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 <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 71 insertions, 46 deletions

diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 5c03eba787e5..6be0f8903be1 100644
--- a/net/ipv4/esp4.c
+++ b/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);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index bdb5427a7a3d..c440de998910 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/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,
diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c
index 2d42e4c35a20..a1350fc25838 100644
--- a/net/ipv4/netfilter/nf_socket_ipv4.c
+++ b/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,
diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c
index b2bae0b0e42a..b22b2c745c76 100644
--- a/net/ipv4/netfilter/nf_tproxy_ipv4.c
+++ b/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();
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 75a1c985f49a..01b50fa79189 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -181,13 +181,21 @@ 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
@@ -195,9 +203,13 @@ 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);
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3bb7da95b757..9aa186af6c44 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -248,9 +248,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (!inet_opt || !inet_opt->opt.srr)
 		daddr = fl4->daddr;
 
+	tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
+
 	if (!inet->inet_saddr) {
 		if (inet_csk(sk)->icsk_bind2_hash) {
-			prev_addr_hashbucket = inet_bhashfn_portaddr(&tcp_hashinfo,
+			prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo,
 								     sk, net, inet->inet_num);
 			prev_sk_rcv_saddr = sk->sk_rcv_saddr;
 		}
@@ -292,7 +294,6 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	 * complete initialization after this.
 	 */
 	tcp_set_state(sk, TCP_SYN_SENT);
-	tcp_death_row = &net->ipv4.tcp_death_row;
 	err = inet_hash_connect(tcp_death_row, sk);
 	if (err)
 		goto failure;
@@ -494,9 +495,9 @@ int tcp_v4_err(struct sk_buff *skb, u32 info)
 	int err;
 	struct net *net = dev_net(skb->dev);
 
-	sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr,
-				       th->dest, iph->saddr, ntohs(th->source),
-				       inet_iif(skb), 0);
+	sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
+				       iph->daddr, th->dest, iph->saddr,
+				       ntohs(th->source), inet_iif(skb), 0);
 	if (!sk) {
 		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
 		return -ENOENT;
@@ -759,8 +760,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 		 * Incoming packet is checked with md5 hash with finding key,
 		 * no RST generated if md5 hash doesn't match.
 		 */
-		sk1 = __inet_lookup_listener(net, &tcp_hashinfo, NULL, 0,
-					     ip_hdr(skb)->saddr,
+		sk1 = __inet_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo,
+					     NULL, 0, ip_hdr(skb)->saddr,
 					     th->source, ip_hdr(skb)->daddr,
 					     ntohs(th->source), dif, sdif);
 		/* don't send rst if it can't find key */
@@ -1728,6 +1729,7 @@ EXPORT_SYMBOL(tcp_v4_do_rcv);
 
 int tcp_v4_early_demux(struct sk_buff *skb)
 {
+	struct net *net = dev_net(skb->dev);
 	const struct iphdr *iph;
 	const struct tcphdr *th;
 	struct sock *sk;
@@ -1744,7 +1746,7 @@ int tcp_v4_early_demux(struct sk_buff *skb)
 	if (th->doff < sizeof(struct tcphdr) / 4)
 		return 0;
 
-	sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
+	sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
 				       iph->saddr, th->source,
 				       iph->daddr, ntohs(th->dest),
 				       skb->skb_iif, inet_sdif(skb));
@@ -1970,7 +1972,8 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	th = (const struct tcphdr *)skb->data;
 	iph = ip_hdr(skb);
 lookup:
-	sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source,
+	sk = __inet_lookup_skb(net->ipv4.tcp_death_row.hashinfo,
+			       skb, __tcp_hdrlen(th), th->source,
 			       th->dest, sdif, &refcounted);
 	if (!sk)
 		goto no_tcp_socket;
@@ -2152,9 +2155,9 @@ do_time_wait:
 	}
 	switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
 	case TCP_TW_SYN: {
-		struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev),
-							&tcp_hashinfo, skb,
-							__tcp_hdrlen(th),
+		struct sock *sk2 = inet_lookup_listener(net,
+							net->ipv4.tcp_death_row.hashinfo,
+							skb, __tcp_hdrlen(th),
 							iph->saddr, th->source,
 							iph->daddr, th->dest,
 							inet_iif(skb),
@@ -2304,15 +2307,16 @@ static bool seq_sk_match(struct seq_file *seq, const struct sock *sk)
  */
 static void *listening_get_first(struct seq_file *seq)
 {
+	struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo;
 	struct tcp_iter_state *st = seq->private;
 
