Exemple #1
0
//smallboy: We change the whole func here;
int ip_local_out(struct sk_buff *skb)
{
	//us_nic_port	*port = NULL;
	//port = get_local_out_port(skb);
	//if (port == NULL  ){
	//	IP_INC_STATS_BH(skb->pnet, IPSTATS_MIB_OUTNOROUTES);
	//	return US_ENETUNREACH;
	//}

	s32 ret = US_RET_OK;
	u32 n ;
	struct rte_mbuf *mbuf = (struct rte_mbuf*)(skb->head);
	struct net		*pnet = skb->pnet;

	if(skb->nohdr ){
		if( skb->nf_trace || skb->used > 0 ){
			rte_pktmbuf_prepend(mbuf, skb->mac_len);
		}

		mbuf_rebuild(skb , pnet->port);	
		//ret = ip_send_out(pnet,mbuf,skb);				//smallboy:  unkown error here; ip traunked; ???
		
		recv_pkt_dump(&mbuf, 1);

		n = rte_eth_tx_burst(pnet->port_id, pnet->send_queue_id , &mbuf, 1);	
		if(n < 1){
			US_ERR("TH:%u ,tx_burst failed on skb_id:%u sk_id:%u \n"
					,US_GET_LCORE(),skb->skb_id,skb->sk->sk_id);
			IP_ADD_STATS(skb->pnet,IPSTATS_MIB_OUTDISCARDS , 1); 
			ret = US_ENETDOWN;  
		}else{
			ret = US_RET_OK;
			IP_ADD_STATS(skb->pnet,IPSTATS_MIB_OUTPKTS , 1);  //skb->gso_segs == 1;
		}

		if(skb->users == 1){		//smallboy: More attention about the users,clone,used and nf_trace;
			__kfree_skb(skb,US_MBUF_FREE_BY_OTHER);		//users == 1; not cloned;  or errors here;
		}else{
			if(ret == US_RET_OK)	//smallboy: data send failed; No recover the users too;	
				skb->users--;
			skb->used++;
			skb_reset_data_header(skb);
		}
	}else{
		if(skb_can_gso(skb)){
			ret = ip_send_out_batch(skb,pnet);
		}
		
		if(skb->users == 1){		//smallboy: More attention about the users,clone,used and nf_trace;
			__kfree_skb(skb,US_MBUF_FREE_BY_STACK);		//users == 1; not cloned;  or errors here;
		}else{
			if(ret == US_RET_OK)
				skb->users--;
			skb->used++;
			skb_reset_data_header(skb);
		}		
	}

	return ret;
}
Exemple #2
0
void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
			     struct net_device *dev)
{
	int status;
	struct netpoll_info *npinfo;

	if (!np || !dev || !netif_running(dev)) {
		__kfree_skb(skb);
		return;
	}

	npinfo = dev->npinfo;

	/* avoid recursion */
	if (npinfo->poll_owner == smp_processor_id() ||
	    np->dev->xmit_lock_owner == smp_processor_id()) {
		if (np->drop)
			np->drop(skb);
		else
			__kfree_skb(skb);
		return;
	}

	do {
		npinfo->tries--;
		netif_tx_lock(dev);

		/*
		 * network drivers do not expect to be called if the queue is
		 * stopped.
		 */
		status = NETDEV_TX_BUSY;
		if (!netif_queue_stopped(dev)) {
			dev->priv_flags |= IFF_IN_NETPOLL;
			status = dev->hard_start_xmit(skb, dev);
			dev->priv_flags &= ~IFF_IN_NETPOLL;
		}

		netif_tx_unlock(dev);

		/* success */
		if(!status) {
			npinfo->tries = MAX_RETRIES; /* reset */
			return;
		}

		/* transmit busy */
		netpoll_poll_dev(dev);
		udelay(50);
	} while (npinfo->tries > 0);
}
Exemple #3
0
static void zap_completion_queue(void)
{
	unsigned long flags;
	struct softnet_data *sd = &get_cpu_var(softnet_data);

	if (sd->completion_queue) {
		struct sk_buff *clist;

		local_irq_save(flags);
		clist = sd->completion_queue;
		sd->completion_queue = NULL;
		local_irq_restore(flags);

		while (clist != NULL) {
			struct sk_buff *skb = clist;
			clist = clist->next;
			if (skb->destructor)
				dev_kfree_skb_any(skb); /* put this one back */
			else
				__kfree_skb(skb);
		}
	}

	put_cpu_var(softnet_data);
}
Exemple #4
0
static void queue_process(struct work_struct *work)
{
	struct netpoll_info *npinfo =
		container_of(work, struct netpoll_info, tx_work.work);
	struct sk_buff *skb;
	unsigned long flags;

	while ((skb = skb_dequeue(&npinfo->txq))) {
		struct net_device *dev = skb->dev;

		if (!netif_device_present(dev) || !netif_running(dev)) {
			__kfree_skb(skb);
			continue;
		}

		local_irq_save(flags);
		netif_tx_lock(dev);
		if (netif_queue_stopped(dev) ||
		    dev->hard_start_xmit(skb, dev) != NETDEV_TX_OK) {
			skb_queue_head(&npinfo->txq, skb);
			netif_tx_unlock(dev);
			local_irq_restore(flags);

			schedule_delayed_work(&npinfo->tx_work, HZ/10);
			return;
		}
		netif_tx_unlock(dev);
		local_irq_restore(flags);
	}
}
int dccp_rcv_established(struct sock *sk, struct sk_buff *skb,
			 const struct dccp_hdr *dh, const unsigned len)
{
	struct dccp_sock *dp = dccp_sk(sk);

	if (dccp_check_seqno(sk, skb))
		goto discard;

	if (dccp_parse_options(sk, skb))
		goto discard;

	if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
		dccp_event_ack_recv(sk, skb);

	if (dccp_msk(sk)->dccpms_send_ack_vector &&
	    dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
			    DCCP_SKB_CB(skb)->dccpd_seq,
			    DCCP_ACKVEC_STATE_RECEIVED))
		goto discard;

	ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb);
	ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb);

	return __dccp_rcv_established(sk, skb, dh, len);
discard:
	__kfree_skb(skb);
	return 0;
}
Exemple #6
0
int emuswitch_process(struct net_bridge_throttle_state *state, 
		      struct sk_buff *skb) {
	static int maxqlen = 0;
	//emuswitch_thunk_t thunk = EMUSWITCH_SKB_CB(skb)->thunk;
	//emuswitch_thunkstate_t thunkState = EMUSWITCH_SKB_CB(skb)->thunkstate;
	maxqlen = max(maxqlen, state->maxQueueLen);

	if(state->queue.qlen < state->maxQueueLen) {
		int oldQlen = state->queue.qlen;
		__skb_queue_tail(&state->queue, skb);
#if 0 // microoptimization
		if(oldQlen == 0) {
			restartTimer(state);
		}
#endif
		//printk("queue length %d\n", state->queue.qlen);
	} else {
		// Drop packet
		printk("dropped packet\n");
		__kfree_skb(skb);
	}
	if(state->queue.qlen > 200) {
		printk("queue length: %d/%d\n", state->queue.qlen, state->maxQueueLen);
	}
	return 1;
}
Exemple #7
0
/**
 *	kfree_skb - free an sk_buff
 *	@skb: buffer to free
 *
 *	Drop a reference to the buffer and free it if the usage count has
 *	hit zero.
 */
void kfree_skb(struct sk_buff *skb)
{
	if (unlikely(!skb))
		return;
	if (likely(atomic_read(&skb->users) == 1))
		smp_rmb();
	else if (likely(!atomic_dec_and_test(&skb->users)))
		return;
	__kfree_skb(skb);
}
Exemple #8
0
/**
 *	consume_skb - free an skbuff
 *	@skb: buffer to free
 *
 *	Drop a ref to the buffer and free it if the usage count has hit zero
 *	Functions identically to kfree_skb, but kfree_skb assumes that the frame
 *	is being dropped after a failure and notes that
 */
void consume_skb(struct sk_buff *skb)
{
	if (unlikely(!skb))
		return ;

	else if (likely(!atomic_dec_and_test(&skb->users)))
		return ;

	__kfree_skb(skb);
} EXPORT_SYMBOL(consume_skb);
Exemple #9
0
int dccp_disconnect(struct sock *sk, int flags)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct inet_sock *inet = inet_sk(sk);
	struct dccp_sock *dp = dccp_sk(sk);
	int err = 0;
	const int old_state = sk->sk_state;

	if (old_state != DCCP_CLOSED)
		dccp_set_state(sk, DCCP_CLOSED);

	/*
	 * This corresponds to the ABORT function of RFC793, sec. 3.8
	 * TCP uses a RST segment, DCCP a Reset packet with Code 2, "Aborted".
	 */
	if (old_state == DCCP_LISTEN) {
		inet_csk_listen_stop(sk);
	} else if (dccp_need_reset(old_state)) {
		dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
		sk->sk_err = ECONNRESET;
	} else if (old_state == DCCP_REQUESTING)
		sk->sk_err = ECONNRESET;

	dccp_clear_xmit_timers(sk);
	ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
	dp->dccps_hc_rx_ccid = NULL;

	__skb_queue_purge(&sk->sk_receive_queue);
	__skb_queue_purge(&sk->sk_write_queue);
	if (sk->sk_send_head != NULL) {
		__kfree_skb(sk->sk_send_head);
		sk->sk_send_head = NULL;
	}

	inet->inet_dport = 0;

	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
		inet_reset_saddr(sk);

	sk->sk_shutdown = 0;
	sock_reset_flag(sk, SOCK_DONE);

	icsk->icsk_backoff = 0;
	inet_csk_delack_init(sk);
	__sk_dst_reset(sk);

	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);

	sk->sk_error_report(sk);
	return err;
}
Exemple #10
0
static int
tfw_bmb_conn_recv(void *cdata, struct sk_buff *skb, unsigned int off)
{
	if (verbose) {
		unsigned int data_off = 0;

		TFW_LOG("Server response:\n------------------------------\n");
		ss_skb_process(skb, &data_off, tfw_bmb_print_msg, NULL);
		printk(KERN_INFO "\n------------------------------\n");
	}

	__kfree_skb(skb);
	return TFW_PASS;
}
void cxgb3i_conn_cleanup_task(struct iscsi_task *task)
{
	struct cxgb3i_task_data *tdata = task->dd_data +
					sizeof(struct iscsi_tcp_task);

	/* never reached the xmit task callout */
	if (tdata->skb)
		__kfree_skb(tdata->skb);
	memset(tdata, 0, sizeof(struct cxgb3i_task_data));

	/* MNC - Do we need a check in case this is called but
	 * cxgb3i_conn_alloc_pdu has never been called on the task */
	cxgb3i_release_itt(task, task->hdr_itt);
	iscsi_tcp_cleanup_task(task);
}
int t3_l2t_send_slow(struct t3cdev *dev, struct sk_buff *skb,
		     struct l2t_entry *e)
{
again:
	switch (e->state) {
	case L2T_STATE_STALE:	/* entry is stale, kick off revalidation */
		neigh_event_send(e->neigh, NULL);
		spin_lock_bh(&e->lock);
		if (e->state == L2T_STATE_STALE)
			e->state = L2T_STATE_VALID;
		spin_unlock_bh(&e->lock);
	case L2T_STATE_VALID:	/* fast-path, send the packet on */
		return cxgb3_ofld_send(dev, skb);
	case L2T_STATE_RESOLVING:
		spin_lock_bh(&e->lock);
		if (e->state != L2T_STATE_RESOLVING) {
			/* ARP already completed */
			spin_unlock_bh(&e->lock);
			goto again;
		}
		arpq_enqueue(e, skb);
		spin_unlock_bh(&e->lock);

		/*
		 * Only the first packet added to the arpq should kick off
		 * resolution.  However, because the alloc_skb below can fail,
		 * we allow each packet added to the arpq to retry resolution
		 * as a way of recovering from transient memory exhaustion.
		 * A better way would be to use a work request to retry L2T
		 * entries when there's no memory.
		 */
		if (!neigh_event_send(e->neigh, NULL)) {
			skb = alloc_skb(sizeof(struct cpl_l2t_write_req),
					GFP_ATOMIC);
			if (!skb)
				break;

			spin_lock_bh(&e->lock);
			if (e->arpq_head)
				setup_l2e_send_pending(dev, skb, e);
			else	/* we lost the race */
				__kfree_skb(skb);
			spin_unlock_bh(&e->lock);
		}
	}
	return 0;
}
void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb)
{
	bool slow;

	if (likely(atomic_read(&skb->users) == 1))
		smp_rmb();
	else if (likely(!atomic_dec_and_test(&skb->users)))
		return;

	slow = lock_sock_fast(sk);
	skb_orphan(skb);
	sk_mem_reclaim_partial(sk);
	unlock_sock_fast(sk, slow);

