Merge tag 'nf-next-2023-05-18' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next

Florian Westphal says:

====================
Netfilter updates for net-next

nftables updates:

1. Allow key existence checks with maps.
   At the moment the kernel requires userspace to pass a destination
   register for the associated value, make this optional so userspace
   can query if the key exists, just like with normal sets.

2. nftables maintains a counter per set that holds the number of
   elements.  This counter gets decremented on element removal,
   but its only incremented if the set has a upper maximum value.
   Increment unconditionally, this will allow us to update the
   maximum value later on.

3. At DCCP option maching, from Jeremy Sowden.

4. use struct_size macro, from Christophe JAILLET.

Conntrack:

5. Squash holes in struct nf_conntrack_expect, also Christophe JAILLET.

6. Allow clash resolution for GRE Protocol to avoid a packet drop,
   from Faicker Mo.

Flowtable:

Simplify route logic and split large functions into smaller
chunks, from Pablo Neira Ayuso.

* tag 'nf-next-2023-05-18' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next:
  netfilter: flowtable: split IPv6 datapath in helper functions
  netfilter: flowtable: split IPv4 datapath in helper functions
  netfilter: flowtable: simplify route logic
  netfilter: conntrack: allow insertion clash of gre protocol
  netfilter: nft_set_pipapo: Use struct_size()
  netfilter: Reorder fields in 'struct nf_conntrack_expect'
  netfilter: nft_exthdr: add boolean DCCP option matching
  netfilter: nf_tables: always increment set element count
  netfilter: nf_tables: relax set/map validation checks
====================

Link: https://lore.kernel.org/r/20230518100759.84858-1-fw@strlen.deSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/netfilter/nf_conntrack_expect.h

@@ -26,6 +26,15 @@ struct nf_conntrack_expect {
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_tuple_mask mask;
 
+	/* Usage count. */
+	refcount_t use;
+
+	/* Flags */
+	unsigned int flags;
+
+	/* Expectation class */
+	unsigned int class;
+
 	/* Function to call after setup and insertion */
 	void (*expectfn)(struct nf_conn *new,
 			 struct nf_conntrack_expect *this);
@@ -39,15 +48,6 @@ struct nf_conntrack_expect {
 	/* Timer function; deletes the expectation. */
 	struct timer_list timeout;
 
-	/* Usage count. */
-	refcount_t use;
-
-	/* Flags */
-	unsigned int flags;
-
-	/* Expectation class */
-	unsigned int class;
-
 #if IS_ENABLED(CONFIG_NF_NAT)
 	union nf_inet_addr saved_addr;
 	/* This is the original per-proto part, used to map the

include/net/netfilter/nf_flow_table.h

@@ -263,8 +263,8 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
 	up_write(&flow_table->flow_block_lock);
 }
 
-int flow_offload_route_init(struct flow_offload *flow,
-			    const struct nf_flow_route *route);
+void flow_offload_route_init(struct flow_offload *flow,
+			     const struct nf_flow_route *route);
 
 int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow);
 void flow_offload_refresh(struct nf_flowtable *flow_table,

include/uapi/linux/netfilter/nf_tables.h

@@ -859,12 +859,14 @@ enum nft_exthdr_flags {
  * @NFT_EXTHDR_OP_TCP: match against tcp options
  * @NFT_EXTHDR_OP_IPV4: match against ipv4 options
  * @NFT_EXTHDR_OP_SCTP: match against sctp chunks
+ * @NFT_EXTHDR_OP_DCCP: match against dccp otions
  */
 enum nft_exthdr_op {
 	NFT_EXTHDR_OP_IPV6,
 	NFT_EXTHDR_OP_TCPOPT,
 	NFT_EXTHDR_OP_IPV4,
 	NFT_EXTHDR_OP_SCTP,
+	NFT_EXTHDR_OP_DCCP,
 	__NFT_EXTHDR_OP_MAX
 };
 #define NFT_EXTHDR_OP_MAX	(__NFT_EXTHDR_OP_MAX - 1)

net/netfilter/nf_conntrack_proto_gre.c

@@ -296,6 +296,7 @@ void nf_conntrack_gre_init_net(struct net *net)
 /* protocol helper struct */
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre = {
 	.l4proto	 = IPPROTO_GRE,
+	.allow_clash	 = true,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack = gre_print_conntrack,
 #endif

net/netfilter/nf_flow_table_core.c

@@ -125,9 +125,6 @@ static int flow_offload_fill_route(struct flow_offload *flow,
 		break;
 	case FLOW_OFFLOAD_XMIT_XFRM:
 	case FLOW_OFFLOAD_XMIT_NEIGH:
-		if (!dst_hold_safe(route->tuple[dir].dst))
-			return -1;
-
 		flow_tuple->dst_cache = dst;
 		flow_tuple->dst_cookie = flow_offload_dst_cookie(flow_tuple);
 		break;
@@ -148,27 +145,12 @@ static void nft_flow_dst_release(struct flow_offload *flow,
 		dst_release(flow->tuplehash[dir].tuple.dst_cache);
 }
 
