kcm: Kernel Connection Multiplexor module

This module implements the Kernel Connection Multiplexor.

Kernel Connection Multiplexor (KCM) is a facility that provides a
message based interface over TCP for generic application protocols.
With KCM an application can efficiently send and receive application
protocol messages over TCP using datagram sockets.

For more information see the included Documentation/networking/kcm.txt

Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/socket.h

@@ -200,7 +200,9 @@ struct ucred {
 #define AF_ALG		38	/* Algorithm sockets		*/
 #define AF_NFC		39	/* NFC sockets			*/
 #define AF_VSOCK	40	/* vSockets			*/
-#define AF_MAX		41	/* For now.. */
+#define AF_KCM		41	/* Kernel Connection Multiplexor*/
+
+#define AF_MAX		42	/* For now.. */
 
 /* Protocol families, same as address families. */
 #define PF_UNSPEC	AF_UNSPEC
@@ -246,6 +248,7 @@ struct ucred {
 #define PF_ALG		AF_ALG
 #define PF_NFC		AF_NFC
 #define PF_VSOCK	AF_VSOCK
+#define PF_KCM		AF_KCM
 #define PF_MAX		AF_MAX
 
 /* Maximum queue length specifiable by listen.  */
@@ -323,6 +326,7 @@ struct ucred {
 #define SOL_CAIF	278
 #define SOL_ALG		279
 #define SOL_NFC		280
+#define SOL_KCM		281
 
 /* IPX options */
 #define IPX_TYPE	1

include/net/kcm.h

@@ -0,0 +1,125 @@
+/*
+ * Kernel Connection Multiplexor
+ *
+ * Copyright (c) 2016 Tom Herbert <tom@herbertland.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef __NET_KCM_H_
+#define __NET_KCM_H_
+
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <uapi/linux/kcm.h>
+
+extern unsigned int kcm_net_id;
+
+struct kcm_tx_msg {
+	unsigned int sent;
+	unsigned int fragidx;
+	unsigned int frag_offset;
+	unsigned int msg_flags;
+	struct sk_buff *frag_skb;
+	struct sk_buff *last_skb;
+};
+
+struct kcm_rx_msg {
+	int full_len;
+	int accum_len;
+	int offset;
+};
+
+/* Socket structure for KCM client sockets */
+struct kcm_sock {
+	struct sock sk;
+	struct kcm_mux *mux;
+	struct list_head kcm_sock_list;
+	int index;
+	u32 done : 1;
+	struct work_struct done_work;
+
+	/* Transmit */
+	struct kcm_psock *tx_psock;
+	struct work_struct tx_work;
+	struct list_head wait_psock_list;
+	struct sk_buff *seq_skb;
+
+	/* Don't use bit fields here, these are set under different locks */
+	bool tx_wait;
+	bool tx_wait_more;
+
+	/* Receive */
+	struct kcm_psock *rx_psock;
+	struct list_head wait_rx_list; /* KCMs waiting for receiving */
+	bool rx_wait;
+	u32 rx_disabled : 1;
+};
+
+struct bpf_prog;
+
+/* Structure for an attached lower socket */
+struct kcm_psock {
+	struct sock *sk;
+	struct kcm_mux *mux;
+	int index;
+
+	u32 tx_stopped : 1;
+	u32 rx_stopped : 1;
+	u32 done : 1;
+	u32 unattaching : 1;
+
+	void (*save_state_change)(struct sock *sk);
+	void (*save_data_ready)(struct sock *sk);
+	void (*save_write_space)(struct sock *sk);
+
+	struct list_head psock_list;
+
+	/* Receive */
+	struct sk_buff *rx_skb_head;
+	struct sk_buff **rx_skb_nextp;
+	struct sk_buff *ready_rx_msg;
+	struct list_head psock_ready_list;
+	struct work_struct rx_work;
+	struct delayed_work rx_delayed_work;
+	struct bpf_prog *bpf_prog;
+	struct kcm_sock *rx_kcm;
+
+	/* Transmit */
+	struct kcm_sock *tx_kcm;
+	struct list_head psock_avail_list;
+};
+
+/* Per net MUX list */
+struct kcm_net {
+	struct mutex mutex;
+	struct list_head mux_list;
+	int count;
+};
+
+/* Structure for a MUX */
+struct kcm_mux {
+	struct list_head kcm_mux_list;
+	struct rcu_head rcu;
+	struct kcm_net *knet;
+
+	struct list_head kcm_socks;	/* All KCM sockets on MUX */
+	int kcm_socks_cnt;		/* Total KCM socket count for MUX */
+	struct list_head psocks;	/* List of all psocks on MUX */
+	int psocks_cnt;		/* Total attached sockets */
+
+	/* Receive */
+	spinlock_t rx_lock ____cacheline_aligned_in_smp;
+	struct list_head kcm_rx_waiters; /* KCMs waiting for receiving */
+	struct list_head psocks_ready;	/* List of psocks with a msg ready */
+	struct sk_buff_head rx_hold_queue;
+
+	/* Transmit */
+	spinlock_t  lock ____cacheline_aligned_in_smp;	/* TX and mux locking */
+	struct list_head psocks_avail;	/* List of available psocks */
+	struct list_head kcm_tx_waiters; /* KCMs waiting for a TX psock */
+};
+
+#endif /* __NET_KCM_H_ */

