Merge tag 'ipsec-2026-06-22' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec

Steffen Klassert says: ==================== pull request (net): ipsec 2026-06-22 1) xfrm: use compat translator only for u64 alignment mismatch Gate the XFRM_USER_COMPAT translator on COMPAT_FOR_U64_ALIGNMENT so 32-bit compat tasks on arches whose 32-bit ABI already matches the native 64-bit layout are no longer rejected with -EOPNOTSUPP. From Sanman Pradhan. 2) net: af_key: initialize alg_key_len for IPComp states Initialize the alg_key_len to 0 in the IPComp branch of pfkey_msg2xfrm_state() so an uninitialized value cannot drive xfrm_alg_len() into a slab-out-of-bounds kmemdup during XFRM_MSG_MIGRATE. From Zijing Yin. 3) xfrm: Fix dev use-after-free in xfrm async resumption Stash the original skb->dev and extend the RCU critical section across xfrm_rcv_cb() and transport_finish() to prevent a tunnel-device UAF and original-device refcount leak when a callback replaces skb->dev. From Dong Chenchen. 4) xfrm: Fix xfrm state cache insertion race Move the state-validity check inside xfrm_state_lock in the input state cache insertion path so a state cannot be killed between the check and the insert. From Herbert Xu. 5) xfrm: annotate data-races around xfrm_policy_count[] and xfrm_policy_default[] Add READ_ONCE()/WRITE_ONCE() annotations on xfrm_policy_count and xfrm_policy_default to silence the KCSAN data race reported on net->xfrm.policy_count. From Eric Dumazet. 6) espintcp: use sk_msg_free_partial to fix partial send Replace the manual skmsg accounting in espintcp with sk_msg_free_partial() so the skmsg stays consistent on every iteration and the partial-send accounting bugs go away. From Sabrina Dubroca. 7) xfrm: validate selector family and prefixlen during match Reject mismatched address families in xfrm_selector_match() and bound prefixlen in addr4_match()/addr_match() to prevent the shift-out-of-bounds syzbot reported when an AF_UNSPEC selector with a large prefixlen is matched against an IPv4 flow. From Eric Dumazet. * tag 'ipsec-2026-06-22' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec: xfrm: validate selector family and prefixlen during match espintcp: use sk_msg_free_partial to fix partial send xfrm: annotate data-races around xfrm_policy_count[] and xfrm_policy_default[] xfrm: Fix xfrm state cache insertion race xfrm: Fix dev use-after-free in xfrm async resumption net: af_key: initialize alg_key_len for IPComp states xfrm: use compat translator only for u64 alignment mismatch ==================== Link: https://patch.msgid.link/20260622075726.29685-1-steffen.klassert@secunet.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-07-16 17:57:38 -04:00 · 2026-06-23 16:22:23 -07:00
parent 5c12248673 40f0b10479
commit e9deb406c1
9 changed files with 75 additions and 78 deletions
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -953,6 +953,9 @@ static inline bool addr_match(const void *token1, const void *token2,
 	unsigned int pdw;
 	unsigned int pbi;

+	if (prefixlen > 128)
+		return false;
+
 	pdw = prefixlen >> 5;	  /* num of whole u32 in prefix */
 	pbi = prefixlen &  0x1f;  /* num of bits in incomplete u32 in prefix */

@@ -977,6 +980,10 @@ static inline bool addr4_match(__be32 a1, __be32 a2, u8 prefixlen)
 	/* C99 6.5.7 (3): u32 << 32 is undefined behaviour */
 	if (sizeof(long) == 4 && prefixlen == 0)
 		return true;
+
+	if (prefixlen > 32)
+		return false;
+
 	return !((a1 ^ a2) & htonl(~0UL << (32 - prefixlen)));
 }

@@ -1260,8 +1267,8 @@ int __xfrm_policy_check(struct sock *, int dir, struct sk_buff *skb,
 static inline bool __xfrm_check_nopolicy(struct net *net, struct sk_buff *skb,
 					 int dir)
 {
-	if (!net->xfrm.policy_count[dir] && !secpath_exists(skb))
-		return net->xfrm.policy_default[dir] == XFRM_USERPOLICY_ACCEPT;
+	if (!READ_ONCE(net->xfrm.policy_count[dir]) && !secpath_exists(skb))
+		return READ_ONCE(net->xfrm.policy_default[dir]) == XFRM_USERPOLICY_ACCEPT;

 	return false;
 }
@@ -1361,8 +1368,8 @@ static inline int xfrm_route_forward(struct sk_buff *skb, unsigned short family)
 {
 	struct net *net = dev_net(skb->dev);

