[mirror_ubuntu-jammy-kernel.git] / include / net / mctp.h

/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Management Component Transport Protocol (MCTP)
 *
 * Copyright (c) 2021 Code Construct
 * Copyright (c) 2021 Google
 */

#ifndef __NET_MCTP_H
#define __NET_MCTP_H

#include <linux/bits.h>
#include <linux/mctp.h>
#include <net/net_namespace.h>
#include <net/sock.h>

/* MCTP packet definitions */
struct mctp_hdr {
	u8	ver;
	u8	dest;
	u8	src;
	u8	flags_seq_tag;
};

#define MCTP_VER_MIN	1
#define MCTP_VER_MAX	1

/* Definitions for flags_seq_tag field */
#define MCTP_HDR_FLAG_SOM	BIT(7)
#define MCTP_HDR_FLAG_EOM	BIT(6)
#define MCTP_HDR_FLAG_TO	BIT(3)
#define MCTP_HDR_FLAGS		GENMASK(5, 3)
#define MCTP_HDR_SEQ_SHIFT	4
#define MCTP_HDR_SEQ_MASK	GENMASK(1, 0)
#define MCTP_HDR_TAG_SHIFT	0
#define MCTP_HDR_TAG_MASK	GENMASK(2, 0)

#define MCTP_HEADER_MAXLEN	4

#define MCTP_INITIAL_DEFAULT_NET	1

static inline bool mctp_address_ok(mctp_eid_t eid)
{
	return eid >= 8 && eid < 255;
}

static inline struct mctp_hdr *mctp_hdr(struct sk_buff *skb)
{
	return (struct mctp_hdr *)skb_network_header(skb);
}

/* socket implementation */
struct mctp_sock {
	struct sock	sk;

	/* bind() params */
	int		bind_net;
	mctp_eid_t	bind_addr;
	__u8		bind_type;

	/* list of mctp_sk_key, for incoming tag lookup. updates protected
	 * by sk->net->keys_lock
	 */
	struct hlist_head keys;
};

/* Key for matching incoming packets to sockets or reassembly contexts.
 * Packets are matched on (src,dest,tag).
 *
 * Lifetime requirements:
 *
 *  - keys are free()ed via RCU
 *
 *  - a mctp_sk_key contains a reference to a struct sock; this is valid
 *    for the life of the key. On sock destruction (through unhash), the key is
 *    removed from lists (see below), and will not be observable after a RCU
 *    grace period.
 *
 *    any RX occurring within that grace period may still queue to the socket,
 *    but will hit the SOCK_DEAD case before the socket is freed.
 *
 * - these mctp_sk_keys appear on two lists:
 *     1) the struct mctp_sock->keys list
 *     2) the struct netns_mctp->keys list
 *
 *        updates to either list are performed under the netns_mctp->keys
 *        lock.
 *
 * - a key may have a sk_buff attached as part of an in-progress message
 *   reassembly (->reasm_head). The reassembly context is protected by
 *   reasm_lock, which may be acquired with the keys lock (above) held, if
 *   necessary. Consequently, keys lock *cannot* be acquired with the
 *   reasm_lock held.
 *
 * - there are two destruction paths for a mctp_sk_key:
 *
 *    - through socket unhash (see mctp_sk_unhash). This performs the list
 *      removal under keys_lock.
 *
 *    - where a key is established to receive a reply message: after receiving
 *      the (complete) reply, or during reassembly errors. Here, we clean up
 *      the reassembly context (marking reasm_dead, to prevent another from
 *      starting), and remove the socket from the netns & socket lists.
 */
struct mctp_sk_key {
	mctp_eid_t	peer_addr;
	mctp_eid_t	local_addr;
	__u8		tag; /* incoming tag match; invert TO for local */

	/* we hold a ref to sk when set */
	struct sock	*sk;

	/* routing lookup list */
	struct hlist_node hlist;

	/* per-socket list */
	struct hlist_node sklist;

	/* incoming fragment reassembly context */
	spinlock_t	reasm_lock;
	struct sk_buff	*reasm_head;
	struct sk_buff	**reasm_tailp;
	bool		reasm_dead;
	u8		last_seq;

	struct rcu_head	rcu;
};

struct mctp_skb_cb {
	unsigned int	magic;
	unsigned int	net;
	mctp_eid_t	src;
};

