Ejemplo n.º 1
0
/*
 *  Send or receive packet.
 */
static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size,
		int msg_flags)
{
	struct socket *sock = nbd->sock;
	int result;
	struct msghdr msg;
	struct kvec iov;
	sigset_t blocked, oldset;
	unsigned long pflags = current->flags;

	if (unlikely(!sock)) {
		dev_err(disk_to_dev(nbd->disk),
			"Attempted %s on closed socket in sock_xmit\n",
			(send ? "send" : "recv"));
		return -EINVAL;
	}

	/* Allow interception of SIGKILL only
	 * Don't allow other signals to interrupt the transmission */
	siginitsetinv(&blocked, sigmask(SIGKILL));
	sigprocmask(SIG_SETMASK, &blocked, &oldset);

	current->flags |= PF_MEMALLOC;
	do {
		sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC;
		iov.iov_base = buf;
		iov.iov_len = size;
		msg.msg_name = NULL;
		msg.msg_namelen = 0;
		msg.msg_control = NULL;
		msg.msg_controllen = 0;
		msg.msg_flags = msg_flags | MSG_NOSIGNAL;

		if (send)
			result = kernel_sendmsg(sock, &msg, &iov, 1, size);
		else
			result = kernel_recvmsg(sock, &msg, &iov, 1, size,
						msg.msg_flags);

		if (result <= 0) {
			if (result == 0)
				result = -EPIPE; /* short read */
			break;
		}
		size -= result;
		buf += result;
	} while (size > 0);

	sigprocmask(SIG_SETMASK, &oldset, NULL);
	tsk_restore_flags(current, pflags, PF_MEMALLOC);

	if (!send && nbd->xmit_timeout)
		mod_timer(&nbd->timeout_timer, jiffies + nbd->xmit_timeout);

	return result;
}
Ejemplo n.º 2
0
/*
 *  Send or receive packet.
 */
static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size,
		int msg_flags)
{
	struct socket *sock = nbd->sock;
	int result;
	struct msghdr msg;
	struct kvec iov;
	unsigned long pflags = current->flags;

	if (unlikely(!sock)) {
		dev_err(disk_to_dev(nbd->disk),
			"Attempted %s on closed socket in sock_xmit\n",
			(send ? "send" : "recv"));
		return -EINVAL;
	}

	current->flags |= PF_MEMALLOC;
	do {
		sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC;
		iov.iov_base = buf;
		iov.iov_len = size;
		msg.msg_name = NULL;
		msg.msg_namelen = 0;
		msg.msg_control = NULL;
		msg.msg_controllen = 0;
		msg.msg_flags = msg_flags | MSG_NOSIGNAL;

		if (send)
			result = kernel_sendmsg(sock, &msg, &iov, 1, size);
		else
			result = kernel_recvmsg(sock, &msg, &iov, 1, size,
						msg.msg_flags);

		if (result <= 0) {
			if (result == 0)
				result = -EPIPE; /* short read */
			break;
		}
		size -= result;
		buf += result;
	} while (size > 0);

	tsk_restore_flags(current, pflags, PF_MEMALLOC);

	if (!send && nbd->xmit_timeout)
		mod_timer(&nbd->timeout_timer, jiffies + nbd->xmit_timeout);

	return result;
}
Ejemplo n.º 3
0
/*
 *  Send or receive packet.
 */
static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size,
		int msg_flags)
{
	struct socket *sock = nbd->sock;
	int result;
	struct msghdr msg;
	struct kvec iov;
	sigset_t blocked, oldset;
	unsigned long pflags = current->flags;

	if (unlikely(!sock)) {
		dev_err(disk_to_dev(nbd->disk),
			"Attempted %s on closed socket in sock_xmit\n",
			(send ? "send" : "recv"));
		return -EINVAL;
	}

