Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Merge conflict of mlx5 resolved using instructions in merge
commit 9566e650bf7fdf58384bb06df634f7531ca3a97e.

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

6 files changed, 116 insertions, 31 deletions

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index a542761e90d1..81a8ef42b88d 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -453,13 +453,12 @@ EXPORT_SYMBOL_GPL(nf_ct_invert_tuple);
  * table location, we assume id gets exposed to userspace.
  *
  * Following nf_conn items do not change throughout lifetime
- * of the nf_conn after it has been committed to main hash table:
+ * of the nf_conn:
  *
  * 1. nf_conn address
- * 2. nf_conn->ext address
- * 3. nf_conn->master address (normally NULL)
- * 4. tuple
- * 5. the associated net namespace
+ * 2. nf_conn->master address (normally NULL)
+ * 3. the associated net namespace
+ * 4. the original direction tuple
  */
 u32 nf_ct_get_id(const struct nf_conn *ct)
 {
@@ -469,9 +468,10 @@ u32 nf_ct_get_id(const struct nf_conn *ct)
 	net_get_random_once(&ct_id_seed, sizeof(ct_id_seed));
 
 	a = (unsigned long)ct;
-	b = (unsigned long)ct->master ^ net_hash_mix(nf_ct_net(ct));
-	c = (unsigned long)ct->ext;
-	d = (unsigned long)siphash(&ct->tuplehash, sizeof(ct->tuplehash),
+	b = (unsigned long)ct->master;
+	c = (unsigned long)nf_ct_net(ct);
+	d = (unsigned long)siphash(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+				   sizeof(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple),
 				   &ct_id_seed);
 #ifdef CONFIG_64BIT
 	return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed);
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index e3d797252a98..80a8f9ae4c93 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -111,15 +111,16 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
 #define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT	(120 * HZ)
 #define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT	(30 * HZ)
 
-static void flow_offload_fixup_ct_state(struct nf_conn *ct)
+static inline __s32 nf_flow_timeout_delta(unsigned int timeout)
+{
+	return (__s32)(timeout - (u32)jiffies);
+}
+
+static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
 {
 	const struct nf_conntrack_l4proto *l4proto;
+	int l4num = nf_ct_protonum(ct);
 	unsigned int timeout;
-	int l4num;
-
-	l4num = nf_ct_protonum(ct);
-	if (l4num == IPPROTO_TCP)
-		flow_offload_fixup_tcp(&ct->proto.tcp);
 
 	l4proto = nf_ct_l4proto_find(l4num);
 	if (!l4proto)
@@ -132,7 +133,20 @@ static void flow_offload_fixup_ct_state(struct nf_conn *ct)
 	else
 		return;
 
-	ct->timeout = nfct_time_stamp + timeout;
+	if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout)
+		ct->timeout = nfct_time_stamp + timeout;
+}
+
+static void flow_offload_fixup_ct_state(struct nf_conn *ct)
+{
+	if (nf_ct_protonum(ct) == IPPROTO_TCP)
+		flow_offload_fixup_tcp(&ct->proto.tcp);
+}
+
+static void flow_offload_fixup_ct(struct nf_conn *ct)
+{
+	flow_offload_fixup_ct_state(ct);
+	flow_offload_fixup_ct_timeout(ct);
 }
 
 void flow_offload_free(struct flow_offload *flow)
@@ -208,6 +222,11 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
 }
 EXPORT_SYMBOL_GPL(flow_offload_add);
 
+static inline bool nf_flow_has_expired(const struct flow_offload *flow)
+{
+	return nf_flow_timeout_delta(flow->timeout) <= 0;
+}
+
 static void flow_offload_del(struct nf_flowtable *flow_table,
 			     struct flow_offload *flow)
 {
@@ -223,6 +242,11 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
 	e = container_of(flow, struct flow_offload_entry, flow);
 	clear_bit(IPS_OFFLOAD_BIT, &e->ct->status);
 
