IPPROTO_SCTP == ciph.protocol)
 		offset += 2 * sizeof(__u16); /* Also mangle ports */
 
-	verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum, &ciph);
+	verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, iph->len, offset, hooknum,
+				     &ciph);
 
 out:
 	if (likely(!new_cp))
@@ -2166,7 +2165,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state
 		if (unlikely(iph.protocol == IPPROTO_ICMP)) {
 			int related;
 			int verdict = ip_vs_in_icmp(ipvs, skb, &related,
-						    hooknum);
+						    hooknum, &iph);
 
 			if (related)
 				return verdict;
@@ -2302,6 +2301,7 @@ ip_vs_forward_icmp(void *priv, struct sk_buff *skb,
 		   const struct nf_hook_state *state)
 {
 	struct netns_ipvs *ipvs = net_ipvs(state->net);
+	struct ip_vs_iphdr iphdr;
 	int r;
 
 	/* ipvs enabled in this netns ? */
@@ -2311,10 +2311,9 @@ ip_vs_forward_icmp(void *priv, struct sk_buff *skb,
 	if (state->pf == NFPROTO_IPV4) {
 		if (ip_hdr(skb)->protocol != IPPROTO_ICMP)
 			return NF_ACCEPT;
+		ip_vs_fill_iph_skb(AF_INET, skb, false, &iphdr);
 #ifdef CONFIG_IP_VS_IPV6
 	} else {
-		struct ip_vs_iphdr iphdr;
-
 		ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr);
 
 		if (iphdr.protocol != IPPROTO_ICMPV6)
@@ -2324,7 +2323,7 @@ ip_vs_forward_icmp(void *priv, struct sk_buff *skb,
 #endif
 	}
 
-	return ip_vs_in_icmp(ipvs, skb, &r, state->hook);
+	return ip_vs_in_icmp(ipvs, skb, &r, state->hook, &iphdr);
 }
 
 static const struct nf_hook_ops ip_vs_ops4[] = {
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index f6f732b7dfa8..3dbd3096e163 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -121,7 +121,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 			payload_csum = true;
 	}
 
-	sctph = (void *) skb_network_header(skb) + sctphoff;
+	sctph = (void *)skb->data + sctphoff;
 
 	/* Only update csum if we really have to */
 	if (sctph->source != cp->vport || payload_csum ||
@@ -169,7 +169,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 			payload_csum = true;
 	}
 
-	sctph = (void *) skb_network_header(skb) + sctphoff;
+	sctph = (void *)skb->data + sctphoff;
 
 	/* Only update csum if we really have to */
 	if (sctph->dest != cp->dport || payload_csum ||
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 533fce3e5e4e..99a286fdc90c 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -179,7 +179,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 			payload_csum = true;
 	}
 
-	tcph = (void *)skb_network_header(skb) + tcphoff;
+	tcph = (void *)skb->data + tcphoff;
 	tcph->source = cp->vport;
 
 	/* Adjust TCP checksums */
@@ -260,7 +260,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 			payload_csum = true;
 	}
 
-	tcph = (void *)skb_network_header(skb) + tcphoff;
+	tcph = (void *)skb->data + tcphoff;
 	tcph->dest = cp->dport;
 
 	/*
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index de3597347542..f32785682402 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -170,7 +170,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 			payload_csum = true;
 	}
 
-	udph = (void *)skb_network_header(skb) + udphoff;
+	udph = (void *)skb->data + udphoff;
 	udph->source = cp->vport;
 
 	/*
@@ -254,7 +254,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 			payload_csum = true;
 	}
 
-	udph = (void *)skb_network_header(skb) + udphoff;
+	udph = (void *)skb->data + udphoff;
 	udph->dest = cp->dport;
 
 	/*
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 9fef4335da13..c23401c789de 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -1502,8 +1502,9 @@ tx_error:
  */
 int
 ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-		struct ip_vs_protocol *pp, int offset, unsigned int hooknum,
-		struct ip_vs_iphdr *iph)
+		struct ip_vs_protocol *pp, unsigned int toff,
+		unsigned int wlen, unsigned int hooknum,
+		struct ip_vs_iphdr *ciph)
 {
 	struct rtable	*rt;	/* Route to the other host */
 	int rc;
@@ -1515,7 +1516,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	   translate address/port back */
 	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
 		if (cp->packet_xmit)
-			rc = cp->packet_xmit(skb, cp, pp, iph);
+			rc = cp->packet_xmit(skb, cp, pp, ciph);
 		else
 			rc = NF_ACCEPT;
 		/* do not touch skb anymore */
@@ -1533,7 +1534,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		  IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
 		  IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
 	local = __ip_vs_get_out_rt(cp->ipvs, cp->af, skb, cp->dest, cp->daddr.ip, rt_mode,
-				   NULL, iph);
+				   NULL, ciph);
 	if (local < 0)
 		goto tx_error;
 	rt = skb_rtable(skb);
@@ -1565,13 +1566,13 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	}
 