-int flow_offload_route_init(struct flow_offload *flow,
+void flow_offload_route_init(struct flow_offload *flow,
 			    const struct nf_flow_route *route)
 {
-	int err;
-
-	err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL);
-	if (err < 0)
-		return err;
-
-	err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY);
-	if (err < 0)
-		goto err_route_reply;
-
+	flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL);
+	flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY);
 	flow->type = NF_FLOW_OFFLOAD_ROUTE;
-
-	return 0;
-
-err_route_reply:
-	nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL);
-
-	return err;
 }
 EXPORT_SYMBOL_GPL(flow_offload_route_init);
 

net/netfilter/nf_flow_table_ip.c

@@ -163,38 +163,43 @@ static void nf_flow_tuple_encap(struct sk_buff *skb,
 	}
 }
 
-static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
-			    struct flow_offload_tuple *tuple, u32 *hdrsize,
-			    u32 offset)
+struct nf_flowtable_ctx {
+	const struct net_device	*in;
+	u32			offset;
+	u32			hdrsize;
+};
+
+static int nf_flow_tuple_ip(struct nf_flowtable_ctx *ctx, struct sk_buff *skb,
+			    struct flow_offload_tuple *tuple)
 {
 	struct flow_ports *ports;
 	unsigned int thoff;
 	struct iphdr *iph;
 	u8 ipproto;
 
-	if (!pskb_may_pull(skb, sizeof(*iph) + offset))
+	if (!pskb_may_pull(skb, sizeof(*iph) + ctx->offset))
 		return -1;
 
-	iph = (struct iphdr *)(skb_network_header(skb) + offset);
+	iph = (struct iphdr *)(skb_network_header(skb) + ctx->offset);
 	thoff = (iph->ihl * 4);
 
 	if (ip_is_fragment(iph) ||
 	    unlikely(ip_has_options(thoff)))
 		return -1;
 
-	thoff += offset;
+	thoff += ctx->offset;
 
 	ipproto = iph->protocol;
 	switch (ipproto) {
 	case IPPROTO_TCP:
-		*hdrsize = sizeof(struct tcphdr);
+		ctx->hdrsize = sizeof(struct tcphdr);
 		break;
 	case IPPROTO_UDP:
-		*hdrsize = sizeof(struct udphdr);
+		ctx->hdrsize = sizeof(struct udphdr);
 		break;
 #ifdef CONFIG_NF_CT_PROTO_GRE
 	case IPPROTO_GRE:
-		*hdrsize = sizeof(struct gre_base_hdr);
+		ctx->hdrsize = sizeof(struct gre_base_hdr);
 		break;
 #endif
 	default:
@@ -204,7 +209,7 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
 	if (iph->ttl <= 1)
 		return -1;
 
-	if (!pskb_may_pull(skb, thoff + *hdrsize))
+	if (!pskb_may_pull(skb, thoff + ctx->hdrsize))
 		return -1;
 
 	switch (ipproto) {
@@ -224,13 +229,13 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
 	}
 	}
 
-	iph = (struct iphdr *)(skb_network_header(skb) + offset);
+	iph = (struct iphdr *)(skb_network_header(skb) + ctx->offset);
 
 	tuple->src_v4.s_addr	= iph->saddr;
 	tuple->dst_v4.s_addr	= iph->daddr;
 	tuple->l3proto		= AF_INET;
 	tuple->l4proto		= ipproto;
-	tuple->iifidx		= dev->ifindex;
+	tuple->iifidx		= ctx->in->ifindex;
 	nf_flow_tuple_encap(skb, tuple);
 
 	return 0;
@@ -336,58 +341,56 @@ static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb,
 	return NF_STOLEN;
 }
 
