iscsi_tcp.c

	 * Use rd_desc to pass 'conn' to iscsi_tcp_data_recv.
	 * We set count to 1 because we want the network layer to
	 * hand us all the skbs that are available. iscsi_tcp_data_recv
	 * handled pdus that cross buffers or pdus that still need data.
	 */
	rd_desc.arg.data = conn;
	rd_desc.count = 1;
	tcp_read_sock(sk, &rd_desc, iscsi_tcp_data_recv);

	read_unlock(&sk->sk_callback_lock);
}

static void
iscsi_tcp_state_change(struct sock *sk)
{
	struct iscsi_tcp_conn *tcp_conn;
	struct iscsi_conn *conn;
	struct iscsi_session *session;
	void (*old_state_change)(struct sock *);

	read_lock(&sk->sk_callback_lock);

	conn = (struct iscsi_conn*)sk->sk_user_data;
	session = conn->session;

	if ((sk->sk_state == TCP_CLOSE_WAIT ||
	     sk->sk_state == TCP_CLOSE) &&
	    !atomic_read(&sk->sk_rmem_alloc)) {
		debug_tcp("iscsi_tcp_state_change: TCP_CLOSE|TCP_CLOSE_WAIT\n");
		iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
	}

	tcp_conn = conn->dd_data;
	old_state_change = tcp_conn->old_state_change;

	read_unlock(&sk->sk_callback_lock);

	old_state_change(sk);
}

/**
 * iscsi_write_space - Called when more output buffer space is available
 * @sk: socket space is available for
 **/
static void
iscsi_write_space(struct sock *sk)
{
	struct iscsi_conn *conn = (struct iscsi_conn*)sk->sk_user_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;

	tcp_conn->old_write_space(sk);
	debug_tcp("iscsi_write_space: cid %d\n", conn->id);
	scsi_queue_work(conn->session->host, &conn->xmitwork);
}

static void
iscsi_conn_set_callbacks(struct iscsi_conn *conn)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct sock *sk = tcp_conn->sock->sk;

	/* assign new callbacks */
	write_lock_bh(&sk->sk_callback_lock);
	sk->sk_user_data = conn;
	tcp_conn->old_data_ready = sk->sk_data_ready;
	tcp_conn->old_state_change = sk->sk_state_change;
	tcp_conn->old_write_space = sk->sk_write_space;
	sk->sk_data_ready = iscsi_tcp_data_ready;
	sk->sk_state_change = iscsi_tcp_state_change;
	sk->sk_write_space = iscsi_write_space;
	write_unlock_bh(&sk->sk_callback_lock);
}

static void
iscsi_conn_restore_callbacks(struct iscsi_tcp_conn *tcp_conn)
{
	struct sock *sk = tcp_conn->sock->sk;

	/* restore socket callbacks, see also: iscsi_conn_set_callbacks() */
	write_lock_bh(&sk->sk_callback_lock);
	sk->sk_user_data    = NULL;
	sk->sk_data_ready   = tcp_conn->old_data_ready;
	sk->sk_state_change = tcp_conn->old_state_change;
	sk->sk_write_space  = tcp_conn->old_write_space;
	sk->sk_no_check	 = 0;
	write_unlock_bh(&sk->sk_callback_lock);
}

/**
 * iscsi_send - generic send routine
 * @sk: kernel's socket
 * @buf: buffer to write from
 * @size: actual size to write
 * @flags: socket's flags
 */
static inline int
iscsi_send(struct iscsi_conn *conn, struct iscsi_buf *buf, int size, int flags)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct socket *sk = tcp_conn->sock;
	int offset = buf->sg.offset + buf->sent, res;

	/*
	 * if we got use_sg=0 or are sending something we kmallocd
	 * then we did not have to do kmap (kmap returns page_address)
	 *
	 * if we got use_sg > 0, but had to drop down, we do not
	 * set clustering so this should only happen for that
	 * slab case.
	 */
	if (buf->use_sendmsg)
		res = sock_no_sendpage(sk, buf->sg.page, offset, size, flags);
	else
		res = tcp_conn->sendpage(sk, buf->sg.page, offset, size, flags);

	if (res >= 0) {
		conn->txdata_octets += res;
		buf->sent += res;
		return res;
	}

	tcp_conn->sendpage_failures_cnt++;
	if (res == -EAGAIN)
		res = -ENOBUFS;
	else
		iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
	return res;
}

