Merge tag 'ipsec-next-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next

Steffen Klassert says:

====================
pull request (net-next): ipsec-next 2023-10-28

1) Remove unused function declarations of xfrm4_extract_input and
   xfrm6_extract_input. From Yue Haibing.

2) Annotate struct xfrm_sec_ctx with __counted_by.
   From Kees Cook.

3) Support GRO decapsulation for ESP in UDP encapsulation.
   From Antony Antony et all.

4) Replace the xfrm session decode with flow dissector.
   From Florian Westphal.

5) Fix a use after free in __xfrm6_udp_encap_rcv.

6) Fix the layer 4 flowi decoding.
   From Florian Westphal.

* tag 'ipsec-next-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next:
  xfrm: policy: fix layer 4 flowi decoding
  xfrm Fix use after free in __xfrm6_udp_encap_rcv.
  xfrm: policy: replace session decode with flow dissector
  xfrm: move mark and oif flowi decode into common code
  xfrm: pass struct net to xfrm_decode_session wrappers
  xfrm: Support GRO for IPv6 ESP in UDP encapsulation
  xfrm: Support GRO for IPv4 ESP in UDP encapsulation
  xfrm: Use the XFRM_GRO to indicate a GRO call on input
  xfrm: Annotate struct xfrm_sec_ctx with __counted_by
  xfrm: Remove unused function declarations
====================

Link: https://lore.kernel.org/r/20231028084328.3119236-1-steffen.klassert@secunet.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 95 insertions, 27 deletions

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c35d302a3da9..13a1833a4df5 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1050,6 +1050,7 @@ static const struct ipv6_stub ipv6_stub_impl = {
 #if IS_ENABLED(CONFIG_XFRM)
 	.xfrm6_local_rxpmtu = xfrm6_local_rxpmtu,
 	.xfrm6_udp_encap_rcv = xfrm6_udp_encap_rcv,
+	.xfrm6_gro_udp_encap_rcv = xfrm6_gro_udp_encap_rcv,
 	.xfrm6_rcv_encap = xfrm6_rcv_encap,
 #endif
 	.nd_tbl	= &nd_tbl,
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index a189e08370a5..527b7caddbc6 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -34,7 +34,9 @@ static __u16 esp6_nexthdr_esp_offset(struct ipv6hdr *ipv6_hdr, int nhlen)
 	int off = sizeof(struct ipv6hdr);
 	struct ipv6_opt_hdr *exthdr;
 
-	if (likely(ipv6_hdr->nexthdr == NEXTHDR_ESP))
+	/* ESP or ESPINUDP */
+	if (likely(ipv6_hdr->nexthdr == NEXTHDR_ESP ||
+		   ipv6_hdr->nexthdr == NEXTHDR_UDP))
 		return offsetof(struct ipv6hdr, nexthdr);
 
 	while (off < nhlen) {
@@ -54,10 +56,14 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 	int offset = skb_gro_offset(skb);
 	struct xfrm_offload *xo;
 	struct xfrm_state *x;
+	int encap_type = 0;
 	__be32 seq;
 	__be32 spi;
 	int nhoff;
 
+	if (NAPI_GRO_CB(skb)->proto == IPPROTO_UDP)
+		encap_type = UDP_ENCAP_ESPINUDP;
+
 	if (!pskb_pull(skb, offset))
 		return NULL;
 
@@ -104,7 +110,7 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 
 	/* We don't need to handle errors from xfrm_input, it does all
 	 * the error handling and frees the resources on error. */
-	xfrm_input(skb, IPPROTO_ESP, spi, -2);
+	xfrm_input(skb, IPPROTO_ESP, spi, encap_type);
 
 	return ERR_PTR(-EINPROGRESS);
 out_reset:
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 8fb4a791881a..f62427097126 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -385,7 +385,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net,
 			return dst;
 	}
 
-	err = xfrm_decode_session_reverse(skb, flowi6_to_flowi(&fl2), AF_INET6);
+	err = xfrm_decode_session_reverse(net, skb, flowi6_to_flowi(&fl2), AF_INET6);
 	if (err)
 		goto relookup_failed;
 
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 73c85d4e0e9c..e550240c85e1 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -569,11 +569,11 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 			goto tx_err;
 
 		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
-		xfrm_decode_session(skb, &fl, AF_INET6);
+		xfrm_decode_session(dev_net(dev), skb, &fl, AF_INET6);
 		break;
 	case htons(ETH_P_IP):
 		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
-		xfrm_decode_session(skb, &fl, AF_INET);
+		xfrm_decode_session(dev_net(dev), skb, &fl, AF_INET);
 		break;
 	default:
 		goto tx_err;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 857713d7a38a..53d255838e6a 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -61,7 +61,7 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff
 
 #ifdef CONFIG_XFRM
 	if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
-	    xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) {
+	    xfrm_decode_session(net, skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) {
 		skb_dst_set(skb, NULL);
 		dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0);
 		if (IS_ERR(dst))
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 4156387248e4..6e36e5047fba 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -16,6 +16,8 @@
 #include <linux/netfilter_ipv6.h>
 #include <net/ipv6.h>
 #include <net/xfrm.h>
+#include <net/protocol.h>
+#include <net/gro.h>
 
 int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi,
 		  struct ip6_tnl *t)
@@ -67,14 +69,7 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
 	return 0;
 }
 