	/* Allow interception of SIGKILL only
	 * Don't allow other signals to interrupt the transmission */
	siginitsetinv(&blocked, sigmask(SIGKILL));
	sigprocmask(SIG_SETMASK, &blocked, &oldset);

	current->flags |= PF_MEMALLOC;
	do {
		sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC;
		iov.iov_base = buf;
		iov.iov_len = size;
		msg.msg_name = NULL;
		msg.msg_namelen = 0;
		msg.msg_control = NULL;
		msg.msg_controllen = 0;
		msg.msg_flags = msg_flags | MSG_NOSIGNAL;

		if (send) {
			struct timer_list ti;

			if (nbd->xmit_timeout) {
				init_timer(&ti);
				ti.function = nbd_xmit_timeout;
				ti.data = (unsigned long)current;
				ti.expires = jiffies + nbd->xmit_timeout;
				add_timer(&ti);
			}
			result = kernel_sendmsg(sock, &msg, &iov, 1, size);
			if (nbd->xmit_timeout)
				del_timer_sync(&ti);
		} else
			result = kernel_recvmsg(sock, &msg, &iov, 1, size,
						msg.msg_flags);

		if (signal_pending(current)) {
			siginfo_t info;
			printk(KERN_WARNING "nbd (pid %d: %s) got signal %d\n",
				task_pid_nr(current), current->comm,
				dequeue_signal_lock(current, &current->blocked, &info));
			result = -EINTR;
			sock_shutdown(nbd, !send);
			break;
		}

		if (result <= 0) {
			if (result == 0)
				result = -EPIPE; /* short read */
			break;
		}
		size -= result;
		buf += result;
	} while (size > 0);

	sigprocmask(SIG_SETMASK, &oldset, NULL);
	tsk_restore_flags(current, pflags, PF_MEMALLOC);

	return result;
}
Ejemplo n.º 4
0
asmlinkage void __do_softirq(void)
{
	struct softirq_action *h;
	__u32 pending;
	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
	int cpu;
	unsigned long old_flags = current->flags;
	int max_restart = MAX_SOFTIRQ_RESTART;

	/*
	 * Mask out PF_MEMALLOC s current task context is borrowed for the
	 * softirq. A softirq handled such as network RX might set PF_MEMALLOC
	 * again if the socket is related to swap
	 */
	current->flags &= ~PF_MEMALLOC;

	pending = local_softirq_pending();
	account_system_vtime(current);

	__local_bh_disable((unsigned long)__builtin_return_address(0),
				SOFTIRQ_OFFSET);
	lockdep_softirq_enter();

	cpu = smp_processor_id();
restart:
	/* Reset the pending bitmask before enabling irqs */
	set_softirq_pending(0);

	local_irq_enable();

	h = softirq_vec;

	do {
		if (pending & 1) {
			unsigned int vec_nr = h - softirq_vec;
			int prev_count = preempt_count();

			kstat_incr_softirqs_this_cpu(vec_nr);

			trace_softirq_entry(vec_nr);
			h->action(h);
			trace_softirq_exit(vec_nr);
			if (unlikely(prev_count != preempt_count())) {
				printk(KERN_ERR "huh, entered softirq %u %s %p"
				       "with preempt_count %08x,"
				       " exited with %08x?\n", vec_nr,
				       softirq_to_name[vec_nr], h->action,
				       prev_count, preempt_count());
				preempt_count_set(prev_count);
			}

			rcu_bh_qs(cpu);
		}
		h++;
		pending >>= 1;
	} while (pending);

	local_irq_disable();

	pending = local_softirq_pending();
	if (pending) {
		if (time_before(jiffies, end) && !need_resched() &&
		    --max_restart)
			goto restart;

		wakeup_softirqd();
	}

	lockdep_softirq_exit();

	account_system_vtime(current);
	__local_bh_enable(SOFTIRQ_OFFSET);
	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
}
Ejemplo n.º 5
0
asmlinkage void __do_softirq(void)
{
	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
	unsigned long old_flags = current->flags;
	int max_restart = MAX_SOFTIRQ_RESTART;
	struct softirq_action *h;
	bool in_hardirq;
	__u32 pending;
	int softirq_bit;
	int cpu;

	/*
	 * Mask out PF_MEMALLOC s current task context is borrowed for the
	 * softirq. A softirq handled such as network RX might set PF_MEMALLOC
	 * again if the socket is related to swap
	 */
	current->flags &= ~PF_MEMALLOC;

	pending = local_softirq_pending();
	account_irq_enter_time(current);