/**
 * iscsi_sendhdr - send PDU Header via tcp_sendpage()
 * @conn: iscsi connection
 * @buf: buffer to write from
 * @datalen: lenght of data to be sent after the header
 *
 * Notes:
 *	(Tx, Fast Path)
 **/
static inline int
iscsi_sendhdr(struct iscsi_conn *conn, struct iscsi_buf *buf, int datalen)
{
	int flags = 0; /* MSG_DONTWAIT; */
	int res, size;

	size = buf->sg.length - buf->sent;
	BUG_ON(buf->sent + size > buf->sg.length);
	if (buf->sent + size != buf->sg.length || datalen)
		flags |= MSG_MORE;

	res = iscsi_send(conn, buf, size, flags);
	debug_tcp("sendhdr %d bytes, sent %d res %d\n", size, buf->sent, res);
	if (res >= 0) {
		if (size != res)
			return -EAGAIN;
		return 0;
	}

	return res;
}

/**
 * iscsi_sendpage - send one page of iSCSI Data-Out.
 * @conn: iscsi connection
 * @buf: buffer to write from
 * @count: remaining data
 * @sent: number of bytes sent
 *
 * Notes:
 *	(Tx, Fast Path)
 **/
static inline int
iscsi_sendpage(struct iscsi_conn *conn, struct iscsi_buf *buf,
	       int *count, int *sent)
{
	int flags = 0; /* MSG_DONTWAIT; */
	int res, size;

	size = buf->sg.length - buf->sent;
	BUG_ON(buf->sent + size > buf->sg.length);
	if (size > *count)
		size = *count;
	if (buf->sent + size != buf->sg.length || *count != size)
		flags |= MSG_MORE;

	res = iscsi_send(conn, buf, size, flags);
	debug_tcp("sendpage: %d bytes, sent %d left %d sent %d res %d\n",
		  size, buf->sent, *count, *sent, res);
	if (res >= 0) {
		*count -= res;
		*sent += res;
		if (size != res)
			return -EAGAIN;
		return 0;
	}

	return res;
}

static inline void
iscsi_data_digest_init(struct iscsi_tcp_conn *tcp_conn,
		      struct iscsi_tcp_cmd_task *tcp_ctask)
{
	crypto_hash_init(&tcp_conn->tx_hash);
	tcp_ctask->digest_count = 4;
}

/**
 * iscsi_solicit_data_cont - initialize next Data-Out
 * @conn: iscsi connection
 * @ctask: scsi command task
 * @r2t: R2T info
 * @left: bytes left to transfer
 *
 * Notes:
 *	Initialize next Data-Out within this R2T sequence and continue
 *	to process next Scatter-Gather element(if any) of this SCSI command.
 *
 *	Called under connection lock.
 **/
static void
iscsi_solicit_data_cont(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask,
			struct iscsi_r2t_info *r2t, int left)
{
	struct iscsi_data *hdr;
	struct scsi_cmnd *sc = ctask->sc;
	int new_offset;

	hdr = &r2t->dtask.hdr;
	memset(hdr, 0, sizeof(struct iscsi_data));
	hdr->ttt = r2t->ttt;
	hdr->datasn = cpu_to_be32(r2t->solicit_datasn);
	r2t->solicit_datasn++;
	hdr->opcode = ISCSI_OP_SCSI_DATA_OUT;
	memcpy(hdr->lun, ctask->hdr->lun, sizeof(hdr->lun));
	hdr->itt = ctask->hdr->itt;
	hdr->exp_statsn = r2t->exp_statsn;
	new_offset = r2t->data_offset + r2t->sent;
	hdr->offset = cpu_to_be32(new_offset);
	if (left > conn->max_xmit_dlength) {
		hton24(hdr->dlength, conn->max_xmit_dlength);
		r2t->data_count = conn->max_xmit_dlength;
	} else {
		hton24(hdr->dlength, left);
		r2t->data_count = left;
		hdr->flags = ISCSI_FLAG_CMD_FINAL;
	}
	conn->dataout_pdus_cnt++;

	iscsi_buf_init_iov(&r2t->headbuf, (char*)hdr,
			   sizeof(struct iscsi_hdr));

	if (iscsi_buf_left(&r2t->sendbuf))
		return;