-unsigned int
-nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
-			const struct nf_hook_state *state)
+static struct flow_offload_tuple_rhash *
+nf_flow_offload_lookup(struct nf_flowtable_ctx *ctx,
+		       struct nf_flowtable *flow_table, struct sk_buff *skb)
 {
-	struct flow_offload_tuple_rhash *tuplehash;
-	struct nf_flowtable *flow_table = priv;
 	struct flow_offload_tuple tuple = {};
-	enum flow_offload_tuple_dir dir;
-	struct flow_offload *flow;
-	struct net_device *outdev;
-	u32 hdrsize, offset = 0;
-	unsigned int thoff, mtu;
-	struct rtable *rt;
-	struct iphdr *iph;
-	__be32 nexthop;
-	int ret;
 
 	if (skb->protocol != htons(ETH_P_IP) &&
-	    !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IP), &offset))
-		return NF_ACCEPT;
+	    !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IP), &ctx->offset))
+		return NULL;
 
-	if (nf_flow_tuple_ip(skb, state->in, &tuple, &hdrsize, offset) < 0)
-		return NF_ACCEPT;
+	if (nf_flow_tuple_ip(ctx, skb, &tuple) < 0)
+		return NULL;
 
-	tuplehash = flow_offload_lookup(flow_table, &tuple);
-	if (tuplehash == NULL)
-		return NF_ACCEPT;
+	return flow_offload_lookup(flow_table, &tuple);
+}
+
+static int nf_flow_offload_forward(struct nf_flowtable_ctx *ctx,
+				   struct nf_flowtable *flow_table,
+				   struct flow_offload_tuple_rhash *tuplehash,
+				   struct sk_buff *skb)
+{
+	enum flow_offload_tuple_dir dir;
+	struct flow_offload *flow;
+	unsigned int thoff, mtu;
+	struct iphdr *iph;
 
 	dir = tuplehash->tuple.dir;
 	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
 
-	mtu = flow->tuplehash[dir].tuple.mtu + offset;
+	mtu = flow->tuplehash[dir].tuple.mtu + ctx->offset;
 	if (unlikely(nf_flow_exceeds_mtu(skb, mtu)))
-		return NF_ACCEPT;
+		return 0;
 
-	iph = (struct iphdr *)(skb_network_header(skb) + offset);
-	thoff = (iph->ihl * 4) + offset;
+	iph = (struct iphdr *)(skb_network_header(skb) + ctx->offset);
+	thoff = (iph->ihl * 4) + ctx->offset;
 	if (nf_flow_state_check(flow, iph->protocol, skb, thoff))
-		return NF_ACCEPT;
+		return 0;
 
 	if (!nf_flow_dst_check(&tuplehash->tuple)) {
 		flow_offload_teardown(flow);
-		return NF_ACCEPT;
+		return 0;
 	}
 
-	if (skb_try_make_writable(skb, thoff + hdrsize))
-		return NF_DROP;
+	if (skb_try_make_writable(skb, thoff + ctx->hdrsize))
+		return -1;
 
 	flow_offload_refresh(flow_table, flow);
 
 	nf_flow_encap_pop(skb, tuplehash);
-	thoff -= offset;
+	thoff -= ctx->offset;
 
 	iph = ip_hdr(skb);
 	nf_flow_nat_ip(flow, skb, thoff, dir, iph);
@@ -398,6 +401,35 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 	if (flow_table->flags & NF_FLOWTABLE_COUNTER)
 		nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len);
 
+	return 1;
+}
+
+unsigned int
+nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
+			const struct nf_hook_state *state)
+{
+	struct flow_offload_tuple_rhash *tuplehash;
+	struct nf_flowtable *flow_table = priv;
+	enum flow_offload_tuple_dir dir;
+	struct nf_flowtable_ctx ctx = {
+		.in	= state->in,
+	};
+	struct flow_offload *flow;
+	struct net_device *outdev;
+	struct rtable *rt;
+	__be32 nexthop;
+	int ret;
+
+	tuplehash = nf_flow_offload_lookup(&ctx, flow_table, skb);
+	if (!tuplehash)
+		return NF_ACCEPT;
+
+	ret = nf_flow_offload_forward(&ctx, flow_table, tuplehash, skb);
+	if (ret < 0)
+		return NF_DROP;
+	else if (ret == 0)
+		return NF_ACCEPT;
+
 	if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) {
 		rt = (struct rtable *)tuplehash->tuple.dst_cache;
 		memset(skb->cb, 0, sizeof(struct inet_skb_parm));
@@ -406,6 +438,9 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 		return nf_flow_xmit_xfrm(skb, state, &rt->dst);
 	}
 
