sock.c

linux 内核源代码

		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
		/*
		 * We double it on the way in to account for
		 * "struct sk_buff" etc. overhead.   Applications
		 * assume that the SO_RCVBUF setting they make will
		 * allow that much actual data to be received on that
		 * socket.
		 *
		 * Applications are unaware that "struct sk_buff" and
		 * other overheads allocate from the receive buffer
		 * during socket buffer allocation.
		 *
		 * And after considering the possible alternatives,
		 * returning the value we actually used in getsockopt
		 * is the most desirable behavior.
		 */
		if ((val * 2) < SOCK_MIN_RCVBUF)
			sk->sk_rcvbuf = SOCK_MIN_RCVBUF;
		else
			sk->sk_rcvbuf = val * 2;
		break;

	case SO_RCVBUFFORCE:
		if (!capable(CAP_NET_ADMIN)) {
			ret = -EPERM;
			break;
		}
		goto set_rcvbuf;

	case SO_KEEPALIVE:
#ifdef CONFIG_INET
		if (sk->sk_protocol == IPPROTO_TCP)
			tcp_set_keepalive(sk, valbool);
#endif
		sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
		break;

	case SO_OOBINLINE:
		sock_valbool_flag(sk, SOCK_URGINLINE, valbool);
		break;

	case SO_NO_CHECK:
		sk->sk_no_check = valbool;
		break;

	case SO_PRIORITY:
		if ((val >= 0 && val <= 6) || capable(CAP_NET_ADMIN))
			sk->sk_priority = val;
		else
			ret = -EPERM;
		break;

	case SO_LINGER:
		if (optlen < sizeof(ling)) {
			ret = -EINVAL;	/* 1003.1g */
			break;
		}
		if (copy_from_user(&ling,optval,sizeof(ling))) {
			ret = -EFAULT;
			break;
		}
		if (!ling.l_onoff)
			sock_reset_flag(sk, SOCK_LINGER);
		else {
#if (BITS_PER_LONG == 32)
			if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
				sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT;
			else
#endif
				sk->sk_lingertime = (unsigned int)ling.l_linger * HZ;
			sock_set_flag(sk, SOCK_LINGER);
		}
		break;

	case SO_BSDCOMPAT:
		sock_warn_obsolete_bsdism("setsockopt");
		break;

	case SO_PASSCRED:
		if (valbool)
			set_bit(SOCK_PASSCRED, &sock->flags);
		else
			clear_bit(SOCK_PASSCRED, &sock->flags);
		break;

	case SO_TIMESTAMP:
	case SO_TIMESTAMPNS:
		if (valbool)  {
			if (optname == SO_TIMESTAMP)
				sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
			else
				sock_set_flag(sk, SOCK_RCVTSTAMPNS);
			sock_set_flag(sk, SOCK_RCVTSTAMP);
			sock_enable_timestamp(sk);
		} else {
			sock_reset_flag(sk, SOCK_RCVTSTAMP);
			sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
		}
		break;

	case SO_RCVLOWAT:
		if (val < 0)
			val = INT_MAX;
		sk->sk_rcvlowat = val ? : 1;
		break;

	case SO_RCVTIMEO:
		ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen);
		break;

	case SO_SNDTIMEO:
		ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen);
		break;

	case SO_ATTACH_FILTER:
		ret = -EINVAL;
		if (optlen == sizeof(struct sock_fprog)) {
			struct sock_fprog fprog;

			ret = -EFAULT;
			if (copy_from_user(&fprog, optval, sizeof(fprog)))
				break;

			ret = sk_attach_filter(&fprog, sk);
		}
		break;

	case SO_DETACH_FILTER:
		ret = sk_detach_filter(sk);
		break;

	case SO_PASSSEC:
		if (valbool)
			set_bit(SOCK_PASSSEC, &sock->flags);
		else
			clear_bit(SOCK_PASSSEC, &sock->flags);
		break;

		/* We implement the SO_SNDLOWAT etc to
		   not be settable (1003.1g 5.3) */
	default:
		ret = -ENOPROTOOPT;
		break;
	}
	release_sock(sk);
	return ret;
}