	if (sc->use_sg) {
		iscsi_buf_init_sg(&r2t->sendbuf, r2t->sg);
		r2t->sg += 1;
	} else {
		iscsi_buf_init_iov(&r2t->sendbuf,
			    (char*)sc->request_buffer + new_offset,
			    r2t->data_count);
		r2t->sg = NULL;
	}
}

static void iscsi_set_padding(struct iscsi_tcp_cmd_task *tcp_ctask,
			      unsigned long len)
{
	tcp_ctask->pad_count = len & (ISCSI_PAD_LEN - 1);
	if (!tcp_ctask->pad_count)
		return;

	tcp_ctask->pad_count = ISCSI_PAD_LEN - tcp_ctask->pad_count;
	debug_scsi("write padding %d bytes\n", tcp_ctask->pad_count);
	tcp_ctask->xmstate |= XMSTATE_W_PAD;
}

/**
 * iscsi_tcp_cmd_init - Initialize iSCSI SCSI_READ or SCSI_WRITE commands
 * @conn: iscsi connection
 * @ctask: scsi command task
 * @sc: scsi command
 **/
static void
iscsi_tcp_cmd_init(struct iscsi_cmd_task *ctask)
{
	struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;

	BUG_ON(__kfifo_len(tcp_ctask->r2tqueue));
	tcp_ctask->xmstate = XMSTATE_CMD_HDR_INIT;
}

/**
 * iscsi_tcp_mtask_xmit - xmit management(immediate) task
 * @conn: iscsi connection
 * @mtask: task management task
 *
 * Notes:
 *	The function can return -EAGAIN in which case caller must
 *	call it again later, or recover. '0' return code means successful
 *	xmit.
 *
 *	Management xmit state machine consists of these states:
 *		XMSTATE_IMM_HDR_INIT	- calculate digest of PDU Header
 *		XMSTATE_IMM_HDR 	- PDU Header xmit in progress
 *		XMSTATE_IMM_DATA 	- PDU Data xmit in progress
 *		XMSTATE_IDLE		- management PDU is done
 **/
static int
iscsi_tcp_mtask_xmit(struct iscsi_conn *conn, struct iscsi_mgmt_task *mtask)
{
	struct iscsi_tcp_mgmt_task *tcp_mtask = mtask->dd_data;
	int rc;

	debug_scsi("mtask deq [cid %d state %x itt 0x%x]\n",
		conn->id, tcp_mtask->xmstate, mtask->itt);

	if (tcp_mtask->xmstate & XMSTATE_IMM_HDR_INIT) {
		iscsi_buf_init_iov(&tcp_mtask->headbuf, (char*)mtask->hdr,
				   sizeof(struct iscsi_hdr));

		if (mtask->data_count) {
			tcp_mtask->xmstate |= XMSTATE_IMM_DATA;
			iscsi_buf_init_iov(&tcp_mtask->sendbuf,
					   (char*)mtask->data,
					   mtask->data_count);
		}

		if (conn->c_stage != ISCSI_CONN_INITIAL_STAGE &&
		    conn->stop_stage != STOP_CONN_RECOVER &&
		    conn->hdrdgst_en)
			iscsi_hdr_digest(conn, &tcp_mtask->headbuf,
					(u8*)tcp_mtask->hdrext);

		tcp_mtask->sent = 0;
		tcp_mtask->xmstate &= ~XMSTATE_IMM_HDR_INIT;
		tcp_mtask->xmstate |= XMSTATE_IMM_HDR;
	}

	if (tcp_mtask->xmstate & XMSTATE_IMM_HDR) {
		rc = iscsi_sendhdr(conn, &tcp_mtask->headbuf,
				   mtask->data_count);
		if (rc)
			return rc;
		tcp_mtask->xmstate &= ~XMSTATE_IMM_HDR;
	}

	if (tcp_mtask->xmstate & XMSTATE_IMM_DATA) {
		BUG_ON(!mtask->data_count);
		tcp_mtask->xmstate &= ~XMSTATE_IMM_DATA;
		/* FIXME: implement.
		 * Virtual buffer could be spreaded across multiple pages...
		 */
		do {
			int rc;

			rc = iscsi_sendpage(conn, &tcp_mtask->sendbuf,
					&mtask->data_count, &tcp_mtask->sent);
			if (rc) {
				tcp_mtask->xmstate |= XMSTATE_IMM_DATA;
				return rc;
			}
		} while (mtask->data_count);
	}