/* skb control-block accessors with a little extra debugging for initial
 * development.
 *
 * TODO: remove checks & mctp_skb_cb->magic; replace callers of __mctp_cb
 * with mctp_cb().
 *
 * __mctp_cb() is only for the initial ingress code; we should see ->magic set
 * at all times after this.
 */
static inline struct mctp_skb_cb *__mctp_cb(struct sk_buff *skb)
{
	struct mctp_skb_cb *cb = (void *)skb->cb;

	cb->magic = 0x4d435450;
	return cb;
}

static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb)
{
	struct mctp_skb_cb *cb = (void *)skb->cb;

	WARN_ON(cb->magic != 0x4d435450);
	return (void *)(skb->cb);
}

/* Route definition.
 *
 * These are held in the pernet->mctp.routes list, with RCU protection for
 * removed routes. We hold a reference to the netdev; routes need to be
 * dropped on NETDEV_UNREGISTER events.
 *
 * Updates to the route table are performed under rtnl; all reads under RCU,
 * so routes cannot be referenced over a RCU grace period. Specifically: A
 * caller cannot block between mctp_route_lookup and passing the route to
 * mctp_do_route.
 */
struct mctp_route {
	mctp_eid_t		min, max;

	struct mctp_dev		*dev;
	unsigned int		mtu;
	unsigned char		type;
	int			(*output)(struct mctp_route *route,
					  struct sk_buff *skb);

	struct list_head	list;
	refcount_t		refs;
	struct rcu_head		rcu;
};

/* route interfaces */
struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet,
				     mctp_eid_t daddr);

int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb);

int mctp_local_output(struct sock *sk, struct mctp_route *rt,
		      struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag);

/* routing <--> device interface */
unsigned int mctp_default_net(struct net *net);
int mctp_default_net_set(struct net *net, unsigned int index);
int mctp_route_add_local(struct mctp_dev *mdev, mctp_eid_t addr);
int mctp_route_remove_local(struct mctp_dev *mdev, mctp_eid_t addr);
void mctp_route_remove_dev(struct mctp_dev *mdev);

/* neighbour definitions */
enum mctp_neigh_source {
	MCTP_NEIGH_STATIC,
	MCTP_NEIGH_DISCOVER,
};

struct mctp_neigh {
	struct mctp_dev		*dev;
	mctp_eid_t		eid;
	enum mctp_neigh_source	source;

	unsigned char		ha[MAX_ADDR_LEN];

	struct list_head	list;
	struct rcu_head		rcu;
};

int mctp_neigh_init(void);
void mctp_neigh_exit(void);

// ret_hwaddr may be NULL, otherwise must have space for MAX_ADDR_LEN
int mctp_neigh_lookup(struct mctp_dev *dev, mctp_eid_t eid,
		      void *ret_hwaddr);
void mctp_neigh_remove_dev(struct mctp_dev *mdev);

int mctp_routes_init(void);
void mctp_routes_exit(void);

void mctp_device_init(void);
void mctp_device_exit(void);

