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>

3 files changed, 129 insertions, 180 deletions

diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index d5ee96789d4b..bd4ce21d76d7 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -462,7 +462,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 	struct xfrm_offload *xo = xfrm_offload(skb);
 	struct sec_path *sp;
 
-	if (encap_type < 0) {
+	if (encap_type < 0 || (xo && xo->flags & XFRM_GRO)) {
 		x = xfrm_input_state(skb);
 
 		if (unlikely(x->km.state != XFRM_STATE_VALID)) {
@@ -485,9 +485,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 			seq = XFRM_SKB_CB(skb)->seq.input.low;
 			goto resume;
 		}
-
-		/* encap_type < -1 indicates a GRO call. */
-		encap_type = 0;
+		/* GRO call */
 		seq = XFRM_SPI_SKB_CB(skb)->seq;
 
 		if (xo && (xo->flags & CRYPTO_DONE)) {
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index e21cc71095bb..21d50d75c260 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -536,7 +536,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
 	switch (skb->protocol) {
 	case htons(ETH_P_IPV6):
 		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
-		xfrm_decode_session(skb, &fl, AF_INET6);
+		xfrm_decode_session(dev_net(dev), skb, &fl, AF_INET6);
 		if (!dst) {
 			fl.u.ip6.flowi6_oif = dev->ifindex;
 			fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
@@ -551,7 +551,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
 		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);
 		if (!dst) {
 			struct rtable *rt;
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 5cdd3bca3637..c13dc3ef7910 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -149,6 +149,21 @@ struct xfrm_pol_inexact_candidates {
 	struct hlist_head *res[XFRM_POL_CAND_MAX];
 };
 
+struct xfrm_flow_keys {
+	struct flow_dissector_key_basic basic;
+	struct flow_dissector_key_control control;
+	union {
+		struct flow_dissector_key_ipv4_addrs ipv4;
+		struct flow_dissector_key_ipv6_addrs ipv6;
+	} addrs;
+	struct flow_dissector_key_ip ip;
+	struct flow_dissector_key_icmp icmp;
+	struct flow_dissector_key_ports ports;
+	struct flow_dissector_key_keyid gre;
+};
+
+static struct flow_dissector xfrm_session_dissector __ro_after_init;
+
 static DEFINE_SPINLOCK(xfrm_if_cb_lock);
 static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly;
 
@@ -2858,7 +2873,7 @@ static void xfrm_policy_queue_process(struct timer_list *t)
 	/* Fixup the mark to support VTI. */
 	skb_mark = skb->mark;
 	skb->mark = pol->mark.v;
-	xfrm_decode_session(skb, &fl, dst->ops->family);
+	xfrm_decode_session(net, skb, &fl, dst->ops->family);
 	skb->mark = skb_mark;
 	spin_unlock(&pq->hold_queue.lock);
 
@@ -2894,7 +2909,7 @@ static void xfrm_policy_queue_process(struct timer_list *t)
 		/* Fixup the mark to support VTI. */
 		skb_mark = skb->mark;
 		skb->mark = pol->mark.v;
-		xfrm_decode_session(skb, &fl, skb_dst(skb)->ops->family);
+		xfrm_decode_session(net, skb, &fl, skb_dst(skb)->ops->family);
 		skb->mark = skb_mark;
 
 		dst_hold(xfrm_dst_path(skb_dst(skb)));
@@ -3372,209 +3387,106 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star
 }
 
 static void
-decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse)
+decode_session4(const struct xfrm_flow_keys *flkeys, struct flowi *fl, bool reverse)
 {
-	const struct iphdr *iph = ip_hdr(skb);
-	int ihl = iph->ihl;
-	u8 *xprth = skb_network_header(skb) + ihl * 4;
 	struct flowi4 *fl4 = &fl->u.ip4;
-	int oif = 0;
-
-	if (skb_dst(skb) && skb_dst(skb)->dev)
-		oif = skb_dst(skb)->dev->ifindex;
 