	BUG_ON(tcp_mtask->xmstate != XMSTATE_IDLE);
	if (mtask->hdr->itt == RESERVED_ITT) {
		struct iscsi_session *session = conn->session;

		spin_lock_bh(&session->lock);
		list_del(&conn->mtask->running);
		__kfifo_put(session->mgmtpool.queue, (void*)&conn->mtask,
			    sizeof(void*));
		spin_unlock_bh(&session->lock);
	}
	return 0;
}

static int
iscsi_send_cmd_hdr(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
{
	struct scsi_cmnd *sc = ctask->sc;
	struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;
	int rc = 0;

	if (tcp_ctask->xmstate & XMSTATE_CMD_HDR_INIT) {
		tcp_ctask->sent = 0;
		tcp_ctask->sg_count = 0;
		tcp_ctask->exp_datasn = 0;

		if (sc->sc_data_direction == DMA_TO_DEVICE) {
			if (sc->use_sg) {
				struct scatterlist *sg = sc->request_buffer;

				iscsi_buf_init_sg(&tcp_ctask->sendbuf, sg);
				tcp_ctask->sg = sg + 1;
				tcp_ctask->bad_sg = sg + sc->use_sg;
			} else {
				iscsi_buf_init_iov(&tcp_ctask->sendbuf,
						   sc->request_buffer,
						   sc->request_bufflen);
				tcp_ctask->sg = NULL;
				tcp_ctask->bad_sg = NULL;
			}

			debug_scsi("cmd [itt 0x%x total %d imm_data %d "
				   "unsol count %d, unsol offset %d]\n",
				   ctask->itt, sc->request_bufflen,
				   ctask->imm_count, ctask->unsol_count,
				   ctask->unsol_offset);
		}

		iscsi_buf_init_iov(&tcp_ctask->headbuf, (char*)ctask->hdr,
				  sizeof(struct iscsi_hdr));

		if (conn->hdrdgst_en)
			iscsi_hdr_digest(conn, &tcp_ctask->headbuf,
					 (u8*)tcp_ctask->hdrext);
		tcp_ctask->xmstate &= ~XMSTATE_CMD_HDR_INIT;
		tcp_ctask->xmstate |= XMSTATE_CMD_HDR_XMIT;
	}

	if (tcp_ctask->xmstate & XMSTATE_CMD_HDR_XMIT) {
		rc = iscsi_sendhdr(conn, &tcp_ctask->headbuf, ctask->imm_count);
		if (rc)
			return rc;
		tcp_ctask->xmstate &= ~XMSTATE_CMD_HDR_XMIT;

		if (sc->sc_data_direction != DMA_TO_DEVICE)
			return 0;

		if (ctask->imm_count) {
			tcp_ctask->xmstate |= XMSTATE_IMM_DATA;
			iscsi_set_padding(tcp_ctask, ctask->imm_count);

			if (ctask->conn->datadgst_en) {
				iscsi_data_digest_init(ctask->conn->dd_data,
						       tcp_ctask);
				tcp_ctask->immdigest = 0;
			}
		}

		if (ctask->unsol_count)
			tcp_ctask->xmstate |=
					XMSTATE_UNS_HDR | XMSTATE_UNS_INIT;
	}
	return rc;
}

static int
iscsi_send_padding(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
{
	struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	int sent = 0, rc;

	if (tcp_ctask->xmstate & XMSTATE_W_PAD) {
		iscsi_buf_init_iov(&tcp_ctask->sendbuf, (char*)&tcp_ctask->pad,
				   tcp_ctask->pad_count);
		if (conn->datadgst_en)
			crypto_hash_update(&tcp_conn->tx_hash,
					   &tcp_ctask->sendbuf.sg,
					   tcp_ctask->sendbuf.sg.length);
	} else if (!(tcp_ctask->xmstate & XMSTATE_W_RESEND_PAD))
		return 0;

	tcp_ctask->xmstate &= ~XMSTATE_W_PAD;
	tcp_ctask->xmstate &= ~XMSTATE_W_RESEND_PAD;
	debug_scsi("sending %d pad bytes for itt 0x%x\n",
		   tcp_ctask->pad_count, ctask->itt);
	rc = iscsi_sendpage(conn, &tcp_ctask->sendbuf, &tcp_ctask->pad_count,
			   &sent);
	if (rc) {
		debug_scsi("padding send failed %d\n", rc);
		tcp_ctask->xmstate |= XMSTATE_W_RESEND_PAD;
	}
	return rc;
}