	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
	in_hardirq = lockdep_softirq_start();

	cpu = smp_processor_id();
restart:
	/* Reset the pending bitmask before enabling irqs */
	set_softirq_pending(0);

	local_irq_enable();

	h = softirq_vec;

	while ((softirq_bit = ffs(pending))) {
		unsigned int vec_nr;
		int prev_count;

		h += softirq_bit - 1;

		vec_nr = h - softirq_vec;
		prev_count = preempt_count();

		kstat_incr_softirqs_this_cpu(vec_nr);

		trace_softirq_entry(vec_nr);
		h->action(h);
		trace_softirq_exit(vec_nr);
		if (unlikely(prev_count != preempt_count())) {
			pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n",
			       vec_nr, softirq_to_name[vec_nr], h->action,
			       prev_count, preempt_count());
			preempt_count_set(prev_count);
		}
		rcu_bh_qs(cpu);
		h++;
		pending >>= softirq_bit;
	}

	local_irq_disable();

	pending = local_softirq_pending();
	if (pending) {
		if (time_before(jiffies, end) && !need_resched() &&
		    --max_restart)
			goto restart;

		wakeup_softirqd();
	}

	lockdep_softirq_end(in_hardirq);
	account_irq_exit_time(current);
	__local_bh_enable(SOFTIRQ_OFFSET);
	WARN_ON_ONCE(in_interrupt());
	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
}
Ejemplo n.º 6
0
/**
 * iscsi_sw_tcp_xmit_segment - transmit segment
 * @tcp_conn: the iSCSI TCP connection
 * @segment: the buffer to transmnit
 *
 * This function transmits as much of the buffer as
 * the network layer will accept, and returns the number of
 * bytes transmitted.
 *
 * If CRC hashing is enabled, the function will compute the
 * hash as it goes. When the entire segment has been transmitted,
 * it will retrieve the hash value and send it as well.
 */
static int iscsi_sw_tcp_xmit_segment(struct iscsi_tcp_conn *tcp_conn,
				     struct iscsi_segment *segment)
{
	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
	struct socket *sk = tcp_sw_conn->sock;
	unsigned int copied = 0;
	int r = 0;

	while (!iscsi_tcp_segment_done(tcp_conn, segment, 0, r)) {
		struct scatterlist *sg;
		unsigned int offset, copy;
		int flags = 0;

		r = 0;
		offset = segment->copied;
		copy = segment->size - offset;

		if (segment->total_copied + segment->size < segment->total_size)
			flags |= MSG_MORE;

		/* Use sendpage if we can; else fall back to sendmsg */
		if (!segment->data) {
			sg = segment->sg;
			offset += segment->sg_offset + sg->offset;
			r = tcp_sw_conn->sendpage(sk, sg_page(sg), offset,
						  copy, flags);
		} else {
			struct msghdr msg = { .msg_flags = flags };
			struct kvec iov = {
				.iov_base = segment->data + offset,
				.iov_len = copy
			};

			r = kernel_sendmsg(sk, &msg, &iov, 1, copy);
		}

		if (r < 0) {
			iscsi_tcp_segment_unmap(segment);
			return r;
		}
		copied += r;
	}
	return copied;
}

/**
 * iscsi_sw_tcp_xmit - TCP transmit
 **/
static int iscsi_sw_tcp_xmit(struct iscsi_conn *conn)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
	struct iscsi_segment *segment = &tcp_sw_conn->out.segment;
	unsigned int consumed = 0;
	int rc = 0;

	while (1) {
		rc = iscsi_sw_tcp_xmit_segment(tcp_conn, segment);
		/*
		 * We may not have been able to send data because the conn
		 * is getting stopped. libiscsi will know so propagate err
		 * for it to do the right thing.
		 */
		if (rc == -EAGAIN)
			return rc;
		else if (rc < 0) {
			rc = ISCSI_ERR_XMIT_FAILED;
			goto error;
		} else if (rc == 0)
			break;

		consumed += rc;

		if (segment->total_copied >= segment->total_size) {
			if (segment->done != NULL) {
				rc = segment->done(tcp_conn, segment);
				if (rc != 0)
					goto error;
			}
		}
	}

