tcp.c

Linux Kernel 2.6.9 for OMAP1710

			timeo = schedule_timeout(timeo);
		lock_sock(sk);
		err = 0;
		if (tp->accept_queue)
			break;
		err = -EINVAL;
		if (sk->sk_state != TCP_LISTEN)
			break;
		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			break;
		err = -EAGAIN;
		if (!timeo)
			break;
	}
	finish_wait(sk->sk_sleep, &wait);
	return err;
}

/*
 *	This will accept the next outstanding connection.
 */

struct sock *tcp_accept(struct sock *sk, int flags, int *err)
{
	struct tcp_opt *tp = tcp_sk(sk);
	struct open_request *req;
	struct sock *newsk;
	int error;

	lock_sock(sk);

	/* We need to make sure that this socket is listening,
	 * and that it has something pending.
	 */
	error = -EINVAL;
	if (sk->sk_state != TCP_LISTEN)
		goto out;

	/* Find already established connection */
	if (!tp->accept_queue) {
		long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);

		/* If this is a non blocking socket don't sleep */
		error = -EAGAIN;
		if (!timeo)
			goto out;

		error = wait_for_connect(sk, timeo);
		if (error)
			goto out;
	}

	req = tp->accept_queue;
	if ((tp->accept_queue = req->dl_next) == NULL)
		tp->accept_queue_tail = NULL;

 	newsk = req->sk;
	sk_acceptq_removed(sk);
	tcp_openreq_fastfree(req);
	BUG_TRAP(newsk->sk_state != TCP_SYN_RECV);
	release_sock(sk);
	return newsk;

out:
	release_sock(sk);
	*err = error;
	return NULL;
}

/*
 *	Socket option code for TCP.
 */
int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
		   int optlen)
{
	struct tcp_opt *tp = tcp_sk(sk);
	int val;
	int err = 0;

	if (level != SOL_TCP)
		return tp->af_specific->setsockopt(sk, level, optname,
						   optval, optlen);

	if (optlen < sizeof(int))
		return -EINVAL;

	if (get_user(val, (int __user *)optval))
		return -EFAULT;

	lock_sock(sk);

	switch (optname) {
	case TCP_MAXSEG:
		/* Values greater than interface MTU won't take effect. However
		 * at the point when this call is done we typically don't yet
		 * know which interface is going to be used */
		if (val < 8 || val > MAX_TCP_WINDOW) {
			err = -EINVAL;
			break;
		}
		tp->user_mss = val;
		break;

	case TCP_NODELAY:
		if (val) {
			/* TCP_NODELAY is weaker than TCP_CORK, so that
			 * this option on corked socket is remembered, but
			 * it is not activated until cork is cleared.
			 *
			 * However, when TCP_NODELAY is set we make
			 * an explicit push, which overrides even TCP_CORK
			 * for currently queued segments.
			 */
			tp->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH;
			tcp_push_pending_frames(sk, tp);
		} else {
			tp->nonagle &= ~TCP_NAGLE_OFF;
		}
		break;

	case TCP_CORK:
		/* When set indicates to always queue non-full frames.
		 * Later the user clears this option and we transmit
		 * any pending partial frames in the queue.  This is
		 * meant to be used alongside sendfile() to get properly
		 * filled frames when the user (for example) must write
		 * out headers with a write() call first and then use
		 * sendfile to send out the data parts.
		 *
		 * TCP_CORK can be set together with TCP_NODELAY and it is
		 * stronger than TCP_NODELAY.
		 */
		if (val) {
			tp->nonagle |= TCP_NAGLE_CORK;
		} else {
			tp->nonagle &= ~TCP_NAGLE_CORK;
			if (tp->nonagle&TCP_NAGLE_OFF)
				tp->nonagle |= TCP_NAGLE_PUSH;
			tcp_push_pending_frames(sk, tp);
		}
		break;

	case TCP_KEEPIDLE:
		if (val < 1 || val > MAX_TCP_KEEPIDLE)
			err = -EINVAL;
		else {
			tp->keepalive_time = val * HZ;
			if (sock_flag(sk, SOCK_KEEPOPEN) &&
			    !((1 << sk->sk_state) &
			      (TCPF_CLOSE | TCPF_LISTEN))) {
				__u32 elapsed = tcp_time_stamp - tp->rcv_tstamp;
				if (tp->keepalive_time > elapsed)
					elapsed = tp->keepalive_time - elapsed;
				else
					elapsed = 0;
				tcp_reset_keepalive_timer(sk, elapsed);
			}
		}
		break;
	case TCP_KEEPINTVL:
		if (val < 1 || val > MAX_TCP_KEEPINTVL)
			err = -EINVAL;
		else
			tp->keepalive_intvl = val * HZ;
		break;
	case TCP_KEEPCNT:
		if (val < 1 || val > MAX_TCP_KEEPCNT)
			err = -EINVAL;
		else
			tp->keepalive_probes = val;
		break;
	case TCP_SYNCNT:
		if (val < 1 || val > MAX_TCP_SYNCNT)
			err = -EINVAL;
		else
			tp->syn_retries = val;
		break;