static int
iscsi_send_digest(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask,
			struct iscsi_buf *buf, uint32_t *digest)
{
	struct iscsi_tcp_cmd_task *tcp_ctask;
	struct iscsi_tcp_conn *tcp_conn;
	int rc, sent = 0;

	if (!conn->datadgst_en)
		return 0;

	tcp_ctask = ctask->dd_data;
	tcp_conn = conn->dd_data;

	if (!(tcp_ctask->xmstate & XMSTATE_W_RESEND_DATA_DIGEST)) {
		crypto_hash_final(&tcp_conn->tx_hash, (u8*)digest);
		iscsi_buf_init_iov(buf, (char*)digest, 4);
	}
	tcp_ctask->xmstate &= ~XMSTATE_W_RESEND_DATA_DIGEST;

	rc = iscsi_sendpage(conn, buf, &tcp_ctask->digest_count, &sent);
	if (!rc)
		debug_scsi("sent digest 0x%x for itt 0x%x\n", *digest,
			  ctask->itt);
	else {
		debug_scsi("sending digest 0x%x failed for itt 0x%x!\n",
			  *digest, ctask->itt);
		tcp_ctask->xmstate |= XMSTATE_W_RESEND_DATA_DIGEST;
	}
	return rc;
}

static int
iscsi_send_data(struct iscsi_cmd_task *ctask, struct iscsi_buf *sendbuf,
		struct scatterlist **sg, int *sent, int *count,
		struct iscsi_buf *digestbuf, uint32_t *digest)
{
	struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;
	struct iscsi_conn *conn = ctask->conn;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	int rc, buf_sent, offset;

	while (*count) {
		buf_sent = 0;
		offset = sendbuf->sent;

		rc = iscsi_sendpage(conn, sendbuf, count, &buf_sent);
		*sent = *sent + buf_sent;
		if (buf_sent && conn->datadgst_en)
			partial_sg_digest_update(&tcp_conn->tx_hash,
				&sendbuf->sg, sendbuf->sg.offset + offset,
				buf_sent);
		if (!iscsi_buf_left(sendbuf) && *sg != tcp_ctask->bad_sg) {
			iscsi_buf_init_sg(sendbuf, *sg);
			*sg = *sg + 1;
		}

		if (rc)
			return rc;
	}

	rc = iscsi_send_padding(conn, ctask);
	if (rc)
		return rc;

	return iscsi_send_digest(conn, ctask, digestbuf, digest);
}

static int
iscsi_send_unsol_hdr(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
{
	struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;
	struct iscsi_data_task *dtask;
	int rc;

	tcp_ctask->xmstate |= XMSTATE_UNS_DATA;
	if (tcp_ctask->xmstate & XMSTATE_UNS_INIT) {
		dtask = &tcp_ctask->unsol_dtask;

		iscsi_prep_unsolicit_data_pdu(ctask, &dtask->hdr);
		iscsi_buf_init_iov(&tcp_ctask->headbuf, (char*)&dtask->hdr,
				   sizeof(struct iscsi_hdr));
		if (conn->hdrdgst_en)
			iscsi_hdr_digest(conn, &tcp_ctask->headbuf,
					(u8*)dtask->hdrext);

		tcp_ctask->xmstate &= ~XMSTATE_UNS_INIT;
		iscsi_set_padding(tcp_ctask, ctask->data_count);
	}

	rc = iscsi_sendhdr(conn, &tcp_ctask->headbuf, ctask->data_count);
	if (rc) {
		tcp_ctask->xmstate &= ~XMSTATE_UNS_DATA;
		tcp_ctask->xmstate |= XMSTATE_UNS_HDR;
		return rc;
	}

	if (conn->datadgst_en) {
		dtask = &tcp_ctask->unsol_dtask;
		iscsi_data_digest_init(ctask->conn->dd_data, tcp_ctask);
		dtask->digest = 0;
	}

	debug_scsi("uns dout [itt 0x%x dlen %d sent %d]\n",
		   ctask->itt, ctask->unsol_count, tcp_ctask->sent);
	return 0;
}

static int
iscsi_send_unsol_pdu(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
{
	struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;
	int rc;

