path: root/drivers/staging/lustre/lnet/klnds/socklnd/socklnd.h

// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
 *
 * Copyright (c) 2011, 2012, Intel Corporation.
 *
 *   Author: Zach Brown <zab@zabbo.net>
 *   Author: Peter J. Braam <braam@clusterfs.com>
 *   Author: Phil Schwan <phil@clusterfs.com>
 *   Author: Eric Barton <eric@bartonsoftware.com>
 *
 *   This file is part of Lustre, http://www.lustre.org
 *
 *   Portals is free software; you can redistribute it and/or
 *   modify it under the terms of version 2 of the GNU General Public
 *   License as published by the Free Software Foundation.
 *
 *   Portals is distributed in the hope that it will be useful,
 *   but WITHOUT ANY WARRANTY; without even the implied warranty of
 *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *   GNU General Public License for more details.
 *
 */

#ifndef _SOCKLND_SOCKLND_H_
#define _SOCKLND_SOCKLND_H_

#define DEBUG_PORTAL_ALLOC
#define DEBUG_SUBSYSTEM S_LND

#include <linux/crc32.h>
#include <linux/errno.h>
#include <linux/if.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/kmod.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/syscalls.h>
#include <linux/sysctl.h>
#include <linux/uio.h>
#include <linux/unistd.h>
#include <asm/irq.h>
#include <net/sock.h>
#include <net/tcp.h>

#include <linux/libcfs/libcfs.h>
#include <linux/lnet/lib-lnet.h>
#include <linux/lnet/socklnd.h>

/* assume one thread for each connection type */
#define SOCKNAL_NSCHEDS		3
#define SOCKNAL_NSCHEDS_HIGH	(SOCKNAL_NSCHEDS << 1)

#define SOCKNAL_PEER_HASH_SIZE  101   /* # peer lists */
#define SOCKNAL_RESCHED         100   /* # scheduler loops before reschedule */
#define SOCKNAL_INSANITY_RECONN 5000  /* connd is trying on reconn infinitely */
#define SOCKNAL_ENOMEM_RETRY    CFS_TICK /* jiffies between retries */

#define SOCKNAL_SINGLE_FRAG_TX  0     /* disable multi-fragment sends */
#define SOCKNAL_SINGLE_FRAG_RX  0     /* disable multi-fragment receives */

#define SOCKNAL_VERSION_DEBUG   0     /* enable protocol version debugging */

/*
 * risk kmap deadlock on multi-frag I/O (backs off to single-frag if disabled).
 * no risk if we're not running on a CONFIG_HIGHMEM platform.
 */
#ifdef CONFIG_HIGHMEM
# define SOCKNAL_RISK_KMAP_DEADLOCK  0
#else
# define SOCKNAL_RISK_KMAP_DEADLOCK  1
#endif

struct ksock_sched_info;

struct ksock_sched {				/* per scheduler state */
	spinlock_t              kss_lock;       /* serialise */
	struct list_head        kss_rx_conns;   /* conn waiting to be read */
	struct list_head        kss_tx_conns;   /* conn waiting to be written */
	struct list_head        kss_zombie_noop_txs; /* zombie noop tx list */
	wait_queue_head_t       kss_waitq;	/* where scheduler sleeps */
	int                     kss_nconns;     /* # connections assigned to
						 * this scheduler
						 */
	struct ksock_sched_info *kss_info;	/* owner of it */
};

struct ksock_sched_info {
	int                     ksi_nthreads_max; /* max allowed threads */
	int                     ksi_nthreads;     /* number of threads */
	int                     ksi_cpt;          /* CPT id */
	struct ksock_sched	*ksi_scheds;	  /* array of schedulers */
};

#define KSOCK_CPT_SHIFT           16
#define KSOCK_THREAD_ID(cpt, sid) (((cpt) << KSOCK_CPT_SHIFT) | (sid))
#define KSOCK_THREAD_CPT(id)      ((id) >> KSOCK_CPT_SHIFT)
#define KSOCK_THREAD_SID(id)      ((id) & ((1UL << KSOCK_CPT_SHIFT) - 1))

struct ksock_interface {			/* in-use interface */
	__u32		ksni_ipaddr;		/* interface's IP address */
	__u32		ksni_netmask;		/* interface's network mask */
	int		ksni_nroutes;		/* # routes using (active) */
	int		ksni_npeers;		/* # peers using (passive) */
	char		ksni_name[IFNAMSIZ];	/* interface name */
};