	/* skb is now orphaned, can be freed outside of locked section */
	__kfree_skb(skb);
}
Exemple #14
0
int dccp_disconnect(struct sock *sk, int flags)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct inet_sock *inet = inet_sk(sk);
	int err = 0;
	const int old_state = sk->sk_state;

	if (old_state != DCCP_CLOSED)
		dccp_set_state(sk, DCCP_CLOSED);

	
	if (old_state == DCCP_LISTEN) {
		inet_csk_listen_stop(sk);
	} else if (dccp_need_reset(old_state)) {
		dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
		sk->sk_err = ECONNRESET;
	} else if (old_state == DCCP_REQUESTING)
		sk->sk_err = ECONNRESET;

	dccp_clear_xmit_timers(sk);

	__skb_queue_purge(&sk->sk_receive_queue);
	__skb_queue_purge(&sk->sk_write_queue);
	if (sk->sk_send_head != NULL) {
		__kfree_skb(sk->sk_send_head);
		sk->sk_send_head = NULL;
	}

	inet->dport = 0;

	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
		inet_reset_saddr(sk);

	sk->sk_shutdown = 0;
	sock_reset_flag(sk, SOCK_DONE);

	icsk->icsk_backoff = 0;
	inet_csk_delack_init(sk);
	__sk_dst_reset(sk);

	WARN_ON(inet->num && !icsk->icsk_bind_hash);

	sk->sk_error_report(sk);
	return err;
}
Exemple #15
0
void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb)
{
	bool slow;

	if (likely(atomic_read(&skb->users) == 1))
		smp_rmb();
	else if (likely(!atomic_dec_and_test(&skb->users)))
		return;

	slow = lock_sock_fast(sk);
	skb_orphan(skb);
	sk_mem_reclaim_partial(sk);
	unlock_sock_fast(sk, slow);

	
	trace_kfree_skb(skb, skb_free_datagram_locked);
	__kfree_skb(skb);
}
Exemple #16
0
void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len)
{
	bool slow;

	if (!skb_unref(skb)) {
		sk_peek_offset_bwd(sk, len);
		return;
	}

	slow = lock_sock_fast(sk);
	sk_peek_offset_bwd(sk, len);
	skb_orphan(skb);
	sk_mem_reclaim_partial(sk);
	unlock_sock_fast(sk, slow);

	/* skb is now orphaned, can be freed outside of locked section */
	__kfree_skb(skb);
}
Exemple #17
0
static inline void 
disable_nb_throttle_state(struct net_bridge_throttle_state *state) {
	if(state->useThrottle) {
		state->useThrottle = 0;

		BUG_TRAP(state->maxQueueLen > 0);
		BUG_TRAP(state->bytesPerSecond > 0);

		state->bytesSentInInterval = 0;
		state->timeout = 0;

		del_timer(&state->queue_timer);
		while(state->queue.qlen > 0) {
			struct sk_buff *skb = __skb_dequeue(&state->queue);
			__kfree_skb(skb);
		}
	}
}
Exemple #18
0
static void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
{
	int status = NETDEV_TX_BUSY;
	unsigned long tries;
	struct net_device *dev = np->dev;
	struct netpoll_info *npinfo = np->dev->npinfo;

	if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
		__kfree_skb(skb);
		return;
	}

	/* don't get messages out of order, and no recursion */
	if (skb_queue_len(&npinfo->txq) == 0 &&
		    npinfo->poll_owner != smp_processor_id()) {
		unsigned long flags;

		local_irq_save(flags);
		/* try until next clock tick */
		for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
		     tries > 0; --tries) {
			if (netif_tx_trylock(dev)) {
				if (!netif_queue_stopped(dev))
					status = dev->hard_start_xmit(skb, dev);
				netif_tx_unlock(dev);

				if (status == NETDEV_TX_OK)
					break;

			}

			/* tickle device maybe there is some cleanup */
			netpoll_poll(np);

			udelay(USEC_PER_POLL);
		}
		local_irq_restore(flags);
	}

	if (status != NETDEV_TX_OK) {
		skb_queue_tail(&npinfo->txq, skb);
		schedule_delayed_work(&npinfo->tx_work,0);
	}
}
Exemple #19
0
void netpoll_queue(struct sk_buff *skb)
{
	unsigned long flags;

	if (queue_depth == MAX_QUEUE_DEPTH) {
		__kfree_skb(skb);
		return;
	}

	spin_lock_irqsave(&queue_lock, flags);
	if (!queue_head)
		queue_head = skb;
	else
		queue_tail->next = skb;
	queue_tail = skb;
	queue_depth++;
	spin_unlock_irqrestore(&queue_lock, flags);

	schedule_work(&send_queue);
}
int dccp_disconnect(struct sock *sk, int flags)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct inet_sock *inet = inet_sk(sk);
	int err = 0;
	const int old_state = sk->sk_state;

	if (old_state != DCCP_CLOSED)
		dccp_set_state(sk, DCCP_CLOSED);

	/* ABORT function of RFC793 */
	if (old_state == DCCP_LISTEN) {
		inet_csk_listen_stop(sk);
	/* FIXME: do the active reset thing */
	} else if (old_state == DCCP_REQUESTING)
		sk->sk_err = ECONNRESET;

	dccp_clear_xmit_timers(sk);
	__skb_queue_purge(&sk->sk_receive_queue);
	if (sk->sk_send_head != NULL) {
		__kfree_skb(sk->sk_send_head);
		sk->sk_send_head = NULL;
	}

	inet->dport = 0;

	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
		inet_reset_saddr(sk);

	sk->sk_shutdown = 0;
	sock_reset_flag(sk, SOCK_DONE);

	icsk->icsk_backoff = 0;
	inet_csk_delack_init(sk);
	__sk_dst_reset(sk);