	if (tcp_ctask->xmstate & XMSTATE_UNS_HDR) {
		BUG_ON(!ctask->unsol_count);
		tcp_ctask->xmstate &= ~XMSTATE_UNS_HDR;
send_hdr:
		rc = iscsi_send_unsol_hdr(conn, ctask);
		if (rc)
			return rc;
	}

	if (tcp_ctask->xmstate & XMSTATE_UNS_DATA) {
		struct iscsi_data_task *dtask = &tcp_ctask->unsol_dtask;
		int start = tcp_ctask->sent;

		rc = iscsi_send_data(ctask, &tcp_ctask->sendbuf, &tcp_ctask->sg,
				     &tcp_ctask->sent, &ctask->data_count,
				     &dtask->digestbuf, &dtask->digest);
		ctask->unsol_count -= tcp_ctask->sent - start;
		if (rc)
			return rc;
		tcp_ctask->xmstate &= ~XMSTATE_UNS_DATA;
		/*
		 * Done with the Data-Out. Next, check if we need
		 * to send another unsolicited Data-Out.
		 */
		if (ctask->unsol_count) {
			debug_scsi("sending more uns\n");
			tcp_ctask->xmstate |= XMSTATE_UNS_INIT;
			goto send_hdr;
		}
	}
	return 0;
}

static int iscsi_send_sol_pdu(struct iscsi_conn *conn,
			      struct iscsi_cmd_task *ctask)
{
	struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;
	struct iscsi_session *session = conn->session;
	struct iscsi_r2t_info *r2t;
	struct iscsi_data_task *dtask;
	int left, rc;

	if (tcp_ctask->xmstate & XMSTATE_SOL_HDR_INIT) {
		if (!tcp_ctask->r2t) {
			spin_lock_bh(&session->lock);
			__kfifo_get(tcp_ctask->r2tqueue, (void*)&tcp_ctask->r2t,
				    sizeof(void*));
			spin_unlock_bh(&session->lock);
		}
send_hdr:
		r2t = tcp_ctask->r2t;
		dtask = &r2t->dtask;

		if (conn->hdrdgst_en)
			iscsi_hdr_digest(conn, &r2t->headbuf,
					(u8*)dtask->hdrext);
		tcp_ctask->xmstate &= ~XMSTATE_SOL_HDR_INIT;
		tcp_ctask->xmstate |= XMSTATE_SOL_HDR;
	}

	if (tcp_ctask->xmstate & XMSTATE_SOL_HDR) {
		r2t = tcp_ctask->r2t;
		dtask = &r2t->dtask;

		rc = iscsi_sendhdr(conn, &r2t->headbuf, r2t->data_count);
		if (rc)
			return rc;
		tcp_ctask->xmstate &= ~XMSTATE_SOL_HDR;
		tcp_ctask->xmstate |= XMSTATE_SOL_DATA;

		if (conn->datadgst_en) {
			iscsi_data_digest_init(conn->dd_data, tcp_ctask);
			dtask->digest = 0;
		}

		iscsi_set_padding(tcp_ctask, r2t->data_count);
		debug_scsi("sol dout [dsn %d itt 0x%x dlen %d sent %d]\n",
			r2t->solicit_datasn - 1, ctask->itt, r2t->data_count,
			r2t->sent);
	}

	if (tcp_ctask->xmstate & XMSTATE_SOL_DATA) {
		r2t = tcp_ctask->r2t;
		dtask = &r2t->dtask;

		rc = iscsi_send_data(ctask, &r2t->sendbuf, &r2t->sg,
				     &r2t->sent, &r2t->data_count,
				     &dtask->digestbuf, &dtask->digest);
		if (rc)
			return rc;
		tcp_ctask->xmstate &= ~XMSTATE_SOL_DATA;

		/*
		 * Done with this Data-Out. Next, check if we have
		 * to send another Data-Out for this R2T.
		 */
		BUG_ON(r2t->data_length - r2t->sent < 0);
		left = r2t->data_length - r2t->sent;
		if (left) {
			iscsi_solicit_data_cont(conn, ctask, r2t, left);
			goto send_hdr;
		}