 	memset(fl4, 0, sizeof(struct flowi4));
-	fl4->flowi4_mark = skb->mark;
-	fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
-
-	fl4->flowi4_proto = iph->protocol;
-	fl4->daddr = reverse ? iph->saddr : iph->daddr;
-	fl4->saddr = reverse ? iph->daddr : iph->saddr;
-	fl4->flowi4_tos = iph->tos & ~INET_ECN_MASK;
-
-	if (!ip_is_fragment(iph)) {
-		switch (iph->protocol) {
-		case IPPROTO_UDP:
-		case IPPROTO_UDPLITE:
-		case IPPROTO_TCP:
-		case IPPROTO_SCTP:
-		case IPPROTO_DCCP:
-			if (xprth + 4 < skb->data ||
-			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
-				__be16 *ports;
-
-				xprth = skb_network_header(skb) + ihl * 4;
-				ports = (__be16 *)xprth;
-
-				fl4->fl4_sport = ports[!!reverse];
-				fl4->fl4_dport = ports[!reverse];
-			}
-			break;
-		case IPPROTO_ICMP:
-			if (xprth + 2 < skb->data ||
-			    pskb_may_pull(skb, xprth + 2 - skb->data)) {
-				u8 *icmp;
 
-				xprth = skb_network_header(skb) + ihl * 4;
-				icmp = xprth;
+	if (reverse) {
+		fl4->saddr = flkeys->addrs.ipv4.dst;
+		fl4->daddr = flkeys->addrs.ipv4.src;
+		fl4->fl4_sport = flkeys->ports.dst;
+		fl4->fl4_dport = flkeys->ports.src;
+	} else {
+		fl4->saddr = flkeys->addrs.ipv4.src;
+		fl4->daddr = flkeys->addrs.ipv4.dst;
+		fl4->fl4_sport = flkeys->ports.src;
+		fl4->fl4_dport = flkeys->ports.dst;
+	}
 
-				fl4->fl4_icmp_type = icmp[0];
-				fl4->fl4_icmp_code = icmp[1];
-			}
-			break;
-		case IPPROTO_GRE:
-			if (xprth + 12 < skb->data ||
-			    pskb_may_pull(skb, xprth + 12 - skb->data)) {
-				__be16 *greflags;
-				__be32 *gre_hdr;
-
-				xprth = skb_network_header(skb) + ihl * 4;
-				greflags = (__be16 *)xprth;
-				gre_hdr = (__be32 *)xprth;
-
-				if (greflags[0] & GRE_KEY) {
-					if (greflags[0] & GRE_CSUM)
-						gre_hdr++;
-					fl4->fl4_gre_key = gre_hdr[1];
-				}
-			}
-			break;
-		default:
-			break;
-		}
+	switch (flkeys->basic.ip_proto) {
+	case IPPROTO_GRE:
+		fl4->fl4_gre_key = flkeys->gre.keyid;
+		break;
+	case IPPROTO_ICMP:
+		fl4->fl4_icmp_type = flkeys->icmp.type;
+		fl4->fl4_icmp_code = flkeys->icmp.code;
+		break;
 	}
+
+	fl4->flowi4_proto = flkeys->basic.ip_proto;
+	fl4->flowi4_tos = flkeys->ip.tos;
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
 static void
-decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse)
+decode_session6(const struct xfrm_flow_keys *flkeys, struct flowi *fl, bool reverse)
 {
 	struct flowi6 *fl6 = &fl->u.ip6;
-	int onlyproto = 0;
-	const struct ipv6hdr *hdr = ipv6_hdr(skb);
-	u32 offset = sizeof(*hdr);
-	struct ipv6_opt_hdr *exthdr;
-	const unsigned char *nh = skb_network_header(skb);
-	u16 nhoff = IP6CB(skb)->nhoff;
-	int oif = 0;
-	u8 nexthdr;
-
-	if (!nhoff)
-		nhoff = offsetof(struct ipv6hdr, nexthdr);
-
-	nexthdr = nh[nhoff];
-
-	if (skb_dst(skb) && skb_dst(skb)->dev)
-		oif = skb_dst(skb)->dev->ifindex;
 