 	st->offset = 0;
-	for (; st->bucket <= tcp_hashinfo.lhash2_mask; st->bucket++) {
+	for (; st->bucket <= hinfo->lhash2_mask; st->bucket++) {
 		struct inet_listen_hashbucket *ilb2;
 		struct hlist_nulls_node *node;
 		struct sock *sk;
 
-		ilb2 = &tcp_hashinfo.lhash2[st->bucket];
+		ilb2 = &hinfo->lhash2[st->bucket];
 		if (hlist_nulls_empty(&ilb2->nulls_head))
 			continue;
 
@@ -2337,6 +2341,7 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 	struct tcp_iter_state *st = seq->private;
 	struct inet_listen_hashbucket *ilb2;
 	struct hlist_nulls_node *node;
+	struct inet_hashinfo *hinfo;
 	struct sock *sk = cur;
 
 	++st->num;
@@ -2348,7 +2353,8 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 			return sk;
 	}
 
-	ilb2 = &tcp_hashinfo.lhash2[st->bucket];
+	hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo;
+	ilb2 = &hinfo->lhash2[st->bucket];
 	spin_unlock(&ilb2->lock);
 	++st->bucket;
 	return listening_get_first(seq);
@@ -2370,9 +2376,10 @@ static void *listening_get_idx(struct seq_file *seq, loff_t *pos)
 	return rc;
 }
 
-static inline bool empty_bucket(const struct tcp_iter_state *st)
+static inline bool empty_bucket(struct inet_hashinfo *hinfo,
+				const struct tcp_iter_state *st)
 {
-	return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain);
+	return hlist_nulls_empty(&hinfo->ehash[st->bucket].chain);
 }
 
 /*
@@ -2381,20 +2388,21 @@ static inline bool empty_bucket(const struct tcp_iter_state *st)
  */
 static void *established_get_first(struct seq_file *seq)
 {
+	struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo;
 	struct tcp_iter_state *st = seq->private;
 
 	st->offset = 0;
-	for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) {
+	for (; st->bucket <= hinfo->ehash_mask; ++st->bucket) {
 		struct sock *sk;
 		struct hlist_nulls_node *node;
-		spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket);
+		spinlock_t *lock = inet_ehash_lockp(hinfo, st->bucket);
 
 		/* Lockless fast path for the common case of empty buckets */
-		if (empty_bucket(st))
+		if (empty_bucket(hinfo, st))
 			continue;
 
 		spin_lock_bh(lock);
-		sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
+		sk_nulls_for_each(sk, node, &hinfo->ehash[st->bucket].chain) {
 			if (seq_sk_match(seq, sk))
 				return sk;
 		}
@@ -2406,6 +2414,7 @@ static void *established_get_first(struct seq_file *seq)
 
 static void *established_get_next(struct seq_file *seq, void *cur)
 {
+	struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo;
 	struct tcp_iter_state *st = seq->private;
 	struct hlist_nulls_node *node;
 	struct sock *sk = cur;
@@ -2420,7 +2429,7 @@ static void *established_get_next(struct seq_file *seq, void *cur)
 			return sk;
 	}
 