-	if (!net->xfrm.policy_count[XFRM_POLICY_OUT] &&
-	    net->xfrm.policy_default[XFRM_POLICY_OUT] == XFRM_USERPOLICY_ACCEPT)
+	if (!READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT]) &&
+	    READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_OUT]) == XFRM_USERPOLICY_ACCEPT)
 		return true;

 	return (skb_dst(skb)->flags & DST_NOXFRM) ||
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -76,8 +76,6 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
 	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
 		dev_net(dev), NULL, skb, dev, NULL,
 		xfrm4_rcv_encap_finish);
-	if (async)
-		dev_put(dev);
 	return 0;
 }

--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -71,8 +71,6 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
 	NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
 		dev_net(dev), NULL, skb, dev, NULL,
 		xfrm6_transport_finish2);
-	if (async)
-		dev_put(dev);
 	return 0;
 }

--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1218,6 +1218,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
 				goto out;
 			}
 			strcpy(x->calg->alg_name, a->name);
+			x->calg->alg_key_len = 0;
 			x->props.calgo = sa->sadb_sa_encrypt;
 		} else {
 			int keysize = 0;
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -212,43 +212,23 @@ static int espintcp_sendskmsg_locked(struct sock *sk,
 	struct sk_msg *skmsg = &emsg->skmsg;
 	bool more = flags & MSG_MORE;
 	struct scatterlist *sg;
-	int done = 0;
 	int ret;

-	sg = &skmsg->sg.data[skmsg->sg.start];
 	do {
 		struct bio_vec bvec;
-		size_t size = sg->length - emsg->offset;
-		int offset = sg->offset + emsg->offset;
-		struct page *p;
-
-		emsg->offset = 0;

+		sg = &skmsg->sg.data[skmsg->sg.start];
 		if (sg_is_last(sg) && !more)
 			msghdr.msg_flags &= ~MSG_MORE;

-		p = sg_page(sg);
-retry:
-		bvec_set_page(&bvec, p, size, offset);
-		iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, size);
-		ret = tcp_sendmsg_locked(sk, &msghdr, size);
-		if (ret < 0) {
-			emsg->offset = offset - sg->offset;
-			skmsg->sg.start += done;
+		bvec_set_page(&bvec, sg_page(sg), sg->length, sg->offset);
+		iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, sg->length);
+		ret = tcp_sendmsg_locked(sk, &msghdr, sg->length);
+		if (ret < 0)
 			return ret;
-		}

-		if (ret != size) {
-			offset += ret;
-			size -= ret;
-			goto retry;
-		}
-
-		done++;
-		put_page(p);
-		sk_mem_uncharge(sk, sg->length);
-		sg = sg_next(sg);
-	} while (sg);
+		sk_msg_free_partial(sk, skmsg, ret);
+	} while (skmsg->sg.size);

 	memset(emsg, 0, sizeof(*emsg));

--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -467,6 +467,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 {
 	const struct xfrm_state_afinfo *afinfo;
 	struct net *net = dev_net(skb->dev);
+	struct net_device *dev = skb->dev;
 	int err;
 	__be32 seq;
 	__be32 seq_hi;
@@ -493,7 +494,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 					       LINUX_MIB_XFRMINSTATEINVALID);

 			if (encap_type == -1)
-				dev_put(skb->dev);
+				dev_put(dev);
 			goto drop;
 		}

@@ -655,16 +656,16 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)

 		if (!crypto_done) {
 			spin_unlock(&x->lock);
-			dev_hold(skb->dev);
+			dev_hold(dev);

 			nexthdr = x->type->input(x, skb);
 			if (nexthdr == -EINPROGRESS) {
 				if (async)
-					dev_put(skb->dev);
+					dev_put(dev);
 				return 0;
 			}

-			dev_put(skb->dev);
+			dev_put(dev);
 			spin_lock(&x->lock);
 		}
 resume:
@@ -699,7 +700,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		err = xfrm_inner_mode_input(x, skb);
 		if (err == -EINPROGRESS) {
 			if (async)
-				dev_put(skb->dev);
+				dev_put(dev);
 			return 0;
 		} else if (err) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
@@ -726,9 +727,12 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		crypto_done = false;
 	} while (!err);

+	rcu_read_lock();
 	err = xfrm_rcv_cb(skb, family, x->type->proto, 0);
-	if (err)
+	if (err) {
+		rcu_read_unlock();
 		goto drop;
+	}

 	nf_reset_ct(skb);

