Merge tag 'ipsec-2026-05-05' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec

Steffen Klassert says:

====================
pull request (net): ipsec 2026-05-05

1. Fix an IPv6 encapsulation error path that leaked route references
   when UDPv6 ESP decapsulation resolved to an error route.
   From Yilin Zhu.

2. Fix AH with ESN on async crypto paths by accounting for the extra
   high-order sequence number when reconstructing the temporary
   authentication layout in the completion callbacks.
   From Michael Bomarito.

3. Fix XFRM output so it does not overwrite already-correct inner header
   pointers when a tunnel layer such as VXLAN has already saved them.
   The fix comes with new selftests. From Cosmin Ratiu.

4. Add the missing native payload size entry for XFRM_MSG_MAPPING in the
   compat translation path. From Ruijie Li.

5. Harden __xfrm_state_delete() against repeated or inconsistent unhashing
   of state list nodes by keying the removal on actual list membership and
   using delete-and-init helpers. From Michal Kosiorek.

6. Prevent ESP from decrypting shared splice-backed skb fragments in place
   by marking UDP splice frags as shared and forcing copy-on-write in ESP
   input when needed. From Kuan-Ting Chen.

* tag 'ipsec-2026-05-05' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec:
  xfrm: esp: avoid in-place decrypt on shared skb frags
  xfrm: defensively unhash xfrm_state lists in __xfrm_state_delete
  xfrm: provide message size for XFRM_MSG_MAPPING
  xfrm: Don't clobber inner headers when already set
  tools/selftests: Add a VXLAN+IPsec traffic test
  tools/selftests: Use a sensible timeout value for iperf3 client
  xfrm: ah: account for ESN high bits in async callbacks
  ipv6: xfrm6: release dst on error in xfrm6_rcv_encap()
====================

Link: https://patch.msgid.link/20260505132326.1362733-1-steffen.klassert@secunet.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

10 files changed, 56 insertions, 19 deletions

diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 5fb812443a08..4366cbac3f06 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -124,9 +124,14 @@ static void ah_output_done(void *data, int err)
 	struct iphdr *top_iph = ip_hdr(skb);
 	struct ip_auth_hdr *ah = ip_auth_hdr(skb);
 	int ihl = ip_hdrlen(skb);
+	int seqhi_len = 0;
+	__be32 *seqhi;
 
+	if (x->props.flags & XFRM_STATE_ESN)
+		seqhi_len = sizeof(*seqhi);
 	iph = AH_SKB_CB(skb)->tmp;
-	icv = ah_tmp_icv(iph, ihl);
+	seqhi = (__be32 *)((char *)iph + ihl);
+	icv = ah_tmp_icv(seqhi, seqhi_len);
 	memcpy(ah->auth_data, icv, ahp->icv_trunc_len);
 
 	top_iph->tos = iph->tos;
@@ -270,12 +275,17 @@ static void ah_input_done(void *data, int err)
 	struct ip_auth_hdr *ah = ip_auth_hdr(skb);
 	int ihl = ip_hdrlen(skb);
 	int ah_hlen = (ah->hdrlen + 2) << 2;
+	int seqhi_len = 0;
+	__be32 *seqhi;
 
 	if (err)
 		goto out;
 
+	if (x->props.flags & XFRM_STATE_ESN)
+		seqhi_len = sizeof(*seqhi);
 	work_iph = AH_SKB_CB(skb)->tmp;
-	auth_data = ah_tmp_auth(work_iph, ihl);
+	seqhi = (__be32 *)((char *)work_iph + ihl);
+	auth_data = ah_tmp_auth(seqhi, seqhi_len);
 	icv = ah_tmp_icv(auth_data, ahp->icv_trunc_len);
 
 	err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 6dfc0bcdef65..6a5febbdbee4 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -873,7 +873,8 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 			nfrags = 1;
 
 			goto skip_cow;
-		} else if (!skb_has_frag_list(skb)) {
+		} else if (!skb_has_frag_list(skb) &&
+			   !skb_has_shared_frag(skb)) {
 			nfrags = skb_shinfo(skb)->nr_frags;
 			nfrags++;
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e4790cc7b5c2..5bcd73cbdb41 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1233,6 +1233,8 @@ alloc_new_skb:
 			if (err < 0)
 				goto error;
 			copy = err;
+			if (!(flags & MSG_NO_SHARED_FRAGS))
+				skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG;
 			wmem_alloc_delta += copy;
 		} else if (!zc) {
 			int i = skb_shinfo(skb)->nr_frags;
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index cb26beea4398..de1e68199a01 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -317,14 +317,19 @@ static void ah6_output_done(void *data, int err)
 	struct ipv6hdr *top_iph = ipv6_hdr(skb);
 	struct ip_auth_hdr *ah = ip_auth_hdr(skb);
 	struct tmp_ext *iph_ext;
+	int seqhi_len = 0;
+	__be32 *seqhi;
 
 	extlen = skb_network_header_len(skb) - sizeof(struct ipv6hdr);
 	if (extlen)
 		extlen += sizeof(*iph_ext);
 
+	if (x->props.flags & XFRM_STATE_ESN)
+		seqhi_len = sizeof(*seqhi);
 	iph_base = AH_SKB_CB(skb)->tmp;
 	iph_ext = ah_tmp_ext(iph_base);
-	icv = ah_tmp_icv(iph_ext, extlen);
+	seqhi = (__be32 *)((char *)iph_ext + extlen);
+	icv = ah_tmp_icv(seqhi, seqhi_len);
 
 	memcpy(ah->auth_data, icv, ahp->icv_trunc_len);
 	memcpy(top_iph, iph_base, IPV6HDR_BASELEN);
@@ -471,13 +476,18 @@ static void ah6_input_done(void *data, int err)
 	struct ip_auth_hdr *ah = ip_auth_hdr(skb);
 	int hdr_len = skb_network_header_len(skb);
 	int ah_hlen = ipv6_authlen(ah);
+	int seqhi_len = 0;
+	__be32 *seqhi;
 
 	if (err)
 		goto out;
 
