public inbox for netdev@vger.kernel.org
 help / color / mirror / Atom feed
From: Martin KaFai Lau <martin.lau@linux.dev>
To: netdev@vger.kernel.org
Cc: 'David Miller ' <davem@davemloft.net>,
	'Jakub Kicinski ' <kuba@kernel.org>,
	'Eric Dumazet ' <edumazet@google.com>,
	'Paolo Abeni ' <pabeni@redhat.com>,
	'Kuniyuki Iwashima ' <kuniyu@google.com>,
	Andrew Onyshchuk <oandrew@meta.com>
Subject: [PATCH net] udp: Fix wildcard bind conflict check when using hash2
Date: Thu, 19 Mar 2026 11:18:17 -0700	[thread overview]
Message-ID: <20260319181817.1901357-1-martin.lau@linux.dev> (raw)

From: Martin KaFai Lau <martin.lau@kernel.org>

When binding a udp_sock to a local address and port, UDP uses
two hashes (udptable->hash and udptable->hash2) for collision
detection. The current code switches to "hash2" when
hslot->count > 10.

"hash2" is keyed by local address and local port.
"hash" is keyed by local port only.

The issue can be shown in the following bind sequence (pseudo code):

bind(fd1,  "[fd00::1]:8888")
bind(fd2,  "[fd00::2]:8888")
bind(fd3,  "[fd00::3]:8888")
bind(fd4,  "[fd00::4]:8888")
bind(fd5,  "[fd00::5]:8888")
bind(fd6,  "[fd00::6]:8888")
bind(fd7,  "[fd00::7]:8888")
bind(fd8,  "[fd00::8]:8888")
bind(fd9,  "[fd00::9]:8888")
bind(fd10, "[fd00::10]:8888")

/* Correctly return -EADDRINUSE because "hash" is used
 * instead of "hash2". udp_lib_lport_inuse() detects the
 * conflict.
 */
bind(fail_fd, "[::]:8888")

/* After one more socket is bound to "[fd00::11]:8888",
 * hslot->count exceeds 10 and "hash2" is used instead.
 */
bind(fd11, "[fd00::11]:8888")
bind(fail_fd, "[::]:8888")      /* succeeds unexpectedly */

The same issue applies to the IPv4 wildcard address "0.0.0.0"
and the IPv4-mapped wildcard address "::ffff:0.0.0.0". For
example, if there are existing sockets bound to
"192.168.1.[1-11]:8888", then binding "0.0.0.0:8888" or
"[::ffff:0.0.0.0]:8888" can also miss the conflict when
hslot->count > 10.

TCP inet_csk_get_port() already has the correct check in
inet_use_bhash2_on_bind(). Rename it to
inet_use_hash2_on_bind() and move it to inet_hashtables.h
so udp.c can reuse it in this fix.

Fixes: 30fff9231fad ("udp: bind() optimisation")
Reported-by: Andrew Onyshchuk <oandrew@meta.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/net/inet_hashtables.h   | 14 ++++++++++++++
 net/ipv4/inet_connection_sock.c | 20 +++-----------------
 net/ipv4/udp.c                  |  2 +-
 3 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 5a979dcab538..6d936e9f2fd3 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -264,6 +264,20 @@ inet_bhashfn_portaddr(const struct inet_hashinfo *hinfo, const struct sock *sk,
 	return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)];
 }
 
+static inline bool inet_use_hash2_on_bind(const struct sock *sk)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6) {
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+			return false;
+
+		if (!ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+			return true;
+	}
+#endif
+	return sk->sk_rcv_saddr != htonl(INADDR_ANY);
+}
+
 struct inet_bind_hashbucket *
 inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port);
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 5dfac6ce1110..e961936b6be7 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -154,20 +154,6 @@ bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high)
 }
 EXPORT_SYMBOL(inet_sk_get_local_port_range);
 
-static bool inet_use_bhash2_on_bind(const struct sock *sk)
-{
-#if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family == AF_INET6) {
-		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
-			return false;
-
-		if (!ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
-			return true;
-	}
-#endif
-	return sk->sk_rcv_saddr != htonl(INADDR_ANY);
-}
-
 static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2,
 			       kuid_t uid, bool relax,
 			       bool reuseport_cb_ok, bool reuseport_ok)
@@ -259,7 +245,7 @@ static int inet_csk_bind_conflict(const struct sock *sk,
 	 * checks separately because their spinlocks have to be acquired/released
 	 * independently of each other, to prevent possible deadlocks
 	 */
-	if (inet_use_bhash2_on_bind(sk))
+	if (inet_use_hash2_on_bind(sk))
 		return tb2 && inet_bhash2_conflict(sk, tb2, uid, relax,
 						   reuseport_cb_ok, reuseport_ok);
 
@@ -376,7 +362,7 @@ inet_csk_find_open_port(const struct sock *sk, struct inet_bind_bucket **tb_ret,
 		head = &hinfo->bhash[inet_bhashfn(net, port,
 						  hinfo->bhash_size)];
 		spin_lock_bh(&head->lock);
-		if (inet_use_bhash2_on_bind(sk)) {
+		if (inet_use_hash2_on_bind(sk)) {
 			if (inet_bhash2_addr_any_conflict(sk, port, l3mdev, relax, false))
 				goto next_port;
 		}
@@ -562,7 +548,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 				check_bind_conflict = false;
 		}
 
-		if (check_bind_conflict && inet_use_bhash2_on_bind(sk)) {
+		if (check_bind_conflict && inet_use_hash2_on_bind(sk)) {
 			if (inet_bhash2_addr_any_conflict(sk, port, l3mdev, true, true))
 				goto fail_unlock;
 		}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b60fad393e18..cb99a3c27053 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -287,7 +287,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 	} else {
 		hslot = udp_hashslot(udptable, net, snum);
 		spin_lock_bh(&hslot->lock);
-		if (hslot->count > 10) {
+		if (inet_use_hash2_on_bind(sk) && hslot->count > 10) {
 			int exist;
 			unsigned int slot2 = udp_sk(sk)->udp_portaddr_hash ^ snum;
 
-- 
2.52.0


             reply	other threads:[~2026-03-19 18:18 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-19 18:18 Martin KaFai Lau [this message]
2026-03-20 23:07 ` [PATCH net] udp: Fix wildcard bind conflict check when using hash2 Kuniyuki Iwashima
2026-03-21  0:59   ` Jakub Kicinski
2026-03-21 13:44     ` Kuniyuki Iwashima
2026-03-24  2:00 ` patchwork-bot+netdevbpf

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260319181817.1901357-1-martin.lau@linux.dev \
    --to=martin.lau@linux.dev \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=kuba@kernel.org \
    --cc=kuniyu@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=oandrew@meta.com \
    --cc=pabeni@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox