Re: [PATCH net-next v3 02/15] net: build socket infrastructure for QUIC protocol

On Tue, Sep 23, 2025 at 7:07 AM Paolo Abeni [off-list ref] wrote:

On 9/19/25 12:34 AM, Xin Long wrote:

quoted

This patch lays the groundwork for QUIC socket support in the kernel.
It defines the core structures and protocol hooks needed to create
QUIC sockets, without implementing any protocol behavior at this stage.

Basic integration is included to allow building the module via
CONFIG_IP_QUIC=m.

This provides the scaffolding necessary for adding actual QUIC socket
behavior in follow-up patches.

Signed-off-by: Pengtao He <redacted>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
v3:
  - Kconfig: add 'default n' for IP_QUIC (reported by Paolo).
  - quic_disconnect(): return -EOPNOTSUPP (suggested by Paolo).
  - quic_init/destroy_sock(): drop local_bh_disable/enable() calls (noted
    by Paolo).
  - sysctl: add alpn_demux option to en/disable ALPN-based demux.
  - SNMP: remove SNMP_MIB_SENTINEL, switch to
    snmp_get_cpu_field_batch_cnt() to align with latest net-next changes.
---
 net/Kconfig         |   1 +
 net/Makefile        |   1 +
 net/quic/Kconfig    |  36 +++++
 net/quic/Makefile   |   8 +
 net/quic/protocol.c | 379 ++++++++++++++++++++++++++++++++++++++++++++
 net/quic/protocol.h |  56 +++++++
 net/quic/socket.c   | 207 ++++++++++++++++++++++++
 net/quic/socket.h   |  79 +++++++++
 8 files changed, 767 insertions(+)
 create mode 100644 net/quic/Kconfig
 create mode 100644 net/quic/Makefile
 create mode 100644 net/quic/protocol.c
 create mode 100644 net/quic/protocol.h
 create mode 100644 net/quic/socket.c
 create mode 100644 net/quic/socket.h

diff --git a/net/Kconfig b/net/Kconfig
index d5865cf19799..1205f5b7cf59 100644
--- a/net/Kconfig
+++ b/net/Kconfig

@@ -249,6 +249,7 @@ source "net/bridge/netfilter/Kconfig"

 endif # if NETFILTER

+source "net/quic/Kconfig"
 source "net/sctp/Kconfig"
 source "net/rds/Kconfig"
 source "net/tipc/Kconfig"

diff --git a/net/Makefile b/net/Makefile
index aac960c41db6..7c6de28e9aa5 100644
--- a/net/Makefile
+++ b/net/Makefile

@@ -42,6 +42,7 @@ obj-$(CONFIG_PHONET)                += phonet/
 ifneq ($(CONFIG_VLAN_8021Q),)
 obj-y                                += 8021q/
 endif
+obj-$(CONFIG_IP_QUIC)                += quic/
 obj-$(CONFIG_IP_SCTP)                += sctp/
 obj-$(CONFIG_RDS)            += rds/
 obj-$(CONFIG_WIRELESS)               += wireless/

diff --git a/net/quic/Kconfig b/net/quic/Kconfig
new file mode 100644
index 000000000000..1f10a452b3a1
--- /dev/null
+++ b/net/quic/Kconfig

@@ -0,0 +1,36 @@
+# SPDX-License-Identifier: GPL-2.0-or-later
+#
+# QUIC configuration
+#
+
+menuconfig IP_QUIC
+     tristate "QUIC: A UDP-Based Multiplexed and Secure Transport (Experimental)"
+     depends on INET
+     depends on IPV6
+     select CRYPTO
+     select CRYPTO_HMAC
+     select CRYPTO_HKDF
+     select CRYPTO_AES
+     select CRYPTO_GCM
+     select CRYPTO_CCM
+     select CRYPTO_CHACHA20POLY1305
+     select NET_UDP_TUNNEL
+     default n
+     help
+       QUIC: A UDP-Based Multiplexed and Secure Transport
+
+       From rfc9000 <https://www.rfc-editor.org/rfc/rfc9000.html>.
+
+       QUIC provides applications with flow-controlled streams for structured
+       communication, low-latency connection establishment, and network path
+       migration.  QUIC includes security measures that ensure
+       confidentiality, integrity, and availability in a range of deployment
+       circumstances.  Accompanying documents describe the integration of
+       TLS for key negotiation, loss detection, and an exemplary congestion
+       control algorithm.
+
+       To compile this protocol support as a module, choose M here: the
+       module will be called quic. Debug messages are handled by the
+       kernel's dynamic debugging framework.
+
+       If in doubt, say N.