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

	union {
		int val;
		struct linger ling;
		struct timeval tm;
	} v;

	unsigned int lv = sizeof(int);
	int len;

	if (get_user(len, optlen))
		return -EFAULT;
	if (len < 0)
		return -EINVAL;

	switch(optname) {
	case SO_DEBUG:
		v.val = sock_flag(sk, SOCK_DBG);
		break;

	case SO_DONTROUTE:
		v.val = sock_flag(sk, SOCK_LOCALROUTE);
		break;

	case SO_BROADCAST:
		v.val = !!sock_flag(sk, SOCK_BROADCAST);
		break;

	case SO_SNDBUF:
		v.val = sk->sk_sndbuf;
		break;

	case SO_RCVBUF:
		v.val = sk->sk_rcvbuf;
		break;

	case SO_REUSEADDR:
		v.val = sk->sk_reuse;
		break;

	case SO_KEEPALIVE:
		v.val = !!sock_flag(sk, SOCK_KEEPOPEN);
		break;

	case SO_TYPE:
		v.val = sk->sk_type;
		break;

	case SO_ERROR:
		v.val = -sock_error(sk);
		if (v.val==0)
			v.val = xchg(&sk->sk_err_soft, 0);
		break;

	case SO_OOBINLINE:
		v.val = !!sock_flag(sk, SOCK_URGINLINE);
		break;

	case SO_NO_CHECK:
		v.val = sk->sk_no_check;
		break;

	case SO_PRIORITY:
		v.val = sk->sk_priority;
		break;

	case SO_LINGER:
		lv		= sizeof(v.ling);
		v.ling.l_onoff	= !!sock_flag(sk, SOCK_LINGER);
		v.ling.l_linger	= sk->sk_lingertime / HZ;
		break;

	case SO_BSDCOMPAT:
		sock_warn_obsolete_bsdism("getsockopt");
		break;

	case SO_TIMESTAMP:
		v.val = sock_flag(sk, SOCK_RCVTSTAMP) &&
				!sock_flag(sk, SOCK_RCVTSTAMPNS);
		break;

	case SO_TIMESTAMPNS:
		v.val = sock_flag(sk, SOCK_RCVTSTAMPNS);
		break;

	case SO_RCVTIMEO:
		lv=sizeof(struct timeval);
		if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) {
			v.tm.tv_sec = 0;
			v.tm.tv_usec = 0;
		} else {
			v.tm.tv_sec = sk->sk_rcvtimeo / HZ;
			v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ;
		}
		break;

	case SO_SNDTIMEO:
		lv=sizeof(struct timeval);
		if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) {
			v.tm.tv_sec = 0;
			v.tm.tv_usec = 0;
		} else {
			v.tm.tv_sec = sk->sk_sndtimeo / HZ;
			v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ;
		}
		break;

	case SO_RCVLOWAT:
		v.val = sk->sk_rcvlowat;
		break;

	case SO_SNDLOWAT:
		v.val=1;
		break;

	case SO_PASSCRED:
		v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0;
		break;

	case SO_PEERCRED:
		if (len > sizeof(sk->sk_peercred))
			len = sizeof(sk->sk_peercred);
		if (copy_to_user(optval, &sk->sk_peercred, len))
			return -EFAULT;
		goto lenout;

	case SO_PEERNAME:
	{
		char address[128];

		if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2))
			return -ENOTCONN;
		if (lv < len)
			return -EINVAL;
		if (copy_to_user(optval, address, len))
			return -EFAULT;
		goto lenout;
	}

	/* Dubious BSD thing... Probably nobody even uses it, but
	 * the UNIX standard wants it for whatever reason... -DaveM
	 */
	case SO_ACCEPTCONN:
		v.val = sk->sk_state == TCP_LISTEN;
		break;

	case SO_PASSSEC:
		v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0;
		break;

	case SO_PEERSEC:
		return security_socket_getpeersec_stream(sock, optval, optlen, len);

	default:
		return -ENOPROTOOPT;
	}

	if (len > lv)
		len = lv;
	if (copy_to_user(optval, &v, len))
		return -EFAULT;
lenout:
	if (put_user(len, optlen))
		return -EFAULT;
	return 0;
}

/*
 * Initialize an sk_lock.
 *
 * (We also register the sk_lock with the lock validator.)
 */
static inline void sock_lock_init(struct sock *sk)
{
	sock_lock_init_class_and_name(sk,
			af_family_slock_key_strings[sk->sk_family],
			af_family_slock_keys + sk->sk_family,
			af_family_key_strings[sk->sk_family],
			af_family_keys + sk->sk_family);
}

static void sock_copy(struct sock *nsk, const struct sock *osk)
{
#ifdef CONFIG_SECURITY_NETWORK
	void *sptr = nsk->sk_security;
#endif

	memcpy(nsk, osk, osk->sk_prot->obj_size);
#ifdef CONFIG_SECURITY_NETWORK
	nsk->sk_security = sptr;
	security_sk_clone(osk, nsk);
#endif
}

static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
		int family)
{
	struct sock *sk;
	struct kmem_cache *slab;

	slab = prot->slab;
	if (slab != NULL)
		sk = kmem_cache_alloc(slab, priority);
	else
		sk = kmalloc(prot->obj_size, priority);

