Merge branch 'another-crack-at-a-handshake-upcall-mechanism'

Chuck Lever says:

====================
Another crack at a handshake upcall mechanism

Here is v10 of a series to add generic support for transport layer
security handshake on behalf of kernel socket consumers (user space
consumers use a security library directly, of course). A summary of
the purpose of these patches is archived here:

https://lore.kernel.org/netdev/1DE06BB1-6BA9-4DB4-B2AA-07DE532963D6@oracle.com/

The first patch in the series applies to the top-level .gitignore
file to address the build warnings reported a few days ago. I intend
to submit that separately. I'd like you to consider taking the rest
of this series for v6.4.

The full patch set to support SunRPC with TLSv1.3 is available in
the topic-rpc-with-tls-upcall branch here, based on net-next/main:

https://git.kernel.org/pub/scm/linux/kernel/git/cel/linux.git

This patch set includes support for in-transit confidentiality and
peer authentication for both the Linux NFS client and server.

A user space handshake agent for TLSv1.3 to go along with the kernel
patches is available in the "main" branch here:

https://github.com/oracle/ktls-utils
====================

Link: https://lore.kernel.org/r/168174169259.9520.1911007910797225963.stgit@91.116.238.104.host.secureserver.netSigned-off-by: Jakub Kicinski <kuba@kernel.org>

.gitignore

@@ -105,6 +105,7 @@ modules.order
 !.gitignore
 !.mailmap
 !.rustfmt.toml
+!.kunitconfig
 
 #
 # Generated include files

Documentation/netlink/specs/handshake.yaml

+# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+#
+# Author: Chuck Lever <chuck.lever@oracle.com>
+#
+# Copyright (c) 2023, Oracle and/or its affiliates.
+#
+
+name: handshake
+
+protocol: genetlink
+
+doc: Netlink protocol to request a transport layer security handshake.
+
+definitions:
+  -
+    type: enum
+    name: handler-class
+    value-start: 0
+    entries: [ none, tlshd, max ]
+  -
+    type: enum
+    name: msg-type
+    value-start: 0
+    entries: [ unspec, clienthello, serverhello ]
+  -
+    type: enum
+    name: auth
+    value-start: 0
+    entries: [ unspec, unauth, psk, x509 ]
+
+attribute-sets:
+  -
+    name: x509
+    attributes:
+      -
+        name: cert
+        type: u32
+      -
+        name: privkey
+        type: u32
+  -
+    name: accept
+    attributes:
+      -
+        name: sockfd
+        type: u32
+      -
+        name: handler-class
+        type: u32
+        enum: handler-class
+      -
+        name: message-type
+        type: u32
+        enum: msg-type
+      -
+        name: timeout
+        type: u32
+      -
+        name: auth-mode
+        type: u32
+        enum: auth
+      -
+        name: peer-identity
+        type: u32
+        multi-attr: true
+      -
+        name: certificate
+        type: nest
+        nested-attributes: x509
+        multi-attr: true
+  -
+    name: done
+    attributes:
+      -
+        name: status
+        type: u32
+      -
+        name: sockfd
+        type: u32
+      -
+        name: remote-auth
+        type: u32
+        multi-attr: true
+
+operations:
+  list:
+    -
+      name: ready
+      doc: Notify handlers that a new handshake request is waiting
+      notify: accept
+    -
+      name: accept
+      doc: Handler retrieves next queued handshake request
+      attribute-set: accept
+      flags: [ admin-perm ]
+      do:
+        request:
+          attributes:
+            - handler-class
+        reply:
+          attributes:
+            - sockfd
+            - message-type
+            - timeout
+            - auth-mode
+            - peer-identity
+            - certificate
+    -
+      name: done
+      doc: Handler reports handshake completion
+      attribute-set: done
+      do:
+        request:
+          attributes:
+            - status
+            - sockfd
+            - remote-auth
+
+mcast-groups:
+  list:
+    -
+      name: none
+    -
+      name: tlshd

Documentation/networking/index.rst

@@ -36,6 +36,7 @@ Contents:
    scaling
    tls
    tls-offload
+   tls-handshake
    nfc
    6lowpan
    6pack