	ISCSI_SW_TCP_DBG(conn, "xmit %d bytes\n", consumed);

	conn->txdata_octets += consumed;
	return consumed;

error:
	/* Transmit error. We could initiate error recovery
	 * here. */
	ISCSI_SW_TCP_DBG(conn, "Error sending PDU, errno=%d\n", rc);
	iscsi_conn_failure(conn, rc);
	return -EIO;
}

/**
 * iscsi_tcp_xmit_qlen - return the number of bytes queued for xmit
 */
static inline int iscsi_sw_tcp_xmit_qlen(struct iscsi_conn *conn)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
	struct iscsi_segment *segment = &tcp_sw_conn->out.segment;

	return segment->total_copied - segment->total_size;
}

static int iscsi_sw_tcp_pdu_xmit(struct iscsi_task *task)
{
	struct iscsi_conn *conn = task->conn;
	unsigned long pflags = current->flags;
	int rc = 0;

	current->flags |= PF_MEMALLOC;

	while (iscsi_sw_tcp_xmit_qlen(conn)) {
		rc = iscsi_sw_tcp_xmit(conn);
		if (rc == 0) {
			rc = -EAGAIN;
			break;
		}
		if (rc < 0)
			break;
		rc = 0;
	}

	tsk_restore_flags(current, pflags, PF_MEMALLOC);
	return rc;
}

/*
 * This is called when we're done sending the header.
 * Simply copy the data_segment to the send segment, and return.
 */
static int iscsi_sw_tcp_send_hdr_done(struct iscsi_tcp_conn *tcp_conn,
				      struct iscsi_segment *segment)
{
	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;

	tcp_sw_conn->out.segment = tcp_sw_conn->out.data_segment;
	ISCSI_SW_TCP_DBG(tcp_conn->iscsi_conn,
			 "Header done. Next segment size %u total_size %u\n",
			 tcp_sw_conn->out.segment.size,
			 tcp_sw_conn->out.segment.total_size);
	return 0;
}

static void iscsi_sw_tcp_send_hdr_prep(struct iscsi_conn *conn, void *hdr,
				       size_t hdrlen)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;

	ISCSI_SW_TCP_DBG(conn, "%s\n", conn->hdrdgst_en ?
			 "digest enabled" : "digest disabled");

	/* Clear the data segment - needs to be filled in by the
	 * caller using iscsi_tcp_send_data_prep() */
	memset(&tcp_sw_conn->out.data_segment, 0,
	       sizeof(struct iscsi_segment));

	/* If header digest is enabled, compute the CRC and
	 * place the digest into the same buffer. We make
	 * sure that both iscsi_tcp_task and mtask have
	 * sufficient room.
	 */
	if (conn->hdrdgst_en) {
		iscsi_tcp_dgst_header(&tcp_sw_conn->tx_hash, hdr, hdrlen,
				      hdr + hdrlen);
		hdrlen += ISCSI_DIGEST_SIZE;
	}

	/* Remember header pointer for later, when we need
	 * to decide whether there's a payload to go along
	 * with the header. */
	tcp_sw_conn->out.hdr = hdr;

	iscsi_segment_init_linear(&tcp_sw_conn->out.segment, hdr, hdrlen,
				  iscsi_sw_tcp_send_hdr_done, NULL);
}

/*
 * Prepare the send buffer for the payload data.
 * Padding and checksumming will all be taken care
 * of by the iscsi_segment routines.
 */
static int
iscsi_sw_tcp_send_data_prep(struct iscsi_conn *conn, struct scatterlist *sg,
			    unsigned int count, unsigned int offset,
			    unsigned int len)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
	struct hash_desc *tx_hash = NULL;
	unsigned int hdr_spec_len;

	ISCSI_SW_TCP_DBG(conn, "offset=%d, datalen=%d %s\n", offset, len,
			 conn->datadgst_en ?
			 "digest enabled" : "digest disabled");