	BUG_TRAP(!inet->num || icsk->icsk_bind_hash);

	sk->sk_error_report(sk);
	return err;
}
void cxgb3i_conn_pdu_ready(struct s3_conn *c3cn)
{
	struct sk_buff *skb;
	unsigned int read = 0;
	struct iscsi_conn *conn = c3cn->user_data;
	int err = 0;

	cxgb3i_rx_debug("cn 0x%p.\n", c3cn);

	read_lock(&c3cn->callback_lock);
	if (unlikely(!conn || conn->suspend_rx)) {
		cxgb3i_rx_debug("conn 0x%p, id %d, suspend_rx %lu!\n",
				conn, conn ? conn->id : 0xFF,
				conn ? conn->suspend_rx : 0xFF);
		read_unlock(&c3cn->callback_lock);
		return;
	}
	skb = skb_peek(&c3cn->receive_queue);
	while (!err && skb) {
		__skb_unlink(skb, &c3cn->receive_queue);
		read += skb_rx_pdulen(skb);
		cxgb3i_rx_debug("conn 0x%p, cn 0x%p, rx skb 0x%p, pdulen %u.\n",
				conn, c3cn, skb, skb_rx_pdulen(skb));
		err = cxgb3i_conn_read_pdu_skb(conn, skb);
		__kfree_skb(skb);
		skb = skb_peek(&c3cn->receive_queue);
	}
	read_unlock(&c3cn->callback_lock);
	if (c3cn) {
		c3cn->copied_seq += read;
		cxgb3i_c3cn_rx_credits(c3cn, read);
	}
	conn->rxdata_octets += read;

	if (err) {
		cxgb3i_log_info("conn 0x%p rx failed err %d.\n", conn, err);
		iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
	}
}
Exemple #22
0
int dccp_rcv_established(struct sock *sk, struct sk_buff *skb,
			 const struct dccp_hdr *dh, const unsigned len)
{
	struct dccp_sock *dp = dccp_sk(sk);

	if (dccp_check_seqno(sk, skb))
		goto discard;

	if (dccp_parse_options(sk, skb))
		goto discard;

	if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
		dccp_event_ack_recv(sk, skb);

	if (dccp_msk(sk)->dccpms_send_ack_vector &&
	    dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
			    DCCP_SKB_CB(skb)->dccpd_seq,
			    DCCP_ACKVEC_STATE_RECEIVED))
		goto discard;

	/*
	 * Deliver to the CCID module in charge.
	 * FIXME: Currently DCCP operates one-directional only, i.e. a listening
	 *        server is not at the same time a connecting client. There is
	 *        not much sense in delivering to both rx/tx sides at the moment
	 *        (only one is active at a time); when moving to bidirectional
	 *        service, this needs to be revised.
	 */
	if (dccp_sk(sk)->dccps_role == DCCP_ROLE_SERVER)
		ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb);
	else
		ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb);

	return __dccp_rcv_established(sk, skb, dh, len);
discard:
	__kfree_skb(skb);
	return 0;
}
Exemple #23
0
/**
 * This is main body of the socket close function in Sync Sockets.
 *
 * inet_release() can sleep (as well as tcp_close()), so we make our own
 * non-sleepable socket closing.
 *
 * This function must be used only for data sockets.
 * Use standard sock_release() for listening sockets.
 *
 * In most cases it is called in softirq context and from ksoftirqd which
 * processes data from the socket (RSS and RPS distribute packets that way).
 *
 * Note: it used to be called in process context as well, at the time when
 * Tempesta starts or stops. That's not the case right now, but it may change.
 *
 * TODO In some cases we need to close socket agresively w/o FIN_WAIT_2 state,
 * e.g. by sending RST. So we need to add second parameter to the function
 * which says how to close the socket.
 * One of the examples is rcl_req_limit() (it should reset connections).
 * See tcp_sk(sk)->linger2 processing in standard tcp_close().
 *
 * Called with locked socket.
 */
static void
ss_do_close(struct sock *sk)
{
	struct sk_buff *skb;
	int data_was_unread = 0;
	int state;

	if (unlikely(!sk))
		return;
	SS_DBG("Close socket %p (%s): cpu=%d account=%d refcnt=%d\n",
	       sk, ss_statename[sk->sk_state], smp_processor_id(),
	       sk_has_account(sk), atomic_read(&sk->sk_refcnt));
	assert_spin_locked(&sk->sk_lock.slock);
	ss_sock_cpu_check(sk);
	BUG_ON(sk->sk_state == TCP_LISTEN);
	/* We must return immediately, so LINGER option is meaningless. */
	WARN_ON(sock_flag(sk, SOCK_LINGER));
	/* We don't support virtual containers, so TCP_REPAIR is prohibited. */
	WARN_ON(tcp_sk(sk)->repair);
	/* The socket must have atomic allocation mask. */
	WARN_ON(!(sk->sk_allocation & GFP_ATOMIC));

	/* The below is mostly copy-paste from tcp_close(). */
	sk->sk_shutdown = SHUTDOWN_MASK;

	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
		u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq -
			  tcp_hdr(skb)->fin;
		data_was_unread += len;
		SS_DBG("free rcv skb %p\n", skb);
		__kfree_skb(skb);
	}

	sk_mem_reclaim(sk);

	if (sk->sk_state == TCP_CLOSE)
		goto adjudge_to_death;

	if (data_was_unread) {
		NET_INC_STATS_USER(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE);
		tcp_set_state(sk, TCP_CLOSE);
		tcp_send_active_reset(sk, sk->sk_allocation);
	}
	else if (tcp_close_state(sk)) {
		/* The code below is taken from tcp_send_fin(). */
		struct tcp_sock *tp = tcp_sk(sk);
		int mss_now = tcp_current_mss(sk);

		skb = tcp_write_queue_tail(sk);

		if (tcp_send_head(sk) != NULL) {
			/* Send FIN with data if we have any. */
			TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
			TCP_SKB_CB(skb)->end_seq++;
			tp->write_seq++;
		}
		else {
			/* No data to send in the socket, allocate new skb. */
			skb = alloc_skb_fclone(MAX_TCP_HEADER,
					       sk->sk_allocation);
			if (!skb) {
				SS_WARN("can't send FIN due to bad alloc");
			} else {
				skb_reserve(skb, MAX_TCP_HEADER);
				tcp_init_nondata_skb(skb, tp->write_seq,
						     TCPHDR_ACK | TCPHDR_FIN);
				tcp_queue_skb(sk, skb);
			}
		}
		__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
	}

adjudge_to_death:
	state = sk->sk_state;
	sock_hold(sk);
	sock_orphan(sk);