-/* If it's a keepalive packet, then just eat it.
- * If it's an encapsulated packet, then pass it to the
- * IPsec xfrm input.
- * Returns 0 if skb passed to xfrm or was dropped.
- * Returns >0 if skb should be passed to UDP.
- * Returns <0 if skb should be resubmitted (-ret is protocol)
- */
-int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
+static int __xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb, bool pull)
 {
 	struct udp_sock *up = udp_sk(sk);
 	struct udphdr *uh;
@@ -85,9 +80,6 @@ int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
 	__be32 *udpdata32;
 	u16 encap_type;
 
-	if (skb->protocol == htons(ETH_P_IP))
-		return xfrm4_udp_encap_rcv(sk, skb);
-
 	encap_type = READ_ONCE(up->encap_type);
 	/* if this is not encapsulated socket, then just return now */
 	if (!encap_type)
@@ -109,7 +101,7 @@ int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
 	case UDP_ENCAP_ESPINUDP:
 		/* Check if this is a keepalive packet.  If so, eat it. */
 		if (len == 1 && udpdata[0] == 0xff) {
-			goto drop;
+			return -EINVAL;
 		} else if (len > sizeof(struct ip_esp_hdr) && udpdata32[0] != 0) {
 			/* ESP Packet without Non-ESP header */
 			len = sizeof(struct udphdr);
@@ -120,7 +112,7 @@ int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
 	case UDP_ENCAP_ESPINUDP_NON_IKE:
 		/* Check if this is a keepalive packet.  If so, eat it. */
 		if (len == 1 && udpdata[0] == 0xff) {
-			goto drop;
+			return -EINVAL;
 		} else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) &&
 			   udpdata32[0] == 0 && udpdata32[1] == 0) {
 
@@ -138,31 +130,100 @@ int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
 	 * protocol to ESP, and then call into the transform receiver.
 	 */
 	if (skb_unclone(skb, GFP_ATOMIC))
-		goto drop;
+		return -EINVAL;
 
 	/* Now we can update and verify the packet length... */
 	ip6h = ipv6_hdr(skb);
 	ip6h->payload_len = htons(ntohs(ip6h->payload_len) - len);
 	if (skb->len < ip6hlen + len) {
 		/* packet is too small!?! */
-		goto drop;
+		return -EINVAL;
 	}
 
 	/* pull the data buffer up to the ESP header and set the
 	 * transport header to point to ESP.  Keep UDP on the stack
 	 * for later.
 	 */
-	__skb_pull(skb, len);
-	skb_reset_transport_header(skb);
+	if (pull) {
+		__skb_pull(skb, len);
+		skb_reset_transport_header(skb);
+	} else {
+		skb_set_transport_header(skb, len);
+	}
 
 	/* process ESP */
-	return xfrm6_rcv_encap(skb, IPPROTO_ESP, 0, encap_type);
-
-drop:
-	kfree_skb(skb);
 	return 0;
 }
 
+/* If it's a keepalive packet, then just eat it.
+ * If it's an encapsulated packet, then pass it to the
+ * IPsec xfrm input.
+ * Returns 0 if skb passed to xfrm or was dropped.
+ * Returns >0 if skb should be passed to UDP.
+ * Returns <0 if skb should be resubmitted (-ret is protocol)
+ */
+int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
+{
+	int ret;
+
+	if (skb->protocol == htons(ETH_P_IP))
+		return xfrm4_udp_encap_rcv(sk, skb);
+
+	ret = __xfrm6_udp_encap_rcv(sk, skb, true);
+	if (!ret)
+		return xfrm6_rcv_encap(skb, IPPROTO_ESP, 0,
+				       udp_sk(sk)->encap_type);
+
+	if (ret < 0) {
+		kfree_skb(skb);
+		return 0;
+	}
+
+	return ret;
+}
+
+struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
+					struct sk_buff *skb)
+{
+	int offset = skb_gro_offset(skb);
+	const struct net_offload *ops;
+	struct sk_buff *pp = NULL;
+	int ret;
+
+	if (skb->protocol == htons(ETH_P_IP))
+		return xfrm4_gro_udp_encap_rcv(sk, head, skb);
+
+	offset = offset - sizeof(struct udphdr);
+
+	if (!pskb_pull(skb, offset))
+		return NULL;
+
+	rcu_read_lock();
+	ops = rcu_dereference(inet6_offloads[IPPROTO_ESP]);
+	if (!ops || !ops->callbacks.gro_receive)
+		goto out;
+
+	ret = __xfrm6_udp_encap_rcv(sk, skb, false);
+	if (ret)
+		goto out;
+
+	skb_push(skb, offset);
+	NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;
+
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
+	rcu_read_unlock();
+
+	return pp;
+
+out:
+	rcu_read_unlock();
+	skb_push(skb, offset);
+	NAPI_GRO_CB(skb)->same_flow = 0;
+	NAPI_GRO_CB(skb)->flush = 1;
+
+	return NULL;
+}
+
 int xfrm6_rcv_tnl(struct sk_buff *skb, struct ip6_tnl *t)
 {
 	return xfrm6_rcv_spi(skb, skb_network_header(skb)[IP6CB(skb)->nhoff],