Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec

Steffen Klassert says:

====================
ipsec 2022-11-23

1) Fix "disable_policy" on ipv4 early demuxP Packets after
   the initial packet in a flow might be incorectly dropped
   on early demux if there are no matching policies.
   From Eyal Birger.

2) Fix a kernel warning in case XFRM encap type is not
   available. From Eyal Birger.

3) Fix ESN wrap around for GSO to avoid a double usage of a
    sequence number. From Christian Langrock.

4) Fix a send_acquire race with pfkey_register.
   From Herbert Xu.

5) Fix a list corruption panic in __xfrm_state_delete().
   Thomas Jarosch.

6) Fix an unchecked return value in xfrm6_init().
   Chen Zhongjin.

* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec:
  xfrm: Fix ignored return value in xfrm6_init()
  xfrm: Fix oops in __xfrm_state_delete()
  af_key: Fix send_acquire race with pfkey_register
  xfrm: replay: Fix ESN wrap around for GSO
  xfrm: lwtunnel: squelch kernel warning in case XFRM encap type is not available
  xfrm: fix "disable_policy" on ipv4 early demux
====================

Link: https://lore.kernel.org/r/20221123093117.434274-1-steffen.klassert@secunet.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

8 files changed, 57 insertions, 15 deletions

diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 6fac2f0ef074..711cd3b4347a 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -48,9 +48,11 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type)
 		return "RPL";
 	case LWTUNNEL_ENCAP_IOAM6:
 		return "IOAM6";
+	case LWTUNNEL_ENCAP_XFRM:
+		/* module autoload not supported for encap type */
+		return NULL;
 	case LWTUNNEL_ENCAP_IP6:
 	case LWTUNNEL_ENCAP_IP:
-	case LWTUNNEL_ENCAP_XFRM:
 	case LWTUNNEL_ENCAP_NONE:
 	case __LWTUNNEL_ENCAP_MAX:
 		/* should not have got here */
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 170152772d33..3969fa805679 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -314,6 +314,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features_
 			xo->seq.low += skb_shinfo(skb)->gso_segs;
 	}
 
+	if (xo->seq.low < seq)
+		xo->seq.hi++;
+
 	esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32));
 
 	ip_hdr(skb)->tot_len = htons(skb->len);
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 1b512390b3cf..e880ce77322a 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -366,6 +366,11 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 					   iph->tos, dev);
 		if (unlikely(err))
 			goto drop_error;
+	} else {
+		struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+		if (in_dev && IN_DEV_ORCONF(in_dev, NOPOLICY))
+			IPCB(skb)->flags |= IPSKB_NOPOLICY;
 	}
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 79d43548279c..242f4295940e 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -346,6 +346,9 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features
 			xo->seq.low += skb_shinfo(skb)->gso_segs;
 	}
 
+	if (xo->seq.low < seq)
+		xo->seq.hi++;
+
 	esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32));
 
 	len = skb->len - sizeof(struct ipv6hdr);
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 4a4b0e49ec92..ea435eba3053 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -287,9 +287,13 @@ int __init xfrm6_init(void)
 	if (ret)
 		goto out_state;
 
-	register_pernet_subsys(&xfrm6_net_ops);
+	ret = register_pernet_subsys(&xfrm6_net_ops);
+	if (ret)
+		goto out_protocol;
 out:
 	return ret;
+out_protocol:
+	xfrm6_protocol_fini();
 out_state:
 	xfrm6_state_fini();
 out_policy:
diff --git a/net/key/af_key.c b/net/key/af_key.c
index c85df5b958d2..95edcbedf6ef 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -2905,7 +2905,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t)
 			break;
 		if (!aalg->pfkey_supported)
 			continue;
-		if (aalg_tmpl_set(t, aalg) && aalg->available)
+		if (aalg_tmpl_set(t, aalg))
 			sz += sizeof(struct sadb_comb);
 	}
 	return sz + sizeof(struct sadb_prop);
@@ -2923,7 +2923,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t)
 		if (!ealg->pfkey_supported)
 			continue;
 
-		if (!(ealg_tmpl_set(t, ealg) && ealg->available))
+		if (!(ealg_tmpl_set(t, ealg)))
 			continue;
 
 		for (k = 1; ; k++) {
@@ -2934,16 +2934,17 @@ static int count_esp_combs(const struct xfrm_tmpl *t)
 			if (!aalg->pfkey_supported)
 				continue;
 
-			if (aalg_tmpl_set(t, aalg) && aalg->available)
+			if (aalg_tmpl_set(t, aalg))
 				sz += sizeof(struct sadb_comb);
 		}
 	}
 	return sz + sizeof(struct sadb_prop);
 }
 