+	dir = tuplehash->tuple.dir;
+	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+
 	switch (tuplehash->tuple.xmit_type) {
 	case FLOW_OFFLOAD_XMIT_NEIGH:
 		rt = (struct rtable *)tuplehash->tuple.dst_cache;
@@ -535,32 +570,31 @@ static void nf_flow_nat_ipv6(const struct flow_offload *flow,
 	}
 }
 
-static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
-			      struct flow_offload_tuple *tuple, u32 *hdrsize,
-			      u32 offset)
+static int nf_flow_tuple_ipv6(struct nf_flowtable_ctx *ctx, struct sk_buff *skb,
+			      struct flow_offload_tuple *tuple)
 {
 	struct flow_ports *ports;
 	struct ipv6hdr *ip6h;
 	unsigned int thoff;
 	u8 nexthdr;
 
-	thoff = sizeof(*ip6h) + offset;
+	thoff = sizeof(*ip6h) + ctx->offset;
 	if (!pskb_may_pull(skb, thoff))
 		return -1;
 
-	ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset);
+	ip6h = (struct ipv6hdr *)(skb_network_header(skb) + ctx->offset);
 
 	nexthdr = ip6h->nexthdr;
 	switch (nexthdr) {
 	case IPPROTO_TCP:
-		*hdrsize = sizeof(struct tcphdr);
+		ctx->hdrsize = sizeof(struct tcphdr);
 		break;
 	case IPPROTO_UDP:
-		*hdrsize = sizeof(struct udphdr);
+		ctx->hdrsize = sizeof(struct udphdr);
 		break;
 #ifdef CONFIG_NF_CT_PROTO_GRE
 	case IPPROTO_GRE:
-		*hdrsize = sizeof(struct gre_base_hdr);
+		ctx->hdrsize = sizeof(struct gre_base_hdr);
 		break;
 #endif
 	default:
@@ -570,7 +604,7 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
 	if (ip6h->hop_limit <= 1)
 		return -1;
 
-	if (!pskb_may_pull(skb, thoff + *hdrsize))
+	if (!pskb_may_pull(skb, thoff + ctx->hdrsize))
 		return -1;
 
 	switch (nexthdr) {
@@ -590,65 +624,47 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
 	}
 	}
 
-	ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset);
+	ip6h = (struct ipv6hdr *)(skb_network_header(skb) + ctx->offset);
 
 	tuple->src_v6		= ip6h->saddr;
 	tuple->dst_v6		= ip6h->daddr;
 	tuple->l3proto		= AF_INET6;
 	tuple->l4proto		= nexthdr;
-	tuple->iifidx		= dev->ifindex;
+	tuple->iifidx		= ctx->in->ifindex;
 	nf_flow_tuple_encap(skb, tuple);
 
 	return 0;
 }
 
-unsigned int
-nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
-			  const struct nf_hook_state *state)
+static int nf_flow_offload_ipv6_forward(struct nf_flowtable_ctx *ctx,
+					struct nf_flowtable *flow_table,
+					struct flow_offload_tuple_rhash *tuplehash,
+					struct sk_buff *skb)
 {
-	struct flow_offload_tuple_rhash *tuplehash;
-	struct nf_flowtable *flow_table = priv;
-	struct flow_offload_tuple tuple = {};
 	enum flow_offload_tuple_dir dir;
-	const struct in6_addr *nexthop;
 	struct flow_offload *flow;
-	struct net_device *outdev;
 	unsigned int thoff, mtu;
-	u32 hdrsize, offset = 0;
 	struct ipv6hdr *ip6h;
-	struct rt6_info *rt;
-	int ret;
-
-	if (skb->protocol != htons(ETH_P_IPV6) &&
-	    !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IPV6), &offset))
-		return NF_ACCEPT;
-
-	if (nf_flow_tuple_ipv6(skb, state->in, &tuple, &hdrsize, offset) < 0)
-		return NF_ACCEPT;
-
-	tuplehash = flow_offload_lookup(flow_table, &tuple);
-	if (tuplehash == NULL)
-		return NF_ACCEPT;
 
 	dir = tuplehash->tuple.dir;
 	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
 