Documentation/networking/tls-handshake.rst

+.. SPDX-License-Identifier: GPL-2.0
+
+=======================
+In-Kernel TLS Handshake
+=======================
+
+Overview
+========
+
+Transport Layer Security (TLS) is a Upper Layer Protocol (ULP) that runs
+over TCP. TLS provides end-to-end data integrity and confidentiality in
+addition to peer authentication.
+
+The kernel's kTLS implementation handles the TLS record subprotocol, but
+does not handle the TLS handshake subprotocol which is used to establish
+a TLS session. Kernel consumers can use the API described here to
+request TLS session establishment.
+
+There are several possible ways to provide a handshake service in the
+kernel. The API described here is designed to hide the details of those
+implementations so that in-kernel TLS consumers do not need to be
+aware of how the handshake gets done.
+
+
+User handshake agent
+====================
+
+As of this writing, there is no TLS handshake implementation in the
+Linux kernel. To provide a handshake service, a handshake agent
+(typically in user space) is started in each network namespace where a
+kernel consumer might require a TLS handshake. Handshake agents listen
+for events sent from the kernel that indicate a handshake request is
+waiting.
+
+An open socket is passed to a handshake agent via a netlink operation,
+which creates a socket descriptor in the agent's file descriptor table.
+If the handshake completes successfully, the handshake agent promotes
+the socket to use the TLS ULP and sets the session information using the
+SOL_TLS socket options. The handshake agent returns the socket to the
+kernel via a second netlink operation.
+
+
+Kernel Handshake API
+====================
+
+A kernel TLS consumer initiates a client-side TLS handshake on an open
+socket by invoking one of the tls_client_hello() functions. First, it
+fills in a structure that contains the parameters of the request:
+
+.. code-block:: c
+
+  struct tls_handshake_args {
+        struct socket   *ta_sock;
+        tls_done_func_t ta_done;
+        void            *ta_data;
+        unsigned int    ta_timeout_ms;
+        key_serial_t    ta_keyring;
+        key_serial_t    ta_my_cert;
+        key_serial_t    ta_my_privkey;
+        unsigned int    ta_num_peerids;
+        key_serial_t    ta_my_peerids[5];
+  };
+
+The @ta_sock field references an open and connected socket. The consumer
+must hold a reference on the socket to prevent it from being destroyed
+while the handshake is in progress. The consumer must also have
+instantiated a struct file in sock->file.
+
+
+@ta_done contains a callback function that is invoked when the handshake
+has completed. Further explanation of this function is in the "Handshake
+Completion" sesction below.
+
+The consumer can fill in the @ta_timeout_ms field to force the servicing
+handshake agent to exit after a number of milliseconds. This enables the
+socket to be fully closed once both the kernel and the handshake agent
+have closed their endpoints.
+
+Authentication material such as x.509 certificates, private certificate
+keys, and pre-shared keys are provided to the handshake agent in keys
+that are instantiated by the consumer before making the handshake
+request. The consumer can provide a private keyring that is linked into
+the handshake agent's process keyring in the @ta_keyring field to prevent
+access of those keys by other subsystems.
+
+To request an x.509-authenticated TLS session, the consumer fills in
+the @ta_my_cert and @ta_my_privkey fields with the serial numbers of
+keys containing an x.509 certificate and the private key for that
+certificate. Then, it invokes this function:
+
+.. code-block:: c
+
+  ret = tls_client_hello_x509(args, gfp_flags);
+
+The function returns zero when the handshake request is under way. A
+zero return guarantees the callback function @ta_done will be invoked
+for this socket. The function returns a negative errno if the handshake
+could not be started. A negative errno guarantees the callback function
+@ta_done will not be invoked on this socket.
+
+
+To initiate a client-side TLS handshake with a pre-shared key, use:
+
+.. code-block:: c
+
+  ret = tls_client_hello_psk(args, gfp_flags);
+
+However, in this case, the consumer fills in the @ta_my_peerids array
+with serial numbers of keys containing the peer identities it wishes
+to offer, and the @ta_num_peerids field with the number of array
+entries it has filled in. The other fields are filled in as above.
+
+
+To initiate an anonymous client-side TLS handshake use:
+
+.. code-block:: c
+
+  ret = tls_client_hello_anon(args, gfp_flags);
+
+The handshake agent presents no peer identity information to the remote
+during this type of handshake. Only server authentication (ie the client
+verifies the server's identity) is performed during the handshake. Thus
+the established session uses encryption only.
+
+
+Consumers that are in-kernel servers use:
+
+.. code-block:: c
+
+  ret = tls_server_hello_x509(args, gfp_flags);
+
+or
+
+.. code-block:: c
+
+  ret = tls_server_hello_psk(args, gfp_flags);
+
+The argument structure is filled in as above.
+
+
+If the consumer needs to cancel the handshake request, say, due to a ^C
+or other exigent event, the consumer can invoke:
+
+.. code-block:: c
+
+  bool tls_handshake_cancel(sock);
+
+This function returns true if the handshake request associated with
+@sock has been canceled. The consumer's handshake completion callback
+will not be invoked. If this function returns false, then the consumer's
+completion callback has already been invoked.
+
+
+Handshake Completion
+====================
+
+When the handshake agent has completed processing, it notifies the
+kernel that the socket may be used by the consumer again. At this point,
+the consumer's handshake completion callback, provided in the @ta_done
+field in the tls_handshake_args structure, is invoked.
+
+The synopsis of this function is:
+
+.. code-block:: c
+
+  typedef void	(*tls_done_func_t)(void *data, int status,
+                                   key_serial_t peerid);
+
+The consumer provides a cookie in the @ta_data field of the
+tls_handshake_args structure that is returned in the @data parameter of
+this callback. The consumer uses the cookie to match the callback to the
+thread waiting for the handshake to complete.
+
+The success status of the handshake is returned via the @status
+parameter:
+
++------------+----------------------------------------------+
+|  status    |  meaning                                     |
++============+==============================================+
+|  0         |  TLS session established successfully        |
++------------+----------------------------------------------+
+|  -EACCESS  |  Remote peer rejected the handshake or       |
+|            |  authentication failed                       |
++------------+----------------------------------------------+
+|  -ENOMEM   |  Temporary resource allocation failure       |
++------------+----------------------------------------------+
+|  -EINVAL   |  Consumer provided an invalid argument       |
++------------+----------------------------------------------+
+|  -ENOKEY   |  Missing authentication material             |
++------------+----------------------------------------------+
+|  -EIO      |  An unexpected fault occurred                |
++------------+----------------------------------------------+
+
+The @peerid parameter contains the serial number of a key containing the
+remote peer's identity or the value TLS_NO_PEERID if the session is not
+authenticated.
+
+A best practice is to close and destroy the socket immediately if the
+handshake failed.
+
+
+Other considerations
+--------------------
+
+While a handshake is under way, the kernel consumer must alter the
+socket's sk_data_ready callback function to ignore all incoming data.
+Once the handshake completion callback function has been invoked, normal
+receive operation can be resumed.
+
+Once a TLS session is established, the consumer must provide a buffer
+for and then examine the control message (CMSG) that is part of every
+subsequent sock_recvmsg(). Each control message indicates whether the
+received message data is TLS record data or session metadata.
+
+See tls.rst for details on how a kTLS consumer recognizes incoming
+(decrypted) application data, alerts, and handshake packets once the
+socket has been promoted to use the TLS ULP.

MAINTAINERS

@@ -8947,6 +8947,17 @@ Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/hackrf/
 
+HANDSHAKE UPCALL FOR TRANSPORT LAYER SECURITY
+M:	Chuck Lever <chuck.lever@oracle.com>
+L:	kernel-tls-handshake@lists.linux.dev
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	Documentation/netlink/specs/handshake.yaml
+F:	Documentation/networking/tls-handshake.rst
+F:	include/net/handshake.h
+F:	include/trace/events/handshake.h
+F:	net/handshake/
+
 HANTRO VPU CODEC DRIVER
 M:	Ezequiel Garcia <ezequiel@vanguardiasur.com.ar>
 M:	Philipp Zabel <p.zabel@pengutronix.de>

