tcp.c

	info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto);
	info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato);
	info->tcpi_snd_mss = tp->mss_cache;
	info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss;

	info->tcpi_unacked = tp->packets_out;
	info->tcpi_sacked = tp->sacked_out;
	info->tcpi_lost = tp->lost_out;
	info->tcpi_retrans = tp->retrans_out;
	info->tcpi_fackets = tp->fackets_out;

	info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime);
	info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime);
	info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp);

	info->tcpi_pmtu = icsk->icsk_pmtu_cookie;
	info->tcpi_rcv_ssthresh = tp->rcv_ssthresh;
	info->tcpi_rtt = jiffies_to_usecs(tp->srtt)>>3;
	info->tcpi_rttvar = jiffies_to_usecs(tp->mdev)>>2;
	info->tcpi_snd_ssthresh = tp->snd_ssthresh;
	info->tcpi_snd_cwnd = tp->snd_cwnd;
	info->tcpi_advmss = tp->advmss;
	info->tcpi_reordering = tp->reordering;

	info->tcpi_rcv_rtt = jiffies_to_usecs(tp->rcv_rtt_est.rtt)>>3;
	info->tcpi_rcv_space = tp->rcvq_space.space;

	info->tcpi_total_retrans = tp->total_retrans;
}

EXPORT_SYMBOL_GPL(tcp_get_info);

static int do_tcp_getsockopt(struct sock *sk, int level,
		int optname, char __user *optval, int __user *optlen)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	int val, len;

	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;
		if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
			val = tp->rx_opt.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 = icsk->icsk_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 = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 :
			((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_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 = !icsk->icsk_ack.pingpong;
		break;

	case TCP_CONGESTION:
		if (get_user(len, optlen))
			return -EFAULT;
		len = min_t(unsigned int, len, TCP_CA_NAME_MAX);
		if (put_user(len, optlen))
			return -EFAULT;
		if (copy_to_user(optval, icsk->icsk_ca_ops->name, len))
			return -EFAULT;
		return 0;
	default:
		return -ENOPROTOOPT;
	};

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

int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
		   int __user *optlen)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	if (level != SOL_TCP)
		return icsk->icsk_af_ops->getsockopt(sk, level, optname,
						     optval, optlen);
	return do_tcp_getsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int __user *optlen)
{
	if (level != SOL_TCP)
		return inet_csk_compat_getsockopt(sk, level, optname,
						  optval, optlen);
	return do_tcp_getsockopt(sk, level, optname, optval, optlen);
}

EXPORT_SYMBOL(compat_tcp_getsockopt);
#endif

struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features)
{
	struct sk_buff *segs = ERR_PTR(-EINVAL);
	struct tcphdr *th;
	unsigned thlen;
	unsigned int seq;
	unsigned int delta;
	unsigned int oldlen;
	unsigned int len;

	if (!pskb_may_pull(skb, sizeof(*th)))
		goto out;

	th = skb->h.th;
	thlen = th->doff * 4;
	if (thlen < sizeof(*th))
		goto out;

	if (!pskb_may_pull(skb, thlen))
		goto out;

	oldlen = (u16)~skb->len;
	__skb_pull(skb, thlen);

	if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
		/* Packet is from an untrusted source, reset gso_segs. */
		int mss = skb_shinfo(skb)->gso_size;

		skb_shinfo(skb)->gso_segs = (skb->len + mss - 1) / mss;

		segs = NULL;
		goto out;
	}

	segs = skb_segment(skb, features);
	if (IS_ERR(segs))
		goto out;

	len = skb_shinfo(skb)->gso_size;
	delta = htonl(oldlen + (thlen + len));

	skb = segs;
	th = skb->h.th;
	seq = ntohl(th->seq);

	do {
		th->fin = th->psh = 0;

		th->check = ~csum_fold(th->check + delta);
		if (skb->ip_summed != CHECKSUM_HW)
			th->check = csum_fold(csum_partial(skb->h.raw, thlen,
							   skb->csum));

