Merge branch 'net-inet-retire-port-only-listening_hash'

Martin KaFai Lau says:

====================
net: inet: Retire port only listening_hash

This series is to retire the port only listening_hash.

The listen sk is currently stored in two hash tables,
listening_hash (hashed by port) and lhash2 (hashed by port and address).

After commit 0ee58dad5b06 ("net: tcp6: prefer listeners bound to an address")
and commit d9fbc7f6431f ("net: tcp: prefer listeners bound to an address"),
the TCP-SYN lookup fast path does not use listening_hash.

The commit 05c0b35709c5 ("tcp: seq_file: Replace listening_hash with lhash2")
also moved the seq_file (/proc/net/tcp) iteration usage from
listening_hash to lhash2.

There are still a few listening_hash usages left.
One of them is inet_reuseport_add_sock() which uses the listening_hash
to search a listen sk during the listen() system call.  This turns
out to be very slow on use cases that listen on many different
VIPs at a popular port (e.g. 443).  [ On top of the slowness in
adding to the tail in the IPv6 case ]. A latter patch has a
selftest to demonstrate this case.

This series takes this chance to move all remaining listening_hash
usages to lhash2 and then retire listening_hash.
====================

Link: https://lore.kernel.org/r/20220512000546.188616-1-kafai@fb.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 9 insertions, 12 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 918816ec5dd4..218ad871c0e4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2283,16 +2283,15 @@ static void *listening_get_first(struct seq_file *seq)
 	st->offset = 0;
 	for (; st->bucket <= tcp_hashinfo.lhash2_mask; st->bucket++) {
 		struct inet_listen_hashbucket *ilb2;
-		struct inet_connection_sock *icsk;
+		struct hlist_nulls_node *node;
 		struct sock *sk;
 
 		ilb2 = &tcp_hashinfo.lhash2[st->bucket];
-		if (hlist_empty(&ilb2->head))
+		if (hlist_nulls_empty(&ilb2->nulls_head))
 			continue;
 
 		spin_lock(&ilb2->lock);
-		inet_lhash2_for_each_icsk(icsk, &ilb2->head) {
-			sk = (struct sock *)icsk;
+		sk_nulls_for_each(sk, node, &ilb2->nulls_head) {
 			if (seq_sk_match(seq, sk))
 				return sk;
 		}
@@ -2311,15 +2310,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 {
 	struct tcp_iter_state *st = seq->private;
 	struct inet_listen_hashbucket *ilb2;
-	struct inet_connection_sock *icsk;
+	struct hlist_nulls_node *node;
 	struct sock *sk = cur;
 
 	++st->num;
 	++st->offset;
 
-	icsk = inet_csk(sk);
-	inet_lhash2_for_each_icsk_continue(icsk) {
-		sk = (struct sock *)icsk;
+	sk = sk_nulls_next(sk);
+	sk_nulls_for_each_from(sk, node) {
 		if (seq_sk_match(seq, sk))
 			return sk;
 	}
@@ -2728,16 +2726,15 @@ static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq,
 {
 	struct bpf_tcp_iter_state *iter = seq->private;
 	struct tcp_iter_state *st = &iter->state;
-	struct inet_connection_sock *icsk;
+	struct hlist_nulls_node *node;
 	unsigned int expected = 1;
 	struct sock *sk;
 
 	sock_hold(start_sk);
 	iter->batch[iter->end_sk++] = start_sk;
 
-	icsk = inet_csk(start_sk);
-	inet_lhash2_for_each_icsk_continue(icsk) {
-		sk = (struct sock *)icsk;
+	sk = sk_nulls_next(start_sk);
+	sk_nulls_for_each_from(sk, node) {
 		if (seq_sk_match(seq, sk)) {
 			if (iter->end_sk < iter->max_sk) {
 				sock_hold(sk);