include/net/handshake.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Generic netlink HANDSHAKE service.
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ */
+
+#ifndef _NET_HANDSHAKE_H
+#define _NET_HANDSHAKE_H
+
+enum {
+	TLS_NO_KEYRING = 0,
+	TLS_NO_PEERID = 0,
+	TLS_NO_CERT = 0,
+	TLS_NO_PRIVKEY = 0,
+};
+
+typedef void	(*tls_done_func_t)(void *data, int status,
+				   key_serial_t peerid);
+
+struct tls_handshake_args {
+	struct socket		*ta_sock;
+	tls_done_func_t		ta_done;
+	void			*ta_data;
+	unsigned int		ta_timeout_ms;
+	key_serial_t		ta_keyring;
+	key_serial_t		ta_my_cert;
+	key_serial_t		ta_my_privkey;
+	unsigned int		ta_num_peerids;
+	key_serial_t		ta_my_peerids[5];
+};
+
+int tls_client_hello_anon(const struct tls_handshake_args *args, gfp_t flags);
+int tls_client_hello_x509(const struct tls_handshake_args *args, gfp_t flags);
+int tls_client_hello_psk(const struct tls_handshake_args *args, gfp_t flags);
+int tls_server_hello_x509(const struct tls_handshake_args *args, gfp_t flags);
+int tls_server_hello_psk(const struct tls_handshake_args *args, gfp_t flags);
+
+bool tls_handshake_cancel(struct sock *sk);
+
+#endif /* _NET_HANDSHAKE_H */

include/trace/events/handshake.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM handshake
+
+#if !defined(_TRACE_HANDSHAKE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_HANDSHAKE_H
+
+#include <linux/net.h>
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(handshake_event_class,
+	TP_PROTO(
+		const struct net *net,
+		const struct handshake_req *req,
+		const struct sock *sk
+	),
+	TP_ARGS(net, req, sk),
+	TP_STRUCT__entry(
+		__field(const void *, req)
+		__field(const void *, sk)
+		__field(unsigned int, netns_ino)
+	),
+	TP_fast_assign(
+		__entry->req = req;
+		__entry->sk = sk;
+		__entry->netns_ino = net->ns.inum;
+	),
+	TP_printk("req=%p sk=%p",
+		__entry->req, __entry->sk
+	)
+);
+#define DEFINE_HANDSHAKE_EVENT(name)				\
+	DEFINE_EVENT(handshake_event_class, name,		\
+		TP_PROTO(					\
+			const struct net *net,			\
+			const struct handshake_req *req,	\
+			const struct sock *sk			\
+		),						\
+		TP_ARGS(net, req, sk))
+
+DECLARE_EVENT_CLASS(handshake_fd_class,
+	TP_PROTO(
+		const struct net *net,
+		const struct handshake_req *req,
+		const struct sock *sk,
+		int fd
+	),
+	TP_ARGS(net, req, sk, fd),
+	TP_STRUCT__entry(
+		__field(const void *, req)
+		__field(const void *, sk)
+		__field(int, fd)
+		__field(unsigned int, netns_ino)
+	),
+	TP_fast_assign(
+		__entry->req = req;
+		__entry->sk = req->hr_sk;
+		__entry->fd = fd;
+		__entry->netns_ino = net->ns.inum;
+	),
+	TP_printk("req=%p sk=%p fd=%d",
+		__entry->req, __entry->sk, __entry->fd
+	)
+);
+#define DEFINE_HANDSHAKE_FD_EVENT(name)				\
+	DEFINE_EVENT(handshake_fd_class, name,			\
+		TP_PROTO(					\
+			const struct net *net,			\
+			const struct handshake_req *req,	\
+			const struct sock *sk,			\
+			int fd					\
+		),						\
+		TP_ARGS(net, req, sk, fd))
+
+DECLARE_EVENT_CLASS(handshake_error_class,
+	TP_PROTO(
+		const struct net *net,
+		const struct handshake_req *req,
+		const struct sock *sk,
+		int err
+	),
+	TP_ARGS(net, req, sk, err),
+	TP_STRUCT__entry(
+		__field(const void *, req)
+		__field(const void *, sk)
+		__field(int, err)
+		__field(unsigned int, netns_ino)
+	),
+	TP_fast_assign(
+		__entry->req = req;
+		__entry->sk = sk;
+		__entry->err = err;
+		__entry->netns_ino = net->ns.inum;
+	),
+	TP_printk("req=%p sk=%p err=%d",
+		__entry->req, __entry->sk, __entry->err
+	)
+);
+#define DEFINE_HANDSHAKE_ERROR(name)				\
+	DEFINE_EVENT(handshake_error_class, name,		\
+		TP_PROTO(					\
+			const struct net *net,			\
+			const struct handshake_req *req,	\
+			const struct sock *sk,			\
+			int err					\
+		),						\
+		TP_ARGS(net, req, sk, err))
+
+
+/*
+ * Request lifetime events
+ */
+
+DEFINE_HANDSHAKE_EVENT(handshake_submit);
+DEFINE_HANDSHAKE_ERROR(handshake_submit_err);
+DEFINE_HANDSHAKE_EVENT(handshake_cancel);
+DEFINE_HANDSHAKE_EVENT(handshake_cancel_none);
+DEFINE_HANDSHAKE_EVENT(handshake_cancel_busy);
+DEFINE_HANDSHAKE_EVENT(handshake_destruct);
+
+
+TRACE_EVENT(handshake_complete,
+	TP_PROTO(
+		const struct net *net,
+		const struct handshake_req *req,
+		const struct sock *sk,
+		int status
+	),
+	TP_ARGS(net, req, sk, status),
+	TP_STRUCT__entry(
+		__field(const void *, req)
+		__field(const void *, sk)
+		__field(int, status)
+		__field(unsigned int, netns_ino)
+	),
+	TP_fast_assign(
+		__entry->req = req;
+		__entry->sk = sk;
+		__entry->status = status;
+		__entry->netns_ino = net->ns.inum;
+	),
+	TP_printk("req=%p sk=%p status=%d",
+		__entry->req, __entry->sk, __entry->status
+	)
+);
+
+/*
+ * Netlink events
+ */
+
+DEFINE_HANDSHAKE_ERROR(handshake_notify_err);
+DEFINE_HANDSHAKE_FD_EVENT(handshake_cmd_accept);
+DEFINE_HANDSHAKE_ERROR(handshake_cmd_accept_err);
+DEFINE_HANDSHAKE_FD_EVENT(handshake_cmd_done);
+DEFINE_HANDSHAKE_ERROR(handshake_cmd_done_err);
+
+#endif /* _TRACE_HANDSHAKE_H */
+
+#include <trace/define_trace.h>

