sock.c

linux 内核源代码

	sk->sk_state		=	TCP_CLOSE;
	sk->sk_socket		=	sock;

	sock_set_flag(sk, SOCK_ZAPPED);

	if (sock) {
		sk->sk_type	=	sock->type;
		sk->sk_sleep	=	&sock->wait;
		sock->sk	=	sk;
	} else
		sk->sk_sleep	=	NULL;

	rwlock_init(&sk->sk_dst_lock);
	rwlock_init(&sk->sk_callback_lock);
	lockdep_set_class_and_name(&sk->sk_callback_lock,
			af_callback_keys + sk->sk_family,
			af_family_clock_key_strings[sk->sk_family]);

	sk->sk_state_change	=	sock_def_wakeup;
	sk->sk_data_ready	=	sock_def_readable;
	sk->sk_write_space	=	sock_def_write_space;
	sk->sk_error_report	=	sock_def_error_report;
	sk->sk_destruct		=	sock_def_destruct;

	sk->sk_sndmsg_page	=	NULL;
	sk->sk_sndmsg_off	=	0;

	sk->sk_peercred.pid 	=	0;
	sk->sk_peercred.uid	=	-1;
	sk->sk_peercred.gid	=	-1;
	sk->sk_write_pending	=	0;
	sk->sk_rcvlowat		=	1;
	sk->sk_rcvtimeo		=	MAX_SCHEDULE_TIMEOUT;
	sk->sk_sndtimeo		=	MAX_SCHEDULE_TIMEOUT;

	sk->sk_stamp = ktime_set(-1L, -1L);

	atomic_set(&sk->sk_refcnt, 1);
}

void fastcall lock_sock_nested(struct sock *sk, int subclass)
{
	might_sleep();
	spin_lock_bh(&sk->sk_lock.slock);
	if (sk->sk_lock.owned)
		__lock_sock(sk);
	sk->sk_lock.owned = 1;
	spin_unlock(&sk->sk_lock.slock);
	/*
	 * The sk_lock has mutex_lock() semantics here:
	 */
	mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
	local_bh_enable();
}

EXPORT_SYMBOL(lock_sock_nested);

void fastcall release_sock(struct sock *sk)
{
	/*
	 * The sk_lock has mutex_unlock() semantics:
	 */
	mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);

	spin_lock_bh(&sk->sk_lock.slock);
	if (sk->sk_backlog.tail)
		__release_sock(sk);
	sk->sk_lock.owned = 0;
	if (waitqueue_active(&sk->sk_lock.wq))
		wake_up(&sk->sk_lock.wq);
	spin_unlock_bh(&sk->sk_lock.slock);
}
EXPORT_SYMBOL(release_sock);

int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
{
	struct timeval tv;
	if (!sock_flag(sk, SOCK_TIMESTAMP))
		sock_enable_timestamp(sk);
	tv = ktime_to_timeval(sk->sk_stamp);
	if (tv.tv_sec == -1)
		return -ENOENT;
	if (tv.tv_sec == 0) {
		sk->sk_stamp = ktime_get_real();
		tv = ktime_to_timeval(sk->sk_stamp);
	}
	return copy_to_user(userstamp, &tv, sizeof(tv)) ? -EFAULT : 0;
}
EXPORT_SYMBOL(sock_get_timestamp);

int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
{
	struct timespec ts;
	if (!sock_flag(sk, SOCK_TIMESTAMP))
		sock_enable_timestamp(sk);
	ts = ktime_to_timespec(sk->sk_stamp);
	if (ts.tv_sec == -1)
		return -ENOENT;
	if (ts.tv_sec == 0) {
		sk->sk_stamp = ktime_get_real();
		ts = ktime_to_timespec(sk->sk_stamp);
	}
	return copy_to_user(userstamp, &ts, sizeof(ts)) ? -EFAULT : 0;
}
EXPORT_SYMBOL(sock_get_timestampns);

void sock_enable_timestamp(struct sock *sk)
{
	if (!sock_flag(sk, SOCK_TIMESTAMP)) {
		sock_set_flag(sk, SOCK_TIMESTAMP);
		net_enable_timestamp();
	}
}