#endif /* __NET_MCTP_H */
Commit	Line	Data
2c8e2e9a JK	1	/* SPDX-License-Identifier: GPL-2.0 */
	2	/*
	3	* Management Component Transport Protocol (MCTP)
	4	*
	5	* Copyright (c) 2021 Code Construct
	6	* Copyright (c) 2021 Google
	7	*/
	8
	9	#ifndef __NET_MCTP_H
	10	#define __NET_MCTP_H
	11
	12	#include <linux/bits.h>
583be982	13	#include <linux/mctp.h>
889b7da2	14	#include <net/net_namespace.h>
833ef3b9	15	#include <net/sock.h>
2c8e2e9a JK	16
	17	/* MCTP packet definitions */
	18	struct mctp_hdr {
	19	u8 ver;
	20	u8 dest;
	21	u8 src;
	22	u8 flags_seq_tag;
	23	};
	24
	25	#define MCTP_VER_MIN 1
	26	#define MCTP_VER_MAX 1
	27
	28	/* Definitions for flags_seq_tag field */
	29	#define MCTP_HDR_FLAG_SOM BIT(7)
	30	#define MCTP_HDR_FLAG_EOM BIT(6)
	31	#define MCTP_HDR_FLAG_TO BIT(3)
	32	#define MCTP_HDR_FLAGS GENMASK(5, 3)
	33	#define MCTP_HDR_SEQ_SHIFT 4
	34	#define MCTP_HDR_SEQ_MASK GENMASK(1, 0)
	35	#define MCTP_HDR_TAG_SHIFT 0
	36	#define MCTP_HDR_TAG_MASK GENMASK(2, 0)
	37
889b7da2 JK	38	#define MCTP_HEADER_MAXLEN 4
889b7da2 JK	39
03f2bbc4 MJ	40	#define MCTP_INITIAL_DEFAULT_NET 1
03f2bbc4 MJ	41
583be982 JK	42	static inline bool mctp_address_ok(mctp_eid_t eid)
	43	{
	44	return eid >= 8 && eid < 255;
	45	}
	46
	47	static inline struct mctp_hdr mctp_hdr(struct sk_buff skb)
	48	{
	49	return (struct mctp_hdr *)skb_network_header(skb);
	50	}
	51
833ef3b9 JK	52	/* socket implementation */
	53	struct mctp_sock {
	54	struct sock sk;
	55
	56	/* bind() params */
	57	int bind_net;
	58	mctp_eid_t bind_addr;
	59	__u8 bind_type;
	60
	61	/* list of mctp_sk_key, for incoming tag lookup. updates protected
	62	* by sk->net->keys_lock
	63	*/
	64	struct hlist_head keys;
	65	};
	66
	67	/* Key for matching incoming packets to sockets or reassembly contexts.
	68	* Packets are matched on (src,dest,tag).
	69	*
	70	* Lifetime requirements:
	71	*
	72	* - keys are free()ed via RCU
	73	*
	74	* - a mctp_sk_key contains a reference to a struct sock; this is valid
	75	* for the life of the key. On sock destruction (through unhash), the key is
	76	* removed from lists (see below), and will not be observable after a RCU
	77	* grace period.
	78	*
	79	* any RX occurring within that grace period may still queue to the socket,
	80	* but will hit the SOCK_DEAD case before the socket is freed.
	81	*
	82	* - these mctp_sk_keys appear on two lists:
	83	* 1) the struct mctp_sock->keys list
	84	* 2) the struct netns_mctp->keys list
	85	*
	86	* updates to either list are performed under the netns_mctp->keys
	87	* lock.
	88	*
4a992bbd JK	89	* - a key may have a sk_buff attached as part of an in-progress message
	90	* reassembly (->reasm_head). The reassembly context is protected by
	91	* reasm_lock, which may be acquired with the keys lock (above) held, if
	92	* necessary. Consequently, keys lock cannot be acquired with the
	93	* reasm_lock held.
	94	*
	95	* - there are two destruction paths for a mctp_sk_key:
	96	*
	97	* - through socket unhash (see mctp_sk_unhash). This performs the list
	98	* removal under keys_lock.
	99	*
	100	* - where a key is established to receive a reply message: after receiving
	101	* the (complete) reply, or during reassembly errors. Here, we clean up
	102	* the reassembly context (marking reasm_dead, to prevent another from
	103	* starting), and remove the socket from the netns & socket lists.
833ef3b9 JK	104	*/
	105	struct mctp_sk_key {
	106	mctp_eid_t peer_addr;
	107	mctp_eid_t local_addr;
	108	__u8 tag; /* incoming tag match; invert TO for local */
	109
	110	/* we hold a ref to sk when set */
	111	struct sock *sk;
	112
	113	/* routing lookup list */