-	mtu = flow->tuplehash[dir].tuple.mtu + offset;
+	mtu = flow->tuplehash[dir].tuple.mtu + ctx->offset;
 	if (unlikely(nf_flow_exceeds_mtu(skb, mtu)))
-		return NF_ACCEPT;
+		return 0;
 
-	ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset);
-	thoff = sizeof(*ip6h) + offset;
+	ip6h = (struct ipv6hdr *)(skb_network_header(skb) + ctx->offset);
+	thoff = sizeof(*ip6h) + ctx->offset;
 	if (nf_flow_state_check(flow, ip6h->nexthdr, skb, thoff))
-		return NF_ACCEPT;
+		return 0;
 
 	if (!nf_flow_dst_check(&tuplehash->tuple)) {
 		flow_offload_teardown(flow);
-		return NF_ACCEPT;
+		return 0;
 	}
 
-	if (skb_try_make_writable(skb, thoff + hdrsize))
-		return NF_DROP;
+	if (skb_try_make_writable(skb, thoff + ctx->hdrsize))
+		return -1;
 
 	flow_offload_refresh(flow_table, flow);
 
@@ -663,6 +679,52 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 	if (flow_table->flags & NF_FLOWTABLE_COUNTER)
 		nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len);
 
+	return 1;
+}
+
+static struct flow_offload_tuple_rhash *
+nf_flow_offload_ipv6_lookup(struct nf_flowtable_ctx *ctx,
+			    struct nf_flowtable *flow_table,
+			    struct sk_buff *skb)
+{
+	struct flow_offload_tuple tuple = {};
+
+	if (skb->protocol != htons(ETH_P_IPV6) &&
+	    !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IPV6), &ctx->offset))
+		return NULL;
+
+	if (nf_flow_tuple_ipv6(ctx, skb, &tuple) < 0)
+		return NULL;
+
+	return flow_offload_lookup(flow_table, &tuple);
+}
+
+unsigned int
+nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
+			  const struct nf_hook_state *state)
+{
+	struct flow_offload_tuple_rhash *tuplehash;
+	struct nf_flowtable *flow_table = priv;
+	enum flow_offload_tuple_dir dir;
+	struct nf_flowtable_ctx ctx = {
+		.in	= state->in,
+	};
+	const struct in6_addr *nexthop;
+	struct flow_offload *flow;
+	struct net_device *outdev;
+	struct rt6_info *rt;
+	int ret;
+
+	tuplehash = nf_flow_offload_ipv6_lookup(&ctx, flow_table, skb);
+	if (tuplehash == NULL)
+		return NF_ACCEPT;
+
+	ret = nf_flow_offload_ipv6_forward(&ctx, flow_table, tuplehash, skb);
+	if (ret < 0)
+		return NF_DROP;
+	else if (ret == 0)
+		return NF_ACCEPT;
+
 	if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) {
 		rt = (struct rt6_info *)tuplehash->tuple.dst_cache;
 		memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
@@ -671,6 +733,9 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 		return nf_flow_xmit_xfrm(skb, state, &rt->dst);
 	}
 
+	dir = tuplehash->tuple.dir;
+	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+
 	switch (tuplehash->tuple.xmit_type) {
 	case FLOW_OFFLOAD_XMIT_NEIGH:
 		rt = (struct rt6_info *)tuplehash->tuple.dst_cache;

net/netfilter/nf_tables_api.c

@@ -6541,10 +6541,13 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		goto err_element_clash;
 	}
 
-	if (!(flags & NFT_SET_ELEM_CATCHALL) && set->size &&
-	    !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) {
-		err = -ENFILE;
-		goto err_set_full;
+	if (!(flags & NFT_SET_ELEM_CATCHALL)) {
+		unsigned int max = set->size ? set->size + set->ndeact : UINT_MAX;
+
+		if (!atomic_add_unless(&set->nelems, 1, max)) {
+			err = -ENFILE;
+			goto err_set_full;
+		}
 	}
 
 	nft_trans_elem(trans) = elem;

net/netfilter/nft_exthdr.c

@@ -10,6 +10,7 @@
 #include <linux/netlink.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
+#include <linux/dccp.h>
 #include <linux/sctp.h>
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nf_tables.h>
@@ -406,6 +407,82 @@ static void nft_exthdr_sctp_eval(const struct nft_expr *expr,
 		regs->verdict.code = NFT_BREAK;
 }
 