diff --git a/net/quic/Makefile b/net/quic/Makefile
new file mode 100644
index 000000000000..020e4dd133d8
--- /dev/null
+++ b/net/quic/Makefile

@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0-or-later
+#
+# Makefile for QUIC support code.
+#
+
+obj-$(CONFIG_IP_QUIC) += quic.o
+
+quic-y := protocol.o socket.o

diff --git a/net/quic/protocol.c b/net/quic/protocol.c
new file mode 100644
index 000000000000..f79f43f0c17f
--- /dev/null
+++ b/net/quic/protocol.c

@@ -0,0 +1,379 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* QUIC kernel implementation
+ * (C) Copyright Red Hat Corp. 2023
+ *
+ * This file is part of the QUIC kernel implementation
+ *
+ * Initialization/cleanup for QUIC protocol support.
+ *
+ * Written or modified by:
+ *    Xin Long <lucien.xin@gmail.com>
+ */
+
+#include <net/inet_common.h>
+#include <linux/proc_fs.h>
+#include <net/protocol.h>
+#include <net/rps.h>
+#include <net/tls.h>
+
+#include "socket.h"
+
+static unsigned int quic_net_id __read_mostly;
+
+struct percpu_counter quic_sockets_allocated;
+
+long sysctl_quic_mem[3];
+int sysctl_quic_rmem[3];
+int sysctl_quic_wmem[3];
+int sysctl_quic_alpn_demux;
+
+static int quic_inet_connect(struct socket *sock, struct sockaddr *addr, int addr_len, int flags)
+{
+     struct sock *sk = sock->sk;
+     const struct proto *prot;
+
+     if (addr_len < (int)sizeof(addr->sa_family))
+             return -EINVAL;
+
+     prot = READ_ONCE(sk->sk_prot);

Is the above _ONCE() annotation for ADDRFORM's sake? If so it should not
be needed (only UDP and TCP sockets are affected).

I will delete it.

quoted

diff --git a/net/quic/socket.h b/net/quic/socket.h
new file mode 100644
index 000000000000..ded8eb2e6a9c
--- /dev/null
+++ b/net/quic/socket.h

@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* QUIC kernel implementation
+ * (C) Copyright Red Hat Corp. 2023
+ *
+ * This file is part of the QUIC kernel implementation
+ *
+ * Written or modified by:
+ *    Xin Long <lucien.xin@gmail.com>
+ */
+
+#include <net/udp_tunnel.h>
+
+#include "protocol.h"
+
+extern struct proto quic_prot;
+extern struct proto quicv6_prot;
+
+enum quic_state {
+     QUIC_SS_CLOSED          = TCP_CLOSE,
+     QUIC_SS_LISTENING       = TCP_LISTEN,
+     QUIC_SS_ESTABLISHING    = TCP_SYN_RECV,
+     QUIC_SS_ESTABLISHED     = TCP_ESTABLISHED,
+};

Any special reason to define protocol-specific states? I guess you could
re-use the TCP ones, as other protocols already do.

I know TIPC and SCTP define the states like this:

enum {
        TIPC_LISTEN = TCP_LISTEN,
        TIPC_ESTABLISHED = TCP_ESTABLISHED,
        TIPC_OPEN = TCP_CLOSE,
        TIPC_DISCONNECTING = TCP_CLOSE_WAIT,
        TIPC_CONNECTING = TCP_SYN_SENT,
};

and

enum sctp_sock_state {
        SCTP_SS_CLOSED         = TCP_CLOSE,
        SCTP_SS_LISTENING      = TCP_LISTEN,
        SCTP_SS_ESTABLISHING   = TCP_SYN_SENT,
        SCTP_SS_ESTABLISHED    = TCP_ESTABLISHED,
        SCTP_SS_CLOSING        = TCP_CLOSE_WAIT,
};

It should be fine to keep as is, or you have more and better
examples from other protocols.

Thanks.