include/uapi/linux/handshake.h

+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/handshake.yaml */
+/* YNL-GEN uapi header */
+
+#ifndef _UAPI_LINUX_HANDSHAKE_H
+#define _UAPI_LINUX_HANDSHAKE_H
+
+#define HANDSHAKE_FAMILY_NAME		"handshake"
+#define HANDSHAKE_FAMILY_VERSION	1
+
+enum handshake_handler_class {
+	HANDSHAKE_HANDLER_CLASS_NONE,
+	HANDSHAKE_HANDLER_CLASS_TLSHD,
+	HANDSHAKE_HANDLER_CLASS_MAX,
+};
+
+enum handshake_msg_type {
+	HANDSHAKE_MSG_TYPE_UNSPEC,
+	HANDSHAKE_MSG_TYPE_CLIENTHELLO,
+	HANDSHAKE_MSG_TYPE_SERVERHELLO,
+};
+
+enum handshake_auth {
+	HANDSHAKE_AUTH_UNSPEC,
+	HANDSHAKE_AUTH_UNAUTH,
+	HANDSHAKE_AUTH_PSK,
+	HANDSHAKE_AUTH_X509,
+};
+
+enum {
+	HANDSHAKE_A_X509_CERT = 1,
+	HANDSHAKE_A_X509_PRIVKEY,
+
+	__HANDSHAKE_A_X509_MAX,
+	HANDSHAKE_A_X509_MAX = (__HANDSHAKE_A_X509_MAX - 1)
+};
+
+enum {
+	HANDSHAKE_A_ACCEPT_SOCKFD = 1,
+	HANDSHAKE_A_ACCEPT_HANDLER_CLASS,
+	HANDSHAKE_A_ACCEPT_MESSAGE_TYPE,
+	HANDSHAKE_A_ACCEPT_TIMEOUT,
+	HANDSHAKE_A_ACCEPT_AUTH_MODE,
+	HANDSHAKE_A_ACCEPT_PEER_IDENTITY,
+	HANDSHAKE_A_ACCEPT_CERTIFICATE,
+
+	__HANDSHAKE_A_ACCEPT_MAX,
+	HANDSHAKE_A_ACCEPT_MAX = (__HANDSHAKE_A_ACCEPT_MAX - 1)
+};
+
+enum {
+	HANDSHAKE_A_DONE_STATUS = 1,
+	HANDSHAKE_A_DONE_SOCKFD,
+	HANDSHAKE_A_DONE_REMOTE_AUTH,
+
+	__HANDSHAKE_A_DONE_MAX,
+	HANDSHAKE_A_DONE_MAX = (__HANDSHAKE_A_DONE_MAX - 1)
+};
+
+enum {
+	HANDSHAKE_CMD_READY = 1,
+	HANDSHAKE_CMD_ACCEPT,
+	HANDSHAKE_CMD_DONE,
+
+	__HANDSHAKE_CMD_MAX,
+	HANDSHAKE_CMD_MAX = (__HANDSHAKE_CMD_MAX - 1)
+};
+
+#define HANDSHAKE_MCGRP_NONE	"none"
+#define HANDSHAKE_MCGRP_TLSHD	"tlshd"
+
+#endif /* _UAPI_LINUX_HANDSHAKE_H */

net/Kconfig

@@ -68,6 +68,26 @@ source "net/iucv/Kconfig"
 source "net/smc/Kconfig"
 source "net/xdp/Kconfig"
 
+config NET_HANDSHAKE
+	bool
+	depends on SUNRPC || NVME_TARGET_TCP || NVME_TCP
+	default y
+
+config NET_HANDSHAKE_KUNIT_TEST
+	tristate "KUnit tests for the handshake upcall mechanism" if !KUNIT_ALL_TESTS
+	default KUNIT_ALL_TESTS
+	depends on KUNIT
+	help
+	  This builds the KUnit tests for the handshake upcall mechanism.
+
+	  KUnit tests run during boot and output the results to the debug
+	  log in TAP format (https://testanything.org/). Only useful for
+	  kernel devs running KUnit test harness and are not for inclusion
+	  into a production build.
+
+	  For more information on KUnit and unit tests in general, refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
 config INET
 	bool "TCP/IP networking"
 	help

net/Makefile

@@ -79,3 +79,4 @@ obj-$(CONFIG_NET_NCSI)		+= ncsi/
 obj-$(CONFIG_XDP_SOCKETS)	+= xdp/
 obj-$(CONFIG_MPTCP)		+= mptcp/
 obj-$(CONFIG_MCTP)		+= mctp/
+obj-$(CONFIG_NET_HANDSHAKE)	+= handshake/

net/handshake/.kunitconfig

+CONFIG_KUNIT=y
+CONFIG_UBSAN=y
+CONFIG_STACKTRACE=y
+CONFIG_NET=y
+CONFIG_NETWORK_FILESYSTEMS=y
+CONFIG_INET=y
+CONFIG_MULTIUSER=y
+CONFIG_NFS_FS=y
+CONFIG_SUNRPC=y
+CONFIG_NET_HANDSHAKE=y
+CONFIG_NET_HANDSHAKE_KUNIT_TEST=y

net/handshake/Makefile

+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the Generic HANDSHAKE service
+#
+# Author: Chuck Lever <chuck.lever@oracle.com>
+#
+# Copyright (c) 2023, Oracle and/or its affiliates.
+#
+
+obj-y += handshake.o
+handshake-y := genl.o netlink.o request.o tlshd.o trace.o
+
+obj-$(CONFIG_NET_HANDSHAKE_KUNIT_TEST) += handshake-test.o