 	/* copy-on-write the packet before mangling it */
-	if (skb_ensure_writable(skb, offset))
+	if (skb_ensure_writable(skb, wlen))
 		goto tx_error;
 
 	if (skb_cow(skb, rt->dst.dev->hard_header_len))
 		goto tx_error;
 
-	ip_vs_nat_icmp(skb, pp, cp, 0);
+	ip_vs_nat_icmp(skb, pp, cp, 0, toff);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->ignore_df = 1;
@@ -1587,8 +1588,9 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 #ifdef CONFIG_IP_VS_IPV6
 int
 ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-		struct ip_vs_protocol *pp, int offset, unsigned int hooknum,
-		struct ip_vs_iphdr *ipvsh)
+		struct ip_vs_protocol *pp, unsigned int toff,
+		unsigned int wlen, unsigned int hooknum,
+		struct ip_vs_iphdr *ciph)
 {
 	struct rt6_info	*rt;	/* Route to the other host */
 	int rc;
@@ -1600,7 +1602,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	   translate address/port back */
 	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
 		if (cp->packet_xmit)
-			rc = cp->packet_xmit(skb, cp, pp, ipvsh);
+			rc = cp->packet_xmit(skb, cp, pp, ciph);
 		else
 			rc = NF_ACCEPT;
 		/* do not touch skb anymore */
@@ -1617,7 +1619,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		  IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
 		  IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
 	local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest,
-				      &cp->daddr.in6, NULL, ipvsh, 0, rt_mode);
+				      &cp->daddr.in6, NULL, ciph, 0, rt_mode);
 	if (local < 0)
 		goto tx_error;
 	rt = dst_rt6_info(skb_dst(skb));
@@ -1649,13 +1651,13 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	}
 
 	/* copy-on-write the packet before mangling it */
-	if (skb_ensure_writable(skb, offset))
+	if (skb_ensure_writable(skb, wlen))
 		goto tx_error;
 
 	if (skb_cow(skb, rt->dst.dev->hard_header_len))
 		goto tx_error;
 
-	ip_vs_nat_icmp_v6(skb, pp, cp, 0);
+	ip_vs_nat_icmp_v6(skb, pp, cp, 0, toff, ciph);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->ignore_df = 1;
-- 
cgit 


From 342e24a339b90e8e339a0f8c151ca479b8565661 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Wed, 22 Jul 2026 13:15:17 +0300
Subject: ipvs: do not mangle ICMP replies for non-first fragments

Sashiko warns that ip_vs_nat_icmp() unconditionally mangles the
payload for embedded non-first IPv4 fragments. The problem is
in the very old inverted pp->dont_defrag check which should not
continue when embedded is a non-first TCP/UDP/SCTP fragment.

Check for embedded non-first fragment is also missing from
ip_vs_out_icmp_v6(), it is needed before any connection
lookups that expect ports after the network headers.

Drop the blocking code from ip_vs_in_icmp_v6() which prevents
ICMPv6 from local clients to use non-MASQ forwarding.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Link: https://sashiko.dev/#/patchset/20260720201122.79882-1-ja%40ssi.bg
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/ip_vs.h             | 11 ++++----
 net/netfilter/ipvs/ip_vs_core.c | 61 ++++++++++++++---------------------------
 net/netfilter/ipvs/ip_vs_xmit.c | 28 +++++++++++++++----
 3 files changed, 48 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4a10a01d6e2f..e6ca930a3507 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1975,8 +1975,7 @@ int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
 int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		    struct ip_vs_protocol *pp, unsigned int toff,
-		    unsigned int wlen, unsigned int hooknum,
-		    struct ip_vs_iphdr *ciph);
+		    unsigned int hooknum, struct ip_vs_iphdr *ciph);
 void ip_vs_dest_dst_rcu_free(struct rcu_head *head);
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -1990,8 +1989,7 @@ int ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		     struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
 int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		       struct ip_vs_protocol *pp, unsigned int toff,
-		       unsigned int wlen, unsigned int hooknum,
-		       struct ip_vs_iphdr *ciph);
+		       unsigned int hooknum, struct ip_vs_iphdr *ciph);
 #endif
 
 #ifdef CONFIG_SYSCTL
@@ -2063,12 +2061,13 @@ static inline bool ip_vs_conn_use_hash2(struct ip_vs_conn *cp)
 }
 
 void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
-		    struct ip_vs_conn *cp, int dir, unsigned int toff);
+		    struct ip_vs_conn *cp, int dir, unsigned int toff,
+		    bool has_ports);
 
