path: root/net/smc/af_smc.c

/*
 *  Shared Memory Communications over RDMA (SMC-R) and RoCE
 *
 *  AF_SMC protocol family socket handler keeping the AF_INET sock address type
 *  applies to SOCK_STREAM sockets only
 *  offers an alternative communication option for TCP-protocol sockets
 *  applicable with RoCE-cards only
 *
 *  Initial restrictions:
 *    - support for alternate links postponed
 *    - partial support for non-blocking sockets only
 *    - support for urgent data postponed
 *
 *  Copyright IBM Corp. 2016, 2018
 *
 *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
 *              based on prototype from Frank Blaschka
 */

#define KMSG_COMPONENT "smc"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt

#include <linux/module.h>
#include <linux/socket.h>
#include <linux/workqueue.h>
#include <linux/in.h>
#include <linux/sched/signal.h>

#include <net/sock.h>
#include <net/tcp.h>
#include <net/smc.h>

#include "smc.h"
#include "smc_clc.h"
#include "smc_llc.h"
#include "smc_cdc.h"
#include "smc_core.h"
#include "smc_ib.h"
#include "smc_pnet.h"
#include "smc_tx.h"
#include "smc_rx.h"
#include "smc_close.h"

static DEFINE_MUTEX(smc_create_lgr_pending);	/* serialize link group
						 * creation
						 */

struct smc_lgr_list smc_lgr_list = {		/* established link groups */
	.lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock),
	.list = LIST_HEAD_INIT(smc_lgr_list.list),
};

static void smc_tcp_listen_work(struct work_struct *);

static void smc_set_keepalive(struct sock *sk, int val)
{
	struct smc_sock *smc = smc_sk(sk);

	smc->clcsock->sk->sk_prot->keepalive(smc->clcsock->sk, val);
}

static struct smc_hashinfo smc_v4_hashinfo = {
	.lock = __RW_LOCK_UNLOCKED(smc_v4_hashinfo.lock),
};

static struct smc_hashinfo smc_v6_hashinfo = {
	.lock = __RW_LOCK_UNLOCKED(smc_v6_hashinfo.lock),
};

int smc_hash_sk(struct sock *sk)
{
	struct smc_hashinfo *h = sk->sk_prot->h.smc_hash;
	struct hlist_head *head;

	head = &h->ht;

	write_lock_bh(&h->lock);
	sk_add_node(sk, head);
	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
	write_unlock_bh(&h->lock);

	return 0;
}
EXPORT_SYMBOL_GPL(smc_hash_sk);

void smc_unhash_sk(struct sock *sk)
{
	struct smc_hashinfo *h = sk->sk_prot->h.smc_hash;

	write_lock_bh(&h->lock);
	if (sk_del_node_init(sk))
		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
	write_unlock_bh(&h->lock);
}
EXPORT_SYMBOL_GPL(smc_unhash_sk);

struct proto smc_proto = {
	.name		= "SMC",
	.owner		= THIS_MODULE,
	.keepalive	= smc_set_keepalive,
	.hash		= smc_hash_sk,
	.unhash		= smc_unhash_sk,
	.obj_size	= sizeof(struct smc_sock),
	.h.smc_hash	= &smc_v4_hashinfo,
	.slab_flags	= SLAB_TYPESAFE_BY_RCU,
};
EXPORT_SYMBOL_GPL(smc_proto);

struct proto smc_proto6 = {
	.name		= "SMC6",
	.owner		= THIS_MODULE,
	.keepalive	= smc_set_keepalive,
	.hash		= smc_hash_sk,
	.unhash		= smc_unhash_sk,
	.obj_size	= sizeof(struct smc_sock),
	.h.smc_hash	= &smc_v6_hashinfo,
	.slab_flags	= SLAB_TYPESAFE_BY_RCU,
};
EXPORT_SYMBOL_GPL(smc_proto6);

static int smc_release(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct smc_sock *smc;
	int rc = 0;

	if (!sk)
		goto out;

	smc = smc_sk(sk);
	if (sk->sk_state == SMC_LISTEN)
		/* smc_close_non_accepted() is called and acquires
		 * sock lock for child sockets again
		 */
		lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
	else
		lock_sock(sk);

	if (!smc->use_fallback) {
		rc = smc_close_active(smc);
		sock_set_flag(sk, SOCK_DEAD);
		sk->sk_shutdown |= SHUTDOWN_MASK;
	}
	if (smc->clcsock) {
		sock_release(smc->clcsock);
		smc->clcsock = NULL;
	}
	if (smc->use_fallback) {
		sock_put(sk); /* passive closing */
		sk->sk_state = SMC_CLOSED;
		sk->sk_state_change(sk);
	}