		/*
		 * Done with this R2T. Check if there are more
		 * outstanding R2Ts ready to be processed.
		 */
		spin_lock_bh(&session->lock);
		tcp_ctask->r2t = NULL;
		__kfifo_put(tcp_ctask->r2tpool.queue, (void*)&r2t,
			    sizeof(void*));
		if (__kfifo_get(tcp_ctask->r2tqueue, (void*)&r2t,
				sizeof(void*))) {
			tcp_ctask->r2t = r2t;
			spin_unlock_bh(&session->lock);
			goto send_hdr;
		}
		spin_unlock_bh(&session->lock);
	}
	return 0;
}

/**
 * iscsi_tcp_ctask_xmit - xmit normal PDU task
 * @conn: iscsi connection
 * @ctask: iscsi command task
 *
 * Notes:
 *	The function can return -EAGAIN in which case caller must
 *	call it again later, or recover. '0' return code means successful
 *	xmit.
 *	The function is devided to logical helpers (above) for the different
 *	xmit stages.
 *
 *iscsi_send_cmd_hdr()
 *	XMSTATE_CMD_HDR_INIT - prepare Header and Data buffers Calculate
 *	                       Header Digest
 *	XMSTATE_CMD_HDR_XMIT - Transmit header in progress
 *
 *iscsi_send_padding
 *	XMSTATE_W_PAD        - Prepare and send pading
 *	XMSTATE_W_RESEND_PAD - retry send pading
 *
 *iscsi_send_digest
 *	XMSTATE_W_RESEND_DATA_DIGEST - Finalize and send Data Digest
 *	XMSTATE_W_RESEND_DATA_DIGEST - retry sending digest
 *
 *iscsi_send_unsol_hdr
 *	XMSTATE_UNS_INIT     - prepare un-solicit data header and digest
 *	XMSTATE_UNS_HDR      - send un-solicit header
 *
 *iscsi_send_unsol_pdu
 *	XMSTATE_UNS_DATA     - send un-solicit data in progress
 *
 *iscsi_send_sol_pdu
 *	XMSTATE_SOL_HDR_INIT - solicit data header and digest initialize
 *	XMSTATE_SOL_HDR      - send solicit header
 *	XMSTATE_SOL_DATA     - send solicit data
 *
 *iscsi_tcp_ctask_xmit
 *	XMSTATE_IMM_DATA     - xmit managment data (??)
 **/
static int
iscsi_tcp_ctask_xmit(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
{
	struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;
	int rc = 0;

	debug_scsi("ctask deq [cid %d xmstate %x itt 0x%x]\n",
		conn->id, tcp_ctask->xmstate, ctask->itt);

	/*
	 * serialize with TMF AbortTask
	 */
	if (ctask->mtask)
		return rc;

	rc = iscsi_send_cmd_hdr(conn, ctask);
	if (rc)
		return rc;
	if (ctask->sc->sc_data_direction != DMA_TO_DEVICE)
		return 0;

	if (tcp_ctask->xmstate & XMSTATE_IMM_DATA) {
		rc = iscsi_send_data(ctask, &tcp_ctask->sendbuf, &tcp_ctask->sg,
				     &tcp_ctask->sent, &ctask->imm_count,
				     &tcp_ctask->immbuf, &tcp_ctask->immdigest);
		if (rc)
			return rc;
		tcp_ctask->xmstate &= ~XMSTATE_IMM_DATA;
	}

	rc = iscsi_send_unsol_pdu(conn, ctask);
	if (rc)
		return rc;

	rc = iscsi_send_sol_pdu(conn, ctask);
	if (rc)
		return rc;

	return rc;
}

static struct iscsi_cls_conn *
iscsi_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;

	cls_conn = iscsi_conn_setup(cls_session, conn_idx);
	if (!cls_conn)
		return NULL;
	conn = cls_conn->dd_data;
	/*
	 * due to strange issues with iser these are not set
	 * in iscsi_conn_setup
	 */
	conn->max_recv_dlength = ISCSI_DEF_MAX_RECV_SEG_LEN;

	tcp_conn = kzalloc(sizeof(*tcp_conn), GFP_KERNEL);
	if (!tcp_conn)
		goto tcp_conn_alloc_fail;

	conn->dd_data = tcp_conn;
	tcp_conn->iscsi_conn = conn;
	tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER;
	/* initial operational parameters */
	tcp_conn->hdr_size = sizeof(struct iscsi_hdr);

