path: root/net/smc/smc.h

/* SPDX-License-Identifier: GPL-2.0 */
/*
 *  Shared Memory Communications over RDMA (SMC-R) and RoCE
 *
 *  Definitions for the SMC module (socket related)
 *
 *  Copyright IBM Corp. 2016
 *
 *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
 */
#ifndef __SMC_H
#define __SMC_H

#include <linux/socket.h>
#include <linux/types.h>
#include <linux/compiler.h> /* __aligned */
#include <net/genetlink.h>
#include <net/sock.h>

#include "smc_ib.h"

#define SMC_V1		1		/* SMC version V1 */
#define SMC_V2		2		/* SMC version V2 */

#define SMC_RELEASE_0 0
#define SMC_RELEASE_1 1
#define SMC_RELEASE	SMC_RELEASE_1 /* the latest release version */

#define SMCPROTO_SMC		0	/* SMC protocol, IPv4 */
#define SMCPROTO_SMC6		1	/* SMC protocol, IPv6 */

#define SMC_AUTOCORKING_DEFAULT_SIZE	0x10000	/* 64K by default */

extern struct proto smc_proto;
extern struct proto smc_proto6;

extern struct smc_hashinfo smc_v4_hashinfo;
extern struct smc_hashinfo smc_v6_hashinfo;

int smc_hash_sk(struct sock *sk);
void smc_unhash_sk(struct sock *sk);
void smc_release_cb(struct sock *sk);

int smc_release(struct socket *sock);
int smc_bind(struct socket *sock, struct sockaddr_unsized *uaddr,
	     int addr_len);
int smc_connect(struct socket *sock, struct sockaddr_unsized *addr,
		int alen, int flags);
int smc_accept(struct socket *sock, struct socket *new_sock,
	       struct proto_accept_arg *arg);
int smc_getname(struct socket *sock, struct sockaddr *addr,
		int peer);
__poll_t smc_poll(struct file *file, struct socket *sock,
		  poll_table *wait);
int smc_ioctl(struct socket *sock, unsigned int cmd,
	      unsigned long arg);
int smc_listen(struct socket *sock, int backlog);
int smc_shutdown(struct socket *sock, int how);
int smc_setsockopt(struct socket *sock, int level, int optname,
		   sockptr_t optval, unsigned int optlen);
int smc_getsockopt(struct socket *sock, int level, int optname,
		   char __user *optval, int __user *optlen);
int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len);
int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
		int flags);
ssize_t smc_splice_read(struct socket *sock, loff_t *ppos,
			struct pipe_inode_info *pipe, size_t len,
			unsigned int flags);

/* smc sock initialization */
void smc_sk_init(struct net *net, struct sock *sk, int protocol);
/* clcsock initialization */
int smc_create_clcsk(struct net *net, struct sock *sk, int family);

#ifdef ATOMIC64_INIT
#define KERNEL_HAS_ATOMIC64
#endif

enum smc_state {		/* possible states of an SMC socket */
	SMC_ACTIVE	= 1,
	SMC_INIT	= 2,
	SMC_CLOSED	= 7,
	SMC_LISTEN	= 10,
	/* normal close */
	SMC_PEERCLOSEWAIT1	= 20,
	SMC_PEERCLOSEWAIT2	= 21,
	SMC_APPFINCLOSEWAIT	= 24,
	SMC_APPCLOSEWAIT1	= 22,
	SMC_APPCLOSEWAIT2	= 23,
	SMC_PEERFINCLOSEWAIT	= 25,
	/* abnormal close */
	SMC_PEERABORTWAIT	= 26,
	SMC_PROCESSABORT	= 27,
};

enum smc_supplemental_features {
	SMC_SPF_EMULATED_ISM_DEV	= 0,
};

#define SMC_FEATURE_MASK \
	(BIT(SMC_SPF_EMULATED_ISM_DEV))

struct smc_link_group;

struct smc_wr_rx_hdr {	/* common prefix part of LLC and CDC to demultiplex */
	union {
		u8 type;
#if defined(__BIG_ENDIAN_BITFIELD)
		struct {
			u8 llc_version:4,
			   llc_type:4;
		};
#elif defined(__LITTLE_ENDIAN_BITFIELD)
		struct {
			u8 llc_type:4,
			   llc_version:4;
		};
#endif
	};
} __aligned(1);

struct smc_cdc_conn_state_flags {
#if defined(__BIG_ENDIAN_BITFIELD)
	u8	peer_done_writing : 1;	/* Sending done indicator */
	u8	peer_conn_closed : 1;	/* Peer connection closed indicator */
	u8	peer_conn_abort : 1;	/* Abnormal close indicator */
	u8	reserved : 5;
#elif defined(__LITTLE_ENDIAN_BITFIELD)
	u8	reserved : 5;
	u8	peer_conn_abort : 1;
	u8	peer_conn_closed : 1;
	u8	peer_done_writing : 1;
#endif
};

struct smc_cdc_producer_flags {
#if defined(__BIG_ENDIAN_BITFIELD)
	u8	write_blocked : 1;	/* Writing Blocked, no rx buf space */
	u8	urg_data_pending : 1;	/* Urgent Data Pending */
	u8	urg_data_present : 1;	/* Urgent Data Present */
	u8	cons_curs_upd_req : 1;	/* cursor update requested */
	u8	failover_validation : 1;/* message replay due to failover */
	u8	reserved : 3;
#elif defined(__LITTLE_ENDIAN_BITFIELD)
	u8	reserved : 3;
	u8	failover_validation : 1;
	u8	cons_curs_upd_req : 1;
	u8	urg_data_present : 1;
	u8	urg_data_pending : 1;
	u8	write_blocked : 1;
#endif
};

