tcp: ULP infrastructure

Add the infrustructure for attaching Upper Layer Protocols (ULPs) over TCP
sockets. Based on a similar infrastructure in tcp_cong.  The idea is that any
ULP can add its own logic by changing the TCP proto_ops structure to its own
methods.

Example usage:

setsockopt(sock, SOL_TCP, TCP_ULP, "tls", sizeof("tls"));

modules will call:
tcp_register_ulp(&tcp_tls_ulp_ops);

to register/unregister their ulp, with an init function and name.

A list of registered ulps will be returned by tcp_get_available_ulp, which is
hooked up to /proc.  Example:

$ cat /proc/sys/net/ipv4/tcp_available_ulp
tls

There is currently no functionality to remove or chain ULPs, but
it should be possible to add these in the future if needed.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 220 insertions, 1 deletions

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index c7a577976bec..13e4c89a8231 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -75,6 +75,8 @@ struct inet_connection_sock_af_ops {
  * @icsk_pmtu_cookie	   Last pmtu seen by socket
  * @icsk_ca_ops		   Pluggable congestion control hook
  * @icsk_af_ops		   Operations which are AF_INET{4,6} specific
+ * @icsk_ulp_ops	   Pluggable ULP control hook
+ * @icsk_ulp_data	   ULP private data
  * @icsk_ca_state:	   Congestion control state
  * @icsk_retransmits:	   Number of unrecovered [RTO] timeouts
  * @icsk_pending:	   Scheduled timer event
@@ -97,6 +99,8 @@ struct inet_connection_sock {
 	__u32			  icsk_pmtu_cookie;
 	const struct tcp_congestion_ops *icsk_ca_ops;
 	const struct inet_connection_sock_af_ops *icsk_af_ops;
+	const struct tcp_ulp_ops  *icsk_ulp_ops;
+	void			  *icsk_ulp_data;
 	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
 	__u8			  icsk_ca_state:6,
 				  icsk_ca_setsockopt:1,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3ab677d11d02..b439f46f149c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1991,4 +1991,29 @@ static inline void tcp_listendrop(const struct sock *sk)
 
 enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer);
 
+/*
+ * Interface for adding Upper Level Protocols over TCP
+ */
+
+#define TCP_ULP_NAME_MAX	16
+#define TCP_ULP_MAX		128
+#define TCP_ULP_BUF_MAX		(TCP_ULP_NAME_MAX*TCP_ULP_MAX)
+
+struct tcp_ulp_ops {
+	struct list_head	list;
+
+	/* initialize ulp */
+	int (*init)(struct sock *sk);
+	/* cleanup ulp */
+	void (*release)(struct sock *sk);
+
+	char		name[TCP_ULP_NAME_MAX];
+	struct module	*owner;
+};
+int tcp_register_ulp(struct tcp_ulp_ops *type);
+void tcp_unregister_ulp(struct tcp_ulp_ops *type);
+int tcp_set_ulp(struct sock *sk, const char *name);
+void tcp_get_available_ulp(char *buf, size_t len);
+void tcp_cleanup_ulp(struct sock *sk);
+
 #endif	/* _TCP_H */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 38a2b07afdff..8204dcebc6f3 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -117,6 +117,7 @@ enum {
 #define TCP_SAVED_SYN		28	/* Get SYN headers recorded for connection */
 #define TCP_REPAIR_WINDOW	29	/* Get/set window parameters */
 #define TCP_FASTOPEN_CONNECT	30	/* Attempt FastOpen with connect */
+#define TCP_ULP		31	/* Attach a ULP to a TCP connection */
 
 struct tcp_repair_opt {
 	__u32	opt_code;
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index f83de23a30e7..afcb435adfbe 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -8,7 +8,7 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     inet_timewait_sock.o inet_connection_sock.o \
 	     tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
 	     tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \
-	     tcp_rate.o tcp_recovery.o \
+	     tcp_rate.o tcp_recovery.o tcp_ulp.o \
 	     tcp_offload.o datagram.o raw.o udp.o udplite.o \
 	     udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
 	     fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 7065234a89a5..9bf809726066 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -360,6 +360,25 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table,
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (write && ret == 0)
 		tcp_fastopen_active_timeout_reset();
+
+	return ret;
+}
+
+static int proc_tcp_available_ulp(struct ctl_table *ctl,
+				  int write,
+				  void __user *buffer, size_t *lenp,
+				  loff_t *ppos)
+{
+	struct ctl_table tbl = { .maxlen = TCP_ULP_BUF_MAX, };
+	int ret;
+
+	tbl.data = kmalloc(tbl.maxlen, GFP_USER);
+	if (!tbl.data)
+		return -ENOMEM;
+	tcp_get_available_ulp(tbl.data, TCP_ULP_BUF_MAX);
+	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+	kfree(tbl.data);
+
 	return ret;
 }
 