	/* Make sure the datalen matches what the caller
	   said he would send. */
	hdr_spec_len = ntoh24(tcp_sw_conn->out.hdr->dlength);
	WARN_ON(iscsi_padded(len) != iscsi_padded(hdr_spec_len));

	if (conn->datadgst_en)
		tx_hash = &tcp_sw_conn->tx_hash;

	return iscsi_segment_seek_sg(&tcp_sw_conn->out.data_segment,
				     sg, count, offset, len,
				     NULL, tx_hash);
}

static void
iscsi_sw_tcp_send_linear_data_prep(struct iscsi_conn *conn, void *data,
				   size_t len)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
	struct hash_desc *tx_hash = NULL;
	unsigned int hdr_spec_len;

	ISCSI_SW_TCP_DBG(conn, "datalen=%zd %s\n", len, conn->datadgst_en ?
			 "digest enabled" : "digest disabled");

	/* Make sure the datalen matches what the caller
	   said he would send. */
	hdr_spec_len = ntoh24(tcp_sw_conn->out.hdr->dlength);
	WARN_ON(iscsi_padded(len) != iscsi_padded(hdr_spec_len));

	if (conn->datadgst_en)
		tx_hash = &tcp_sw_conn->tx_hash;

	iscsi_segment_init_linear(&tcp_sw_conn->out.data_segment,
				data, len, NULL, tx_hash);
}

static int iscsi_sw_tcp_pdu_init(struct iscsi_task *task,
				 unsigned int offset, unsigned int count)
{
	struct iscsi_conn *conn = task->conn;
	int err = 0;

	iscsi_sw_tcp_send_hdr_prep(conn, task->hdr, task->hdr_len);

	if (!count)
		return 0;

	if (!task->sc)
		iscsi_sw_tcp_send_linear_data_prep(conn, task->data, count);
	else {
		struct scsi_data_buffer *sdb = scsi_out(task->sc);

		err = iscsi_sw_tcp_send_data_prep(conn, sdb->table.sgl,
						  sdb->table.nents, offset,
						  count);
	}

	if (err) {
		/* got invalid offset/len */
		return -EIO;
	}
	return 0;
}

static int iscsi_sw_tcp_pdu_alloc(struct iscsi_task *task, uint8_t opcode)
{
	struct iscsi_tcp_task *tcp_task = task->dd_data;

	task->hdr = task->dd_data + sizeof(*tcp_task);
	task->hdr_max = sizeof(struct iscsi_sw_tcp_hdrbuf) - ISCSI_DIGEST_SIZE;
	return 0;
}

static struct iscsi_cls_conn *
iscsi_sw_tcp_conn_create(struct iscsi_cls_session *cls_session,
			 uint32_t conn_idx)
{
	struct iscsi_conn *conn;
	struct iscsi_cls_conn *cls_conn;
	struct iscsi_tcp_conn *tcp_conn;
	struct iscsi_sw_tcp_conn *tcp_sw_conn;

	cls_conn = iscsi_tcp_conn_setup(cls_session, sizeof(*tcp_sw_conn),
					conn_idx);
	if (!cls_conn)
		return NULL;
	conn = cls_conn->dd_data;
	tcp_conn = conn->dd_data;
	tcp_sw_conn = tcp_conn->dd_data;

	tcp_sw_conn->tx_hash.tfm = crypto_alloc_hash("crc32c", 0,
						     CRYPTO_ALG_ASYNC);
	tcp_sw_conn->tx_hash.flags = 0;
	if (IS_ERR(tcp_sw_conn->tx_hash.tfm))
		goto free_conn;

	tcp_sw_conn->rx_hash.tfm = crypto_alloc_hash("crc32c", 0,
						     CRYPTO_ALG_ASYNC);
	tcp_sw_conn->rx_hash.flags = 0;
	if (IS_ERR(tcp_sw_conn->rx_hash.tfm))
		goto free_tx_tfm;
	tcp_conn->rx_hash = &tcp_sw_conn->rx_hash;

	return cls_conn;

free_tx_tfm:
	crypto_free_hash(tcp_sw_conn->tx_hash.tfm);
free_conn:
	iscsi_conn_printk(KERN_ERR, conn,
			  "Could not create connection due to crc32c "
			  "loading error. Make sure the crc32c "
			  "module is built as a module or into the "
			  "kernel\n");
	iscsi_tcp_conn_teardown(cls_conn);
	return NULL;
}