/* in host byte order */
union smc_host_cursor {	/* SMC cursor - an offset in an RMBE */
	struct {
		u16	reserved;
		u16	wrap;		/* window wrap sequence number */
		u32	count;		/* cursor (= offset) part */
	};
#ifdef KERNEL_HAS_ATOMIC64
	atomic64_t		acurs;	/* for atomic processing */
#else
	u64			acurs;	/* for atomic processing */
#endif
} __aligned(8);

/* in host byte order, except for flag bitfields in network byte order */
struct smc_host_cdc_msg {		/* Connection Data Control message */
	struct smc_wr_rx_hdr		common; /* .type = 0xFE */
	u8				len;	/* length = 44 */
	u16				seqno;	/* connection seq # */
	u32				token;	/* alert_token */
	union smc_host_cursor		prod;		/* producer cursor */
	union smc_host_cursor		cons;		/* consumer cursor,
							 * piggy backed "ack"
							 */
	struct smc_cdc_producer_flags	prod_flags;	/* conn. tx/rx status */
	struct smc_cdc_conn_state_flags	conn_state_flags; /* peer conn. status*/
	u8				reserved[18];
} __aligned(8);

enum smc_urg_state {
	SMC_URG_VALID	= 1,			/* data present */
	SMC_URG_NOTYET	= 2,			/* data pending */
	SMC_URG_READ	= 3,			/* data was already read */
};

struct smc_mark_woken {
	bool woken;
	void *key;
	wait_queue_entry_t wait_entry;
};

struct smc_connection {
	struct rb_node		alert_node;
	struct smc_link_group	*lgr;		/* link group of connection */
	struct smc_link		*lnk;		/* assigned SMC-R link */
	u32			alert_token_local; /* unique conn. id */
	u8			peer_rmbe_idx;	/* from tcp handshake */
	int			peer_rmbe_size;	/* size of peer rx buffer */
	atomic_t		peer_rmbe_space;/* remaining free bytes in peer
						 * rmbe
						 */
	int			rtoken_idx;	/* idx to peer RMB rkey/addr */

	struct smc_buf_desc	*sndbuf_desc;	/* send buffer descriptor */
	struct smc_buf_desc	*rmb_desc;	/* RMBE descriptor */
	int                     rmbe_size_comp; /* compressed notation */
	int			rmbe_update_limit;
						/* lower limit for consumer
						 * cursor update
						 */

	struct smc_host_cdc_msg	local_tx_ctrl;	/* host byte order staging
						 * buffer for CDC msg send
						 * .prod cf. TCP snd_nxt
						 * .cons cf. TCP sends ack
						 */
	union smc_host_cursor	local_tx_ctrl_fin;
						/* prod crsr - confirmed by peer
						 */
	union smc_host_cursor	tx_curs_prep;	/* tx - prepared data
						 * snd_max..wmem_alloc
						 */
	union smc_host_cursor	tx_curs_sent;	/* tx - sent data
						 * snd_nxt ?
						 */
	union smc_host_cursor	tx_curs_fin;	/* tx - confirmed by peer
						 * snd-wnd-begin ?
						 */
	atomic_t		sndbuf_space;	/* remaining space in sndbuf */
	u16			tx_cdc_seq;	/* sequence # for CDC send */
	u16			tx_cdc_seq_fin;	/* sequence # - tx completed */
	spinlock_t		send_lock;	/* protect wr_sends */
	atomic_t		cdc_pend_tx_wr; /* number of pending tx CDC wqe
						 * - inc when post wqe,
						 * - dec on polled tx cqe
						 */
	wait_queue_head_t	cdc_pend_tx_wq; /* wakeup on no cdc_pend_tx_wr*/
	struct delayed_work	tx_work;	/* retry of smc_cdc_msg_send */
	u32			tx_off;		/* base offset in peer rmb */

	struct smc_host_cdc_msg	local_rx_ctrl;	/* filled during event_handl.
						 * .prod cf. TCP rcv_nxt
						 * .cons cf. TCP snd_una
						 */
	union smc_host_cursor	rx_curs_confirmed; /* confirmed to peer
						    * source of snd_una ?
						    */
	union smc_host_cursor	urg_curs;	/* points at urgent byte */
	enum smc_urg_state	urg_state;
	bool			urg_tx_pend;	/* urgent data staged */
	bool			urg_rx_skip_pend;
						/* indicate urgent oob data
						 * read, but previous regular
						 * data still pending
						 */
	char			urg_rx_byte;	/* urgent byte */
	bool			tx_in_release_sock;
						/* flush pending tx data in
						 * sock release_cb()
						 */
	atomic_t		bytes_to_rcv;	/* arrived data,
						 * not yet received
						 */
	atomic_t		splice_pending;	/* number of spliced bytes
						 * pending processing
						 */
#ifndef KERNEL_HAS_ATOMIC64
	spinlock_t		acurs_lock;	/* protect cursors */
#endif
	struct work_struct	close_work;	/* peer sent some closing */
	struct work_struct	abort_work;</