Merge tag 'ipsec-2026-08-18' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec

Steffen Klassert says:

====================
pull request (net): ipsec 2026-08-18

1) xfrm6: fix out-of-bounds write in xfrm6_input_addr() when secpath is full
   Tighten the secpath-depth check so a full chain can't write
   past xvec[].

2) Add and revert "esp: do not unref managed frag pages in esp_ssg_unref()"
   The patch does not fully fully resolve the issue, a corrected version
   will follow.

3) xfrm: espintcp: fix UAF during close
   Synchronize espintcp close with the xfrm_trans_reinject work
   queue so the freed socket message isn't dereferenced again.

4) xfrm: drop ESP-in-TCP packets with no ingress device
   Drop queued ESP-in-TCP records whose saved ingress device has
   gone away, avoiding a NULL device deref in the XFRM input path.

5) xfrm: avoid lock inversion in nat keepalive work
   Split the NAT keepalive walk into a reference-collection phase
   and a per-state lock phase to break the AB-BA with state removal.
   This patch has some issues that are fixed with a followup patch.

6) xfrm: Fix skb double-free in xfrm_dev_direct_output()
   Stop freeing the skb unconditionally in xfrm_dev_direct_output(),
   letting local_out()'s result indicate when ownership has moved on.

7) xfrm: ah6: validate routing header segments_left
   Validate the segments_left/hdrlen invariant before rearranging
   the routing-header addresses, avoiding an OOB memmove on
   malformed HDRINCL packets.

8) xfrm: fix xfrm_state_construct() auth-trunc leak
   Detect an already-attached auth-trunc allocation by the pointer
   rather than inferring it from the algorithm id, so a prior
   attach isn't overwritten and lost.

9) xfrm: bound nat keepalive state collection
   Replace the per-state allocation in the NAT keepalive walk
   with a fixed-size batch that drains under BH-disabled locking
   and resumes from the cursor, bounding the worker's memory.

* tag 'ipsec-2026-08-18' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec:
  xfrm: bound nat keepalive state collection
  Revert "esp: do not unref managed frag pages in esp_ssg_unref()"
  xfrm: fix xfrm_state_construct() auth-trunc leak
  xfrm: ah6: validate routing header segments_left
  xfrm: Fix skb double-free in xfrm_dev_direct_output()
  xfrm: avoid lock inversion in nat keepalive work
  xfrm: drop ESP-in-TCP packets with no ingress device
  xfrm: espintcp: fix UAF during close
  esp: do not unref managed frag pages in esp_ssg_unref()
  xfrm6: fix out-of-bounds write in xfrm6_input_addr() when secpath is full
====================

Link: https://patch.msgid.link/20260818092920.653034-1-steffen.klassert@secunet.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

net/ipv6/ah6.c

@@ -232,26 +232,28 @@ static void ipv6_rearrange_destopt(struct ipv6hdr *iph, struct ipv6_opt_hdr *des
  *	Rearrange the destination address in @iph and the addresses in @rthdr
  *	so that they appear in the order they will at the final destination.
  *	See Appendix A2 of RFC 2402 for details.
+ *
+ * Return: 0 on success, -EINVAL if segments_left exceeds the number of
+ * addresses described by hdrlen.
  */
-static void ipv6_rearrange_rthdr(struct ipv6hdr *iph, struct ipv6_rt_hdr *rthdr)
+static int ipv6_rearrange_rthdr(struct ipv6hdr *iph, struct ipv6_rt_hdr *rthdr)
 {
-	int segments, segments_left;
+	unsigned int segments, segments_left;
 	struct in6_addr *addrs;
 	struct in6_addr final_addr;
 
 	segments_left = rthdr->segments_left;
 	if (segments_left == 0)
-		return;
-	rthdr->segments_left = 0;
+		return 0;
 