	/*
	 * SS sockets are processed in softirq only,
	 * so backlog queue should be empty.
	 */
	WARN_ON(sk->sk_backlog.tail);

	percpu_counter_inc(sk->sk_prot->orphan_count);

	if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE)
		return;

	if (sk->sk_state == TCP_FIN_WAIT2) {
		const int tmo = tcp_fin_time(sk);
		if (tmo > TCP_TIMEWAIT_LEN) {
			inet_csk_reset_keepalive_timer(sk,
						tmo - TCP_TIMEWAIT_LEN);
		} else {
			tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
			return;
		}
	}
	if (sk->sk_state != TCP_CLOSE) {
		sk_mem_reclaim(sk);
		if (tcp_check_oom(sk, 0)) {
			tcp_set_state(sk, TCP_CLOSE);
			tcp_send_active_reset(sk, GFP_ATOMIC);
			NET_INC_STATS_BH(sock_net(sk),
					 LINUX_MIB_TCPABORTONMEMORY);
		}
	}
	if (sk->sk_state == TCP_CLOSE) {
		struct request_sock *req = tcp_sk(sk)->fastopen_rsk;
		if (req != NULL)
			reqsk_fastopen_remove(sk, req, false);
		inet_csk_destroy_sock(sk);
	}
}
Exemple #24
0
void dccp_close(struct sock *sk, long timeout)
{
	struct dccp_sock *dp = dccp_sk(sk);
	struct sk_buff *skb;
	u32 data_was_unread = 0;
	int state;

	lock_sock(sk);

	sk->sk_shutdown = SHUTDOWN_MASK;

	if (sk->sk_state == DCCP_LISTEN) {
		dccp_set_state(sk, DCCP_CLOSED);

		/* Special case. */
		inet_csk_listen_stop(sk);

		goto adjudge_to_death;
	}

	sk_stop_timer(sk, &dp->dccps_xmit_timer);

	/*
	 * We need to flush the recv. buffs.  We do this only on the
	 * descriptor close, not protocol-sourced closes, because the
	  *reader process may not have drained the data yet!
	 */
	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
		data_was_unread += skb->len;
		__kfree_skb(skb);
	}

	if (data_was_unread) {
		/* Unread data was tossed, send an appropriate Reset Code */
		DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread);
		dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
		dccp_set_state(sk, DCCP_CLOSED);
	} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
		/* Check zero linger _after_ checking for unread data. */
		sk->sk_prot->disconnect(sk, 0);
	} else if (sk->sk_state != DCCP_CLOSED) {
		/*
		 * Normal connection termination. May need to wait if there are
		 * still packets in the TX queue that are delayed by the CCID.
		 */
		dccp_flush_write_queue(sk, &timeout);
		dccp_terminate_connection(sk);
	}

	/*
	 * Flush write queue. This may be necessary in several cases:
	 * - we have been closed by the peer but still have application data;
	 * - abortive termination (unread data or zero linger time),
	 * - normal termination but queue could not be flushed within time limit
	 */
	__skb_queue_purge(&sk->sk_write_queue);

	sk_stream_wait_close(sk, timeout);

adjudge_to_death:
	state = sk->sk_state;
	sock_hold(sk);
	sock_orphan(sk);

	/*
	 * It is the last release_sock in its life. It will remove backlog.
	 */
	release_sock(sk);
	/*
	 * Now socket is owned by kernel and we acquire BH lock
	 * to finish close. No need to check for user refs.
	 */
	local_bh_disable();
	bh_lock_sock(sk);
	WARN_ON(sock_owned_by_user(sk));

	percpu_counter_inc(sk->sk_prot->orphan_count);

	/* Have we already been destroyed by a softirq or backlog? */
	if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED)
		goto out;

	if (sk->sk_state == DCCP_CLOSED)
		inet_csk_destroy_sock(sk);

	/* Otherwise, socket is reprieved until protocol close. */

out:
	bh_unlock_sock(sk);
	local_bh_enable();
	sock_put(sk);
}
void dccp_close(struct sock *sk, long timeout)
{
	struct sk_buff *skb;

	lock_sock(sk);

	sk->sk_shutdown = SHUTDOWN_MASK;

	if (sk->sk_state == DCCP_LISTEN) {
		dccp_set_state(sk, DCCP_CLOSED);

		/* Special case. */
		inet_csk_listen_stop(sk);

		goto adjudge_to_death;
	}

	/*
	 * We need to flush the recv. buffs.  We do this only on the
	 * descriptor close, not protocol-sourced closes, because the
	  *reader process may not have drained the data yet!
	 */
	/* FIXME: check for unread data */
	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
		__kfree_skb(skb);
	}

	if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
		/* Check zero linger _after_ checking for unread data. */
		sk->sk_prot->disconnect(sk, 0);
	} else if (dccp_close_state(sk)) {
		dccp_send_close(sk, 1);
	}

	sk_stream_wait_close(sk, timeout);

adjudge_to_death:
	/*
	 * It is the last release_sock in its life. It will remove backlog.
	 */
	release_sock(sk);
	/*
	 * Now socket is owned by kernel and we acquire BH lock
	 * to finish close. No need to check for user refs.
	 */
	local_bh_disable();
	bh_lock_sock(sk);
	BUG_TRAP(!sock_owned_by_user(sk));

	sock_hold(sk);
	sock_orphan(sk);

	/*
	 * The last release_sock may have processed the CLOSE or RESET
	 * packet moving sock to CLOSED state, if not we have to fire
	 * the CLOSE/CLOSEREQ retransmission timer, see "8.3. Termination"
	 * in draft-ietf-dccp-spec-11. -acme
	 */
	if (sk->sk_state == DCCP_CLOSING) {
		/* FIXME: should start at 2 * RTT */
		/* Timer for repeating the CLOSE/CLOSEREQ until an answer. */
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
					  inet_csk(sk)->icsk_rto,
					  DCCP_RTO_MAX);
#if 0
		/* Yeah, we should use sk->sk_prot->orphan_count, etc */
		dccp_set_state(sk, DCCP_CLOSED);
#endif
	}

	atomic_inc(sk->sk_prot->orphan_count);
	if (sk->sk_state == DCCP_CLOSED)
		inet_csk_destroy_sock(sk);

	/* Otherwise, socket is reprieved until protocol close. */

	bh_unlock_sock(sk);
	local_bh_enable();
	sock_put(sk);
}
Exemple #26
0
void dccp_close(struct sock *sk, long timeout)
{
	struct dccp_sock *dp = dccp_sk(sk);
	struct sk_buff *skb;
	u32 data_was_unread = 0;
	int state;

	lock_sock(sk);

	sk->sk_shutdown = SHUTDOWN_MASK;

	if (sk->sk_state == DCCP_LISTEN) {
		dccp_set_state(sk, DCCP_CLOSED);

		/* Special case. */
		inet_csk_listen_stop(sk);

		goto adjudge_to_death;
	}

	sk_stop_timer(sk, &dp->dccps_xmit_timer);