 #ifdef CONFIG_IP_VS_IPV6
 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		       struct ip_vs_conn *cp, int dir, unsigned int toff,
-		       struct ip_vs_iphdr *ciph);
+		       bool has_ports, struct ip_vs_iphdr *ciph);
 #endif
 
 static inline __wsum ip_vs_check_diff4(__be32 old, __be32 new, __wsum oldsum)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index cd5eb71543ec..7efa209a517b 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -924,7 +924,8 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af,
  * - inout: 1=in->out, 0=out->in
  */
 void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
-		    struct ip_vs_conn *cp, int inout, unsigned int toff)
+		    struct ip_vs_conn *cp, int inout, unsigned int toff,
+		    bool has_ports)
 {
 	struct iphdr *iph	 = ip_hdr(skb);
 	struct icmphdr *icmph	 = (struct icmphdr *)(skb->data + toff);
@@ -944,8 +945,7 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
 	}
 
 	/* the TCP/UDP/SCTP port */
-	if (IPPROTO_TCP == ciph->protocol || IPPROTO_UDP == ciph->protocol ||
-	    IPPROTO_SCTP == ciph->protocol) {
+	if (has_ports) {
 		__be16 *ports = (void *)ciph + ciph->ihl*4;
 
 		if (inout)
@@ -970,18 +970,15 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
 #ifdef CONFIG_IP_VS_IPV6
 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		       struct ip_vs_conn *cp, int inout, unsigned int toff,
-		       struct ip_vs_iphdr *ciph)
+		       bool has_ports, struct ip_vs_iphdr *ciph)
 {
 	struct ipv6hdr *iph	 = ipv6_hdr(skb);
-	int protocol;
 	struct icmp6hdr *icmph;
 	struct ipv6hdr *cih;
 
 	icmph = (struct icmp6hdr *)(skb->data + toff);
 	cih = (struct ipv6hdr *)(skb->data + ciph->off);
 
-	protocol = ciph->protocol;
-
 	if (inout) {
 		iph->saddr = cp->vaddr.in6;
 		cih->daddr = cp->vaddr.in6;
@@ -991,9 +988,7 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
 	}
 
 	/* the TCP/UDP/SCTP port */
-	if (!ciph->fragoffs &&
-	    (protocol == IPPROTO_TCP  || protocol == IPPROTO_UDP ||
-	     protocol == IPPROTO_SCTP)) {
+	if (has_ports) {
 		__be16 *ports = (void *)(skb->data + ciph->len);
 
 		IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__,
@@ -1035,6 +1030,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 	int iproto = af == AF_INET6 ? IPPROTO_ICMPV6 : IPPROTO_ICMP;
 	unsigned int verdict = NF_DROP;
 	unsigned int ctoff = ciph->len;
+	bool has_ports = false;
 
 	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
 		goto after_nat;
@@ -1048,17 +1044,19 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 	}
 
 	if (ciph->protocol == IPPROTO_TCP || ciph->protocol == IPPROTO_UDP ||
-	    ciph->protocol == IPPROTO_SCTP)
+	    ciph->protocol == IPPROTO_SCTP) {
 		ctoff += 2 * sizeof(__u16);
+		has_ports = true;
+	}
 	if (skb_ensure_writable(skb, ctoff))
 		goto out;
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6)
-		ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, ciph);
+		ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, has_ports, ciph);
 	else
 #endif
-		ip_vs_nat_icmp(skb, pp, cp, 1, toff);
+		ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports);
 
 	if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum))
 		goto out;
@@ -1142,8 +1140,7 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb,
 		return NF_ACCEPT;
 
 	/* Is the embedded protocol header present? */
-	if (unlikely(cih->frag_off & htons(IP_OFFSET) &&
-		     pp->dont_defrag))
+	if (unlikely(cih->frag_off & htons(IP_OFFSET) && !pp->dont_defrag))
 		return NF_ACCEPT;
 
 	IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
@@ -1207,6 +1204,10 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
 	if (!pp)
 		return NF_ACCEPT;
 
+	/* Is the embedded protocol header present? */
+	if (unlikely(ciph.fragoffs && !pp->dont_defrag))
+		return NF_ACCEPT;
+
 	/* The embedded headers contain source and dest in reverse order */
 	cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto,
 			     ipvs, AF_INET6, skb, &ciph);
@@ -1865,8 +1866,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 	pp = pd->pp;
 
 	/* Is the embedded protocol header present? */
-	if (unlikely(cih->frag_off & htons(IP_OFFSET) &&
-		     pp->dont_defrag))
+	if (unlikely(cih->frag_off & htons(IP_OFFSET) && !pp->dont_defrag))
 		return NF_ACCEPT;
 
 	IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
@@ -1874,7 +1874,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 
 	offset2 = offset;
 	ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph);
-	offset = ciph.len;
 