net/handshake/genl.c

+// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/handshake.yaml */
+/* YNL-GEN kernel source */
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "genl.h"
+
+#include <linux/handshake.h>
+
+/* HANDSHAKE_CMD_ACCEPT - do */
+static const struct nla_policy handshake_accept_nl_policy[HANDSHAKE_A_ACCEPT_HANDLER_CLASS + 1] = {
+	[HANDSHAKE_A_ACCEPT_HANDLER_CLASS] = NLA_POLICY_MAX(NLA_U32, 2),
+};
+
+/* HANDSHAKE_CMD_DONE - do */
+static const struct nla_policy handshake_done_nl_policy[HANDSHAKE_A_DONE_REMOTE_AUTH + 1] = {
+	[HANDSHAKE_A_DONE_STATUS] = { .type = NLA_U32, },
+	[HANDSHAKE_A_DONE_SOCKFD] = { .type = NLA_U32, },
+	[HANDSHAKE_A_DONE_REMOTE_AUTH] = { .type = NLA_U32, },
+};
+
+/* Ops table for handshake */
+static const struct genl_split_ops handshake_nl_ops[] = {
+	{
+		.cmd		= HANDSHAKE_CMD_ACCEPT,
+		.doit		= handshake_nl_accept_doit,
+		.policy		= handshake_accept_nl_policy,
+		.maxattr	= HANDSHAKE_A_ACCEPT_HANDLER_CLASS,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= HANDSHAKE_CMD_DONE,
+		.doit		= handshake_nl_done_doit,
+		.policy		= handshake_done_nl_policy,
+		.maxattr	= HANDSHAKE_A_DONE_REMOTE_AUTH,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+};
+
+static const struct genl_multicast_group handshake_nl_mcgrps[] = {
+	[HANDSHAKE_NLGRP_NONE] = { "none", },
+	[HANDSHAKE_NLGRP_TLSHD] = { "tlshd", },
+};
+
+struct genl_family handshake_nl_family __ro_after_init = {
+	.name		= HANDSHAKE_FAMILY_NAME,
+	.version	= HANDSHAKE_FAMILY_VERSION,
+	.netnsok	= true,
+	.parallel_ops	= true,
+	.module		= THIS_MODULE,
+	.split_ops	= handshake_nl_ops,
+	.n_split_ops	= ARRAY_SIZE(handshake_nl_ops),
+	.mcgrps		= handshake_nl_mcgrps,
+	.n_mcgrps	= ARRAY_SIZE(handshake_nl_mcgrps),
+};

net/handshake/genl.h

+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/handshake.yaml */
+/* YNL-GEN kernel header */
+
+#ifndef _LINUX_HANDSHAKE_GEN_H
+#define _LINUX_HANDSHAKE_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <linux/handshake.h>
+
+int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info);
+int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info);
+
+enum {
+	HANDSHAKE_NLGRP_NONE,
+	HANDSHAKE_NLGRP_TLSHD,
+};
+
+extern struct genl_family handshake_nl_family;
+
+#endif /* _LINUX_HANDSHAKE_GEN_H */

net/handshake/handshake.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Generic netlink handshake service
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ */
+
+#ifndef _INTERNAL_HANDSHAKE_H
+#define _INTERNAL_HANDSHAKE_H
+
+/* Per-net namespace context */
+struct handshake_net {
+	spinlock_t		hn_lock;	/* protects next 3 fields */
+	int			hn_pending;
+	int			hn_pending_max;
+	struct list_head	hn_requests;
+
+	unsigned long		hn_flags;
+};
+
+enum hn_flags_bits {
+	HANDSHAKE_F_NET_DRAINING,
+};
+
+struct handshake_proto;
+
+/* One handshake request */
+struct handshake_req {
+	struct list_head		hr_list;
+	struct rhash_head		hr_rhash;
+	unsigned long			hr_flags;
+	const struct handshake_proto	*hr_proto;
+	struct sock			*hr_sk;
+	void				(*hr_odestruct)(struct sock *sk);
+
+	/* Always the last field */
+	char				hr_priv[];
+};
+
+enum hr_flags_bits {
+	HANDSHAKE_F_REQ_COMPLETED,
+};
+
+/* Invariants for all handshake requests for one transport layer
+ * security protocol
+ */
+struct handshake_proto {
+	int			hp_handler_class;
+	size_t			hp_privsize;
+	unsigned long		hp_flags;
+
+	int			(*hp_accept)(struct handshake_req *req,
+					     struct genl_info *info, int fd);
+	void			(*hp_done)(struct handshake_req *req,
+					   unsigned int status,
+					   struct genl_info *info);
+	void			(*hp_destroy)(struct handshake_req *req);
+};
+
+enum hp_flags_bits {
+	HANDSHAKE_F_PROTO_NOTIFY,
+};
+
+/* netlink.c */
+int handshake_genl_notify(struct net *net, const struct handshake_proto *proto,
+			  gfp_t flags);
+struct nlmsghdr *handshake_genl_put(struct sk_buff *msg,
+				    struct genl_info *info);
+struct handshake_net *handshake_pernet(struct net *net);
+
+/* request.c */
+struct handshake_req *handshake_req_alloc(const struct handshake_proto *proto,
+					  gfp_t flags);
+int handshake_req_hash_init(void);
+void handshake_req_hash_destroy(void);
+void *handshake_req_private(struct handshake_req *req);
+struct handshake_req *handshake_req_hash_lookup(struct sock *sk);
+struct handshake_req *handshake_req_next(struct handshake_net *hn, int class);
+int handshake_req_submit(struct socket *sock, struct handshake_req *req,
+			 gfp_t flags);
+void handshake_complete(struct handshake_req *req, unsigned int status,
+			struct genl_info *info);
+bool handshake_req_cancel(struct sock *sk);
+
+#endif /* _INTERNAL_HANDSHAKE_H */

