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

Steffen Klassert says:

====================
pull request (net): ipsec 2020-05-29

1) Several fixes for ESP gro/gso in transport and beet mode when
   IPv6 extension headers are present. From Xin Long.

2) Fix a wrong comment on XFRMA_OFFLOAD_DEV.
   From Antony Antony.

3) Fix sk_destruct callback handling on ESP in TCP encapsulation.
   From Sabrina Dubroca.

4) Fix a use after free in xfrm_output_gso when used with vxlan.
   From Xin Long.

5) Fix secpath handling of VTI when used wiuth IPCOMP.
   From Xin Long.

6) Fix an oops when deleting a x-netns xfrm interface.
   From Nicolas Dichtel.

7) Fix a possible warning on policy updates. We had a case where it was
   possible to add two policies with the same lookup keys.
   From Xin Long.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

11 files changed, 104 insertions, 44 deletions

diff --git a/include/net/espintcp.h b/include/net/espintcp.h
index dd7026a00066..0335bbd76552 100644
--- a/include/net/espintcp.h
+++ b/include/net/espintcp.h
@@ -25,6 +25,7 @@ struct espintcp_ctx {
 	struct espintcp_msg partial;
 	void (*saved_data_ready)(struct sock *sk);
 	void (*saved_write_space)(struct sock *sk);
+	void (*saved_destruct)(struct sock *sk);
 	struct work_struct work;
 	bool tx_running;
 };
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index 5f3b9fec7b5f..ff7cfdc6cb44 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -304,7 +304,7 @@ enum xfrm_attr_type_t {
 	XFRMA_PROTO,		/* __u8 */
 	XFRMA_ADDRESS_FILTER,	/* struct xfrm_address_filter */
 	XFRMA_PAD,
-	XFRMA_OFFLOAD_DEV,	/* struct xfrm_state_offload */
+	XFRMA_OFFLOAD_DEV,	/* struct xfrm_user_offload */
 	XFRMA_SET_MARK,		/* __u32 */
 	XFRMA_SET_MARK_MASK,	/* __u32 */
 	XFRMA_IF_ID,		/* __u32 */
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 731022cff600..d14133eac476 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -63,10 +63,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 		sp->olen++;
 
 		xo = xfrm_offload(skb);
-		if (!xo) {
-			xfrm_state_put(x);
+		if (!xo)
 			goto out_reset;
-		}
 	}
 
 	xo->flags |= XFRM_GRO;
@@ -139,19 +137,27 @@ static struct sk_buff *xfrm4_beet_gso_segment(struct xfrm_state *x,
 	struct xfrm_offload *xo = xfrm_offload(skb);
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
-	int proto = xo->proto;
+	u8 proto = xo->proto;
 
 	skb->transport_header += x->props.header_len;
 
-	if (proto == IPPROTO_BEETPH) {
-		struct ip_beet_phdr *ph = (struct ip_beet_phdr *)skb->data;
+	if (x->sel.family != AF_INET6) {
+		if (proto == IPPROTO_BEETPH) {
+			struct ip_beet_phdr *ph =
+				(struct ip_beet_phdr *)skb->data;
+
+			skb->transport_header += ph->hdrlen * 8;
+			proto = ph->nexthdr;
+		} else {
+			skb->transport_header -= IPV4_BEET_PHMAXLEN;
+		}
+	} else {
+		__be16 frag;
 
-		skb->transport_header += ph->hdrlen * 8;
-		proto = ph->nexthdr;
-	} else if (x->sel.family != AF_INET6) {
-		skb->transport_header -= IPV4_BEET_PHMAXLEN;
-	} else if (proto == IPPROTO_TCP) {
-		skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
+		skb->transport_header +=
+			ipv6_skip_exthdr(skb, 0, &proto, &frag);
+		if (proto == IPPROTO_TCP)
+			skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
 	}
 
