tcp.c

linux 内核源代码

			}
		}
		break;

#ifdef CONFIG_TCP_MD5SIG
	case TCP_MD5SIG:
		/* Read the IP->Key mappings from userspace */
		err = tp->af_specific->md5_parse(sk, optval, optlen);
		break;
#endif

	default:
		err = -ENOPROTOOPT;
		break;
	}

	release_sock(sk);
	return err;
}

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

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

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

EXPORT_SYMBOL(compat_tcp_setsockopt);
#endif

/* Return information about state of tcp endpoint in API format. */
void tcp_get_info(struct sock *sk, struct tcp_info *info)
{
	struct tcp_sock *tp = tcp_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);
	u32 now = tcp_time_stamp;

	memset(info, 0, sizeof(*info));

	info->tcpi_state = sk->sk_state;
	info->tcpi_ca_state = icsk->icsk_ca_state;
	info->tcpi_retransmits = icsk->icsk_retransmits;
	info->tcpi_probes = icsk->icsk_probes_out;
	info->tcpi_backoff = icsk->icsk_backoff;

	if (tp->rx_opt.tstamp_ok)
		info->tcpi_options |= TCPI_OPT_TIMESTAMPS;
	if (tcp_is_sack(tp))
		info->tcpi_options |= TCPI_OPT_SACK;
	if (tp->rx_opt.wscale_ok) {
		info->tcpi_options |= TCPI_OPT_WSCALE;
		info->tcpi_snd_wscale = tp->rx_opt.snd_wscale;
		info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale;
	}

	if (tp->ecn_flags&TCP_ECN_OK)
		info->tcpi_options |= TCPI_OPT_ECN;

	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;

	if (sk->sk_state == TCP_LISTEN) {
		info->tcpi_unacked = sk->sk_ack_backlog;
		info->tcpi_sacked = sk->sk_max_ack_backlog;
	} else {
		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;
	__be32 delta;
	unsigned int oldlen;
	unsigned int len;

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

	th = tcp_hdr(skb);
	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 type = skb_shinfo(skb)->gso_type;
		int mss;

		if (unlikely(type &
			     ~(SKB_GSO_TCPV4 |
			       SKB_GSO_DODGY |
			       SKB_GSO_TCP_ECN |
			       SKB_GSO_TCPV6 |
			       0) ||
			     !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
			goto out;

		mss = skb_shinfo(skb)->gso_size;
		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, 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 = tcp_hdr(skb);
	seq = ntohl(th->seq);

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

		th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
				       (__force u32)delta));
		if (skb->ip_summed != CHECKSUM_PARTIAL)
			th->check =
			     csum_fold(csum_partial(skb_transport_header(skb),
						    thlen, skb->csum));

		seq += len;
		skb = skb->next;
		th = tcp_hdr(skb);

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

	delta = htonl(oldlen + (skb->tail - skb->transport_header) +
		      skb->data_len);
	th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
				(__force u32)delta));
	if (skb->ip_summed != CHECKSUM_PARTIAL)
		th->check = csum_fold(csum_partial(skb_transport_header(skb),
						   thlen, skb->csum));

out:
	return segs;
}
EXPORT_SYMBOL(tcp_tso_segment);

#ifdef CONFIG_TCP_MD5SIG
static unsigned long tcp_md5sig_users;
static struct tcp_md5sig_pool **tcp_md5sig_pool;
static DEFINE_SPINLOCK(tcp_md5sig_pool_lock);

static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool **pool)
{
	int cpu;
	for_each_possible_cpu(cpu) {
		struct tcp_md5sig_pool *p = *per_cpu_ptr(pool, cpu);
		if (p) {
			if (p->md5_desc.tfm)
				crypto_free_hash(p->md5_desc.tfm);
			kfree(p);
			p = NULL;
		}
	}
	free_percpu(pool);
}

void tcp_free_md5sig_pool(void)
{
	struct tcp_md5sig_pool **pool = NULL;

	spin_lock_bh(&tcp_md5sig_pool_lock);
	if (--tcp_md5sig_users == 0) {
		pool = tcp_md5sig_pool;
		tcp_md5sig_pool = NULL;
	}
	spin_unlock_bh(&tcp_md5sig_pool_lock);
	if (pool)
		__tcp_free_md5sig_pool(pool);
}