+static void nft_exthdr_dccp_eval(const struct nft_expr *expr,
+				 struct nft_regs *regs,
+				 const struct nft_pktinfo *pkt)
+{
+	struct nft_exthdr *priv = nft_expr_priv(expr);
+	unsigned int thoff, dataoff, optoff, optlen, i;
+	u32 *dest = &regs->data[priv->dreg];
+	const struct dccp_hdr *dh;
+	struct dccp_hdr _dh;
+
+	if (pkt->tprot != IPPROTO_DCCP || pkt->fragoff)
+		goto err;
+
+	thoff = nft_thoff(pkt);
+
+	dh = skb_header_pointer(pkt->skb, thoff, sizeof(_dh), &_dh);
+	if (!dh)
+		goto err;
+
+	dataoff = dh->dccph_doff * sizeof(u32);
+	optoff = __dccp_hdr_len(dh);
+	if (dataoff <= optoff)
+		goto err;
+
+	optlen = dataoff - optoff;
+
+	for (i = 0; i < optlen; ) {
+		/* Options 0 (DCCPO_PADDING) - 31 (DCCPO_MAX_RESERVED) are 1B in
+		 * the length; the remaining options are at least 2B long.  In
+		 * all cases, the first byte contains the option type.  In
+		 * multi-byte options, the second byte contains the option
+		 * length, which must be at least two: 1 for the type plus 1 for
+		 * the length plus 0-253 for any following option data.  We
+		 * aren't interested in the option data, only the type and the
+		 * length, so we don't need to read more than two bytes at a
+		 * time.
+		 */
+		unsigned int buflen = optlen - i;
+		u8 buf[2], *bufp;
+		u8 type, len;
+
+		if (buflen > sizeof(buf))
+			buflen = sizeof(buf);
+
+		bufp = skb_header_pointer(pkt->skb, thoff + optoff + i, buflen,
+					  &buf);
+		if (!bufp)
+			goto err;
+
+		type = bufp[0];
+
+		if (type == priv->type) {
+			*dest = 1;
+			return;
+		}
+
+		if (type <= DCCPO_MAX_RESERVED) {
+			i++;
+			continue;
+		}
+
+		if (buflen < 2)
+			goto err;
+
+		len = bufp[1];
+
+		if (len < 2)
+			goto err;
+
+		i += len;
+	}
+
+err:
+	*dest = 0;
+}
+
 static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = {
 	[NFTA_EXTHDR_DREG]		= { .type = NLA_U32 },
 	[NFTA_EXTHDR_TYPE]		= { .type = NLA_U8 },
@@ -557,6 +634,22 @@ static int nft_exthdr_ipv4_init(const struct nft_ctx *ctx,
 	return 0;
 }
 
+static int nft_exthdr_dccp_init(const struct nft_ctx *ctx,
+				const struct nft_expr *expr,
+				const struct nlattr * const tb[])
+{
+	struct nft_exthdr *priv = nft_expr_priv(expr);
+	int err = nft_exthdr_init(ctx, expr, tb);
+
+	if (err < 0)
+		return err;
+
+	if (!(priv->flags & NFT_EXTHDR_F_PRESENT))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
 static int nft_exthdr_dump_common(struct sk_buff *skb, const struct nft_exthdr *priv)
 {
 	if (nla_put_u8(skb, NFTA_EXTHDR_TYPE, priv->type))
@@ -686,6 +779,15 @@ static const struct nft_expr_ops nft_exthdr_sctp_ops = {
 	.reduce		= nft_exthdr_reduce,
 };
 
+static const struct nft_expr_ops nft_exthdr_dccp_ops = {
+	.type		= &nft_exthdr_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
+	.eval		= nft_exthdr_dccp_eval,
+	.init		= nft_exthdr_dccp_init,
+	.dump		= nft_exthdr_dump,
+	.reduce		= nft_exthdr_reduce,
+};
+
 static const struct nft_expr_ops *
 nft_exthdr_select_ops(const struct nft_ctx *ctx,
 		      const struct nlattr * const tb[])
@@ -720,6 +822,10 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx,
 		if (tb[NFTA_EXTHDR_DREG])
 			return &nft_exthdr_sctp_ops;
 		break;
+	case NFT_EXTHDR_OP_DCCP:
+		if (tb[NFTA_EXTHDR_DREG])
+			return &nft_exthdr_dccp_ops;
+		break;
 	}
 
 	return ERR_PTR(-EOPNOTSUPP);

net/netfilter/nft_flow_offload.c

@@ -250,9 +250,14 @@ static int nft_flow_route(const struct nft_pktinfo *pkt,
 		break;
 	}
 