+	if (nf_flow_has_expired(flow))
+		flow_offload_fixup_ct(e->ct);
+	else if (flow->flags & FLOW_OFFLOAD_TEARDOWN)
+		flow_offload_fixup_ct_timeout(e->ct);
+
 	flow_offload_free(flow);
 }
 
@@ -298,11 +322,6 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table,
 	return err;
 }
 
-static inline bool nf_flow_has_expired(const struct flow_offload *flow)
-{
-	return (__s32)(flow->timeout - (u32)jiffies) <= 0;
-}
-
 static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data)
 {
 	struct nf_flowtable *flow_table = data;
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index cdfc33517e85..d68c801dd614 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -214,6 +214,25 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	return true;
 }
 
+static int nf_flow_offload_dst_check(struct dst_entry *dst)
+{
+	if (unlikely(dst_xfrm(dst)))
+		return dst_check(dst, 0) ? 0 : -1;
+
+	return 0;
+}
+
+static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
+				      const struct nf_hook_state *state,
+				      struct dst_entry *dst)
+{
+	skb_orphan(skb);
+	skb_dst_set_noref(skb, dst);
+	skb->tstamp = 0;
+	dst_output(state->net, state->sk, skb);
+	return NF_STOLEN;
+}
+
 unsigned int
 nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 			const struct nf_hook_state *state)
@@ -254,6 +273,11 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 	if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff))
 		return NF_ACCEPT;
 
+	if (nf_flow_offload_dst_check(&rt->dst)) {
+		flow_offload_teardown(flow);
+		return NF_ACCEPT;
+	}
+
 	if (nf_flow_nat_ip(flow, skb, thoff, dir) < 0)
 		return NF_DROP;
 
@@ -261,6 +285,13 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 	iph = ip_hdr(skb);
 	ip_decrease_ttl(iph);
 
+	if (unlikely(dst_xfrm(&rt->dst))) {
+		memset(skb->cb, 0, sizeof(struct inet_skb_parm));
+		IPCB(skb)->iif = skb->dev->ifindex;
+		IPCB(skb)->flags = IPSKB_FORWARDED;
+		return nf_flow_xmit_xfrm(skb, state, &rt->dst);
+	}
+
 	skb->dev = outdev;
 	nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
 	skb_dst_set_noref(skb, &rt->dst);
@@ -467,6 +498,11 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 				sizeof(*ip6h)))
 		return NF_ACCEPT;
 
+	if (nf_flow_offload_dst_check(&rt->dst)) {
+		flow_offload_teardown(flow);
+		return NF_ACCEPT;
+	}
+
 	if (skb_try_make_writable(skb, sizeof(*ip6h)))
 		return NF_DROP;
 
@@ -477,6 +513,13 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 	ip6h = ipv6_hdr(skb);
 	ip6h->hop_limit--;
 
+	if (unlikely(dst_xfrm(&rt->dst))) {
+		memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
+		IP6CB(skb)->iif = skb->dev->ifindex;
+		IP6CB(skb)->flags = IP6SKB_FORWARDED;
+		return nf_flow_xmit_xfrm(skb, state, &rt->dst);
+	}
+
 	skb->dev = outdev;
 	nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6);
 	skb_dst_set_noref(skb, &rt->dst);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index fe3b7b0c6c66..6d00bef023c4 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -138,9 +138,14 @@ static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set)
 		return;
 