include/uapi/linux/kcm.h

@@ -0,0 +1,40 @@
+/*
+ * Kernel Connection Multiplexor
+ *
+ * Copyright (c) 2016 Tom Herbert <tom@herbertland.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * User API to clone KCM sockets and attach transport socket to a KCM
+ * multiplexor.
+ */
+
+#ifndef KCM_KERNEL_H
+#define KCM_KERNEL_H
+
+struct kcm_attach {
+	int fd;
+	int bpf_fd;
+};
+
+struct kcm_unattach {
+	int fd;
+};
+
+struct kcm_clone {
+	int fd;
+};
+
+#define SIOCKCMATTACH	(SIOCPROTOPRIVATE + 0)
+#define SIOCKCMUNATTACH	(SIOCPROTOPRIVATE + 1)
+#define SIOCKCMCLONE	(SIOCPROTOPRIVATE + 2)
+
+#define KCMPROTO_CONNECTED	0
+
+/* Socket options */
+#define KCM_RECV_DISABLE	1
+
+#endif
+

net/Kconfig

@@ -360,6 +360,7 @@ source "net/can/Kconfig"
 source "net/irda/Kconfig"
 source "net/bluetooth/Kconfig"
 source "net/rxrpc/Kconfig"
+source "net/kcm/Kconfig"
 
 config FIB_RULES
 	bool

net/Makefile

@@ -34,6 +34,7 @@ obj-$(CONFIG_IRDA)		+= irda/
 obj-$(CONFIG_BT)		+= bluetooth/
 obj-$(CONFIG_SUNRPC)		+= sunrpc/
 obj-$(CONFIG_AF_RXRPC)		+= rxrpc/
+obj-$(CONFIG_AF_KCM)		+= kcm/
 obj-$(CONFIG_ATM)		+= atm/
 obj-$(CONFIG_L2TP)		+= l2tp/
 obj-$(CONFIG_DECNET)		+= decnet/

net/kcm/Kconfig

@@ -0,0 +1,10 @@
+
+config AF_KCM
+	tristate "KCM sockets"
+	depends on INET
+	select BPF_SYSCALL
+	---help---
+	  KCM (Kernel Connection Multiplexor) sockets provide a method
+	  for multiplexing messages of a message based application
+	  protocol over kernel connectons (e.g. TCP connections).
+

net/kcm/Makefile

@@ -0,0 +1,3 @@
+obj-$(CONFIG_AF_KCM) += kcm.o
+
+kcm-y := kcmsock.o