 	__skb_pull(skb, skb_transport_offset(skb));
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 1b4e6f298648..1dda7c155c48 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -93,7 +93,28 @@ static int vti_rcv_proto(struct sk_buff *skb)
 
 static int vti_rcv_tunnel(struct sk_buff *skb)
 {
-	return vti_rcv(skb, ip_hdr(skb)->saddr, true);
+	struct ip_tunnel_net *itn = net_generic(dev_net(skb->dev), vti_net_id);
+	const struct iphdr *iph = ip_hdr(skb);
+	struct ip_tunnel *tunnel;
+
+	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+				  iph->saddr, iph->daddr, 0);
+	if (tunnel) {
+		struct tnl_ptk_info tpi = {
+			.proto = htons(ETH_P_IP),
+		};
+
+		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+			goto drop;
+		if (iptunnel_pull_header(skb, 0, tpi.proto, false))
+			goto drop;
+		return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, false);
+	}
+
+	return -EINVAL;
+drop:
+	kfree_skb(skb);
+	return 0;
 }
 
 static int vti_rcv_cb(struct sk_buff *skb, int err)
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 8eab2c869d61..ab0eea336c70 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -85,10 +85,8 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 		sp->olen++;
 
 		xo = xfrm_offload(skb);
-		if (!xo) {
-			xfrm_state_put(x);
+		if (!xo)
 			goto out_reset;
-		}
 	}
 
 	xo->flags |= XFRM_GRO;
@@ -123,9 +121,16 @@ static void esp6_gso_encap(struct xfrm_state *x, struct sk_buff *skb)
 	struct ip_esp_hdr *esph;
 	struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct xfrm_offload *xo = xfrm_offload(skb);
-	int proto = iph->nexthdr;
+	u8 proto = iph->nexthdr;
 
 	skb_push(skb, -skb_network_offset(skb));
+
+	if (x->outer_mode.encap == XFRM_MODE_TRANSPORT) {
+		__be16 frag;
+
+		ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &proto, &frag);
+	}
+
 	esph = ip_esp_hdr(skb);
 	*skb_mac_header(skb) = IPPROTO_ESP;
 
@@ -166,23 +171,31 @@ static struct sk_buff *xfrm6_beet_gso_segment(struct xfrm_state *x,
 	struct xfrm_offload *xo = xfrm_offload(skb);
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
-	int proto = xo->proto;
+	u8 proto = xo->proto;
 
 	skb->transport_header += x->props.header_len;
 
-	if (proto == IPPROTO_BEETPH) {
-		struct ip_beet_phdr *ph = (struct ip_beet_phdr *)skb->data;
-
-		skb->transport_header += ph->hdrlen * 8;
-		proto = ph->nexthdr;
-	}
-
 	if (x->sel.family != AF_INET6) {
 		skb->transport_header -=
 			(sizeof(struct ipv6hdr) - sizeof(struct iphdr));
 
+		if (proto == IPPROTO_BEETPH) {
+			struct ip_beet_phdr *ph =
+				(struct ip_beet_phdr *)skb->data;
+
+			skb->transport_header += ph->hdrlen * 8;
+			proto = ph->nexthdr;
+		} else {
+			skb->transport_header -= IPV4_BEET_PHMAXLEN;
+		}
+
 		if (proto == IPPROTO_TCP)
 			skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6;
+	} else {
+		__be16 frag;
+
+		skb->transport_header +=
+			ipv6_skip_exthdr(skb, 0, &proto, &frag);
 	}
 
 	__skb_pull(skb, skb_transport_offset(skb));
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index 037ea156d2f9..5a0ff665b71a 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -379,6 +379,7 @@ static void espintcp_destruct(struct sock *sk)
 {
 	struct espintcp_ctx *ctx = espintcp_getctx(sk);
 