	/*
	 * We need to flush the recv. buffs.  We do this only on the
	 * descriptor close, not protocol-sourced closes, because the
	  *reader process may not have drained the data yet!
	 */
	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
		data_was_unread += skb->len;
		__kfree_skb(skb);
	}

	if (data_was_unread) {
		/* Unread data was tossed, send an appropriate Reset Code */
		DCCP_WARN("DCCP: ABORT -- %u bytes unread\n", data_was_unread);
		dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
		dccp_set_state(sk, DCCP_CLOSED);
	} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
		/* Check zero linger _after_ checking for unread data. */
		sk->sk_prot->disconnect(sk, 0);
	} else if (sk->sk_state != DCCP_CLOSED) {
		dccp_terminate_connection(sk);
	}

	sk_stream_wait_close(sk, timeout);

adjudge_to_death:
	state = sk->sk_state;
	sock_hold(sk);
	sock_orphan(sk);
	atomic_inc(sk->sk_prot->orphan_count);

	/*
	 * It is the last release_sock in its life. It will remove backlog.
	 */
	release_sock(sk);
	/*
	 * Now socket is owned by kernel and we acquire BH lock
	 * to finish close. No need to check for user refs.
	 */
	local_bh_disable();
	bh_lock_sock(sk);
	BUG_TRAP(!sock_owned_by_user(sk));

	/* Have we already been destroyed by a softirq or backlog? */
	if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED)
		goto out;

	if (sk->sk_state == DCCP_CLOSED)
		inet_csk_destroy_sock(sk);

	/* Otherwise, socket is reprieved until protocol close. */

out:
	bh_unlock_sock(sk);
	local_bh_enable();
	sock_put(sk);
}
Exemple #27
0
/* The socket must have it's spinlock held when we get
 * here.
 *
 * We have a potential double-lock case here, so even when
 * doing backlog processing we use the BH locking scheme.
 * This is because we cannot sleep with the original spinlock
 * held.
 */
static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sk_buff *opt_skb = NULL;

	/* Imagine: socket is IPv6. IPv4 packet arrives,
	   goes to IPv4 receive handler and backlogged.
	   From backlog it always goes here. Kerboom...
	   Fortunately, dccp_rcv_established and rcv_established
	   handle them correctly, but it is not case with
	   dccp_v6_hnd_req and dccp_v6_ctl_send_reset().   --ANK
	 */

	if (skb->protocol == htons(ETH_P_IP))
		return dccp_v4_do_rcv(sk, skb);

	if (sk_filter(sk, skb))
		goto discard;

	/*
	 * socket locking is here for SMP purposes as backlog rcv is currently
	 * called with bh processing disabled.
	 */

	/* Do Stevens' IPV6_PKTOPTIONS.

	   Yes, guys, it is the only place in our code, where we
	   may make it not affecting IPv4.
	   The rest of code is protocol independent,
	   and I do not like idea to uglify IPv4.

	   Actually, all the idea behind IPV6_PKTOPTIONS
	   looks not very well thought. For now we latch
	   options, received in the last packet, enqueued
	   by tcp. Feel free to propose better solution.
					       --ANK (980728)
	 */
	if (np->rxopt.all)
	/*
	 * FIXME: Add handling of IPV6_PKTOPTIONS skb. See the comments below
	 *        (wrt ipv6_pktopions) and net/ipv6/tcp_ipv6.c for an example.
	 */
		opt_skb = skb_clone(skb, GFP_ATOMIC);

	if (sk->sk_state == DCCP_OPEN) { /* Fast path */
		if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len))
			goto reset;
		if (opt_skb) {
			/* XXX This is where we would goto ipv6_pktoptions. */
			__kfree_skb(opt_skb);
		}
		return 0;
	}

	/*
	 *  Step 3: Process LISTEN state
	 *     If S.state == LISTEN,
	 *	 If P.type == Request or P contains a valid Init Cookie option,
	 *	      (* Must scan the packet's options to check for Init
	 *		 Cookies.  Only Init Cookies are processed here,
	 *		 however; other options are processed in Step 8.  This
	 *		 scan need only be performed if the endpoint uses Init
	 *		 Cookies *)
	 *	      (* Generate a new socket and switch to that socket *)
	 *	      Set S := new socket for this port pair
	 *	      S.state = RESPOND
	 *	      Choose S.ISS (initial seqno) or set from Init Cookies
	 *	      Initialize S.GAR := S.ISS
	 *	      Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookies
	 *	      Continue with S.state == RESPOND
	 *	      (* A Response packet will be generated in Step 11 *)
	 *	 Otherwise,
	 *	      Generate Reset(No Connection) unless P.type == Reset
	 *	      Drop packet and return
	 *
	 * NOTE: the check for the packet types is done in
	 *	 dccp_rcv_state_process
	 */
	if (sk->sk_state == DCCP_LISTEN) {
		struct sock *nsk = dccp_v6_hnd_req(sk, skb);

		if (nsk == NULL)
			goto discard;
		/*
		 * Queue it on the new socket if the new socket is active,
		 * otherwise we just shortcircuit this and continue with
		 * the new socket..
		 */
		if (nsk != sk) {
			if (dccp_child_process(sk, nsk, skb))
				goto reset;
			if (opt_skb != NULL)
				__kfree_skb(opt_skb);
			return 0;
		}
	}

	if (dccp_rcv_state_process(sk, skb, dccp_hdr(skb), skb->len))
		goto reset;
	if (opt_skb) {
		/* XXX This is where we would goto ipv6_pktoptions. */
		__kfree_skb(opt_skb);
	}
	return 0;

reset:
	dccp_v6_ctl_send_reset(sk, skb);
discard:
	if (opt_skb != NULL)
		__kfree_skb(opt_skb);
	kfree_skb(skb);
	return 0;
}
Exemple #28
0
static int dccp_rcv_request_sent_state_process(struct sock *sk,
					       struct sk_buff *skb,
					       const struct dccp_hdr *dh,
					       const unsigned len)
{
	/*
	 *  Step 4: Prepare sequence numbers in REQUEST
	 *     If S.state == REQUEST,
	 *	  If (P.type == Response or P.type == Reset)
	 *		and S.AWL <= P.ackno <= S.AWH,
	 *	     / * Set sequence number variables corresponding to the
	 *		other endpoint, so P will pass the tests in Step 6 * /
	 *	     Set S.GSR, S.ISR, S.SWL, S.SWH
	 *	     / * Response processing continues in Step 10; Reset
	 *		processing continues in Step 9 * /
	*/
	if (dh->dccph_type == DCCP_PKT_RESPONSE) {
		const struct inet_connection_sock *icsk = inet_csk(sk);
		struct dccp_sock *dp = dccp_sk(sk);