+	if (!dst_hold_safe(this_dst))
+		return -ENOENT;
+
 	nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt));
-	if (!other_dst)
+	if (!other_dst) {
+		dst_release(this_dst);
 		return -ENOENT;
+	}
 
 	nft_default_forward_path(route, this_dst, dir);
 	nft_default_forward_path(route, other_dst, !dir);
@@ -349,8 +354,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 	if (!flow)
 		goto err_flow_alloc;
 
-	if (flow_offload_route_init(flow, &route) < 0)
-		goto err_flow_add;
+	flow_offload_route_init(flow, &route);
 
 	if (tcph) {
 		ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
@@ -361,12 +365,12 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 	if (ret < 0)
 		goto err_flow_add;
 
-	dst_release(route.tuple[!dir].dst);
 	return;
 
 err_flow_add:
 	flow_offload_free(flow);
 err_flow_alloc:
+	dst_release(route.tuple[dir].dst);
 	dst_release(route.tuple[!dir].dst);
 err_flow_route:
 	clear_bit(IPS_OFFLOAD_BIT, &ct->status);

net/netfilter/nft_lookup.c

@@ -19,6 +19,7 @@ struct nft_lookup {
 	struct nft_set			*set;
 	u8				sreg;
 	u8				dreg;
+	bool				dreg_set;
 	bool				invert;
 	struct nft_set_binding		binding;
 };
@@ -75,7 +76,7 @@ void nft_lookup_eval(const struct nft_expr *expr,
 	}
 
 	if (ext) {
-		if (set->flags & NFT_SET_MAP)
+		if (priv->dreg_set)
 			nft_data_copy(&regs->data[priv->dreg],
 				      nft_set_ext_data(ext), set->dlen);
 
@@ -122,11 +123,8 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 		if (flags & ~NFT_LOOKUP_F_INV)
 			return -EINVAL;
 
-		if (flags & NFT_LOOKUP_F_INV) {
-			if (set->flags & NFT_SET_MAP)
-				return -EINVAL;
+		if (flags & NFT_LOOKUP_F_INV)
 			priv->invert = true;
-		}
 	}
 
 	if (tb[NFTA_LOOKUP_DREG] != NULL) {
@@ -140,8 +138,17 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 					       set->dlen);
 		if (err < 0)
 			return err;
-	} else if (set->flags & NFT_SET_MAP)
-		return -EINVAL;
+		priv->dreg_set = true;
+	} else if (set->flags & NFT_SET_MAP) {
+		/* Map given, but user asks for lookup only (i.e. to
+		 * ignore value assoicated with key).
+		 *
+		 * This makes no sense for anonymous maps since they are
+		 * scoped to the rule, but for named sets this can be useful.
+		 */
+		if (set->flags & NFT_SET_ANONYMOUS)
+			return -EINVAL;
+	}
 
 	priv->binding.flags = set->flags & NFT_SET_MAP;
 
@@ -188,7 +195,7 @@ static int nft_lookup_dump(struct sk_buff *skb,
 		goto nla_put_failure;
 	if (nft_dump_register(skb, NFTA_LOOKUP_SREG, priv->sreg))
 		goto nla_put_failure;
-	if (priv->set->flags & NFT_SET_MAP)
+	if (priv->dreg_set)
 		if (nft_dump_register(skb, NFTA_LOOKUP_DREG, priv->dreg))
 			goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_LOOKUP_FLAGS, htonl(flags)))

net/netfilter/nft_set_pipapo.c

@@ -1274,8 +1274,7 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
 	struct nft_pipapo_match *new;
 	int i;
 
-	new = kmalloc(sizeof(*new) + sizeof(*dst) * old->field_count,
-		      GFP_KERNEL);
+	new = kmalloc(struct_size(new, f, old->field_count), GFP_KERNEL);
 	if (!new)
 		return ERR_PTR(-ENOMEM);
 
@@ -2059,8 +2058,7 @@ static int nft_pipapo_init(const struct nft_set *set,
 	if (field_count > NFT_PIPAPO_MAX_FIELDS)
 		return -EINVAL;
 
-	m = kmalloc(sizeof(*priv->match) + sizeof(*f) * field_count,
-		    GFP_KERNEL);
+	m = kmalloc(struct_size(m, f, field_count), GFP_KERNEL);
 	if (!m)
 		return -ENOMEM;