+	ctx->saved_destruct(sk);
 	kfree(ctx);
 }
 
@@ -419,6 +420,7 @@ static int espintcp_init_sk(struct sock *sk)
 	sk->sk_socket->ops = &espintcp_ops;
 	ctx->saved_data_ready = sk->sk_data_ready;
 	ctx->saved_write_space = sk->sk_write_space;
+	ctx->saved_destruct = sk->sk_destruct;
 	sk->sk_data_ready = espintcp_data_ready;
 	sk->sk_write_space = espintcp_write_space;
 	sk->sk_destruct = espintcp_destruct;
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 6cc7f7f1dd68..f50d1f97cf8e 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -25,12 +25,10 @@ static void __xfrm_transport_prep(struct xfrm_state *x, struct sk_buff *skb,
 	struct xfrm_offload *xo = xfrm_offload(skb);
 
 	skb_reset_mac_len(skb);
-	pskb_pull(skb, skb->mac_len + hsize + x->props.header_len);
-
-	if (xo->flags & XFRM_GSO_SEGMENT) {
-		skb_reset_transport_header(skb);
+	if (xo->flags & XFRM_GSO_SEGMENT)
 		skb->transport_header -= x->props.header_len;
-	}
+
+	pskb_pull(skb, skb_transport_offset(skb) + x->props.header_len);
 }
 
 static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb,
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index aa35f23c4912..8a202c44f89a 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -644,7 +644,7 @@ resume:
 		dev_put(skb->dev);
 
 		spin_lock(&x->lock);
-		if (nexthdr <= 0) {
+		if (nexthdr < 0) {
 			if (nexthdr == -EBADMSG) {
 				xfrm_audit_state_icvfail(x, skb,
 							 x->type->proto);
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 3361e3ac5714..1e115cbf21d3 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -750,7 +750,28 @@ static struct rtnl_link_ops xfrmi_link_ops __read_mostly = {
 	.get_link_net	= xfrmi_get_link_net,
 };
 
+static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list)
+{
+	struct net *net;
+	LIST_HEAD(list);
+
+	rtnl_lock();
+	list_for_each_entry(net, net_exit_list, exit_list) {
+		struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+		struct xfrm_if __rcu **xip;
+		struct xfrm_if *xi;
+
+		for (xip = &xfrmn->xfrmi[0];
+		     (xi = rtnl_dereference(*xip)) != NULL;
+		     xip = &xi->next)
+			unregister_netdevice_queue(xi->dev, &list);
+	}
+	unregister_netdevice_many(&list);
+	rtnl_unlock();
+}
+
 static struct pernet_operations xfrmi_net_ops = {
+	.exit_batch = xfrmi_exit_batch_net,
 	.id   = &xfrmi_net_id,
 	.size = sizeof(struct xfrmi_net),
 };
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 2fd3d990d992..69c4900db817 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -583,18 +583,20 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 		xfrm_state_hold(x);
 
 		if (skb_is_gso(skb)) {
-			skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
+			if (skb->inner_protocol)
+				return xfrm_output_gso(net, sk, skb);
 
-			return xfrm_output2(net, sk, skb);
+			skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
+			goto out;
 		}
 
 		if (x->xso.dev && x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM)
 			goto out;
+	} else {
+		if (skb_is_gso(skb))
+			return xfrm_output_gso(net, sk, skb);
 	}
 
-	if (skb_is_gso(skb))
-		return xfrm_output_gso(net, sk, skb);
-
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		err = skb_checksum_help(skb);
 		if (err) {
@@ -640,7 +642,8 @@ void xfrm_local_error(struct sk_buff *skb, int mtu)
 
 	if (skb->protocol == htons(ETH_P_IP))
 		proto = AF_INET;
-	else if (skb->protocol == htons(ETH_P_IPV6))
+	else if (skb->protocol == htons(ETH_P_IPV6) &&
+		 skb->sk->sk_family == AF_INET6)
 		proto = AF_INET6;
 	else
 		return;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 297b2fdb3c29..564aa6492e7c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1436,12 +1436,7 @@ static void xfrm_policy_requeue(struct xfrm_policy *old,
 static bool xfrm_policy_mark_match(struct xfrm_policy *policy,
 				   struct xfrm_policy *pol)
 {
-	u32 mark = policy->mark.v & policy->mark.m;
-
-	if (policy->mark.v == pol->mark.v && policy->mark.m == pol->mark.m)
-		return true;
-
-	if ((mark & pol->mark.m) == pol->mark.v &&
+	if (policy->mark.v == pol->mark.v &&
 	    policy->priority == pol->priority)
 		return true;