-	/* The value of rthdr->hdrlen has been verified either by the system
-	 * call if it is locally generated, or by ipv6_rthdr_rcv() for incoming
-	 * packets.  So we can assume that it is even and that segments is
-	 * greater than or equal to segments_left.
-	 *
-	 * For the same reason we can assume that this option is of type 0.
+	/* Raw locally generated packets can reach AH6 without the invariant
+	 * required by the rt0-style address rearrangement below.
 	 */
 	segments = rthdr->hdrlen >> 1;
+	if (segments_left > segments)
+		return -EINVAL;
+
+	rthdr->segments_left = 0;
 
 	addrs = ((struct rt0_hdr *)rthdr)->addr;
 	final_addr = addrs[segments - 1];
@@ -261,6 +263,8 @@ static void ipv6_rearrange_rthdr(struct ipv6hdr *iph, struct ipv6_rt_hdr *rthdr)
 
 	addrs[0] = iph->daddr;
 	iph->daddr = final_addr;
+
+	return 0;
 }
 
 static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir)
@@ -273,6 +277,7 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir)
 	} exthdr = { .iph = iph };
 	char *end = exthdr.raw + len;
 	int nexthdr = iph->nexthdr;
+	int err;
 
 	exthdr.iph++;
 
@@ -292,7 +297,9 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir)
 			break;
 
 		case NEXTHDR_ROUTING:
-			ipv6_rearrange_rthdr(iph, exthdr.rth);
+			err = ipv6_rearrange_rthdr(iph, exthdr.rth);
+			if (err)
+				return err;
 			break;
 
 		default:

net/ipv6/xfrm6_input.c

@@ -247,7 +247,7 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
 		goto drop;
 	}
 
-	if (1 + sp->len == XFRM_MAX_DEPTH) {
+	if (sp->len >= XFRM_MAX_DEPTH) {
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
 		goto drop;
 	}

net/xfrm/espintcp.c

@@ -37,6 +37,11 @@ static void handle_esp(struct sk_buff *skb, struct sock *sk)
 
 	rcu_read_lock();
 	skb->dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
+	if (!skb->dev) {
+		XFRM_INC_STATS(sock_net(sk), LINUX_MIB_XFRMINERROR);
+		kfree_skb(skb);
+		goto out;
+	}
 	local_bh_disable();
 #if IS_ENABLED(CONFIG_IPV6)
 	if (sk->sk_family == AF_INET6)
@@ -45,6 +50,7 @@ static void handle_esp(struct sk_buff *skb, struct sock *sk)
 #endif
 		xfrm4_rcv_encap(skb, IPPROTO_ESP, 0, TCP_ENCAP_ESPINTCP);
 	local_bh_enable();
+out:
 	rcu_read_unlock();
 }
 
@@ -515,7 +521,8 @@ static void espintcp_close(struct sock *sk, long timeout)
 	strp_stop(&ctx->strp);
 
 	sk->sk_prot = &tcp_prot;
-	barrier();
+
+	synchronize_rcu();
 
 	disable_work_sync(&ctx->work);
 	strp_done(&ctx->strp);

net/xfrm/xfrm_nat_keepalive.c

@@ -155,25 +155,50 @@ static void nat_keepalive_send(struct nat_keepalive *ka)
 	}
 }
 
+enum {
+	NAT_KEEPALIVE_BATCH_SIZE = 16,
+	NAT_KEEPALIVE_BATCH_FULL = 1,
+};
+
 struct nat_keepalive_work_ctx {
+	struct xfrm_state *batch[NAT_KEEPALIVE_BATCH_SIZE];
+	unsigned int nr;
 	time64_t next_run;
 	time64_t now;
 };
 