/*
 *	Get a socket option on an socket.
 *
 *	FIX: POSIX 1003.1g is very ambiguous here. It states that
 *	asynchronous errors should be reported by getsockopt. We assume
 *	this means if you specify SO_ERROR (otherwise whats the point of it).
 */
int sock_common_getsockopt(struct socket *sock, int level, int optname,
			   char __user *optval, int __user *optlen)
{
	struct sock *sk = sock->sk;

	return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen);
}

EXPORT_SYMBOL(sock_common_getsockopt);

#ifdef CONFIG_COMPAT
int compat_sock_common_getsockopt(struct socket *sock, int level, int optname,
				  char __user *optval, int __user *optlen)
{
	struct sock *sk = sock->sk;

	if (sk->sk_prot->compat_getsockopt != NULL)
		return sk->sk_prot->compat_getsockopt(sk, level, optname,
						      optval, optlen);
	return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(compat_sock_common_getsockopt);
#endif

int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
			struct msghdr *msg, size_t size, int flags)
{
	struct sock *sk = sock->sk;
	int addr_len = 0;
	int err;

	err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT,
				   flags & ~MSG_DONTWAIT, &addr_len);
	if (err >= 0)
		msg->msg_namelen = addr_len;
	return err;
}

EXPORT_SYMBOL(sock_common_recvmsg);

/*
 *	Set socket options on an inet socket.
 */
int sock_common_setsockopt(struct socket *sock, int level, int optname,
			   char __user *optval, int optlen)
{
	struct sock *sk = sock->sk;

	return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen);
}

EXPORT_SYMBOL(sock_common_setsockopt);

#ifdef CONFIG_COMPAT
int compat_sock_common_setsockopt(struct socket *sock, int level, int optname,
				  char __user *optval, int optlen)
{
	struct sock *sk = sock->sk;

	if (sk->sk_prot->compat_setsockopt != NULL)
		return sk->sk_prot->compat_setsockopt(sk, level, optname,
						      optval, optlen);
	return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(compat_sock_common_setsockopt);
#endif

void sk_common_release(struct sock *sk)
{
	if (sk->sk_prot->destroy)
		sk->sk_prot->destroy(sk);

	/*
	 * Observation: when sock_common_release is called, processes have
	 * no access to socket. But net still has.
	 * Step one, detach it from networking:
	 *
	 * A. Remove from hash tables.
	 */

	sk->sk_prot->unhash(sk);

	/*
	 * In this point socket cannot receive new packets, but it is possible
	 * that some packets are in flight because some CPU runs receiver and
	 * did hash table lookup before we unhashed socket. They will achieve
	 * receive queue and will be purged by socket destructor.
	 *
	 * Also we still have packets pending on receive queue and probably,
	 * our own packets waiting in device queues. sock_destroy will drain
	 * receive queue, but transmitted packets will delay socket destruction
	 * until the last reference will be released.
	 */

	sock_orphan(sk);

	xfrm_sk_free_policy(sk);

	sk_refcnt_debug_release(sk);
	sock_put(sk);
}

EXPORT_SYMBOL(sk_common_release);

static DEFINE_RWLOCK(proto_list_lock);
static LIST_HEAD(proto_list);

#ifdef CONFIG_SMP
/*
 * Define default functions to keep track of inuse sockets per protocol
 * Note that often used protocols use dedicated functions to get a speed increase.
 * (see DEFINE_PROTO_INUSE/REF_PROTO_INUSE)
 */
static void inuse_add(struct proto *prot, int inc)
{
	per_cpu_ptr(prot->inuse_ptr, smp_processor_id())[0] += inc;
}

static int inuse_get(const struct proto *prot)
{
	int res = 0, cpu;
	for_each_possible_cpu(cpu)
		res += per_cpu_ptr(prot->inuse_ptr, cpu)[0];
	return res;
}

static int inuse_init(struct proto *prot)
{
	if (!prot->inuse_getval || !prot->inuse_add) {
		prot->inuse_ptr = alloc_percpu(int);
		if (prot->inuse_ptr == NULL)
			return -ENOBUFS;

		prot->inuse_getval = inuse_get;
		prot->inuse_add = inuse_add;
	}
	return 0;
}

static void inuse_fini(struct proto *prot)
{
	if (prot->inuse_ptr != NULL) {
		free_percpu(prot->inuse_ptr);
		prot->inuse_ptr = NULL;
		prot->inuse_getval = NULL;
		prot->inuse_add = NULL;
	}
}
#else
static inline int inuse_init(struct proto *prot)
{
	return 0;
}

