net/handshake: Create a NETLINK service for handling handshake requests

When a kernel consumer needs a transport layer security session, it
first needs a handshake to negotiate and establish a session. This
negotiation can be done in user space via one of the several
existing library implementations, or it can be done in the kernel.

No in-kernel handshake implementations yet exist. In their absence,
we add a netlink service that can:

a. Notify a user space daemon that a handshake is needed.

b. Once notified, the daemon calls the kernel back via this
   netlink service to get the handshake parameters, including an
   open socket on which to establish the session.

c. Once the handshake is complete, the daemon reports the
   session status and other information via a second netlink
   operation. This operation marks that it is safe for the
   kernel to use the open socket and the security session
   established there.

The notification service uses a multicast group. Each handshake
mechanism (eg, tlshd) adopts its own group number so that the
handshake services are completely independent of one another. The
kernel can then tell via netlink_has_listeners() whether a handshake
service is active and prepared to handle a handshake request.

A new netlink operation, ACCEPT, acts like accept(2) in that it
instantiates a file descriptor in the user space daemon's fd table.
If this operation is successful, the reply carries the fd number,
which can be treated as an open and ready file descriptor.

While user space is performing the handshake, the kernel keeps its
muddy paws off the open socket. A second new netlink operation,
DONE, indicates that the user space daemon is finished with the
socket and it is safe for the kernel to use again. The operation
also indicates whether a session was established successfully.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 312 insertions, 0 deletions

diff --git a/net/handshake/netlink.c b/net/handshake/netlink.c
new file mode 100644
index 000000000000..7264cac04047
--- /dev/null
+++ b/net/handshake/netlink.c
@@ -0,0 +1,312 @@
+// 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 <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;
+
+	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;
+}
+
+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);