-static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
+static int dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
 {
 	struct sadb_prop *p;
+	int sz = 0;
 	int i;
 
 	p = skb_put(skb, sizeof(struct sadb_prop));
@@ -2971,13 +2972,17 @@ static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
 			c->sadb_comb_soft_addtime = 20*60*60;
 			c->sadb_comb_hard_usetime = 8*60*60;
 			c->sadb_comb_soft_usetime = 7*60*60;
+			sz += sizeof(*c);
 		}
 	}
+
+	return sz + sizeof(*p);
 }
 
-static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
+static int dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
 {
 	struct sadb_prop *p;
+	int sz = 0;
 	int i, k;
 
 	p = skb_put(skb, sizeof(struct sadb_prop));
@@ -3019,8 +3024,11 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
 			c->sadb_comb_soft_addtime = 20*60*60;
 			c->sadb_comb_hard_usetime = 8*60*60;
 			c->sadb_comb_soft_usetime = 7*60*60;
+			sz += sizeof(*c);
 		}
 	}
+
+	return sz + sizeof(*p);
 }
 
 static int key_notify_policy_expire(struct xfrm_policy *xp, const struct km_event *c)
@@ -3150,6 +3158,7 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct
 	struct sadb_x_sec_ctx *sec_ctx;
 	struct xfrm_sec_ctx *xfrm_ctx;
 	int ctx_size = 0;
+	int alg_size = 0;
 
 	sockaddr_size = pfkey_sockaddr_size(x->props.family);
 	if (!sockaddr_size)
@@ -3161,16 +3170,16 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct
 		sizeof(struct sadb_x_policy);
 
 	if (x->id.proto == IPPROTO_AH)
-		size += count_ah_combs(t);
+		alg_size = count_ah_combs(t);
 	else if (x->id.proto == IPPROTO_ESP)
-		size += count_esp_combs(t);
+		alg_size = count_esp_combs(t);
 
 	if ((xfrm_ctx = x->security)) {
 		ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len);
 		size +=  sizeof(struct sadb_x_sec_ctx) + ctx_size;
 	}
 
-	skb =  alloc_skb(size + 16, GFP_ATOMIC);
+	skb =  alloc_skb(size + alg_size + 16, GFP_ATOMIC);
 	if (skb == NULL)
 		return -ENOMEM;
 
@@ -3224,10 +3233,13 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct
 	pol->sadb_x_policy_priority = xp->priority;
 
 	/* Set sadb_comb's. */
+	alg_size = 0;
 	if (x->id.proto == IPPROTO_AH)
-		dump_ah_combs(skb, t);
+		alg_size = dump_ah_combs(skb, t);
 	else if (x->id.proto == IPPROTO_ESP)
-		dump_esp_combs(skb, t);
+		alg_size = dump_esp_combs(skb, t);
+
+	hdr->sadb_msg_len += alg_size / 8;
 
 	/* security context */
 	if (xfrm_ctx) {
@@ -3382,7 +3394,7 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
 	hdr->sadb_msg_len = size / sizeof(uint64_t);
 	hdr->sadb_msg_errno = 0;
 	hdr->sadb_msg_reserved = 0;
-	hdr->sadb_msg_seq = x->km.seq = get_acqseq();
+	hdr->sadb_msg_seq = x->km.seq;
 	hdr->sadb_msg_pid = 0;
 
 	/* SA */
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 5f5aafd418af..21269e8f2db4 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -97,6 +97,18 @@ static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb)
 	}
 }
 
+static inline bool xmit_xfrm_check_overflow(struct sk_buff *skb)
+{
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	__u32 seq = xo->seq.low;
+
+	seq += skb_shinfo(skb)->gso_segs;
+	if (unlikely(seq < xo->seq.low))
+		return true;
+
+	return false;
+}
+
 struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again)
 {
 	int err;
@@ -134,7 +146,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
 		return skb;
 	}
 
-	if (skb_is_gso(skb) && unlikely(x->xso.dev != dev)) {
+	if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) ||
+				unlikely(xmit_xfrm_check_overflow(skb)))) {
 		struct sk_buff *segs;
 
 		/* Packet got rerouted, fixup features and segment it. */
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
index 9f4d42eb090f..ce56d659c55a 100644
--- a/net/xfrm/xfrm_replay.c
+++ b/net/xfrm/xfrm_replay.c
@@ -714,7 +714,7 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff
 			oseq += skb_shinfo(skb)->gso_segs;
 		}
 
-		if (unlikely(oseq < replay_esn->oseq)) {
+		if (unlikely(xo->seq.low < replay_esn->oseq)) {
 			XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi;
 			xo->seq.hi = oseq_hi;
 			replay_esn->oseq_hi = oseq_hi;