-static int nat_keepalive_work_single(struct xfrm_state *x, int count, void *ptr)
+static int nat_keepalive_work_collect(struct xfrm_state *x, int count, void *ptr)
 {
 	struct nat_keepalive_work_ctx *ctx = ptr;
+
+	if (!READ_ONCE(x->nat_keepalive_interval))
+		return 0;
+
+	if (ctx->nr == ARRAY_SIZE(ctx->batch))
+		return NAT_KEEPALIVE_BATCH_FULL;
+
+	xfrm_state_hold(x);
+	ctx->batch[ctx->nr++] = x;
+	return 0;
+}
+
+static void nat_keepalive_work_single(struct xfrm_state *x,
+				      struct nat_keepalive_work_ctx *ctx)
+{
 	bool send_keepalive = false;
 	struct nat_keepalive ka;
-	time64_t next_run;
+	time64_t next_run = 0;
 	u32 interval;
 	int delta;
 
+	spin_lock_bh(&x->lock);
+
+	if (x->km.state == XFRM_STATE_DEAD)
+		goto out;
+
 	interval = x->nat_keepalive_interval;
 	if (!interval)
-		return 0;
-
-	spin_lock(&x->lock);
+		goto out;
 
 	delta = (int)(ctx->now - x->lastused);
 	if (delta < interval) {
@@ -187,14 +212,14 @@ static int nat_keepalive_work_single(struct xfrm_state *x, int count, void *ptr)
 		send_keepalive = true;
 	}
 
-	spin_unlock(&x->lock);
+out:
+	spin_unlock_bh(&x->lock);
 
 	if (send_keepalive)
 		nat_keepalive_send(&ka);
 
-	if (!ctx->next_run || next_run < ctx->next_run)
+	if (next_run && (!ctx->next_run || next_run < ctx->next_run))
 		ctx->next_run = next_run;
-	return 0;
 }
 
 static void nat_keepalive_work(struct work_struct *work)
@@ -202,13 +227,23 @@ static void nat_keepalive_work(struct work_struct *work)
 	struct nat_keepalive_work_ctx ctx;
 	struct xfrm_state_walk walk;
 	struct net *net;
+	int err, i;
 
 	ctx.next_run = 0;
 	ctx.now = ktime_get_real_seconds();
 
 	net = container_of(work, struct net, xfrm.nat_keepalive_work.work);
 	xfrm_state_walk_init(&walk, IPPROTO_ESP, NULL);
-	xfrm_state_walk(net, &walk, nat_keepalive_work_single, &ctx);
+	do {
+		ctx.nr = 0;
+		err = xfrm_state_walk(net, &walk, nat_keepalive_work_collect, &ctx);
+		local_bh_disable();
+		for (i = 0; i < ctx.nr; i++) {
+			nat_keepalive_work_single(ctx.batch[i], &ctx);
+			xfrm_state_put(ctx.batch[i]);
+		}
+		local_bh_enable();
+	} while (err == NAT_KEEPALIVE_BATCH_FULL);
 	xfrm_state_walk_done(&walk, net);
 	if (ctx.next_run)
 		schedule_delayed_work(&net->xfrm.nat_keepalive_work,

net/xfrm/xfrm_output.c

@@ -636,10 +636,8 @@ static int xfrm_dev_direct_output(struct sock *sk, struct xfrm_state *x,
 	nf_reset_ct(skb);
 
 	err = skb_dst(skb)->ops->local_out(net, sk, skb);
-	if (unlikely(err != 1)) {
-		kfree_skb(skb);
+	if (unlikely(err != 1))
 		return err;
-	}
 
 	/* In transport mode, network destination is
 	 * directly reachable, while in tunnel mode,

net/xfrm/xfrm_user.c

@@ -940,7 +940,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 	if ((err = attach_auth_trunc(&x->aalg, &x->props.aalgo,
 				     attrs[XFRMA_ALG_AUTH_TRUNC], extack)))
 		goto error;
-	if (!x->props.aalgo) {
+	if (!x->aalg) {
 		if ((err = attach_auth(&x->aalg, &x->props.aalgo,
 				       attrs[XFRMA_ALG_AUTH], extack)))
 			goto error;