@@ -739,8 +743,9 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		if (skb_valid_dst(skb))
 			skb_dst_drop(skb);
 		if (async)
-			dev_put(skb->dev);
+			dev_put(dev);
 		gro_cells_receive(&gro_cells, skb);
+		rcu_read_unlock();
 		return 0;
 	} else {
 		xo = xfrm_offload(skb);
@@ -748,23 +753,21 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 			xfrm_gro = xo->flags & XFRM_GRO;

 		err = -EAFNOSUPPORT;
-		rcu_read_lock();
 		afinfo = xfrm_state_afinfo_get_rcu(x->props.family);
 		if (likely(afinfo))
 			err = afinfo->transport_finish(skb, xfrm_gro || async);
-		rcu_read_unlock();
 		if (xfrm_gro) {
 			sp = skb_sec_path(skb);
 			if (sp)
 				sp->olen = 0;
 			if (skb_valid_dst(skb))
 				skb_dst_drop(skb);
-			if (async)
-				dev_put(skb->dev);
 			gro_cells_receive(&gro_cells, skb);
-			return err;
 		}

+		if (async)
+			dev_put(dev);
+		rcu_read_unlock();
 		return err;
 	}

@@ -772,7 +775,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 	spin_unlock(&x->lock);
 drop:
 	if (async)
-		dev_put(skb->dev);
+		dev_put(dev);
 	xfrm_rcv_cb(skb, family, x && x->type ? x->type->proto : nexthdr, -1);
 	kfree_skb(skb);
 	return 0;
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -242,6 +242,9 @@ __xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
 bool xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl,
 			 unsigned short family)
 {
+	if (family != sel->family && sel->family != AF_UNSPEC)
+		return false;
+
 	switch (family) {
 	case AF_INET:
 		return __xfrm4_selector_match(sel, fl);
@@ -685,7 +688,7 @@ static void xfrm_byidx_resize(struct net *net)

 static inline int xfrm_bydst_should_resize(struct net *net, int dir, int *total)
 {
-	unsigned int cnt = net->xfrm.policy_count[dir];
+	unsigned int cnt = READ_ONCE(net->xfrm.policy_count[dir]);
 	unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;

 	if (total)
@@ -711,12 +714,12 @@ static inline int xfrm_byidx_should_resize(struct net *net, int total)

 void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si)
 {
-	si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN];
-	si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT];
-	si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD];
-	si->inscnt = net->xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX];
-	si->outscnt = net->xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX];
-	si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX];
+	si->incnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_IN]);
+	si->outcnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT]);
+	si->fwdcnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_FWD]);
+	si->inscnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX]);
+	si->outscnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX]);
+	si->fwdscnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]);
 	si->spdhcnt = net->xfrm.policy_idx_hmask;
 	si->spdhmcnt = xfrm_policy_hashmax;
 }
@@ -2318,7 +2321,7 @@ static void __xfrm_policy_link(struct xfrm_policy *pol, int dir)
 	}

 	list_add(&pol->walk.all, &net->xfrm.policy_all);
-	net->xfrm.policy_count[dir]++;
+	WRITE_ONCE(net->xfrm.policy_count[dir], net->xfrm.policy_count[dir] + 1);
 	xfrm_pol_hold(pol);
 }

@@ -2337,7 +2340,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 	}

 	list_del_init(&pol->walk.all);
-	net->xfrm.policy_count[dir]--;
+	WRITE_ONCE(net->xfrm.policy_count[dir], net->xfrm.policy_count[dir] - 1);

 	return pol;
 }
@@ -3222,7 +3225,7 @@ struct dst_entry *xfrm_lookup_with_ifid(struct net *net,

 		/* To accelerate a bit...  */
 		if (!if_id && ((dst_orig->flags & DST_NOXFRM) ||
-			       !net->xfrm.policy_count[XFRM_POLICY_OUT]))
+			       !READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT])))
 			goto nopol;

 		xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id);
@@ -3296,7 +3299,7 @@ struct dst_entry *xfrm_lookup_with_ifid(struct net *net,

 nopol:
 	if ((!dst_orig->dev || !(dst_orig->dev->flags & IFF_LOOPBACK)) &&
-	    net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) {
+	    READ_ONCE(net->xfrm.policy_default[dir]) == XFRM_USERPOLICY_BLOCK) {
 		err = -EPERM;
 		goto error;
 	}
@@ -3750,7 +3753,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		const bool is_crypto_offload = sp &&
 			(xfrm_input_state(skb)->xso.type == XFRM_DEV_OFFLOAD_CRYPTO);