+	if (x->props.flags & XFRM_STATE_ESN)
+		seqhi_len = sizeof(*seqhi);
 	work_iph = AH_SKB_CB(skb)->tmp;
 	auth_data = ah_tmp_auth(work_iph, hdr_len);
-	icv = ah_tmp_icv(auth_data, ahp->icv_trunc_len);
+	seqhi = (__be32 *)(auth_data + ahp->icv_trunc_len);
+	icv = ah_tmp_icv(seqhi, seqhi_len);
 
 	err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0;
 	if (err)
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 9f75313734f8..9c06c5a1419d 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -915,7 +915,8 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 			nfrags = 1;
 
 			goto skip_cow;
-		} else if (!skb_has_frag_list(skb)) {
+		} else if (!skb_has_frag_list(skb) &&
+			   !skb_has_shared_frag(skb)) {
 			nfrags = skb_shinfo(skb)->nr_frags;
 			nfrags++;
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 7e92909ab5be..1f2a33fbed6e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1794,6 +1794,8 @@ alloc_new_skb:
 			if (err < 0)
 				goto error;
 			copy = err;
+			if (!(flags & MSG_NO_SHARED_FRAGS))
+				skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG;
 			wmem_alloc_delta += copy;
 		} else if (!zc) {
 			int i = skb_shinfo(skb)->nr_frags;
diff --git a/net/ipv6/xfrm6_protocol.c b/net/ipv6/xfrm6_protocol.c
index ea2f805d3b01..9b586fcec485 100644
--- a/net/ipv6/xfrm6_protocol.c
+++ b/net/ipv6/xfrm6_protocol.c
@@ -88,8 +88,10 @@ int xfrm6_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
 
 		dst = ip6_route_input_lookup(dev_net(skb->dev), skb->dev, &fl6,
 					     skb, flags);
-		if (dst->error)
+		if (dst->error) {
+			dst_release(dst);
 			goto drop;
+		}
 		skb_dst_set(skb, dst);
 	}
 
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index a9652b422f51..cc35c2fcbbe0 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -66,7 +66,9 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 	struct iphdr *iph = ip_hdr(skb);
 	int ihl = iph->ihl * 4;
 
-	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+	if (!skb->inner_protocol)
+		skb_set_inner_transport_header(skb,
+					       skb_transport_offset(skb));
 
 	skb_set_network_header(skb, -x->props.header_len);
 	skb->mac_header = skb->network_header +
@@ -167,7 +169,9 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 	int hdr_len;
 
 	iph = ipv6_hdr(skb);
-	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+	if (!skb->inner_protocol)
+		skb_set_inner_transport_header(skb,
+					       skb_transport_offset(skb));
 
 	hdr_len = xfrm6_hdr_offset(x, skb, &prevhdr);
 	if (hdr_len < 0)
@@ -276,8 +280,10 @@ static int xfrm4_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb)
 	struct iphdr *top_iph;
 	int flags;
 
-	skb_set_inner_network_header(skb, skb_network_offset(skb));
-	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+	if (!skb->inner_protocol) {
+		skb_set_inner_network_header(skb, skb_network_offset(skb));
+		skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+	}
 
 	skb_set_network_header(skb, -x->props.header_len);
 	skb->mac_header = skb->network_header +
@@ -321,8 +327,10 @@ static int xfrm6_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb)
 	struct ipv6hdr *top_iph;
 	int dsfield;
 
-	skb_set_inner_network_header(skb, skb_network_offset(skb));
-	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+	if (!skb->inner_protocol) {
+		skb_set_inner_network_header(skb, skb_network_offset(skb));
+		skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+	}
 
 	skb_set_network_header(skb, -x->props.header_len);
 	skb->mac_header = skb->network_header +
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 1748d374abca..686014d39429 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -818,17 +818,17 @@ int __xfrm_state_delete(struct xfrm_state *x)
 
 		spin_lock(&net->xfrm.xfrm_state_lock);
 		list_del(&x->km.all);
-		hlist_del_rcu(&x->bydst);
-		hlist_del_rcu(&x->bysrc);
-		if (x->km.seq)
-			hlist_del_rcu(&x->byseq);
+		hlist_del_init_rcu(&x->bydst);
+		hlist_del_init_rcu(&x->bysrc);
+		if (!hlist_unhashed(&x->byseq))
+			hlist_del_init_rcu(&x->byseq);
 		if (!hlist_unhashed(&x->state_cache))
 			hlist_del_rcu(&x->state_cache);
 		if (!hlist_unhashed(&x->state_cache_input))
 			hlist_del_rcu(&x->state_cache_input);
 
-		if (x->id.spi)
-			hlist_del_rcu(&x->byspi);
+		if (!hlist_unhashed(&x->byspi))
+			hlist_del_init_rcu(&x->byspi);
 		net->xfrm.state_num--;
 		xfrm_nat_keepalive_state_updated(x);
 		spin_unlock(&net->xfrm.xfrm_state_lock);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index d56450f61669..38a90e5ee3d9 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -3323,6 +3323,7 @@ const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
 	[XFRM_MSG_GETSADINFO  - XFRM_MSG_BASE] = sizeof(u32),
 	[XFRM_MSG_NEWSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
 	[XFRM_MSG_GETSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_MAPPING     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping),
 	[XFRM_MSG_SETDEFAULT  - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_default),
 	[XFRM_MSG_GETDEFAULT  - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_default),
 };