tcp: Access &tcp_hashinfo via net.

We will soon introduce an optional per-netns ehash.

This means we cannot use tcp_hashinfo directly in most places.

Instead, access it via net->ipv4.tcp_death_row.hashinfo.

The access will be valid only while initialising tcp_hashinfo
itself and creating/destroying each netns.

Signed-off-by: Kuniyuki Iwashima <[email protected]>
Reviewed-by: Eric Dumazet <[email protected]>
Signed-off-by: Jakub Kicinski <[email protected]>

Author: q2ven

drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c

@@ -1069,8 +1069,7 @@ static void chtls_pass_accept_rpl(struct sk_buff *skb,
 	cxgb4_l2t_send(csk->egress_dev, skb, csk->l2t_entry);
 }
 
-static void inet_inherit_port(struct inet_hashinfo *hash_info,
-			      struct sock *lsk, struct sock *newsk)
+static void inet_inherit_port(struct sock *lsk, struct sock *newsk)
 {
 	local_bh_disable();
 	__inet_inherit_port(lsk, newsk);
@@ -1240,7 +1239,7 @@ static struct sock *chtls_recv_sock(struct sock *lsk,
 						     ipv4.sysctl_tcp_window_scaling),
 					   tp->window_clamp);
 	neigh_release(n);
-	inet_inherit_port(&tcp_hashinfo, lsk, newsk);
+	inet_inherit_port(lsk, newsk);
 	csk_set_flag(csk, CSK_CONN_INLINE);
 	bh_unlock_sock(newsk); /* tcp_create_openreq_child ->sk_clone_lock */
 

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c

@@ -461,6 +461,7 @@ static void resync_update_sn(struct mlx5e_rq *rq, struct sk_buff *skb)
 {
 	struct ethhdr *eth = (struct ethhdr *)(skb->data);
 	struct net_device *netdev = rq->netdev;
+	struct net *net = dev_net(netdev);
 	struct sock *sk = NULL;
 	unsigned int datalen;
 	struct iphdr *iph;
@@ -475,7 +476,7 @@ static void resync_update_sn(struct mlx5e_rq *rq, struct sk_buff *skb)
 		depth += sizeof(struct iphdr);
 		th = (void *)iph + sizeof(struct iphdr);
 
-		sk = inet_lookup_established(dev_net(netdev), &tcp_hashinfo,
+		sk = inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
 					     iph->saddr, th->source, iph->daddr,
 					     th->dest, netdev->ifindex);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -485,7 +486,7 @@ static void resync_update_sn(struct mlx5e_rq *rq, struct sk_buff *skb)
 		depth += sizeof(struct ipv6hdr);
 		th = (void *)ipv6h + sizeof(struct ipv6hdr);
 
-		sk = __inet6_lookup_established(dev_net(netdev), &tcp_hashinfo,
+		sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
 						&ipv6h->saddr, th->source,
 						&ipv6h->daddr, ntohs(th->dest),
 						netdev->ifindex, 0);

drivers/net/ethernet/netronome/nfp/crypto/tls.c

@@ -474,6 +474,7 @@ int nfp_net_tls_rx_resync_req(struct net_device *netdev,
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	struct nfp_net_tls_offload_ctx *ntls;
+	struct net *net = dev_net(netdev);
 	struct ipv6hdr *ipv6h;
 	struct tcphdr *th;
 	struct iphdr *iph;
@@ -494,13 +495,13 @@ int nfp_net_tls_rx_resync_req(struct net_device *netdev,
 
 	switch (ipv6h->version) {
 	case 4:
-		sk = inet_lookup_established(dev_net(netdev), &tcp_hashinfo,
+		sk = inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
 					     iph->saddr, th->source, iph->daddr,
 					     th->dest, netdev->ifindex);
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case 6:
-		sk = __inet6_lookup_established(dev_net(netdev), &tcp_hashinfo,
+		sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
 						&ipv6h->saddr, th->source,
 						&ipv6h->daddr, ntohs(th->dest),
 						netdev->ifindex, 0);

net/core/filter.c

@@ -6373,6 +6373,7 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
 static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 			      int dif, int sdif, u8 family, u8 proto)
 {
+	struct inet_hashinfo *hinfo = net->ipv4.tcp_death_row.hashinfo;
 	bool refcounted = false;
 	struct sock *sk = NULL;
 
@@ -6381,7 +6382,7 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 		__be32 dst4 = tuple->ipv4.daddr;
 
 		if (proto == IPPROTO_TCP)
-			sk = __inet_lookup(net, &tcp_hashinfo, NULL, 0,
+			sk = __inet_lookup(net, hinfo, NULL, 0,
 					   src4, tuple->ipv4.sport,
 					   dst4, tuple->ipv4.dport,
 					   dif, sdif, &refcounted);
@@ -6395,7 +6396,7 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 		struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr;
 
 		if (proto == IPPROTO_TCP)
-			sk = __inet6_lookup(net, &tcp_hashinfo, NULL, 0,
+			sk = __inet6_lookup(net, hinfo, NULL, 0,
 					    src6, tuple->ipv6.sport,
 					    dst6, ntohs(tuple->ipv6.dport),
 					    dif, sdif, &refcounted);

net/ipv4/esp4.c

@@ -134,6 +134,7 @@ static void esp_free_tcp_sk(struct rcu_head *head)
 static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
 {
 	struct xfrm_encap_tmpl *encap = x->encap;
+	struct net *net = xs_net(x);
 	struct esp_tcp_sk *esk;
 	__be16 sport, dport;
 	struct sock *nsk;
@@ -160,7 +161,7 @@ static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
 	}
 	spin_unlock_bh(&x->lock);
 