-		if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) {
+		if (READ_ONCE(net->xfrm.policy_default[dir]) == XFRM_USERPOLICY_BLOCK) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS);
 			return 0;
 		}
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1207,9 +1207,11 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
 	struct hlist_head *state_cache_input;
 	struct xfrm_state *x = NULL;

+	/* BH is always disabled on the input path. */
+	lockdep_assert_in_softirq();
+
 	state_cache_input = raw_cpu_ptr(net->xfrm.state_cache_input);

-	rcu_read_lock();
 	hlist_for_each_entry_rcu(x, state_cache_input, state_cache_input) {
 		if (x->props.family != family ||
 		    x->id.spi       != spi ||
@@ -1227,20 +1229,25 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
 	xfrm_hash_ptrs_get(net, &state_ptrs);

 	x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family);
-
-	if (x && x->km.state == XFRM_STATE_VALID) {
-		spin_lock_bh(&net->xfrm.xfrm_state_lock);
-		if (hlist_unhashed(&x->state_cache_input)) {
+	if (x) {
+		spin_lock(&net->xfrm.xfrm_state_lock);
+		if (x->km.state != XFRM_STATE_VALID) {
+			/*
+			 * The state is about to be destroyed.
+			 *
+			 * Don't add it to the cache but still
+			 * return it to the caller.
+			 */
+		} else if (hlist_unhashed(&x->state_cache_input)) {
 			hlist_add_head_rcu(&x->state_cache_input, state_cache_input);
 		} else {
 			hlist_del_rcu(&x->state_cache_input);
 			hlist_add_head_rcu(&x->state_cache_input, state_cache_input);
 		}
-		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+		spin_unlock(&net->xfrm.xfrm_state_lock);
 	}

 out:
-	rcu_read_unlock();
 	return x;
 }
 EXPORT_SYMBOL(xfrm_input_state_lookup);
@@ -3014,7 +3021,7 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen)
 	if (IS_ERR(data))
 		return PTR_ERR(data);

-	if (in_compat_syscall()) {
+	if (IS_ENABLED(CONFIG_COMPAT_FOR_U64_ALIGNMENT) && in_compat_syscall()) {
 		struct xfrm_translator *xtr = xfrm_get_translator();

 		if (!xtr) {
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -2511,9 +2511,9 @@ static int xfrm_notify_userpolicy(struct net *net)
 	}

 	up = nlmsg_data(nlh);
-	up->in = net->xfrm.policy_default[XFRM_POLICY_IN];
-	up->fwd = net->xfrm.policy_default[XFRM_POLICY_FWD];
-	up->out = net->xfrm.policy_default[XFRM_POLICY_OUT];
+	up->in = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_IN]);
+	up->fwd = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_FWD]);
+	up->out = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_OUT]);

 	nlmsg_end(skb, nlh);

@@ -2537,13 +2537,13 @@ static int xfrm_set_default(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct xfrm_userpolicy_default *up = nlmsg_data(nlh);

 	if (xfrm_userpolicy_is_valid(up->in))
-		net->xfrm.policy_default[XFRM_POLICY_IN] = up->in;
+		WRITE_ONCE(net->xfrm.policy_default[XFRM_POLICY_IN], up->in);

 	if (xfrm_userpolicy_is_valid(up->fwd))
-		net->xfrm.policy_default[XFRM_POLICY_FWD] = up->fwd;
+		WRITE_ONCE(net->xfrm.policy_default[XFRM_POLICY_FWD], up->fwd);

 	if (xfrm_userpolicy_is_valid(up->out))
-		net->xfrm.policy_default[XFRM_POLICY_OUT] = up->out;
+		WRITE_ONCE(net->xfrm.policy_default[XFRM_POLICY_OUT], up->out);

 	rt_genid_bump_all(net);

@@ -2573,9 +2573,9 @@ static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}

 	r_up = nlmsg_data(r_nlh);
-	r_up->in = net->xfrm.policy_default[XFRM_POLICY_IN];
-	r_up->fwd = net->xfrm.policy_default[XFRM_POLICY_FWD];
-	r_up->out = net->xfrm.policy_default[XFRM_POLICY_OUT];
+	r_up->in = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_IN]);
+	r_up->fwd = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_FWD]);
+	r_up->out = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_OUT]);
 	nlmsg_end(r_skb, r_nlh);

 	return nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, portid);
@@ -3835,7 +3835,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;

-	if (in_compat_syscall()) {
+	if (IS_ENABLED(CONFIG_COMPAT_FOR_U64_ALIGNMENT) && in_compat_syscall()) {
 		struct xfrm_translator *xtr = xfrm_get_translator();

 		if (!xtr)