static inline void inuse_fini(struct proto *prot)
{
}
#endif

int proto_register(struct proto *prot, int alloc_slab)
{
	char *request_sock_slab_name = NULL;
	char *timewait_sock_slab_name;

	if (inuse_init(prot))
		goto out;

	if (alloc_slab) {
		prot->slab = kmem_cache_create(prot->name, prot->obj_size, 0,
					       SLAB_HWCACHE_ALIGN, NULL);

		if (prot->slab == NULL) {
			printk(KERN_CRIT "%s: Can't create sock SLAB cache!\n",
			       prot->name);
			goto out_free_inuse;
		}

		if (prot->rsk_prot != NULL) {
			static const char mask[] = "request_sock_%s";

			request_sock_slab_name = kmalloc(strlen(prot->name) + sizeof(mask) - 1, GFP_KERNEL);
			if (request_sock_slab_name == NULL)
				goto out_free_sock_slab;

			sprintf(request_sock_slab_name, mask, prot->name);
			prot->rsk_prot->slab = kmem_cache_create(request_sock_slab_name,
								 prot->rsk_prot->obj_size, 0,
								 SLAB_HWCACHE_ALIGN, NULL);

			if (prot->rsk_prot->slab == NULL) {
				printk(KERN_CRIT "%s: Can't create request sock SLAB cache!\n",
				       prot->name);
				goto out_free_request_sock_slab_name;
			}
		}

		if (prot->twsk_prot != NULL) {
			static const char mask[] = "tw_sock_%s";

			timewait_sock_slab_name = kmalloc(strlen(prot->name) + sizeof(mask) - 1, GFP_KERNEL);

			if (timewait_sock_slab_name == NULL)
				goto out_free_request_sock_slab;

			sprintf(timewait_sock_slab_name, mask, prot->name);
			prot->twsk_prot->twsk_slab =
				kmem_cache_create(timewait_sock_slab_name,
						  prot->twsk_prot->twsk_obj_size,
						  0, SLAB_HWCACHE_ALIGN,
						  NULL);
			if (prot->twsk_prot->twsk_slab == NULL)
				goto out_free_timewait_sock_slab_name;
		}
	}

	write_lock(&proto_list_lock);
	list_add(&prot->node, &proto_list);
	write_unlock(&proto_list_lock);
	return 0;

out_free_timewait_sock_slab_name:
	kfree(timewait_sock_slab_name);
out_free_request_sock_slab:
	if (prot->rsk_prot && prot->rsk_prot->slab) {
		kmem_cache_destroy(prot->rsk_prot->slab);
		prot->rsk_prot->slab = NULL;
	}
out_free_request_sock_slab_name:
	kfree(request_sock_slab_name);
out_free_sock_slab:
	kmem_cache_destroy(prot->slab);
	prot->slab = NULL;
out_free_inuse:
	inuse_fini(prot);
out:
	return -ENOBUFS;
}

EXPORT_SYMBOL(proto_register);

void proto_unregister(struct proto *prot)
{
	write_lock(&proto_list_lock);
	list_del(&prot->node);
	write_unlock(&proto_list_lock);

	inuse_fini(prot);
	if (prot->slab != NULL) {
		kmem_cache_destroy(prot->slab);
		prot->slab = NULL;
	}

	if (prot->rsk_prot != NULL && prot->rsk_prot->slab != NULL) {
		const char *name = kmem_cache_name(prot->rsk_prot->slab);

		kmem_cache_destroy(prot->rsk_prot->slab);
		kfree(name);
		prot->rsk_prot->slab = NULL;
	}

	if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) {
		const char *name = kmem_cache_name(prot->twsk_prot->twsk_slab);

		kmem_cache_destroy(prot->twsk_prot->twsk_slab);
		kfree(name);
		prot->twsk_prot->twsk_slab = NULL;
	}
}

EXPORT_SYMBOL(proto_unregister);