 	list_for_each_entry_reverse(trans, &net->nft.commit_list, list) {
-		if (trans->msg_type == NFT_MSG_NEWSET &&
-		    nft_trans_set(trans) == set) {
-			set->bound = true;
+		switch (trans->msg_type) {
+		case NFT_MSG_NEWSET:
+			if (nft_trans_set(trans) == set)
+				nft_trans_set_bound(trans) = true;
+			break;
+		case NFT_MSG_NEWSETELEM:
+			if (nft_trans_elem_set(trans) == set)
+				nft_trans_elem_set_bound(trans) = true;
 			break;
 		}
 	}
@@ -1662,6 +1667,10 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 
 		chain->flags |= NFT_BASE_CHAIN | flags;
 		basechain->policy = NF_ACCEPT;
+		if (chain->flags & NFT_CHAIN_HW_OFFLOAD &&
+		    nft_chain_offload_priority(basechain) < 0)
+			return -EOPNOTSUPP;
+
 		flow_block_init(&basechain->flow_block);
 	} else {
 		chain = kzalloc(sizeof(*chain), GFP_KERNEL);
@@ -6906,7 +6915,7 @@ static int __nf_tables_abort(struct net *net)
 			break;
 		case NFT_MSG_NEWSET:
 			trans->ctx.table->use--;
-			if (nft_trans_set(trans)->bound) {
+			if (nft_trans_set_bound(trans)) {
 				nft_trans_destroy(trans);
 				break;
 			}
@@ -6918,7 +6927,7 @@ static int __nf_tables_abort(struct net *net)
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_NEWSETELEM:
-			if (nft_trans_elem_set(trans)->bound) {
+			if (nft_trans_elem_set_bound(trans)) {
 				nft_trans_destroy(trans);
 				break;
 			}
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index d3c4c9c88bc8..3c2725ade61b 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -103,10 +103,11 @@ void nft_offload_update_dependency(struct nft_offload_ctx *ctx,
 }
 
 static void nft_flow_offload_common_init(struct flow_cls_common_offload *common,
-					 __be16 proto,
-					struct netlink_ext_ack *extack)
+					 __be16 proto, int priority,
+					 struct netlink_ext_ack *extack)
 {
 	common->protocol = proto;
+	common->prio = priority;
 	common->extack = extack;
 }
 
@@ -124,6 +125,15 @@ static int nft_setup_cb_call(struct nft_base_chain *basechain,
 	return 0;
 }
 
+int nft_chain_offload_priority(struct nft_base_chain *basechain)
+{
+	if (basechain->ops.priority <= 0 ||
+	    basechain->ops.priority > USHRT_MAX)
+		return -1;
+
+	return 0;
+}
+
 static int nft_flow_offload_rule(struct nft_trans *trans,
 				 enum flow_cls_command command)
 {
@@ -142,7 +152,8 @@ static int nft_flow_offload_rule(struct nft_trans *trans,
 	if (flow)
 		proto = flow->proto;
 
-	nft_flow_offload_common_init(&cls_flow.common, proto, &extack);
+	nft_flow_offload_common_init(&cls_flow.common, proto,
+				     basechain->ops.priority, &extack);
 	cls_flow.command = command;
 	cls_flow.cookie = (unsigned long) rule;
 	if (flow)
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index aa5f571d4361..060a4ed46d5e 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -72,11 +72,11 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 {
 	struct nft_flow_offload *priv = nft_expr_priv(expr);
 	struct nf_flowtable *flowtable = &priv->flowtable->data;
+	struct tcphdr _tcph, *tcph = NULL;
 	enum ip_conntrack_info ctinfo;
 	struct nf_flow_route route;
 	struct flow_offload *flow;
 	enum ip_conntrack_dir dir;
-	bool is_tcp = false;
 	struct nf_conn *ct;
 	int ret;
 
@@ -89,7 +89,10 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 
 	switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) {
 	case IPPROTO_TCP:
-		is_tcp = true;
+		tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff,
+					  sizeof(_tcph), &_tcph);
+		if (unlikely(!tcph || tcph->fin || tcph->rst))
+			goto out;
 		break;
 	case IPPROTO_UDP:
 		break;
@@ -115,7 +118,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 	if (!flow)
 		goto err_flow_alloc;
 
-	if (is_tcp) {
+	if (tcph) {
 		ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
 		ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
 	}