	case TCP_LINGER2:
		if (val < 0)
			tp->linger2 = -1;
		else if (val > sysctl_tcp_fin_timeout / HZ)
			tp->linger2 = 0;
		else
			tp->linger2 = val * HZ;
		break;

	case TCP_DEFER_ACCEPT:
		tp->defer_accept = 0;
		if (val > 0) {
			/* Translate value in seconds to number of
			 * retransmits */
			while (tp->defer_accept < 32 &&
			       val > ((TCP_TIMEOUT_INIT / HZ) <<
				       tp->defer_accept))
				tp->defer_accept++;
			tp->defer_accept++;
		}
		break;

	case TCP_WINDOW_CLAMP:
		if (!val) {
			if (sk->sk_state != TCP_CLOSE) {
				err = -EINVAL;
				break;
			}
			tp->window_clamp = 0;
		} else
			tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
						SOCK_MIN_RCVBUF / 2 : val;
		break;

	case TCP_QUICKACK:
		if (!val) {
			tp->ack.pingpong = 1;
		} else {
			tp->ack.pingpong = 0;
			if ((1 << sk->sk_state) &
			    (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) &&
			    tcp_ack_scheduled(tp)) {
				tp->ack.pending |= TCP_ACK_PUSHED;
				cleanup_rbuf(sk, 1);
				if (!(val & 1))
					tp->ack.pingpong = 1;
			}
		}
		break;

	default:
		err = -ENOPROTOOPT;
		break;
	};
	release_sock(sk);
	return err;
}

int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
		   int __user *optlen)
{
	struct tcp_opt *tp = tcp_sk(sk);
	int val, len;

	if (level != SOL_TCP)
		return tp->af_specific->getsockopt(sk, level, optname,
						   optval, optlen);

	if (get_user(len, optlen))
		return -EFAULT;

	len = min_t(unsigned int, len, sizeof(int));

	if (len < 0)
		return -EINVAL;

	switch (optname) {
	case TCP_MAXSEG:
		val = tp->mss_cache_std;
		if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
			val = tp->user_mss;
		break;
	case TCP_NODELAY:
		val = !!(tp->nonagle&TCP_NAGLE_OFF);
		break;
	case TCP_CORK:
		val = !!(tp->nonagle&TCP_NAGLE_CORK);
		break;
	case TCP_KEEPIDLE:
		val = (tp->keepalive_time ? : sysctl_tcp_keepalive_time) / HZ;
		break;
	case TCP_KEEPINTVL:
		val = (tp->keepalive_intvl ? : sysctl_tcp_keepalive_intvl) / HZ;
		break;
	case TCP_KEEPCNT:
		val = tp->keepalive_probes ? : sysctl_tcp_keepalive_probes;
		break;
	case TCP_SYNCNT:
		val = tp->syn_retries ? : sysctl_tcp_syn_retries;
		break;
	case TCP_LINGER2:
		val = tp->linger2;
		if (val >= 0)
			val = (val ? : sysctl_tcp_fin_timeout) / HZ;
		break;
	case TCP_DEFER_ACCEPT:
		val = !tp->defer_accept ? 0 : ((TCP_TIMEOUT_INIT / HZ) <<
					       (tp->defer_accept - 1));
		break;
	case TCP_WINDOW_CLAMP:
		val = tp->window_clamp;
		break;
	case TCP_INFO: {
		struct tcp_info info;

		if (get_user(len, optlen))
			return -EFAULT;

		tcp_get_info(sk, &info);

		len = min_t(unsigned int, len, sizeof(info));
		if (put_user(len, optlen))
			return -EFAULT;
		if (copy_to_user(optval, &info, len))
			return -EFAULT;
		return 0;
	}
	case TCP_QUICKACK:
		val = !tp->ack.pingpong;
		break;
	default:
		return -ENOPROTOOPT;
	};

	if (put_user(len, optlen))
		return -EFAULT;
	if (copy_to_user(optval, &val, len))
		return -EFAULT;
	return 0;
}


extern void __skb_cb_too_small_for_tcp(int, int);
extern void tcpdiag_init(void);

static __initdata unsigned long thash_entries;
static int __init set_thash_entries(char *str)
{
	if (!str)
		return 0;
	thash_entries = simple_strtoul(str, &str, 0);
	return 1;
}
__setup("thash_entries=", set_thash_entries);

void __init tcp_init(void)
{
	struct sk_buff *skb = NULL;
	unsigned long goal;
	int order, i;

	if (sizeof(struct tcp_skb_cb) > sizeof(skb->cb))
		__skb_cb_too_small_for_tcp(sizeof(struct tcp_skb_cb),
					   sizeof(skb->cb));

	tcp_openreq_cachep = kmem_cache_create("tcp_open_request",
						   sizeof(struct open_request),
					       0, SLAB_HWCACHE_ALIGN,
					       NULL, NULL);
	if (!tcp_openreq_cachep)
		panic("tcp_init: Cannot alloc open_request cache.");

	tcp_bucket_cachep = kmem_cache_create("tcp_bind_bucket",
					      sizeof(struct tcp_bind_bucket),
					      0, SLAB_HWCACHE_ALIGN,
					      NULL, NULL);
	if (!tcp_bucket_cachep)
		panic("tcp_init: Cannot alloc tcp_bind_bucket cache.");

	tcp_timewait_cachep = kmem_cache_create("tcp_tw_bucket",
						sizeof(struct tcp_tw_bucket),
						0, SLAB_HWCACHE_ALIGN,
						NULL, NULL);
	if (!tcp_timewait_cachep)
		panic("tcp_init: Cannot alloc tcp_tw_bucket cache.");