static void iscsi_sw_tcp_release_conn(struct iscsi_conn *conn)
{
	struct iscsi_session *session = conn->session;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
	struct socket *sock = tcp_sw_conn->sock;

	if (!sock)
		return;

	sock_hold(sock->sk);
	iscsi_sw_tcp_conn_restore_callbacks(conn);
	sock_put(sock->sk);

	spin_lock_bh(&session->frwd_lock);
	tcp_sw_conn->sock = NULL;
	spin_unlock_bh(&session->frwd_lock);
	sockfd_put(sock);
}

static void iscsi_sw_tcp_conn_destroy(struct iscsi_cls_conn *cls_conn)
{
	struct iscsi_conn *conn = cls_conn->dd_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;

	iscsi_sw_tcp_release_conn(conn);

	if (tcp_sw_conn->tx_hash.tfm)
		crypto_free_hash(tcp_sw_conn->tx_hash.tfm);
	if (tcp_sw_conn->rx_hash.tfm)
		crypto_free_hash(tcp_sw_conn->rx_hash.tfm);

	iscsi_tcp_conn_teardown(cls_conn);
}

static void iscsi_sw_tcp_conn_stop(struct iscsi_cls_conn *cls_conn, int flag)
{
	struct iscsi_conn *conn = cls_conn->dd_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
	struct socket *sock = tcp_sw_conn->sock;

	/* userspace may have goofed up and not bound us */
	if (!sock)
		return;

	sock->sk->sk_err = EIO;
	wake_up_interruptible(sk_sleep(sock->sk));

	/* stop xmit side */
	iscsi_suspend_tx(conn);

	/* stop recv side and release socket */
	iscsi_sw_tcp_release_conn(conn);

	iscsi_conn_stop(cls_conn, flag);
}

static int
iscsi_sw_tcp_conn_bind(struct iscsi_cls_session *cls_session,
		       struct iscsi_cls_conn *cls_conn, uint64_t transport_eph,
		       int is_leading)
{
	struct iscsi_session *session = cls_session->dd_data;
	struct iscsi_conn *conn = cls_conn->dd_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
	struct sock *sk;
	struct socket *sock;
	int err;

	/* lookup for existing socket */
	sock = sockfd_lookup((int)transport_eph, &err);
	if (!sock) {
		iscsi_conn_printk(KERN_ERR, conn,
				  "sockfd_lookup failed %d\n", err);
		return -EEXIST;
	}

	err = iscsi_conn_bind(cls_session, cls_conn, is_leading);
	if (err)
		goto free_socket;

	spin_lock_bh(&session->frwd_lock);
	/* bind iSCSI connection and socket */
	tcp_sw_conn->sock = sock;
	spin_unlock_bh(&session->frwd_lock);

	/* setup Socket parameters */
	sk = sock->sk;
	sk->sk_reuse = SK_CAN_REUSE;
	sk->sk_sndtimeo = 15 * HZ; /* FIXME: make it configurable */
	sk->sk_allocation = GFP_ATOMIC;
	sk_set_memalloc(sk);

	iscsi_sw_tcp_conn_set_callbacks(conn);
	tcp_sw_conn->sendpage = tcp_sw_conn->sock->ops->sendpage;
	/*
	 * set receive state machine into initial state
	 */
	iscsi_tcp_hdr_recv_prep(tcp_conn);
	return 0;

free_socket:
	sockfd_put(sock);
	return err;
}

static int iscsi_sw_tcp_conn_set_param(struct iscsi_cls_conn *cls_conn,
				       enum iscsi_param param, char *buf,
				       int buflen)
{
	struct iscsi_conn *conn = cls_conn->dd_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;

	switch(param) {
	case ISCSI_PARAM_HDRDGST_EN:
		iscsi_set_param(cls_conn, param, buf, buflen);
		break;
	case ISCSI_PARAM_DATADGST_EN:
		iscsi_set_param(cls_conn, param, buf, buflen);
		tcp_sw_conn->sendpage = conn->datadgst_en ?
			sock_no_sendpage : tcp_sw_conn->sock->ops->sendpage;
		break;
	case ISCSI_PARAM_MAX_R2T:
		return iscsi_tcp_set_max_r2t(conn, buf);
	default:
		return iscsi_set_param(cls_conn, param, buf, buflen);
	}