		/* Stop the REQUEST timer */
		inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
		BUG_TRAP(sk->sk_send_head != NULL);
		__kfree_skb(sk->sk_send_head);
		sk->sk_send_head = NULL;

		if (!between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
			       dp->dccps_awl, dp->dccps_awh)) {
			dccp_pr_debug("invalid ackno: S.AWL=%llu, "
				      "P.ackno=%llu, S.AWH=%llu \n",
				      (unsigned long long)dp->dccps_awl,
			   (unsigned long long)DCCP_SKB_CB(skb)->dccpd_ack_seq,
				      (unsigned long long)dp->dccps_awh);
			goto out_invalid_packet;
		}

		if (dccp_parse_options(sk, skb))
			goto out_invalid_packet;

                if (dccp_msk(sk)->dccpms_send_ack_vector &&
                    dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
                                    DCCP_SKB_CB(skb)->dccpd_seq,
                                    DCCP_ACKVEC_STATE_RECEIVED))
                        goto out_invalid_packet; /* FIXME: change error code */

		dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq;
		dccp_update_gsr(sk, dp->dccps_isr);
		/*
		 * SWL and AWL are initially adjusted so that they are not less than
		 * the initial Sequence Numbers received and sent, respectively:
		 *	SWL := max(GSR + 1 - floor(W/4), ISR),
		 *	AWL := max(GSS - W' + 1, ISS).
		 * These adjustments MUST be applied only at the beginning of the
		 * connection.
		 *
		 * AWL was adjusted in dccp_v4_connect -acme
		 */
		dccp_set_seqno(&dp->dccps_swl,
			       max48(dp->dccps_swl, dp->dccps_isr));

		dccp_sync_mss(sk, icsk->icsk_pmtu_cookie);

		/*
		 *    Step 10: Process REQUEST state (second part)
		 *       If S.state == REQUEST,
		 *	  / * If we get here, P is a valid Response from the
		 *	      server (see Step 4), and we should move to
		 *	      PARTOPEN state. PARTOPEN means send an Ack,
		 *	      don't send Data packets, retransmit Acks
		 *	      periodically, and always include any Init Cookie
		 *	      from the Response * /
		 *	  S.state := PARTOPEN
		 *	  Set PARTOPEN timer
		 *	  Continue with S.state == PARTOPEN
		 *	  / * Step 12 will send the Ack completing the
		 *	      three-way handshake * /
		 */
		dccp_set_state(sk, DCCP_PARTOPEN);

		/* Make sure socket is routed, for correct metrics. */
		icsk->icsk_af_ops->rebuild_header(sk);

		if (!sock_flag(sk, SOCK_DEAD)) {
			sk->sk_state_change(sk);
			sk_wake_async(sk, 0, POLL_OUT);
		}

		if (sk->sk_write_pending || icsk->icsk_ack.pingpong ||
		    icsk->icsk_accept_queue.rskq_defer_accept) {
			/* Save one ACK. Data will be ready after
			 * several ticks, if write_pending is set.
			 *
			 * It may be deleted, but with this feature tcpdumps
			 * look so _wonderfully_ clever, that I was not able
			 * to stand against the temptation 8)     --ANK
			 */
			/*
			 * OK, in DCCP we can as well do a similar trick, its
			 * even in the draft, but there is no need for us to
			 * schedule an ack here, as dccp_sendmsg does this for
			 * us, also stated in the draft. -acme
			 */
			__kfree_skb(skb);
			return 0;
		}
		dccp_send_ack(sk);
		return -1;
	}

out_invalid_packet:
	/* dccp_v4_do_rcv will send a reset */
	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;
	return 1;
}
Exemple #29
0
int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
			   struct dccp_hdr *dh, unsigned len)
{
	struct dccp_sock *dp = dccp_sk(sk);
	struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
	const int old_state = sk->sk_state;
	int queued = 0;

	/*
	 *  Step 3: Process LISTEN state
	 *
	 *     If S.state == LISTEN,
	 *	 If P.type == Request or P contains a valid Init Cookie option,
	 *	      (* Must scan the packet's options to check for Init
	 *		 Cookies.  Only Init Cookies are processed here,
	 *		 however; other options are processed in Step 8.  This
	 *		 scan need only be performed if the endpoint uses Init
	 *		 Cookies *)
	 *	      (* Generate a new socket and switch to that socket *)
	 *	      Set S := new socket for this port pair
	 *	      S.state = RESPOND
	 *	      Choose S.ISS (initial seqno) or set from Init Cookies
	 *	      Initialize S.GAR := S.ISS
	 *	      Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init
	 *	      Cookies Continue with S.state == RESPOND
	 *	      (* A Response packet will be generated in Step 11 *)
	 *	 Otherwise,
	 *	      Generate Reset(No Connection) unless P.type == Reset
	 *	      Drop packet and return
	 */
	if (sk->sk_state == DCCP_LISTEN) {
		if (dh->dccph_type == DCCP_PKT_REQUEST) {
			if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
								    skb) < 0)
				return 1;

			/* FIXME: do congestion control initialization */
			goto discard;
		}
		if (dh->dccph_type == DCCP_PKT_RESET)
			goto discard;

		/* Caller (dccp_v4_do_rcv) will send Reset */
		dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
		return 1;
	}

	if (sk->sk_state != DCCP_REQUESTING) {
		if (dccp_check_seqno(sk, skb))
			goto discard;

		/*
		 * Step 8: Process options and mark acknowledgeable
		 */
		if (dccp_parse_options(sk, skb))
			goto discard;

		if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
			dccp_event_ack_recv(sk, skb);

		if (dccp_msk(sk)->dccpms_send_ack_vector &&
		    dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
				    DCCP_SKB_CB(skb)->dccpd_seq,
				    DCCP_ACKVEC_STATE_RECEIVED))
			goto discard;

		/* XXX see the comments in dccp_rcv_established about this */
		if (dccp_sk(sk)->dccps_role == DCCP_ROLE_SERVER)
			ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb);
		else
			ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb);
	}