	/* Size and allocate the main established and bind bucket
	 * hash tables.
	 *
	 * The methodology is similar to that of the buffer cache.
	 */
	if (num_physpages >= (128 * 1024))
		goal = num_physpages >> (21 - PAGE_SHIFT);
	else
		goal = num_physpages >> (23 - PAGE_SHIFT);

	if (thash_entries)
		goal = (thash_entries * sizeof(struct tcp_ehash_bucket)) >> PAGE_SHIFT;
	for (order = 0; (1UL << order) < goal; order++)
		;
	do {
		tcp_ehash_size = (1UL << order) * PAGE_SIZE /
			sizeof(struct tcp_ehash_bucket);
		tcp_ehash_size >>= 1;
		while (tcp_ehash_size & (tcp_ehash_size - 1))
			tcp_ehash_size--;
		tcp_ehash = (struct tcp_ehash_bucket *)
			__get_free_pages(GFP_ATOMIC, order);
	} while (!tcp_ehash && --order > 0);

	if (!tcp_ehash)
		panic("Failed to allocate TCP established hash table\n");
	for (i = 0; i < (tcp_ehash_size << 1); i++) {
		tcp_ehash[i].lock = RW_LOCK_UNLOCKED;
		INIT_HLIST_HEAD(&tcp_ehash[i].chain);
	}

	do {
		tcp_bhash_size = (1UL << order) * PAGE_SIZE /
			sizeof(struct tcp_bind_hashbucket);
		if ((tcp_bhash_size > (64 * 1024)) && order > 0)
			continue;
		tcp_bhash = (struct tcp_bind_hashbucket *)
			__get_free_pages(GFP_ATOMIC, order);
	} while (!tcp_bhash && --order >= 0);

	if (!tcp_bhash)
		panic("Failed to allocate TCP bind hash table\n");
	for (i = 0; i < tcp_bhash_size; i++) {
		tcp_bhash[i].lock = SPIN_LOCK_UNLOCKED;
		INIT_HLIST_HEAD(&tcp_bhash[i].chain);
	}

	/* Try to be a bit smarter and adjust defaults depending
	 * on available memory.
	 */
	if (order > 4) {
		sysctl_local_port_range[0] = 32768;
		sysctl_local_port_range[1] = 61000;
		sysctl_tcp_max_tw_buckets = 180000;
		sysctl_tcp_max_orphans = 4096 << (order - 4);
		sysctl_max_syn_backlog = 1024;
	} else if (order < 3) {
		sysctl_local_port_range[0] = 1024 * (3 - order);
		sysctl_tcp_max_tw_buckets >>= (3 - order);
		sysctl_tcp_max_orphans >>= (3 - order);
		sysctl_max_syn_backlog = 128;
	}
	tcp_port_rover = sysctl_local_port_range[0] - 1;

	sysctl_tcp_mem[0] =  768 << order;
	sysctl_tcp_mem[1] = 1024 << order;
	sysctl_tcp_mem[2] = 1536 << order;

	if (order < 3) {
		sysctl_tcp_wmem[2] = 64 * 1024;
		sysctl_tcp_rmem[0] = PAGE_SIZE;
		sysctl_tcp_rmem[1] = 43689;
		sysctl_tcp_rmem[2] = 2 * 43689;
	}

	printk(KERN_INFO "TCP: Hash tables configured "
	       "(established %d bind %d)\n",
	       tcp_ehash_size << 1, tcp_bhash_size);

	tcpdiag_init();
}

EXPORT_SYMBOL(tcp_accept);
EXPORT_SYMBOL(tcp_close);
EXPORT_SYMBOL(tcp_close_state);
EXPORT_SYMBOL(tcp_destroy_sock);
EXPORT_SYMBOL(tcp_disconnect);
EXPORT_SYMBOL(tcp_getsockopt);
EXPORT_SYMBOL(tcp_ioctl);
EXPORT_SYMBOL(tcp_openreq_cachep);
EXPORT_SYMBOL(tcp_poll);
EXPORT_SYMBOL(tcp_read_sock);
EXPORT_SYMBOL(tcp_recvmsg);
EXPORT_SYMBOL(tcp_sendmsg);
EXPORT_SYMBOL(tcp_sendpage);
EXPORT_SYMBOL(tcp_setsockopt);
EXPORT_SYMBOL(tcp_shutdown);
EXPORT_SYMBOL(tcp_statistics);
EXPORT_SYMBOL(tcp_timewait_cachep);