	114	struct hlist_node hlist;
	115
	116	/* per-socket list */
	117	struct hlist_node sklist;
	118
4a992bbd JK	119	/* incoming fragment reassembly context */
	120	spinlock_t reasm_lock;
	121	struct sk_buff *reasm_head;
	122	struct sk_buff **reasm_tailp;
	123	bool reasm_dead;
	124	u8 last_seq;
	125
833ef3b9 JK	126	struct rcu_head rcu;
	127	};
	128
889b7da2 JK	129	struct mctp_skb_cb {
	130	unsigned int magic;
	131	unsigned int net;
	132	mctp_eid_t src;
	133	};
	134
	135	/* skb control-block accessors with a little extra debugging for initial
	136	* development.
	137	*
	138	* TODO: remove checks & mctp_skb_cb->magic; replace callers of __mctp_cb
	139	* with mctp_cb().
	140	*
	141	* __mctp_cb() is only for the initial ingress code; we should see ->magic set
	142	* at all times after this.
	143	*/
	144	static inline struct mctp_skb_cb __mctp_cb(struct sk_buff skb)
	145	{
	146	struct mctp_skb_cb cb = (void )skb->cb;
	147
	148	cb->magic = 0x4d435450;
	149	return cb;
	150	}
	151
	152	static inline struct mctp_skb_cb mctp_cb(struct sk_buff skb)
	153	{
	154	struct mctp_skb_cb cb = (void )skb->cb;
	155
	156	WARN_ON(cb->magic != 0x4d435450);
	157	return (void *)(skb->cb);
	158	}
	159
	160	/* Route definition.
	161	*
	162	* These are held in the pernet->mctp.routes list, with RCU protection for
	163	* removed routes. We hold a reference to the netdev; routes need to be
	164	* dropped on NETDEV_UNREGISTER events.
	165	*
	166	* Updates to the route table are performed under rtnl; all reads under RCU,
	167	* so routes cannot be referenced over a RCU grace period. Specifically: A
	168	* caller cannot block between mctp_route_lookup and passing the route to
	169	* mctp_do_route.
	170	*/
	171	struct mctp_route {
	172	mctp_eid_t min, max;
	173
	174	struct mctp_dev *dev;
	175	unsigned int mtu;
83f0a0b7	176	unsigned char type;
889b7da2 JK	177	int (output)(struct mctp_route route,
	178	struct sk_buff *skb);
	179
	180	struct list_head list;
	181	refcount_t refs;
	182	struct rcu_head rcu;
	183	};
	184
	185	/* route interfaces */
	186	struct mctp_route mctp_route_lookup(struct net net, unsigned int dnet,
	187	mctp_eid_t daddr);
	188
	189	int mctp_do_route(struct mctp_route rt, struct sk_buff skb);
	190
	191	int mctp_local_output(struct sock sk, struct mctp_route rt,
	192	struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag);
	193
	194	/* routing <--> device interface */
06d2f4c5 MJ	195	unsigned int mctp_default_net(struct net *net);
06d2f4c5 MJ	196	int mctp_default_net_set(struct net *net, unsigned int index);
889b7da2 JK	197	int mctp_route_add_local(struct mctp_dev *mdev, mctp_eid_t addr);
	198	int mctp_route_remove_local(struct mctp_dev *mdev, mctp_eid_t addr);
	199	void mctp_route_remove_dev(struct mctp_dev *mdev);
	200
4d8b9319 MJ	201	/* neighbour definitions */
	202	enum mctp_neigh_source {
	203	MCTP_NEIGH_STATIC,
	204	MCTP_NEIGH_DISCOVER,
	205	};
	206
	207	struct mctp_neigh {
	208	struct mctp_dev *dev;
	209	mctp_eid_t eid;
	210	enum mctp_neigh_source source;
	211
	212	unsigned char ha[MAX_ADDR_LEN];
	213
	214	struct list_head list;
	215	struct rcu_head rcu;
	216	};
	217
	218	int mctp_neigh_init(void);
	219	void mctp_neigh_exit(void);
	220
	221	// ret_hwaddr may be NULL, otherwise must have space for MAX_ADDR_LEN
	222	int mctp_neigh_lookup(struct mctp_dev *dev, mctp_eid_t eid,
	223	void *ret_hwaddr);
	224	void mctp_neigh_remove_dev(struct mctp_dev *mdev);
	225
889b7da2 JK	226	int mctp_routes_init(void);
	227	void mctp_routes_exit(void);
	228
583be982 JK	229	void mctp_device_init(void);
	230	void mctp_device_exit(void);
	231
2c8e2e9a	232	#endif /* __NET_MCTP_H */