net/handshake/netlink.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Generic netlink handshake service
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ */
+
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/mm.h>
+
+#include <net/sock.h>
+#include <net/genetlink.h>
+#include <net/netns/generic.h>
+
+#include <kunit/visibility.h>
+
+#include <uapi/linux/handshake.h>
+#include "handshake.h"
+#include "genl.h"
+
+#include <trace/events/handshake.h>
+
+/**
+ * handshake_genl_notify - Notify handlers that a request is waiting
+ * @net: target network namespace
+ * @proto: handshake protocol
+ * @flags: memory allocation control flags
+ *
+ * Returns zero on success or a negative errno if notification failed.
+ */
+int handshake_genl_notify(struct net *net, const struct handshake_proto *proto,
+			  gfp_t flags)
+{
+	struct sk_buff *msg;
+	void *hdr;
+
+	/* Disable notifications during unit testing */
+	if (!test_bit(HANDSHAKE_F_PROTO_NOTIFY, &proto->hp_flags))
+		return 0;
+
+	if (!genl_has_listeners(&handshake_nl_family, net,
+				proto->hp_handler_class))
+		return -ESRCH;
+
+	msg = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_put(msg, 0, 0, &handshake_nl_family, 0,
+			  HANDSHAKE_CMD_READY);
+	if (!hdr)
+		goto out_free;
+
+	if (nla_put_u32(msg, HANDSHAKE_A_ACCEPT_HANDLER_CLASS,
+			proto->hp_handler_class) < 0) {
+		genlmsg_cancel(msg, hdr);
+		goto out_free;
+	}
+
+	genlmsg_end(msg, hdr);
+	return genlmsg_multicast_netns(&handshake_nl_family, net, msg,
+				       0, proto->hp_handler_class, flags);
+
+out_free:
+	nlmsg_free(msg);
+	return -EMSGSIZE;
+}
+
+/**
+ * handshake_genl_put - Create a generic netlink message header
+ * @msg: buffer in which to create the header
+ * @info: generic netlink message context
+ *
+ * Returns a ready-to-use header, or NULL.
+ */
+struct nlmsghdr *handshake_genl_put(struct sk_buff *msg,
+				    struct genl_info *info)
+{
+	return genlmsg_put(msg, info->snd_portid, info->snd_seq,
+			   &handshake_nl_family, 0, info->genlhdr->cmd);
+}
+EXPORT_SYMBOL(handshake_genl_put);
+
+/*
+ * dup() a kernel socket for use as a user space file descriptor
+ * in the current process. The kernel socket must have an
+ * instatiated struct file.
+ *
+ * Implicit argument: "current()"
+ */
+static int handshake_dup(struct socket *sock)
+{
+	struct file *file;
+	int newfd;
+
+	if (!sock->file)
+		return -EBADF;
+
+	file = get_file(sock->file);
+	newfd = get_unused_fd_flags(O_CLOEXEC);
+	if (newfd < 0) {
+		fput(file);
+		return newfd;
+	}
+
+	fd_install(newfd, file);
+	return newfd;
+}
+
+int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = sock_net(skb->sk);
+	struct handshake_net *hn = handshake_pernet(net);
+	struct handshake_req *req = NULL;
+	struct socket *sock;
+	int class, fd, err;
+
+	err = -EOPNOTSUPP;
+	if (!hn)
+		goto out_status;
+
+	err = -EINVAL;
+	if (GENL_REQ_ATTR_CHECK(info, HANDSHAKE_A_ACCEPT_HANDLER_CLASS))
+		goto out_status;
+	class = nla_get_u32(info->attrs[HANDSHAKE_A_ACCEPT_HANDLER_CLASS]);
+
+	err = -EAGAIN;
+	req = handshake_req_next(hn, class);
+	if (!req)
+		goto out_status;
+
+	sock = req->hr_sk->sk_socket;
+	fd = handshake_dup(sock);
+	if (fd < 0) {
+		err = fd;
+		goto out_complete;
+	}
+	err = req->hr_proto->hp_accept(req, info, fd);
+	if (err)
+		goto out_complete;
+
+	trace_handshake_cmd_accept(net, req, req->hr_sk, fd);
+	return 0;
+
+out_complete:
+	handshake_complete(req, -EIO, NULL);
+	fput(sock->file);
+out_status:
+	trace_handshake_cmd_accept_err(net, req, NULL, err);
+	return err;
+}
+
+int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = sock_net(skb->sk);
+	struct socket *sock = NULL;
+	struct handshake_req *req;
+	int fd, status, err;
+
+	if (GENL_REQ_ATTR_CHECK(info, HANDSHAKE_A_DONE_SOCKFD))
+		return -EINVAL;
+	fd = nla_get_u32(info->attrs[HANDSHAKE_A_DONE_SOCKFD]);
+
+	err = 0;
+	sock = sockfd_lookup(fd, &err);
+	if (err) {
+		err = -EBADF;
+		goto out_status;
+	}
+
+	req = handshake_req_hash_lookup(sock->sk);
+	if (!req) {
+		err = -EBUSY;
+		fput(sock->file);
+		goto out_status;
+	}
+
+	trace_handshake_cmd_done(net, req, sock->sk, fd);
+
+	status = -EIO;
+	if (info->attrs[HANDSHAKE_A_DONE_STATUS])
+		status = nla_get_u32(info->attrs[HANDSHAKE_A_DONE_STATUS]);
+
+	handshake_complete(req, status, info);
+	fput(sock->file);
+	return 0;
+
+out_status:
+	trace_handshake_cmd_done_err(net, req, sock->sk, err);
+	return err;
+}
+
+static unsigned int handshake_net_id;
+
+static int __net_init handshake_net_init(struct net *net)
+{
+	struct handshake_net *hn = net_generic(net, handshake_net_id);
+	unsigned long tmp;
+	struct sysinfo si;
+
+	/*
+	 * Arbitrary limit to prevent handshakes that do not make
+	 * progress from clogging up the system. The cap scales up
+	 * with the amount of physical memory on the system.
+	 */
+	si_meminfo(&si);
+	tmp = si.totalram / (25 * si.mem_unit);
+	hn->hn_pending_max = clamp(tmp, 3UL, 50UL);
+
+	spin_lock_init(&hn->hn_lock);
+	hn->hn_pending = 0;
+	hn->hn_flags = 0;
+	INIT_LIST_HEAD(&hn->hn_requests);
+	return 0;
+}
+
+static void __net_exit handshake_net_exit(struct net *net)
+{
+	struct handshake_net *hn = net_generic(net, handshake_net_id);
+	struct handshake_req *req;
+	LIST_HEAD(requests);
+
+	/*
+	 * Drain the net's pending list. Requests that have been
+	 * accepted and are in progress will be destroyed when
+	 * the socket is closed.
+	 */
+	spin_lock(&hn->hn_lock);
+	set_bit(HANDSHAKE_F_NET_DRAINING, &hn->hn_flags);
+	list_splice_init(&requests, &hn->hn_requests);
+	spin_unlock(&hn->hn_lock);
+
+	while (!list_empty(&requests)) {
+		req = list_first_entry(&requests, struct handshake_req, hr_list);
+		list_del(&req->hr_list);
+
+		/*
+		 * Requests on this list have not yet been
+		 * accepted, so they do not have an fd to put.
+		 */
+
+		handshake_complete(req, -ETIMEDOUT, NULL);
+	}
+}
+
+static struct pernet_operations __net_initdata handshake_genl_net_ops = {
+	.init		= handshake_net_init,
+	.exit		= handshake_net_exit,
+	.id		= &handshake_net_id,
+	.size		= sizeof(struct handshake_net),
+};
+
+/**
+ * handshake_pernet - Get the handshake private per-net structure
+ * @net: network namespace
+ *
+ * Returns a pointer to the net's private per-net structure for the
+ * handshake module, or NULL if handshake_init() failed.
+ */
+struct handshake_net *handshake_pernet(struct net *net)
+{
+	return handshake_net_id ?
+		net_generic(net, handshake_net_id) : NULL;
+}
+EXPORT_SYMBOL_IF_KUNIT(handshake_pernet);
+
+static int __init handshake_init(void)
+{
+	int ret;
+
+	ret = handshake_req_hash_init();
+	if (ret) {
+		pr_warn("handshake: hash initialization failed (%d)\n", ret);
+		return ret;
+	}
+
+	ret = genl_register_family(&handshake_nl_family);
+	if (ret) {
+		pr_warn("handshake: netlink registration failed (%d)\n", ret);
+		handshake_req_hash_destroy();
+		return ret;
+	}
+
+	/*
+	 * ORDER: register_pernet_subsys must be done last.
+	 *
+	 *	If initialization does not make it past pernet_subsys
+	 *	registration, then handshake_net_id will remain 0. That
+	 *	shunts the handshake consumer API to return ENOTSUPP
+	 *	to prevent it from dereferencing something that hasn't
+	 *	been allocated.
+	 */
+	ret = register_pernet_subsys(&handshake_genl_net_ops);
+	if (ret) {
+		pr_warn("handshake: pernet registration failed (%d)\n", ret);
+		genl_unregister_family(&handshake_nl_family);
+		handshake_req_hash_destroy();
+	}
+
+	return ret;
+}
+
+static void __exit handshake_exit(void)
+{
+	unregister_pernet_subsys(&handshake_genl_net_ops);
+	handshake_net_id = 0;
+
+	handshake_req_hash_destroy();
+	genl_unregister_family(&handshake_nl_family);
+}
+
+module_init(handshake_init);
+module_exit(handshake_exit);