	if (sk != NULL) {
		if (security_sk_alloc(sk, family, priority))
			goto out_free;

		if (!try_module_get(prot->owner))
			goto out_free_sec;
	}

	return sk;

out_free_sec:
	security_sk_free(sk);
out_free:
	if (slab != NULL)
		kmem_cache_free(slab, sk);
	else
		kfree(sk);
	return NULL;
}

static void sk_prot_free(struct proto *prot, struct sock *sk)
{
	struct kmem_cache *slab;
	struct module *owner;

	owner = prot->owner;
	slab = prot->slab;

	security_sk_free(sk);
	if (slab != NULL)
		kmem_cache_free(slab, sk);
	else
		kfree(sk);
	module_put(owner);
}

/**
 *	sk_alloc - All socket objects are allocated here
 *	@net: the applicable net namespace
 *	@family: protocol family
 *	@priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
 *	@prot: struct proto associated with this new sock instance
 *	@zero_it: if we should zero the newly allocated sock
 */
struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
		      struct proto *prot)
{
	struct sock *sk;

	sk = sk_prot_alloc(prot, priority | __GFP_ZERO, family);
	if (sk) {
		sk->sk_family = family;
		/*
		 * See comment in struct sock definition to understand
		 * why we need sk_prot_creator -acme
		 */
		sk->sk_prot = sk->sk_prot_creator = prot;
		sock_lock_init(sk);
		sk->sk_net = get_net(net);
	}

	return sk;
}

void sk_free(struct sock *sk)
{
	struct sk_filter *filter;

	if (sk->sk_destruct)
		sk->sk_destruct(sk);

	filter = rcu_dereference(sk->sk_filter);
	if (filter) {
		sk_filter_uncharge(sk, filter);
		rcu_assign_pointer(sk->sk_filter, NULL);
	}

	sock_disable_timestamp(sk);

	if (atomic_read(&sk->sk_omem_alloc))
		printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n",
		       __FUNCTION__, atomic_read(&sk->sk_omem_alloc));

	put_net(sk->sk_net);
	sk_prot_free(sk->sk_prot_creator, sk);
}

struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
{
	struct sock *newsk;

	newsk = sk_prot_alloc(sk->sk_prot, priority, sk->sk_family);
	if (newsk != NULL) {
		struct sk_filter *filter;

		sock_copy(newsk, sk);

		/* SANITY */
		get_net(newsk->sk_net);
		sk_node_init(&newsk->sk_node);
		sock_lock_init(newsk);
		bh_lock_sock(newsk);
		newsk->sk_backlog.head	= newsk->sk_backlog.tail = NULL;

		atomic_set(&newsk->sk_rmem_alloc, 0);
		atomic_set(&newsk->sk_wmem_alloc, 0);
		atomic_set(&newsk->sk_omem_alloc, 0);
		skb_queue_head_init(&newsk->sk_receive_queue);
		skb_queue_head_init(&newsk->sk_write_queue);
#ifdef CONFIG_NET_DMA
		skb_queue_head_init(&newsk->sk_async_wait_queue);
#endif

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

		newsk->sk_dst_cache	= NULL;
		newsk->sk_wmem_queued	= 0;
		newsk->sk_forward_alloc = 0;
		newsk->sk_send_head	= NULL;
		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;

		sock_reset_flag(newsk, SOCK_DONE);
		skb_queue_head_init(&newsk->sk_error_queue);

		filter = newsk->sk_filter;
		if (filter != NULL)
			sk_filter_charge(newsk, filter);

		if (unlikely(xfrm_sk_clone_policy(newsk))) {
			/* It is still raw copy of parent, so invalidate
			 * destructor and make plain sk_free() */
			newsk->sk_destruct = NULL;
			sk_free(newsk);
			newsk = NULL;
			goto out;
		}

		newsk->sk_err	   = 0;
		newsk->sk_priority = 0;
		atomic_set(&newsk->sk_refcnt, 2);

		/*
		 * Increment the counter in the same struct proto as the master
		 * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that
		 * is the same as sk->sk_prot->socks, as this field was copied
		 * with memcpy).
		 *
		 * This _changes_ the previous behaviour, where
		 * tcp_create_openreq_child always was incrementing the
		 * equivalent to tcp_prot->socks (inet_sock_nr), so this have
		 * to be taken into account in all callers. -acme
		 */
		sk_refcnt_debug_inc(newsk);
		newsk->sk_socket = NULL;
		newsk->sk_sleep	 = NULL;

		if (newsk->sk_prot->sockets_allocated)
			atomic_inc(newsk->sk_prot->sockets_allocated);
	}
out:
	return newsk;
}