@@ -686,6 +705,12 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec_ms_jiffies,
 	},
 	{
+		.procname	= "tcp_available_ulp",
+		.maxlen		= TCP_ULP_BUF_MAX,
+		.mode		= 0444,
+		.proc_handler   = proc_tcp_available_ulp,
+	},
+	{
 		.procname	= "icmp_msgs_per_sec",
 		.data		= &sysctl_icmp_msgs_per_sec,
 		.maxlen		= sizeof(int),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cc8fd8b747a4..b06ee3086a0e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2482,6 +2482,24 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		release_sock(sk);
 		return err;
 	}
+	case TCP_ULP: {
+		char name[TCP_ULP_NAME_MAX];
+
+		if (optlen < 1)
+			return -EINVAL;
+
+		val = strncpy_from_user(name, optval,
+					min_t(long, TCP_ULP_NAME_MAX - 1,
+					      optlen));
+		if (val < 0)
+			return -EFAULT;
+		name[val] = 0;
+
+		lock_sock(sk);
+		err = tcp_set_ulp(sk, name);
+		release_sock(sk);
+		return err;
+	}
 	default:
 		/* fallthru */
 		break;
@@ -3038,6 +3056,16 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			return -EFAULT;
 		return 0;
 
+	case TCP_ULP:
+		if (get_user(len, optlen))
+			return -EFAULT;
+		len = min_t(unsigned int, len, TCP_ULP_NAME_MAX);
+		if (put_user(len, optlen))
+			return -EFAULT;
+		if (copy_to_user(optval, icsk->icsk_ulp_ops->name, len))
+			return -EFAULT;
+		return 0;
+
 	case TCP_THIN_LINEAR_TIMEOUTS:
 		val = tp->thin_lto;
 		break;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1dc8c449e16a..eec2ff907279 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1860,6 +1860,8 @@ void tcp_v4_destroy_sock(struct sock *sk)
 
 	tcp_cleanup_congestion_control(sk);
 
+	tcp_cleanup_ulp(sk);
+
 	/* Cleanup up the write buffer. */
 	tcp_write_queue_purge(sk);
 
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
new file mode 100644
index 000000000000..e855ea70819b
--- /dev/null
+++ b/net/ipv4/tcp_ulp.c
@@ -0,0 +1,134 @@
+/*
+ * Pluggable TCP upper layer protocol support.
+ *
+ * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved.
+ *
+ */
+
+#include<linux/module.h>
+#include <linux/mm.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/gfp.h>
+#include <net/tcp.h>
+
+static DEFINE_SPINLOCK(tcp_ulp_list_lock);
+static LIST_HEAD(tcp_ulp_list);
+
+/* Simple linear search, don't expect many entries! */
+static struct tcp_ulp_ops *tcp_ulp_find(const char *name)
+{
+	struct tcp_ulp_ops *e;
+
+	list_for_each_entry_rcu(e, &tcp_ulp_list, list) {
+		if (strcmp(e->name, name) == 0)
+			return e;
+	}
+
+	return NULL;
+}
+
+static const struct tcp_ulp_ops *__tcp_ulp_find_autoload(const char *name)
+{
+	const struct tcp_ulp_ops *ulp = NULL;
+
+	rcu_read_lock();
+	ulp = tcp_ulp_find(name);
+
+#ifdef CONFIG_MODULES
+	if (!ulp && capable(CAP_NET_ADMIN)) {
+		rcu_read_unlock();
+		request_module("%s", name);
+		rcu_read_lock();
+		ulp = tcp_ulp_find(name);
+	}
+#endif
+	if (!ulp || !try_module_get(ulp->owner))
+		ulp = NULL;
+
+	rcu_read_unlock();
+	return ulp;
+}
+
+/* Attach new upper layer protocol to the list
+ * of available protocols.
+ */
+int tcp_register_ulp(struct tcp_ulp_ops *ulp)
+{
+	int ret = 0;
+
+	spin_lock(&tcp_ulp_list_lock);
+	if (tcp_ulp_find(ulp->name)) {
+		pr_notice("%s already registered or non-unique name\n",
+			  ulp->name);
+		ret = -EEXIST;
+	} else {
+		list_add_tail_rcu(&ulp->list, &tcp_ulp_list);
+	}
+	spin_unlock(&tcp_ulp_list_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tcp_register_ulp);
+
+void tcp_unregister_ulp(struct tcp_ulp_ops *ulp)
+{
+	spin_lock(&tcp_ulp_list_lock);
+	list_del_rcu(&ulp->list);
+	spin_unlock(&tcp_ulp_list_lock);
+
+	synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(tcp_unregister_ulp);
+
+/* Build string with list of available upper layer protocl values */
+void tcp_get_available_ulp(char *buf, size_t maxlen)
+{
+	struct tcp_ulp_ops *ulp_ops;
+	size_t offs = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ulp_ops, &tcp_ulp_list, list) {
+		offs += snprintf(buf + offs, maxlen - offs,
+				 "%s%s",
+				 offs == 0 ? "" : " ", ulp_ops->name);
+	}
+	rcu_read_unlock();
+}
+
+void tcp_cleanup_ulp(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	if (!icsk->icsk_ulp_ops)
+		return;
+
+	if (icsk->icsk_ulp_ops->release)
+		icsk->icsk_ulp_ops->release(sk);
+	module_put(icsk->icsk_ulp_ops->owner);
+}
+
+/* Change upper layer protocol for socket */
+int tcp_set_ulp(struct sock *sk, const char *name)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	const struct tcp_ulp_ops *ulp_ops;
+	int err = 0;
+
+	if (icsk->icsk_ulp_ops)
+		return -EEXIST;
+
+	ulp_ops = __tcp_ulp_find_autoload(name);
+	if (!ulp_ops)
+		err = -ENOENT;
+	else
+		err = ulp_ops->init(sk);
+
+	if (err)
+		goto out;
+
+	icsk->icsk_ulp_ops = ulp_ops;
+ out:
+	return err;
+}