-	spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
+	spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket));
 	++st->bucket;
 	return established_get_first(seq);
 }
@@ -2458,6 +2467,7 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos)
 
 static void *tcp_seek_last_pos(struct seq_file *seq)
 {
+	struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo;
 	struct tcp_iter_state *st = seq->private;
 	int bucket = st->bucket;
 	int offset = st->offset;
@@ -2466,7 +2476,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq)
 
 	switch (st->state) {
 	case TCP_SEQ_STATE_LISTENING:
-		if (st->bucket > tcp_hashinfo.lhash2_mask)
+		if (st->bucket > hinfo->lhash2_mask)
 			break;
 		st->state = TCP_SEQ_STATE_LISTENING;
 		rc = listening_get_first(seq);
@@ -2478,7 +2488,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq)
 		st->state = TCP_SEQ_STATE_ESTABLISHED;
 		fallthrough;
 	case TCP_SEQ_STATE_ESTABLISHED:
-		if (st->bucket > tcp_hashinfo.ehash_mask)
+		if (st->bucket > hinfo->ehash_mask)
 			break;
 		rc = established_get_first(seq);
 		while (offset-- && rc && bucket == st->bucket)
@@ -2546,16 +2556,17 @@ EXPORT_SYMBOL(tcp_seq_next);
 
 void tcp_seq_stop(struct seq_file *seq, void *v)
 {
+	struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo;
 	struct tcp_iter_state *st = seq->private;
 
 	switch (st->state) {
 	case TCP_SEQ_STATE_LISTENING:
 		if (v != SEQ_START_TOKEN)
-			spin_unlock(&tcp_hashinfo.lhash2[st->bucket].lock);
+			spin_unlock(&hinfo->lhash2[st->bucket].lock);
 		break;
 	case TCP_SEQ_STATE_ESTABLISHED:
 		if (v)
-			spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
+			spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket));
 		break;
 	}
 }
@@ -2750,6 +2761,7 @@ static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter,
 static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq,
 						 struct sock *start_sk)
 {
+	struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo;
 	struct bpf_tcp_iter_state *iter = seq->private;
 	struct tcp_iter_state *st = &iter->state;
 	struct hlist_nulls_node *node;
@@ -2769,7 +2781,7 @@ static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq,
 			expected++;
 		}
 	}
-	spin_unlock(&tcp_hashinfo.lhash2[st->bucket].lock);
+	spin_unlock(&hinfo->lhash2[st->bucket].lock);
 
 	return expected;
 }
@@ -2777,6 +2789,7 @@ static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq,
 static unsigned int bpf_iter_tcp_established_batch(struct seq_file *seq,
 						   struct sock *start_sk)
 {
+	struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo;
 	struct bpf_tcp_iter_state *iter = seq->private;
 	struct tcp_iter_state *st = &iter->state;
 	struct hlist_nulls_node *node;
@@ -2796,13 +2809,14 @@ static unsigned int bpf_iter_tcp_established_batch(struct seq_file *seq,
 			expected++;
 		}
 	}
-	spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
+	spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket));
 
 	return expected;
 }
 
 static struct sock *bpf_iter_tcp_batch(struct seq_file *seq)
 {
+	struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo;
 	struct bpf_tcp_iter_state *iter = seq->private;
 	struct tcp_iter_state *st = &iter->state;
 	unsigned int expected;
@@ -2818,7 +2832,7 @@ static struct sock *bpf_iter_tcp_batch(struct seq_file *seq)
 		st->offset = 0;
 		st->bucket++;
 		if (st->state == TCP_SEQ_STATE_LISTENING &&
-		    st->bucket > tcp_hashinfo.lhash2_mask) {
+		    st->bucket > hinfo->lhash2_mask) {
 			st->state = TCP_SEQ_STATE_ESTABLISHED;
 			st->bucket = 0;
 		}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 8bddb2a78b21..2e53981252d9 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -319,7 +319,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		/* Linkage updates.
 		 * Note that access to tw after this point is illegal.
 		 */
-		inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
+		inet_twsk_hashdance(tw, sk, net->ipv4.tcp_death_row.hashinfo);
 		local_bh_enable();
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this