	return 0;
}

static int iscsi_sw_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn,
				       enum iscsi_param param, char *buf)
{
	struct iscsi_conn *conn = cls_conn->dd_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
	struct sockaddr_in6 addr;
	int rc, len;

	switch(param) {
	case ISCSI_PARAM_CONN_PORT:
	case ISCSI_PARAM_CONN_ADDRESS:
		spin_lock_bh(&conn->session->frwd_lock);
		if (!tcp_sw_conn || !tcp_sw_conn->sock) {
			spin_unlock_bh(&conn->session->frwd_lock);
			return -ENOTCONN;
		}
		rc = kernel_getpeername(tcp_sw_conn->sock,
					(struct sockaddr *)&addr, &len);
		spin_unlock_bh(&conn->session->frwd_lock);
		if (rc)
			return rc;

		return iscsi_conn_get_addr_param((struct sockaddr_storage *)
						 &addr, param, buf);
	default:
		return iscsi_conn_get_param(cls_conn, param, buf);
	}

	return 0;
}

static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost,
				       enum iscsi_host_param param, char *buf)
{
	struct iscsi_sw_tcp_host *tcp_sw_host = iscsi_host_priv(shost);
	struct iscsi_session *session = tcp_sw_host->session;
	struct iscsi_conn *conn;
	struct iscsi_tcp_conn *tcp_conn;
	struct iscsi_sw_tcp_conn *tcp_sw_conn;
	struct sockaddr_in6 addr;
	int rc, len;

	switch (param) {
	case ISCSI_HOST_PARAM_IPADDRESS:
		if (!session)
			return -ENOTCONN;

		spin_lock_bh(&session->frwd_lock);
		conn = session->leadconn;
		if (!conn) {
			spin_unlock_bh(&session->frwd_lock);
			return -ENOTCONN;
		}
		tcp_conn = conn->dd_data;

		tcp_sw_conn = tcp_conn->dd_data;
		if (!tcp_sw_conn->sock) {
			spin_unlock_bh(&session->frwd_lock);
			return -ENOTCONN;
		}

		rc = kernel_getsockname(tcp_sw_conn->sock,
					(struct sockaddr *)&addr, &len);
		spin_unlock_bh(&session->frwd_lock);
		if (rc)
			return rc;

		return iscsi_conn_get_addr_param((struct sockaddr_storage *)
						 &addr, param, buf);
	default:
		return iscsi_host_get_param(shost, param, buf);
	}

	return 0;
}

static void
iscsi_sw_tcp_conn_get_stats(struct iscsi_cls_conn *cls_conn,
			    struct iscsi_stats *stats)
{
	struct iscsi_conn *conn = cls_conn->dd_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;

	stats->custom_length = 3;
	strcpy(stats->custom[0].desc, "tx_sendpage_failures");
	stats->custom[0].value = tcp_sw_conn->sendpage_failures_cnt;
	strcpy(stats->custom[1].desc, "rx_discontiguous_hdr");
	stats->custom[1].value = tcp_sw_conn->discontiguous_hdr_cnt;
	strcpy(stats->custom[2].desc, "eh_abort_cnt");
	stats->custom[2].value = conn->eh_abort_cnt;

	iscsi_tcp_conn_get_stats(cls_conn, stats);
}

static struct iscsi_cls_session *
iscsi_sw_tcp_session_create(struct iscsi_endpoint *ep, uint16_t cmds_max,
			    uint16_t qdepth, uint32_t initial_cmdsn)
{
	struct iscsi_cls_session *cls_session;
	struct iscsi_session *session;
	struct iscsi_sw_tcp_host *tcp_sw_host;
	struct Scsi_Host *shost;

	if (ep) {
		printk(KERN_ERR "iscsi_tcp: invalid ep %p.\n", ep);
		return NULL;
	}

	shost = iscsi_host_alloc(&iscsi_sw_tcp_sht,
				 sizeof(struct iscsi_sw_tcp_host), 1);
	if (!shost)
		return NULL;
	shost->transportt = iscsi_sw_tcp_scsi_transport;
	shost->cmd_per_lun = qdepth;
	shost->max_lun = iscsi_max_lun;
	shost->max_id = 0;
	shost->max_channel = 0;
	shost->max_cmd_len = SCSI_MAX_VARLEN_CDB_SIZE;