struct ksock_tunables {
	int          *ksnd_timeout;            /* "stuck" socket timeout
						* (seconds)
						*/
	int          *ksnd_nscheds;            /* # scheduler threads in each
						* pool while starting
						*/
	int          *ksnd_nconnds;            /* # connection daemons */
	int          *ksnd_nconnds_max;        /* max # connection daemons */
	int          *ksnd_min_reconnectms;    /* first connection retry after
						* (ms)...
						*/
	int          *ksnd_max_reconnectms;    /* ...exponentially increasing to
						* this
						*/
	int          *ksnd_eager_ack;          /* make TCP ack eagerly? */
	int          *ksnd_typed_conns;        /* drive sockets by type? */
	int          *ksnd_min_bulk;           /* smallest "large" message */
	int          *ksnd_tx_buffer_size;     /* socket tx buffer size */
	int          *ksnd_rx_buffer_size;     /* socket rx buffer size */
	int          *ksnd_nagle;              /* enable NAGLE? */
	int          *ksnd_round_robin;        /* round robin for multiple
						* interfaces
						*/
	int          *ksnd_keepalive;          /* # secs for sending keepalive
						* NOOP
						*/
	int          *ksnd_keepalive_idle;     /* # idle secs before 1st probe
						*/
	int          *ksnd_keepalive_count;    /* # probes */
	int          *ksnd_keepalive_intvl;    /* time between probes */
	int          *ksnd_credits;            /* # concurrent sends */
	int          *ksnd_peertxcredits;      /* # concurrent sends to 1 peer
						*/
	int          *ksnd_peerrtrcredits;     /* # per-peer router buffer
						* credits
						*/
	int          *ksnd_peertimeout;        /* seconds to consider peer dead
						*/
	int          *ksnd_enable_csum;        /* enable check sum */
	int          *ksnd_inject_csum_error;  /* set non-zero to inject
						* checksum error
						*/
	int          *ksnd_nonblk_zcack;       /* always send zc-ack on
						* non-blocking connection
						*/
	unsigned int *ksnd_zc_min_payload;     /* minimum zero copy payload
						* size
						*/
	int          *ksnd_zc_recv;            /* enable ZC receive (for
						* Chelsio TOE)
						*/
	int          *ksnd_zc_recv_min_nfrags; /* minimum # of fragments to
						* enable ZC receive
						*/
};

struct ksock_net {
	__u64		  ksnn_incarnation;	/* my epoch */
	spinlock_t	  ksnn_lock;		/* serialise */
	struct list_head	  ksnn_list;		/* chain on global list */
	int		  ksnn_npeers;		/* # peers */
	int		  ksnn_shutdown;	/* shutting down? */
	int		  ksnn_ninterfaces;	/* IP interfaces */
	struct ksock_interface ksnn_interfaces[LNET_MAX_INTERFACES];
};

/** connd timeout */
#define SOCKNAL_CONND_TIMEOUT  120
/** reserved thread for accepting & creating new connd */
#define SOCKNAL_CONND_RESV     1

struct ksock_nal_data {
	int                     ksnd_init;              /* initialisation state
							 */
	int                     ksnd_nnets;             /* # networks set up */
	struct list_head        ksnd_nets;              /* list of nets */
	rwlock_t                ksnd_global_lock;       /* stabilize peer/conn
							 * ops
							 */
	struct list_head        *ksnd_peers;            /* hash table of all my
							 * known peers
							 */
	int                     ksnd_peer_hash_size;    /* size of ksnd_peers */

	int                     ksnd_nthreads;          /* # live threads */
	int                     ksnd_shuttingdown;      /* tell threads to exit
							 */
	struct ksock_sched_info **ksnd_sched_info;      /* schedulers info */

	atomic_t                ksnd_nactive_txs;       /* #active txs */

	struct list_head        ksnd_deathrow_conns;    /* conns to close:
							 * reaper_lock
							 */
	struct list_head        ksnd_zombie_conns;      /* conns to free:
							 * reaper_lock
							 */
	struct list_head        ksnd_enomem_conns;      /* conns to retry:
							 * reaper_lock
							 */
	wait_queue_head_t       ksnd_reaper_waitq;      /* reaper sleeps here */
	unsigned long	        ksnd_reaper_waketime;   /* when reaper will wake
							 */
	spinlock_t              ksnd_reaper_lock;       /* serialise */

	int                     ksnd_enomem_tx;         /* test ENOMEM sender */
	int                     ksnd_stall_tx;          /* test sluggish sender
							 */
	int                     ksnd_stall_rx;          /* test sluggish
							 * receiver
							 */
	struct list_head        ksnd_connd_connreqs;    /* incoming connection
							 * requests
							 */
	struct list_head        ksnd_connd_routes;      /* routes waiting to be
							 * connected
							 */
	wait_queue_head_t       ksnd_connd_waitq;       /* connds sleep here */
	int                     ksnd_connd_connecting;  /* # connds connecting
							 */
	time64_t                ksnd_connd_failed_stamp;/* time stamp of the
							 * last failed
							 * connecting attempt
							 */
	time64_t                ksnd_connd_starting_stamp;/* time stamp of the
							   * last starting connd
							   */
	unsigned int		ksnd_connd_starting;	/* # starting connd */
	unsigned int		ksnd_connd_running;	/* # running connd */
	spinlock_t              ksnd_connd_lock;        /* serialise */

	struct list_head        ksnd_idle_noop_txs;     /* list head for freed
							 * noop tx
							 */
	spinlock_t              ksnd_tx_lock;           /* serialise, g_lock
							 * unsafe
							 */
};

#define SOCKNAL_INIT_NOTHING 0
#define SOCKNAL_INIT_DATA    1
#define SOCKNAL_INIT_ALL     2

/*
 * A packet just assembled for transmission is represented by 1 or more
 * struct iovec fragments (the first frag contains the portals header),
 * followed by 0 or more struct bio_vec fragments.
 *
 * On the receive side, initially 1 struct iovec fragment is posted for
 * receive (the header).  Once the header has been received, the payload is
 * received into either struct iovec or struct bio_vec fragments, depending on
 * what the header matched or whether the message needs forwarding.
 */
struct ksock_conn;  /* forward ref */
struct ksock_peer;  /* forward ref */
struct ksock_route; /* forward ref */
struct ksock_proto; /* forward ref */

struct ksock_tx {			   /* transmit packet */
	struct list_head  tx_list;         /* queue on conn for transmission etc
					    */
	struct list_head  tx_zc_list;      /* queue on peer for ZC request */
	atomic_t          tx_refcount;