EXPORT_SYMBOL(tcp_free_md5sig_pool);

static struct tcp_md5sig_pool **__tcp_alloc_md5sig_pool(void)
{
	int cpu;
	struct tcp_md5sig_pool **pool;

	pool = alloc_percpu(struct tcp_md5sig_pool *);
	if (!pool)
		return NULL;

	for_each_possible_cpu(cpu) {
		struct tcp_md5sig_pool *p;
		struct crypto_hash *hash;

		p = kzalloc(sizeof(*p), GFP_KERNEL);
		if (!p)
			goto out_free;
		*per_cpu_ptr(pool, cpu) = p;

		hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
		if (!hash || IS_ERR(hash))
			goto out_free;

		p->md5_desc.tfm = hash;
	}
	return pool;
out_free:
	__tcp_free_md5sig_pool(pool);
	return NULL;
}

struct tcp_md5sig_pool **tcp_alloc_md5sig_pool(void)
{
	struct tcp_md5sig_pool **pool;
	int alloc = 0;

retry:
	spin_lock_bh(&tcp_md5sig_pool_lock);
	pool = tcp_md5sig_pool;
	if (tcp_md5sig_users++ == 0) {
		alloc = 1;
		spin_unlock_bh(&tcp_md5sig_pool_lock);
	} else if (!pool) {
		tcp_md5sig_users--;
		spin_unlock_bh(&tcp_md5sig_pool_lock);
		cpu_relax();
		goto retry;
	} else
		spin_unlock_bh(&tcp_md5sig_pool_lock);

	if (alloc) {
		/* we cannot hold spinlock here because this may sleep. */
		struct tcp_md5sig_pool **p = __tcp_alloc_md5sig_pool();
		spin_lock_bh(&tcp_md5sig_pool_lock);
		if (!p) {
			tcp_md5sig_users--;
			spin_unlock_bh(&tcp_md5sig_pool_lock);
			return NULL;
		}
		pool = tcp_md5sig_pool;
		if (pool) {
			/* oops, it has already been assigned. */
			spin_unlock_bh(&tcp_md5sig_pool_lock);
			__tcp_free_md5sig_pool(p);
		} else {
			tcp_md5sig_pool = pool = p;
			spin_unlock_bh(&tcp_md5sig_pool_lock);
		}
	}
	return pool;
}

EXPORT_SYMBOL(tcp_alloc_md5sig_pool);

struct tcp_md5sig_pool *__tcp_get_md5sig_pool(int cpu)
{
	struct tcp_md5sig_pool **p;
	spin_lock_bh(&tcp_md5sig_pool_lock);
	p = tcp_md5sig_pool;
	if (p)
		tcp_md5sig_users++;
	spin_unlock_bh(&tcp_md5sig_pool_lock);
	return (p ? *per_cpu_ptr(p, cpu) : NULL);
}

EXPORT_SYMBOL(__tcp_get_md5sig_pool);

void __tcp_put_md5sig_pool(void)
{
	tcp_free_md5sig_pool();
}

EXPORT_SYMBOL(__tcp_put_md5sig_pool);
#endif

void tcp_done(struct sock *sk)
{
	if(sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
		TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS);

	tcp_set_state(sk, TCP_CLOSE);
	tcp_clear_xmit_timers(sk);

	sk->sk_shutdown = SHUTDOWN_MASK;

	if (!sock_flag(sk, SOCK_DEAD))
		sk->sk_state_change(sk);
	else
		inet_csk_destroy_sock(sk);
}
EXPORT_SYMBOL_GPL(tcp_done);

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|SLAB_PANIC, NULL);

	/* Size and allocate the main established and bind bucket
	 * hash tables.
	 *
	 * The methodology is similar to that