	if (iscsi_host_add(shost, NULL))
		goto free_host;

	cls_session = iscsi_session_setup(&iscsi_sw_tcp_transport, shost,
					  cmds_max, 0,
					  sizeof(struct iscsi_tcp_task) +
					  sizeof(struct iscsi_sw_tcp_hdrbuf),
					  initial_cmdsn, 0);
	if (!cls_session)
		goto remove_host;
	session = cls_session->dd_data;
	tcp_sw_host = iscsi_host_priv(shost);
	tcp_sw_host->session = session;

	shost->can_queue = session->scsi_cmds_max;
	if (iscsi_tcp_r2tpool_alloc(session))
		goto remove_session;
	return cls_session;

remove_session:
	iscsi_session_teardown(cls_session);
remove_host:
	iscsi_host_remove(shost);
free_host:
	iscsi_host_free(shost);
	return NULL;
}

static void iscsi_sw_tcp_session_destroy(struct iscsi_cls_session *cls_session)
{
	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);

	iscsi_tcp_r2tpool_free(cls_session->dd_data);
	iscsi_session_teardown(cls_session);

	iscsi_host_remove(shost);
	iscsi_host_free(shost);
}

static umode_t iscsi_sw_tcp_attr_is_visible(int param_type, int param)
{
	switch (param_type) {
	case ISCSI_HOST_PARAM:
		switch (param) {
		case ISCSI_HOST_PARAM_NETDEV_NAME:
		case ISCSI_HOST_PARAM_HWADDRESS:
		case ISCSI_HOST_PARAM_IPADDRESS:
		case ISCSI_HOST_PARAM_INITIATOR_NAME:
			return S_IRUGO;
		default:
			return 0;
		}
	case ISCSI_PARAM:
		switch (param) {
		case ISCSI_PARAM_MAX_RECV_DLENGTH:
		case ISCSI_PARAM_MAX_XMIT_DLENGTH:
		case ISCSI_PARAM_HDRDGST_EN:
		case ISCSI_PARAM_DATADGST_EN:
		case ISCSI_PARAM_CONN_ADDRESS:
		case ISCSI_PARAM_CONN_PORT:
		case ISCSI_PARAM_EXP_STATSN:
		case ISCSI_PARAM_PERSISTENT_ADDRESS:
		case ISCSI_PARAM_PERSISTENT_PORT:
		case ISCSI_PARAM_PING_TMO:
		case ISCSI_PARAM_RECV_TMO:
		case ISCSI_PARAM_INITIAL_R2T_EN:
		case ISCSI_PARAM_MAX_R2T:
		case ISCSI_PARAM_IMM_DATA_EN:
		case ISCSI_PARAM_FIRST_BURST:
		case ISCSI_PARAM_MAX_BURST:
		case ISCSI_PARAM_PDU_INORDER_EN:
		case ISCSI_PARAM_DATASEQ_INORDER_EN:
		case ISCSI_PARAM_ERL:
		case ISCSI_PARAM_TARGET_NAME:
		case ISCSI_PARAM_TPGT:
		case ISCSI_PARAM_USERNAME:
		case ISCSI_PARAM_PASSWORD:
		case ISCSI_PARAM_USERNAME_IN:
		case ISCSI_PARAM_PASSWORD_IN:
		case ISCSI_PARAM_FAST_ABORT:
		case ISCSI_PARAM_ABORT_TMO:
		case ISCSI_PARAM_LU_RESET_TMO:
		case ISCSI_PARAM_TGT_RESET_TMO:
		case ISCSI_PARAM_IFACE_NAME:
		case ISCSI_PARAM_INITIATOR_NAME:
			return S_IRUGO;
		default:
			return 0;
		}
	}

	return 0;
}

static int iscsi_sw_tcp_slave_alloc(struct scsi_device *sdev)
{
	set_bit(QUEUE_FLAG_BIDI, &sdev->request_queue->queue_flags);
	return 0;
}