 	memset(fl6, 0, sizeof(struct flowi6));
-	fl6->flowi6_mark = skb->mark;
-	fl6->flowi6_oif = reverse ? skb->skb_iif : oif;
-
-	fl6->daddr = reverse ? hdr->saddr : hdr->daddr;
-	fl6->saddr = reverse ? hdr->daddr : hdr->saddr;
-
-	while (nh + offset + sizeof(*exthdr) < skb->data ||
-	       pskb_may_pull(skb, nh + offset + sizeof(*exthdr) - skb->data)) {
-		nh = skb_network_header(skb);
-		exthdr = (struct ipv6_opt_hdr *)(nh + offset);
-
-		switch (nexthdr) {
-		case NEXTHDR_FRAGMENT:
-			onlyproto = 1;
-			fallthrough;
-		case NEXTHDR_ROUTING:
-		case NEXTHDR_HOP:
-		case NEXTHDR_DEST:
-			offset += ipv6_optlen(exthdr);
-			nexthdr = exthdr->nexthdr;
-			break;
-		case IPPROTO_UDP:
-		case IPPROTO_UDPLITE:
-		case IPPROTO_TCP:
-		case IPPROTO_SCTP:
-		case IPPROTO_DCCP:
-			if (!onlyproto && (nh + offset + 4 < skb->data ||
-			     pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
-				__be16 *ports;
-
-				nh = skb_network_header(skb);
-				ports = (__be16 *)(nh + offset);
-				fl6->fl6_sport = ports[!!reverse];
-				fl6->fl6_dport = ports[!reverse];
-			}
-			fl6->flowi6_proto = nexthdr;
-			return;
-		case IPPROTO_ICMPV6:
-			if (!onlyproto && (nh + offset + 2 < skb->data ||
-			    pskb_may_pull(skb, nh + offset + 2 - skb->data))) {
-				u8 *icmp;
-
-				nh = skb_network_header(skb);
-				icmp = (u8 *)(nh + offset);
-				fl6->fl6_icmp_type = icmp[0];
-				fl6->fl6_icmp_code = icmp[1];
-			}
-			fl6->flowi6_proto = nexthdr;
-			return;
-		case IPPROTO_GRE:
-			if (!onlyproto &&
-			    (nh + offset + 12 < skb->data ||
-			     pskb_may_pull(skb, nh + offset + 12 - skb->data))) {
-				struct gre_base_hdr *gre_hdr;
-				__be32 *gre_key;
-
-				nh = skb_network_header(skb);
-				gre_hdr = (struct gre_base_hdr *)(nh + offset);
-				gre_key = (__be32 *)(gre_hdr + 1);
-
-				if (gre_hdr->flags & GRE_KEY) {
-					if (gre_hdr->flags & GRE_CSUM)
-						gre_key++;
-					fl6->fl6_gre_key = *gre_key;
-				}
-			}
-			fl6->flowi6_proto = nexthdr;
-			return;
 
-#if IS_ENABLED(CONFIG_IPV6_MIP6)
-		case IPPROTO_MH:
-			offset += ipv6_optlen(exthdr);
-			if (!onlyproto && (nh + offset + 3 < skb->data ||
-			    pskb_may_pull(skb, nh + offset + 3 - skb->data))) {
-				struct ip6_mh *mh;
-
-				nh = skb_network_header(skb);
-				mh = (struct ip6_mh *)(nh + offset);
-				fl6->fl6_mh_type = mh->ip6mh_type;
-			}
-			fl6->flowi6_proto = nexthdr;
-			return;
-#endif
-		default:
-			fl6->flowi6_proto = nexthdr;
-			return;
-		}
+	if (reverse) {
+		fl6->saddr = flkeys->addrs.ipv6.dst;
+		fl6->daddr = flkeys->addrs.ipv6.src;
+		fl6->fl6_sport = flkeys->ports.dst;
+		fl6->fl6_dport = flkeys->ports.src;
+	} else {
+		fl6->saddr = flkeys->addrs.ipv6.src;
+		fl6->daddr = flkeys->addrs.ipv6.dst;
+		fl6->fl6_sport = flkeys->ports.src;
+		fl6->fl6_dport = flkeys->ports.dst;
+	}
+
+	switch (flkeys->basic.ip_proto) {
+	case IPPROTO_GRE:
+		fl6->fl6_gre_key = flkeys->gre.keyid;
+		break;
+	case IPPROTO_ICMPV6:
+		fl6->fl6_icmp_type = flkeys->icmp.type;
+		fl6->fl6_icmp_code = flkeys->icmp.code;
+		break;
 	}
+
+	fl6->flowi6_proto = flkeys->basic.ip_proto;
 }
 #endif
 