net/handshake/request.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Handshake request lifetime events
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ */
+
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/inet.h>
+#include <linux/fdtable.h>
+#include <linux/rhashtable.h>
+
+#include <net/sock.h>
+#include <net/genetlink.h>
+#include <net/netns/generic.h>
+
+#include <kunit/visibility.h>
+
+#include <uapi/linux/handshake.h>
+#include "handshake.h"
+
+#include <trace/events/handshake.h>
+
+/*
+ * We need both a handshake_req -> sock mapping, and a sock ->
+ * handshake_req mapping. Both are one-to-one.
+ *
+ * To avoid adding another pointer field to struct sock, net/handshake
+ * maintains a hash table, indexed by the memory address of @sock, to
+ * find the struct handshake_req outstanding for that socket. The
+ * reverse direction uses a simple pointer field in the handshake_req
+ * struct.
+ */
+
+static struct rhashtable handshake_rhashtbl ____cacheline_aligned_in_smp;
+
+static const struct rhashtable_params handshake_rhash_params = {
+	.key_len		= sizeof_field(struct handshake_req, hr_sk),
+	.key_offset		= offsetof(struct handshake_req, hr_sk),
+	.head_offset		= offsetof(struct handshake_req, hr_rhash),
+	.automatic_shrinking	= true,
+};
+
+int handshake_req_hash_init(void)
+{
+	return rhashtable_init(&handshake_rhashtbl, &handshake_rhash_params);
+}
+
+void handshake_req_hash_destroy(void)
+{
+	rhashtable_destroy(&handshake_rhashtbl);
+}
+
+struct handshake_req *handshake_req_hash_lookup(struct sock *sk)
+{
+	return rhashtable_lookup_fast(&handshake_rhashtbl, &sk,
+				      handshake_rhash_params);
+}
+EXPORT_SYMBOL_IF_KUNIT(handshake_req_hash_lookup);
+
+static bool handshake_req_hash_add(struct handshake_req *req)
+{
+	int ret;
+
+	ret = rhashtable_lookup_insert_fast(&handshake_rhashtbl,
+					    &req->hr_rhash,
+					    handshake_rhash_params);
+	return ret == 0;
+}
+
+static void handshake_req_destroy(struct handshake_req *req)
+{
+	if (req->hr_proto->hp_destroy)
+		req->hr_proto->hp_destroy(req);
+	rhashtable_remove_fast(&handshake_rhashtbl, &req->hr_rhash,
+			       handshake_rhash_params);
+	kfree(req);
+}
+
+static void handshake_sk_destruct(struct sock *sk)
+{
+	void (*sk_destruct)(struct sock *sk);
+	struct handshake_req *req;
+
+	req = handshake_req_hash_lookup(sk);
+	if (!req)
+		return;
+
+	trace_handshake_destruct(sock_net(sk), req, sk);
+	sk_destruct = req->hr_odestruct;
+	handshake_req_destroy(req);
+	if (sk_destruct)
+		sk_destruct(sk);
+}
+
+/**
+ * handshake_req_alloc - Allocate a handshake request
+ * @proto: security protocol
+ * @flags: memory allocation flags
+ *
+ * Returns an initialized handshake_req or NULL.
+ */
+struct handshake_req *handshake_req_alloc(const struct handshake_proto *proto,
+					  gfp_t flags)
+{
+	struct handshake_req *req;
+
+	if (!proto)
+		return NULL;
+	if (proto->hp_handler_class <= HANDSHAKE_HANDLER_CLASS_NONE)
+		return NULL;
+	if (proto->hp_handler_class >= HANDSHAKE_HANDLER_CLASS_MAX)
+		return NULL;
+	if (!proto->hp_accept || !proto->hp_done)
+		return NULL;
+
+	req = kzalloc(struct_size(req, hr_priv, proto->hp_privsize), flags);
+	if (!req)
+		return NULL;
+
+	INIT_LIST_HEAD(&req->hr_list);
+	req->hr_proto = proto;
+	return req;
+}
+EXPORT_SYMBOL(handshake_req_alloc);
+
+/**
+ * handshake_req_private - Get per-handshake private data
+ * @req: handshake arguments
+ *
+ */
+void *handshake_req_private(struct handshake_req *req)
+{
+	return (void *)&req->hr_priv;
+}
+EXPORT_SYMBOL(handshake_req_private);
+
+static bool __add_pending_locked(struct handshake_net *hn,
+				 struct handshake_req *req)
+{
+	if (WARN_ON_ONCE(!list_empty(&req->hr_list)))
+		return false;
+	hn->hn_pending++;
+	list_add_tail(&req->hr_list, &hn->hn_requests);
+	return true;
+}
+
+static void __remove_pending_locked(struct handshake_net *hn,
+				    struct handshake_req *req)
+{
+	hn->hn_pending--;
+	list_del_init(&req->hr_list);
+}
+
+/*
+ * Returns %true if the request was found on @net's pending list,
+ * otherwise %false.
+ *
+ * If @req was on a pending list, it has not yet been accepted.
+ */
+static bool remove_pending(struct handshake_net *hn, struct handshake_req *req)
+{
+	bool ret = false;
+
+	spin_lock(&hn->hn_lock);
+	if (!list_empty(&req->hr_list)) {
+		__remove_pending_locked(hn, req);
+		ret = true;
+	}
+	spin_unlock(&hn->hn_lock);
+
+	return ret;
+}
+
+struct handshake_req *handshake_req_next(struct handshake_net *hn, int class)
+{
+	struct handshake_req *req, *pos;
+
+	req = NULL;
+	spin_lock(&hn->hn_lock);