 	/* The embedded headers contain source and dest in reverse order.
 	 * For IPIP/UDP/GRE tunnel this is error for request, not for reply.
@@ -1968,11 +1967,7 @@ ignore_tunnel:
 
 	/* do the statistics and put it back */
 	ip_vs_in_stats(cp, skb);
-	if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol ||
-	    IPPROTO_SCTP == cih->protocol)
-		offset += 2 * sizeof(__u16);
-	verdict = ip_vs_icmp_xmit(skb, cp, pp, iph->len, offset, hooknum,
-				  &ciph);
+	verdict = ip_vs_icmp_xmit(skb, cp, pp, iph->len, hooknum, &ciph);
 
 out:
 	if (likely(!new_cp))
@@ -2032,8 +2027,8 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
 		return NF_ACCEPT;
 	pp = pd->pp;
 
-	/* Cannot handle fragmented embedded protocol */
-	if (ciph.fragoffs)
+	/* Is the embedded protocol header present? */
+	if (ciph.fragoffs && !pp->dont_defrag)
 		return NF_ACCEPT;
 
 	IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset,
@@ -2057,13 +2052,6 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
 		new_cp = true;
 	}
 
-	/* VS/TUN, VS/DR and LOCALNODE just let it go */
-	if ((hooknum == NF_INET_LOCAL_OUT) &&
-	    (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) {
-		verdict = NF_ACCEPT;
-		goto out;
-	}
-
 	verdict = NF_DROP;
 
 	/* Ensure the checksum is correct */
@@ -2079,14 +2067,7 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
 	/* do the statistics and put it back */
 	ip_vs_in_stats(cp, skb);
 
-	/* Need to mangle contained IPv6 header in ICMPv6 packet */
-	offset = ciph.len;
-	if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol ||
-	    IPPROTO_SCTP == ciph.protocol)
-		offset += 2 * sizeof(__u16); /* Also mangle ports */
-
-	verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, iph->len, offset, hooknum,
-				     &ciph);
+	verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, iph->len, hooknum, &ciph);
 
 out:
 	if (likely(!new_cp))
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index c23401c789de..0b0c5304993a 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -1503,13 +1503,14 @@ tx_error:
 int
 ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		struct ip_vs_protocol *pp, unsigned int toff,
-		unsigned int wlen, unsigned int hooknum,
-		struct ip_vs_iphdr *ciph)
+		unsigned int hooknum, struct ip_vs_iphdr *ciph)
 {
 	struct rtable	*rt;	/* Route to the other host */
 	int rc;
 	int local;
 	int rt_mode, was_input;
+	bool has_ports = false;
+	unsigned int wlen;
 
 	/* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be
 	   forwarded directly here, because there is no need to
@@ -1565,6 +1566,13 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		goto tx_error;
 	}
 
+	wlen = ciph->len;
+	if (ciph->protocol == IPPROTO_TCP || ciph->protocol == IPPROTO_UDP ||
+	    ciph->protocol == IPPROTO_SCTP) {
+		wlen += 2 * sizeof(__u16); /* Also mangle ports */
+		has_ports = true;
+	}
+
 	/* copy-on-write the packet before mangling it */
 	if (skb_ensure_writable(skb, wlen))
 		goto tx_error;
@@ -1572,7 +1580,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	if (skb_cow(skb, rt->dst.dev->hard_header_len))
 		goto tx_error;
 
-	ip_vs_nat_icmp(skb, pp, cp, 0, toff);
+	ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->ignore_df = 1;
@@ -1589,10 +1597,11 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 int
 ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		struct ip_vs_protocol *pp, unsigned int toff,
-		unsigned int wlen, unsigned int hooknum,
-		struct ip_vs_iphdr *ciph)
+		unsigned int hooknum, struct ip_vs_iphdr *ciph)
 {
+	bool has_ports = false;
 	struct rt6_info	*rt;	/* Route to the other host */
+	unsigned int wlen;
 	int rc;
 	int local;
 	int rt_mode;
@@ -1650,6 +1659,13 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		goto tx_error;
 	}
 
+	wlen = ciph->len;
+	if (ciph->protocol == IPPROTO_TCP || ciph->protocol == IPPROTO_UDP ||
+	    ciph->protocol == IPPROTO_SCTP) {
+		wlen += 2 * sizeof(__u16); /* Also mangle ports */
+		has_ports = true;
+	}
+
 	/* copy-on-write the packet before mangling it */
 	if (skb_ensure_writable(skb, wlen))
 		goto tx_error;
@@ -1657,7 +1673,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	if (skb_cow(skb, rt->dst.dev->hard_header_len))
 		goto tx_error;
 
-	ip_vs_nat_icmp_v6(skb, pp, cp, 0, toff, ciph);
+	ip_vs_nat_icmp_v6(skb, pp, cp, 0, toff, has_ports, ciph);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->ignore_df = 1;
-- 
cgit