tcp/dccp: change source port selection at connect() time

In commit 1580ab63fc9a ("tcp/dccp: better use of ephemeral ports in connect()")
we added an heuristic to select even ports for connect() and odd ports for bind().

This was nice because no applications changes were needed.

But it added more costs when all even ports are in use,
when there are few listeners and many active connections.

Since then, IP_LOCAL_PORT_RANGE has been added to permit an application
to partition ephemeral port range at will.

This patch extends the idea so that if IP_LOCAL_PORT_RANGE is set on
a socket before accept(), port selection no longer favors even ports.

This means that connect() can find a suitable source port faster,
and applications can use a different split between connect() and bind()
users.

This should give more entropy to Toeplitz hash used in RSS: Using even
ports was wasting one bit from the 16bit sport.

A similar change can be done in inet_csk_find_open_port() if needed.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jakub Sitnicki <jakub@cloudflare.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://lore.kernel.org/r/20231214192939.1962891-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 16 insertions, 11 deletions

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index a532f749e477..9ff201bc4e6d 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -1012,7 +1012,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 	bool tb_created = false;
 	u32 remaining, offset;
 	int ret, i, low, high;
-	int l3mdev;
+	bool local_ports;
+	int step, l3mdev;
 	u32 index;
 
 	if (port) {
@@ -1024,10 +1025,12 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 
 	l3mdev = inet_sk_bound_l3mdev(sk);
 
-	inet_sk_get_local_port_range(sk, &low, &high);
+	local_ports = inet_sk_get_local_port_range(sk, &low, &high);
+	step = local_ports ? 1 : 2;
+
 	high++; /* [32768, 60999] -> [32768, 61000[ */
 	remaining = high - low;
-	if (likely(remaining > 1))
+	if (!local_ports && remaining > 1)
 		remaining &= ~1U;
 
 	get_random_sleepable_once(table_perturb,
@@ -1040,10 +1043,11 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 	/* In first pass we try ports of @low parity.
 	 * inet_csk_get_port() does the opposite choice.
 	 */
-	offset &= ~1U;
+	if (!local_ports)
+		offset &= ~1U;
 other_parity_scan:
 	port = low + offset;
-	for (i = 0; i < remaining; i += 2, port += 2) {
+	for (i = 0; i < remaining; i += step, port += step) {
 		if (unlikely(port >= high))
 			port -= remaining;
 		if (inet_is_local_reserved_port(net, port))
@@ -1083,10 +1087,11 @@ next_port:
 		cond_resched();
 	}
 
-	offset++;
-	if ((offset & 1) && remaining > 1)
-		goto other_parity_scan;
-
+	if (!local_ports) {
+		offset++;
+		if ((offset & 1) && remaining > 1)
+			goto other_parity_scan;
+	}
 	return -EADDRNOTAVAIL;
 
 ok:
@@ -1109,8 +1114,8 @@ ok:
 	 * on low contention the randomness is maximal and on high contention
 	 * it may be inexistent.
 	 */
-	i = max_t(int, i, get_random_u32_below(8) * 2);
-	WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2);
+	i = max_t(int, i, get_random_u32_below(8) * step);
+	WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + step);
 
 	/* Head lock still held and bh's disabled */
 	inet_bind_hash(sk, tb, tb2, port);