+	list_for_each_entry(pos, &hn->hn_requests, hr_list) {
+		if (pos->hr_proto->hp_handler_class != class)
+			continue;
+		__remove_pending_locked(hn, pos);
+		req = pos;
+		break;
+	}
+	spin_unlock(&hn->hn_lock);
+
+	return req;
+}
+EXPORT_SYMBOL_IF_KUNIT(handshake_req_next);
+
+/**
+ * handshake_req_submit - Submit a handshake request
+ * @sock: open socket on which to perform the handshake
+ * @req: handshake arguments
+ * @flags: memory allocation flags
+ *
+ * Return values:
+ *   %0: Request queued
+ *   %-EINVAL: Invalid argument
+ *   %-EBUSY: A handshake is already under way for this socket
+ *   %-ESRCH: No handshake agent is available
+ *   %-EAGAIN: Too many pending handshake requests
+ *   %-ENOMEM: Failed to allocate memory
+ *   %-EMSGSIZE: Failed to construct notification message
+ *   %-EOPNOTSUPP: Handshake module not initialized
+ *
+ * A zero return value from handshake_req_submit() means that
+ * exactly one subsequent completion callback is guaranteed.
+ *
+ * A negative return value from handshake_req_submit() means that
+ * no completion callback will be done and that @req has been
+ * destroyed.
+ */
+int handshake_req_submit(struct socket *sock, struct handshake_req *req,
+			 gfp_t flags)
+{
+	struct handshake_net *hn;
+	struct net *net;
+	int ret;
+
+	if (!sock || !req || !sock->file) {
+		kfree(req);
+		return -EINVAL;
+	}
+
+	req->hr_sk = sock->sk;
+	if (!req->hr_sk) {
+		kfree(req);
+		return -EINVAL;
+	}
+	req->hr_odestruct = req->hr_sk->sk_destruct;
+	req->hr_sk->sk_destruct = handshake_sk_destruct;
+
+	ret = -EOPNOTSUPP;
+	net = sock_net(req->hr_sk);
+	hn = handshake_pernet(net);
+	if (!hn)
+		goto out_err;
+
+	ret = -EAGAIN;
+	if (READ_ONCE(hn->hn_pending) >= hn->hn_pending_max)
+		goto out_err;
+
+	spin_lock(&hn->hn_lock);
+	ret = -EOPNOTSUPP;
+	if (test_bit(HANDSHAKE_F_NET_DRAINING, &hn->hn_flags))
+		goto out_unlock;
+	ret = -EBUSY;
+	if (!handshake_req_hash_add(req))
+		goto out_unlock;
+	if (!__add_pending_locked(hn, req))
+		goto out_unlock;
+	spin_unlock(&hn->hn_lock);
+
+	ret = handshake_genl_notify(net, req->hr_proto, flags);
+	if (ret) {
+		trace_handshake_notify_err(net, req, req->hr_sk, ret);
+		if (remove_pending(hn, req))
+			goto out_err;
+	}
+
+	/* Prevent socket release while a handshake request is pending */
+	sock_hold(req->hr_sk);
+
+	trace_handshake_submit(net, req, req->hr_sk);
+	return 0;
+
+out_unlock:
+	spin_unlock(&hn->hn_lock);
+out_err:
+	trace_handshake_submit_err(net, req, req->hr_sk, ret);
+	handshake_req_destroy(req);
+	return ret;
+}
+EXPORT_SYMBOL(handshake_req_submit);
+
+void handshake_complete(struct handshake_req *req, unsigned int status,
+			struct genl_info *info)
+{
+	struct sock *sk = req->hr_sk;
+	struct net *net = sock_net(sk);
+
+	if (!test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) {
+		trace_handshake_complete(net, req, sk, status);
+		req->hr_proto->hp_done(req, status, info);
+
+		/* Handshake request is no longer pending */
+		sock_put(sk);
+	}
+}
+EXPORT_SYMBOL_IF_KUNIT(handshake_complete);
+
+/**
+ * handshake_req_cancel - Cancel an in-progress handshake
+ * @sk: socket on which there is an ongoing handshake
+ *
+ * Request cancellation races with request completion. To determine
+ * who won, callers examine the return value from this function.
+ *
+ * Return values:
+ *   %true - Uncompleted handshake request was canceled
+ *   %false - Handshake request already completed or not found
+ */
+bool handshake_req_cancel(struct sock *sk)
+{
+	struct handshake_req *req;
+	struct handshake_net *hn;
+	struct net *net;
+
+	net = sock_net(sk);
+	req = handshake_req_hash_lookup(sk);
+	if (!req) {
+		trace_handshake_cancel_none(net, req, sk);
+		return false;
+	}
+
+	hn = handshake_pernet(net);
+	if (hn && remove_pending(hn, req)) {
+		/* Request hadn't been accepted */
+		goto out_true;
+	}
+	if (test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) {
+		/* Request already completed */
+		trace_handshake_cancel_busy(net, req, sk);
+		return false;
+	}
+
+out_true:
+	trace_handshake_cancel(net, req, sk);
+
+	/* Handshake request is no longer pending */
+	sock_put(sk);
+	return true;
+}
+EXPORT_SYMBOL(handshake_req_cancel);

net/handshake/trace.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Trace points for transport security layer handshakes.
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ */
+
+#include <linux/types.h>
+
+#include <net/sock.h>
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "handshake.h"
+
+#define CREATE_TRACE_POINTS
+
+#include <trace/events/handshake.h>