Merge branch 'tcp-dccp-refine-source-port-selection'

Eric Dumazet says:

====================
tcp/dccp: refine source port selection

This patch series leverages IP_LOCAL_PORT_RANGE option
to no longer favor even source port selection at connect() time.

This should lower time taken by connect() for hosts having
many active connections to the same destination.
====================

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

include/net/ip.h

@@ -356,7 +356,7 @@ static inline void inet_get_local_port_range(const struct net *net, int *low, in
 	*low = range & 0xffff;
 	*high = range >> 16;
 }
-void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
+bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
 
 #ifdef CONFIG_SYSCTL
 static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port)

net/ipv4/inet_connection_sock.c

@@ -117,16 +117,25 @@ bool inet_rcv_saddr_any(const struct sock *sk)
 	return !sk->sk_rcv_saddr;
 }
 
-void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high)
+/**
+ *	inet_sk_get_local_port_range - fetch ephemeral ports range
+ *	@sk: socket
+ *	@low: pointer to low port
+ *	@high: pointer to high port
+ *
+ *	Fetch netns port range (/proc/sys/net/ipv4/ip_local_port_range)
+ *	Range can be overridden if socket got IP_LOCAL_PORT_RANGE option.
+ *	Returns true if IP_LOCAL_PORT_RANGE was set on this socket.
+ */
+bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high)
 {
-	const struct inet_sock *inet = inet_sk(sk);
-	const struct net *net = sock_net(sk);
 	int lo, hi, sk_lo, sk_hi;
+	bool local_range = false;
 	u32 sk_range;
 
-	inet_get_local_port_range(net, &lo, &hi);
+	inet_get_local_port_range(sock_net(sk), &lo, &hi);
 
-	sk_range = READ_ONCE(inet->local_port_range);
+	sk_range = READ_ONCE(inet_sk(sk)->local_port_range);
 	if (unlikely(sk_range)) {
 		sk_lo = sk_range & 0xffff;
 		sk_hi = sk_range >> 16;
@@ -135,10 +144,12 @@ void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high)
 			lo = sk_lo;
 		if (lo <= sk_hi && sk_hi <= hi)
 			hi = sk_hi;
+		local_range = true;
 	}
 
 	*low = lo;
 	*high = hi;
+	return local_range;
 }
 EXPORT_SYMBOL(inet_sk_get_local_port_range);
 

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 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		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 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 	 * 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);