		seq += len;
		skb = skb->next;
		th = skb->h.th;

		th->seq = htonl(seq);
		th->cwr = 0;
	} while (skb->next);

	delta = htonl(oldlen + (skb->tail - skb->h.raw) + skb->data_len);
	th->check = ~csum_fold(th->check + delta);
	if (skb->ip_summed != CHECKSUM_HW)
		th->check = csum_fold(csum_partial(skb->h.raw, thlen,
						   skb->csum));

out:
	return segs;
}
EXPORT_SYMBOL(tcp_tso_segment);

extern void __skb_cb_too_small_for_tcp(int, int);
extern struct tcp_congestion_ops tcp_reno;

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 limit;
	int order, i, max_share;

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

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

	/* Size and allocate the main established and bind bucket
	 * hash tables.
	 *
	 * The methodology is similar to that of the buffer cache.
	 */
	tcp_hashinfo.ehash =
		alloc_large_system_hash("TCP established",
					sizeof(struct inet_ehash_bucket),
					thash_entries,
					(num_physpages >= 128 * 1024) ?
					13 : 15,
					HASH_HIGHMEM,
					&tcp_hashinfo.ehash_size,
					NULL,
					0);
	tcp_hashinfo.ehash_size = (1 << tcp_hashinfo.ehash_size) >> 1;
	for (i = 0; i < (tcp_hashinfo.ehash_size << 1); i++) {
		rwlock_init(&tcp_hashinfo.ehash[i].lock);
		INIT_HLIST_HEAD(&tcp_hashinfo.ehash[i].chain);
	}

	tcp_hashinfo.bhash =
		alloc_large_system_hash("TCP bind",
					sizeof(struct inet_bind_hashbucket),
					tcp_hashinfo.ehash_size,
					(num_physpages >= 128 * 1024) ?
					13 : 15,
					HASH_HIGHMEM,
					&tcp_hashinfo.bhash_size,
					NULL,
					64 * 1024);
	tcp_hashinfo.bhash_size = 1 << tcp_hashinfo.bhash_size;
	for (i = 0; i < tcp_hashinfo.bhash_size; i++) {
		spin_lock_init(&tcp_hashinfo.bhash[i].lock);
		INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain);
	}

	/* Try to be a bit smarter and adjust defaults depending
	 * on available memory.
	 */
	for (order = 0; ((1 << order) << PAGE_SHIFT) <
			(tcp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket));
			order++)
		;
	if (order >= 4) {
		sysctl_local_port_range[0] = 32768;
		sysctl_local_port_range[1] = 61000;
		tcp_death_row.sysctl_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);
		tcp_death_row.sysctl_max_tw_buckets >>= (3 - order);
		sysctl_tcp_max_orphans >>= (3 - order);
		sysctl_max_syn_backlog = 128;
	}

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

	limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7);
	max_share = min(4UL*1024*1024, limit);

	sysctl_tcp_wmem[0] = SK_STREAM_MEM_QUANTUM;
	sysctl_tcp_wmem[1] = 16*1024;
	sysctl_tcp_wmem[2] = max(64*1024, max_share);

	sysctl_tcp_rmem[0] = SK_STREAM_MEM_QUANTUM;
	sysctl_tcp_rmem[1] = 87380;
	sysctl_tcp_rmem[2] = max(87380, max_share);

	printk(KERN_INFO "TCP: Hash tables configured "
	       "(established %d bind %d)\n",
	       tcp_hashinfo.ehash_size << 1, tcp_hashinfo.bhash_size);

	tcp_register_congestion_control(&tcp_reno);
}

EXPORT_SYMBOL(tcp_close);
EXPORT_SYMBOL(tcp_disconnect);
EXPORT_SYMBOL(tcp_getsockopt);
EXPORT_SYMBOL(tcp_ioctl);
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);