	/*
	 *  Step 9: Process Reset
	 *	If P.type == Reset,
	 *		Tear down connection
	 *		S.state := TIMEWAIT
	 *		Set TIMEWAIT timer
	 *		Drop packet and return
	*/
	if (dh->dccph_type == DCCP_PKT_RESET) {
		/*
		 * Queue the equivalent of TCP fin so that dccp_recvmsg
		 * exits the loop
		 */
		dccp_fin(sk, skb);
		dccp_time_wait(sk, DCCP_TIME_WAIT, 0);
		return 0;
		/*
		 *   Step 7: Check for unexpected packet types
		 *      If (S.is_server and P.type == CloseReq)
		 *	    or (S.is_server and P.type == Response)
		 *	    or (S.is_client and P.type == Request)
		 *	    or (S.state == RESPOND and P.type == Data),
		 *	  Send Sync packet acknowledging P.seqno
		 *	  Drop packet and return
		 */
	} else if ((dp->dccps_role != DCCP_ROLE_CLIENT &&
		    (dh->dccph_type == DCCP_PKT_RESPONSE ||
		     dh->dccph_type == DCCP_PKT_CLOSEREQ)) ||
		    (dp->dccps_role == DCCP_ROLE_CLIENT &&
		     dh->dccph_type == DCCP_PKT_REQUEST) ||
		    (sk->sk_state == DCCP_RESPOND &&
		     dh->dccph_type == DCCP_PKT_DATA)) {
		dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNC);
		goto discard;
	} else if (dh->dccph_type == DCCP_PKT_CLOSEREQ) {
		dccp_rcv_closereq(sk, skb);
		goto discard;
	} else if (dh->dccph_type == DCCP_PKT_CLOSE) {
		dccp_rcv_close(sk, skb);
		return 0;
	}

	if (unlikely(dh->dccph_type == DCCP_PKT_SYNC)) {
		dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNCACK);
		goto discard;
	}

	switch (sk->sk_state) {
	case DCCP_CLOSED:
		dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
		return 1;

	case DCCP_REQUESTING:
		/* FIXME: do congestion control initialization */

		queued = dccp_rcv_request_sent_state_process(sk, skb, dh, len);
		if (queued >= 0)
			return queued;

		__kfree_skb(skb);
		return 0;

	case DCCP_RESPOND:
	case DCCP_PARTOPEN:
		queued = dccp_rcv_respond_partopen_state_process(sk, skb,
								 dh, len);
		break;
	}

	if (dh->dccph_type == DCCP_PKT_ACK ||
	    dh->dccph_type == DCCP_PKT_DATAACK) {
		switch (old_state) {
		case DCCP_PARTOPEN:
			sk->sk_state_change(sk);
			sk_wake_async(sk, 0, POLL_OUT);
			break;
		}
	}

	if (!queued) {
discard:
		__kfree_skb(skb);
	}
	return 0;
}
Exemple #30
0
/* The socket must have it's spinlock held when we get
 * here.
 *
 * We have a potential double-lock case here, so even when
 * doing backlog processing we use the BH locking scheme.
 * This is because we cannot sleep with the original spinlock
 * held.
 */
static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sk_buff *opt_skb = NULL;

	/* Imagine: socket is IPv6. IPv4 packet arrives,
	   goes to IPv4 receive handler and backlogged.
	   From backlog it always goes here. Kerboom...
	   Fortunately, dccp_rcv_established and rcv_established
	   handle them correctly, but it is not case with
	   dccp_v6_hnd_req and dccp_v6_ctl_send_reset().   --ANK
	 */

	if (skb->protocol == htons(ETH_P_IP))
		return dccp_v4_do_rcv(sk, skb);

	if (sk_filter(sk, skb))
		goto discard;

	/*
	 * socket locking is here for SMP purposes as backlog rcv is currently
	 * called with bh processing disabled.
	 */

	/* Do Stevens' IPV6_PKTOPTIONS.

	   Yes, guys, it is the only place in our code, where we
	   may make it not affecting IPv4.
	   The rest of code is protocol independent,
	   and I do not like idea to uglify IPv4.

	   Actually, all the idea behind IPV6_PKTOPTIONS
	   looks not very well thought. For now we latch
	   options, received in the last packet, enqueued
	   by tcp. Feel free to propose better solution.
					       --ANK (980728)
	 */
	if (np->rxopt.all)
		opt_skb = skb_clone(skb, GFP_ATOMIC);

	if (sk->sk_state == DCCP_OPEN) { /* Fast path */
		if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len))
			goto reset;
		if (opt_skb)
			goto ipv6_pktoptions;
		return 0;
	}

	/*
	 *  Step 3: Process LISTEN state
	 *     If S.state == LISTEN,
	 *	 If P.type == Request or P contains a valid Init Cookie option,
	 *	      (* Must scan the packet's options to check for Init
	 *		 Cookies.  Only Init Cookies are processed here,
	 *		 however; other options are processed in Step 8.  This
	 *		 scan need only be performed if the endpoint uses Init
	 *		 Cookies *)
	 *	      (* Generate a new socket and switch to that socket *)
	 *	      Set S := new socket for this port pair
	 *	      S.state = RESPOND
	 *	      Choose S.ISS (initial seqno) or set from Init Cookies
	 *	      Initialize S.GAR := S.ISS
	 *	      Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookies
	 *	      Continue with S.state == RESPOND
	 *	      (* A Response packet will be generated in Step 11 *)
	 *	 Otherwise,
	 *	      Generate Reset(No Connection) unless P.type == Reset
	 *	      Drop packet and return
	 *
	 * NOTE: the check for the packet types is done in
	 *	 dccp_rcv_state_process
	 */

	if (dccp_rcv_state_process(sk, skb, dccp_hdr(skb), skb->len))
		goto reset;
	if (opt_skb)
		goto ipv6_pktoptions;
	return 0;

reset:
	dccp_v6_ctl_send_reset(sk, skb);
discard:
	if (opt_skb != NULL)
		__kfree_skb(opt_skb);
	kfree_skb(skb);
	return 0;

/* Handling IPV6_PKTOPTIONS skb the similar
 * way it's done for net/ipv6/tcp_ipv6.c
 */
ipv6_pktoptions:
	if (!((1 << sk->sk_state) & (DCCPF_CLOSED | DCCPF_LISTEN))) {
		if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo)
			np->mcast_oif = inet6_iif(opt_skb);
		if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
			np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
		if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
			np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb));
		if (np->repflow)
			np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
		if (ipv6_opt_accepted(sk, opt_skb,
				      &DCCP_SKB_CB(opt_skb)->header.h6)) {
			skb_set_owner_r(opt_skb, sk);
			memmove(IP6CB(opt_skb),
				&DCCP_SKB_CB(opt_skb)->header.h6,
				sizeof(struct inet6_skb_parm));
			opt_skb = xchg(&np->pktoptions, opt_skb);
		} else {
			__kfree_skb(opt_skb);
			opt_skb = xchg(&np->pktoptions, NULL);
		}
	}

	kfree_skb(opt_skb);
	return 0;
}