	/* detach socket */
	sock_orphan(sk);
	sock->sk = NULL;
	if (!smc->use_fallback && sk->sk_state == SMC_CLOSED)
		smc_conn_free(&smc->conn);
	release_sock(sk);

	sk->sk_prot->unhash(sk);
	sock_put(sk); /* final sock_put */
out:
	return rc;
}

static void smc_destruct(struct sock *sk)
{
	if (sk->sk_state != SMC_CLOSED)
		return;
	if (!sock_flag(sk, SOCK_DEAD))
		return;

	sk_refcnt_debug_dec(sk);
}

static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
				   int protocol)
{
	struct smc_sock *smc;
	struct proto *prot;
	struct sock *sk;

	prot = (protocol == SMCPROTO_SMC6) ? &smc_proto6 : &smc_proto;
	sk = sk_alloc(net, PF_SMC, GFP_KERNEL, prot, 0);
	if (!sk)
		return NULL;

	sock_init_data(sock, sk); /* sets sk_refcnt to 1 */
	sk->sk_state = SMC_INIT;
	sk->sk_destruct = smc_destruct;
	sk->sk_protocol = protocol;
	smc = smc_sk(sk);
	INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
	INIT_LIST_HEAD(&smc->accept_q);
	spin_lock_init(&smc->accept_q_lock);
	sk->sk_prot->hash(sk);
	sk_refcnt_debug_inc(sk);

	return sk;
}

static int smc_bind(struct socket *sock, struct sockaddr *uaddr,
		    int addr_len)
{
	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
	struct sock *sk = sock->sk;
	struct smc_sock *smc;
	int rc;

	smc = smc_sk(sk);

	/* replicate tests from inet_bind(), to be safe wrt. future changes */
	rc = -EINVAL;
	if (addr_len < sizeof(struct sockaddr_in))
		goto out;

	rc = -EAFNOSUPPORT;
	if (addr->sin_family != AF_INET &&
	    addr->sin_family != AF_INET6 &&
	    addr->sin_family != AF_UNSPEC)
		goto out;
	/* accept AF_UNSPEC (mapped to AF_INET) only if s_addr is INADDR_ANY */
	if (addr->sin_family == AF_UNSPEC &&
	    addr->sin_addr.s_addr != htonl(INADDR_ANY))
		goto out;

	lock_sock(sk);

	/* Check if socket is already active */
	rc = -EINVAL;
	if (sk->sk_state != SMC_INIT)
		goto out_rel;

	smc->clcsock->sk->sk_reuse = sk->sk_reuse;
	rc = kernel_bind(smc->clcsock, uaddr, addr_len);

out_rel:
	release_sock(sk);
out:
	return rc;
}

static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk,
				   unsigned long mask)
{
	/* options we don't get control via setsockopt for */
	nsk->sk_type = osk->sk_type;
	nsk->sk_sndbuf = osk->sk_sndbuf;
	nsk->sk_rcvbuf = osk->sk_rcvbuf;
	nsk->sk_sndtimeo = osk->sk_sndtimeo;
	nsk->sk_rcvtimeo = osk->sk_rcvtimeo;
	nsk->sk_mark = osk->sk_mark;
	nsk->sk_priority = osk->sk_priority;
	nsk->sk_rcvlowat = osk->sk_rcvlowat;
	nsk->sk_bound_dev_if = osk->sk_bound_dev_if;
	nsk->sk_err = osk->sk_err;

	nsk->sk_flags &= ~mask;
	nsk->sk_flags |= osk->sk_flags & mask;
}

#define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \
			     (1UL << SOCK_KEEPOPEN) | \
			     (1UL << SOCK_LINGER) | \
			     (1UL << SOCK_BROADCAST) | \
			     (1UL << SOCK_TIMESTAMP) | \
			     (1UL << SOCK_DBG) | \
			     (1UL << SOCK_RCVTSTAMP) | \
			     (1UL << SOCK_RCVTSTAMPNS) | \
			     (1UL << SOCK_LOCALROUTE) | \
			     (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \
			     (1UL << SOCK_RXQ_OVFL) | \
			     (1UL << SOCK_WIFI_STATUS) | \
			     (1UL << SOCK_NOFCS) | \
			     (1UL << SOCK_FILTER_LOCKED))
/* copy only relevant settings and flags of SOL_SOCKET level from smc to
 * clc socket (since smc is not called for these options from net/core)
 */
static void smc_copy_sock_settings_to_clc(struct smc_sock *smc)
{
	smc_copy_sock_settings(smc->clcsock->sk, &smc->sk, SK_FLAGS_SMC_TO_CLC);
}

#define SK_FLAGS_CLC_TO_SMC ((1UL << SOCK_URGINLINE) | \
			     (1UL << SOCK_KEEPOPEN) | \
			     (1UL << SOCK_LINGER) | \
			     (1UL << SOCK_DBG))
/* copy only settings and flags relevant for smc from clc to smc socket */
static void smc_copy_sock_settings_to_smc(struct smc_sock *smc)
{
	smc_copy_sock_settings(&smc->sk, smc->clcsock->sk, SK_FLAGS_CLC_TO_SMC);
}

static int smc_clnt_conf_first_link(struct smc_sock *smc)
{
	struct smc_link_group *lgr = smc->conn.lgr;
	struct smc_link *link;
	int rest;
	int rc;

	link = &lgr->lnk[SMC_SINGLE_LINK];
	/* receive CONFIRM LINK request from server over RoCE fabric */
	rest = wait_for_completion_interruptible_timeout(