-int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
+int __xfrm_decode_session(struct net *net, struct sk_buff *skb, struct flowi *fl,
 			  unsigned int family, int reverse)
 {
+	struct xfrm_flow_keys flkeys;
+
+	memset(&flkeys, 0, sizeof(flkeys));
+	__skb_flow_dissect(net, skb, &xfrm_session_dissector, &flkeys,
+			   NULL, 0, 0, 0, FLOW_DISSECTOR_F_STOP_AT_ENCAP);
+
 	switch (family) {
 	case AF_INET:
-		decode_session4(skb, fl, reverse);
+		decode_session4(&flkeys, fl, reverse);
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
-		decode_session6(skb, fl, reverse);
+		decode_session6(&flkeys, fl, reverse);
 		break;
 #endif
 	default:
 		return -EAFNOSUPPORT;
 	}
 
+	fl->flowi_mark = skb->mark;
+	if (reverse) {
+		fl->flowi_oif = skb->skb_iif;
+	} else {
+		int oif = 0;
+
+		if (skb_dst(skb) && skb_dst(skb)->dev)
+			oif = skb_dst(skb)->dev->ifindex;
+
+		fl->flowi_oif = oif;
+	}
+
 	return security_xfrm_decode_session(skb, &fl->flowi_secid);
 }
 EXPORT_SYMBOL(__xfrm_decode_session);
@@ -3623,7 +3535,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	reverse = dir & ~XFRM_POLICY_MASK;
 	dir &= XFRM_POLICY_MASK;
 
-	if (__xfrm_decode_session(skb, &fl, family, reverse) < 0) {
+	if (__xfrm_decode_session(net, skb, &fl, family, reverse) < 0) {
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
 		return 0;
 	}
@@ -3779,7 +3691,7 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family)
 	struct dst_entry *dst;
 	int res = 1;
 
-	if (xfrm_decode_session(skb, &fl, family) < 0) {
+	if (xfrm_decode_session(net, skb, &fl, family) < 0) {
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR);
 		return 0;
 	}
@@ -4258,8 +4170,47 @@ static struct pernet_operations __net_initdata xfrm_net_ops = {
 	.exit = xfrm_net_exit,
 };
 
+static const struct flow_dissector_key xfrm_flow_dissector_keys[] = {
+	{
+		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
+		.offset = offsetof(struct xfrm_flow_keys, control),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_BASIC,
+		.offset = offsetof(struct xfrm_flow_keys, basic),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+		.offset = offsetof(struct xfrm_flow_keys, addrs.ipv4),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+		.offset = offsetof(struct xfrm_flow_keys, addrs.ipv6),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_PORTS,
+		.offset = offsetof(struct xfrm_flow_keys, ports),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_GRE_KEYID,
+		.offset = offsetof(struct xfrm_flow_keys, gre),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IP,
+		.offset = offsetof(struct xfrm_flow_keys, ip),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_ICMP,
+		.offset = offsetof(struct xfrm_flow_keys, icmp),
+	},
+};
+
 void __init xfrm_init(void)
 {
+	skb_flow_dissector_init(&xfrm_session_dissector,
+				xfrm_flow_dissector_keys,
+				ARRAY_SIZE(xfrm_flow_dissector_keys));
+
 	register_pernet_subsys(&xfrm_net_ops);
 	xfrm_dev_init();
 	xfrm_input_init();