#ifdef CONFIG_PROC_FS
static void *proto_seq_start(struct seq_file *seq, loff_t *pos)
{
	read_lock(&proto_list_lock);
	return seq_list_start_head(&proto_list, *pos);
}

static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	return seq_list_next(v, &proto_list, pos);
}

static void proto_seq_stop(struct seq_file *seq, void *v)
{
	read_unlock(&proto_list_lock);
}

static char proto_method_implemented(const void *method)
{
	return method == NULL ? 'n' : 'y';
}

static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
{
	seq_printf(seq, "%-9s %4u %6d  %6d   %-3s %6u   %-3s  %-10s "
			"%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
		   proto->name,
		   proto->obj_size,
		   proto->sockets_allocated != NULL ? atomic_read(proto->sockets_allocated) : -1,
		   proto->memory_allocated != NULL ? atomic_read(proto->memory_allocated) : -1,
		   proto->memory_pressure != NULL ? *proto->memory_pressure ? "yes" : "no" : "NI",
		   proto->max_header,
		   proto->slab == NULL ? "no" : "yes",
		   module_name(proto->owner),
		   proto_method_implemented(proto->close),
		   proto_method_implemented(proto->connect),
		   proto_method_implemented(proto->disconnect),
		   proto_method_implemented(proto->accept),
		   proto_method_implemented(proto->ioctl),
		   proto_method_implemented(proto->init),
		   proto_method_implemented(proto->destroy),
		   proto_method_implemented(proto->shutdown),
		   proto_method_implemented(proto->setsockopt),
		   proto_method_implemented(proto->getsockopt),
		   proto_method_implemented(proto->sendmsg),
		   proto_method_implemented(proto->recvmsg),
		   proto_method_implemented(proto->sendpage),
		   proto_method_implemented(proto->bind),
		   proto_method_implemented(proto->backlog_rcv),
		   proto_method_implemented(proto->hash),
		   proto_method_implemented(proto->unhash),
		   proto_method_implemented(proto->get_port),
		   proto_method_implemented(proto->enter_memory_pressure));
}

static int proto_seq_show(struct seq_file *seq, void *v)
{
	if (v == &proto_list)
		seq_printf(seq, "%-9s %-4s %-8s %-6s %-5s %-7s %-4s %-10s %s",
			   "protocol",
			   "size",
			   "sockets",
			   "memory",
			   "press",
			   "maxhdr",
			   "slab",
			   "module",
			   "cl co di ac io in de sh ss gs se re sp bi br ha uh gp em\n");
	else
		proto_seq_printf(seq, list_entry(v, struct proto, node));
	return 0;
}

static const struct seq_operations proto_seq_ops = {
	.start  = proto_seq_start,
	.next   = proto_seq_next,
	.stop   = proto_seq_stop,
	.show   = proto_seq_show,
};

static int proto_seq_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &proto_seq_ops);
}

static const struct file_operations proto_seq_fops = {
	.owner		= THIS_MODULE,
	.open		= proto_seq_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

static int __init proto_init(void)
{
	/* register /proc/net/protocols */
	return proc_net_fops_create(&init_net, "protocols", S_IRUGO, &proto_seq_fops) == NULL ? -ENOBUFS : 0;
}

subsys_initcall(proto_init);

#endif /* PROC_FS */

EXPORT_SYMBOL(sk_alloc);
EXPORT_SYMBOL(sk_free);
EXPORT_SYMBOL(sk_send_sigurg);
EXPORT_SYMBOL(sock_alloc_send_skb);
EXPORT_SYMBOL(sock_init_data);
EXPORT_SYMBOL(sock_kfree_s);
EXPORT_SYMBOL(sock_kmalloc);
EXPORT_SYMBOL(sock_no_accept);
EXPORT_SYMBOL(sock_no_bind);
EXPORT_SYMBOL(sock_no_connect);
EXPORT_SYMBOL(sock_no_getname);
EXPORT_SYMBOL(sock_no_getsockopt);
EXPORT_SYMBOL(sock_no_ioctl);
EXPORT_SYMBOL(sock_no_listen);
EXPORT_SYMBOL(sock_no_mmap);
EXPORT_SYMBOL(sock_no_poll);
EXPORT_SYMBOL(sock_no_recvmsg);
EXPORT_SYMBOL(sock_no_sendmsg);
EXPORT_SYMBOL(sock_no_sendpage);
EXPORT_SYMBOL(sock_no_setsockopt);
EXPORT_SYMBOL(sock_no_shutdown);
EXPORT_SYMBOL(sock_no_socketpair);
EXPORT_SYMBOL(sock_rfree);
EXPORT_SYMBOL(sock_setsockopt);
EXPORT_SYMBOL(sock_wfree);
EXPORT_SYMBOL(sock_wmalloc);
EXPORT_SYMBOL(sock_i_uid);
EXPORT_SYMBOL(sock_i_ino);
EXPORT_SYMBOL(sysctl_optmem_max);