-	sk = inet_lookup_established(xs_net(x), &tcp_hashinfo, x->id.daddr.a4,
+	sk = inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, x->id.daddr.a4,
 				     dport, x->props.saddr.a4, sport, 0);
 	if (!sk)
 		return ERR_PTR(-ENOENT);

net/ipv4/inet_hashtables.c

@@ -386,7 +386,7 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net,
 	struct sock *sk, *reuse_sk;
 	bool no_reuseport;
 
-	if (hashinfo != &tcp_hashinfo)
+	if (hashinfo != net->ipv4.tcp_death_row.hashinfo)
 		return NULL; /* only TCP is supported */
 
 	no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, saddr, sport,

net/ipv4/netfilter/nf_socket_ipv4.c

@@ -71,8 +71,8 @@ nf_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff,
 {
 	switch (protocol) {
 	case IPPROTO_TCP:
-		return inet_lookup(net, &tcp_hashinfo, skb, doff,
-				   saddr, sport, daddr, dport,
+		return inet_lookup(net, net->ipv4.tcp_death_row.hashinfo,
+				   skb, doff, saddr, sport, daddr, dport,
 				   in->ifindex);
 	case IPPROTO_UDP:
 		return udp4_lib_lookup(net, saddr, sport, daddr, dport,

net/ipv4/netfilter/nf_tproxy_ipv4.c

@@ -79,6 +79,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb,
 		      const struct net_device *in,
 		      const enum nf_tproxy_lookup_t lookup_type)
 {
+	struct inet_hashinfo *hinfo = net->ipv4.tcp_death_row.hashinfo;
 	struct sock *sk;
 
 	switch (protocol) {
@@ -92,12 +93,10 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb,
 
 		switch (lookup_type) {
 		case NF_TPROXY_LOOKUP_LISTENER:
-			sk = inet_lookup_listener(net, &tcp_hashinfo, skb,
-						    ip_hdrlen(skb) +
-						      __tcp_hdrlen(hp),
-						    saddr, sport,
-						    daddr, dport,
-						    in->ifindex, 0);
+			sk = inet_lookup_listener(net, hinfo, skb,
+						  ip_hdrlen(skb) + __tcp_hdrlen(hp),
+						  saddr, sport, daddr, dport,
+						  in->ifindex, 0);
 
 			if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
 				sk = NULL;
@@ -108,9 +107,8 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb,
 			 */
 			break;
 		case NF_TPROXY_LOOKUP_ESTABLISHED:
-			sk = inet_lookup_established(net, &tcp_hashinfo,
-						    saddr, sport, daddr, dport,
-						    in->ifindex);
+			sk = inet_lookup_established(net, hinfo, saddr, sport,
+						     daddr, dport, in->ifindex);
 			break;
 		default:
 			BUG();

net/ipv4/tcp_diag.c

@@ -181,23 +181,35 @@ static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin)
 static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 			  const struct inet_diag_req_v2 *r)
 {
-	inet_diag_dump_icsk(&tcp_hashinfo, skb, cb, r);
+	struct inet_hashinfo *hinfo;
+
+	hinfo = sock_net(cb->skb->sk)->ipv4.tcp_death_row.hashinfo;
+
+	inet_diag_dump_icsk(hinfo, skb, cb, r);
 }
 
 static int tcp_diag_dump_one(struct netlink_callback *cb,
 			     const struct inet_diag_req_v2 *req)
 {
-	return inet_diag_dump_one_icsk(&tcp_hashinfo, cb, req);
+	struct inet_hashinfo *hinfo;
+
+	hinfo = sock_net(cb->skb->sk)->ipv4.tcp_death_row.hashinfo;
+
+	return inet_diag_dump_one_icsk(hinfo, cb, req);
 }
 
 #ifdef CONFIG_INET_DIAG_DESTROY
 static int tcp_diag_destroy(struct sk_buff *in_skb,
 			    const struct inet_diag_req_v2 *req)
 {
 	struct net *net = sock_net(in_skb->sk);
-	struct sock *sk = inet_diag_find_one_icsk(net, &tcp_hashinfo, req);
+	struct inet_hashinfo *hinfo;
+	struct sock *sk;
 	int err;
 
+	hinfo = net->ipv4.tcp_death_row.hashinfo;
+	sk = inet_diag_find_one_icsk(net, hinfo, req);
+
 	if (IS_ERR(sk))
 		return PTR_ERR(sk);