	tcp_conn->tx_hash.tfm = crypto_alloc_hash("crc32c", 0,
						  CRYPTO_ALG_ASYNC);
	tcp_conn->tx_hash.flags = 0;
	if (IS_ERR(tcp_conn->tx_hash.tfm)) {
		printk(KERN_ERR "Could not create connection due to crc32c "
		       "loading error %ld. Make sure the crc32c module is "
		       "built as a module or into the kernel\n",
			PTR_ERR(tcp_conn->tx_hash.tfm));
		goto free_tcp_conn;
	}

	tcp_conn->rx_hash.tfm = crypto_alloc_hash("crc32c", 0,
						  CRYPTO_ALG_ASYNC);
	tcp_conn->rx_hash.flags = 0;
	if (IS_ERR(tcp_conn->rx_hash.tfm)) {
		printk(KERN_ERR "Could not create connection due to crc32c "
		       "loading error %ld. Make sure the crc32c module is "
		       "built as a module or into the kernel\n",
			PTR_ERR(tcp_conn->rx_hash.tfm));
		goto free_tx_tfm;
	}

	return cls_conn;

free_tx_tfm:
	crypto_free_hash(tcp_conn->tx_hash.tfm);
free_tcp_conn:
	kfree(tcp_conn);
tcp_conn_alloc_fail:
	iscsi_conn_teardown(cls_conn);
	return NULL;
}

static void
iscsi_tcp_release_conn(struct iscsi_conn *conn)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;

	if (!tcp_conn->sock)
		return;

	sock_hold(tcp_conn->sock->sk);
	iscsi_conn_restore_callbacks(tcp_conn);
	sock_put(tcp_conn->sock->sk);

	sock_release(tcp_conn->sock);
	tcp_conn->sock = NULL;
	conn->recv_lock = NULL;
}

static void
iscsi_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;

	iscsi_tcp_release_conn(conn);
	iscsi_conn_teardown(cls_conn);

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

	kfree(tcp_conn);
}

static void
iscsi_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;

	iscsi_conn_stop(cls_conn, flag);
	iscsi_tcp_release_conn(conn);
	tcp_conn->hdr_size = sizeof(struct iscsi_hdr);
}

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

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

	err = iscsi_conn_bind(cls_session, cls_conn, is_leading);
	if (err)
		return err;

	/* bind iSCSI connection and socket */
	tcp_conn->sock = sock;

	/* setup Socket parameters */
	sk = sock->sk;
	sk->sk_reuse = 1;
	sk->sk_sndtimeo = 15 * HZ; /* FIXME: make it configurable */
	sk->sk_allocation = GFP_ATOMIC;

	/* FIXME: disable Nagle's algorithm */

	/*
	 * Intercept TCP callbacks for sendfile like receive
	 * processing.
	 */
	conn->recv_lock = &sk->sk_callback_lock;
	iscsi_conn_set_callbacks(conn);
	tcp_conn->sendpage = tcp_conn->sock->ops->sendpage;
	/*
	 * set receive state machine into initial state
	 */
	tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER;

	return 0;
}

/* called with host lock */
static void
iscsi_tcp_mgmt_init(struct iscsi_conn *conn, struct iscsi_mgmt_task *mtask,
		    char *data, uint32_t data_size)
{
	struct iscsi_tcp_mgmt_task *tcp_mtask = mtask->dd_data;
	tcp_mtask->xmstate = XMSTATE_IMM_HDR_INIT;
}

static int
iscsi_r2tpool_alloc(struct iscsi_session *session)
{
	int i;
	int cmd_i;

	/*
	 * initialize per-task: R2T pool and xmit queue
	 */
	for (cmd_i = 0; cmd_i < session->cmds_max; cmd_i++) {
	        struct iscsi_cmd_task *ctask = session->cmds[cmd_i];
		struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;

		/*
		 * pre-allocated x4 as much r2ts to handle race when
		 * target acks DataOut faster than we data_xmit() queues
		 * could replenish r2tqueue.
		 */

		/* R2T pool */
		if (iscsi_pool_init(&tcp_ctask->r2tpool, session->max_r2t * 4,
				    (void***)&tcp_ctask->r2ts,
				    sizeof(struct iscsi_r2t_info))) {
			goto r2t_alloc_fail;
		}

		/* R2T xmit queue */
		tcp_ctask->r2tqueue = kfifo_alloc(
		      session->max_r2t * 4 * sizeof(void*), GFP_KERNEL, NULL);
		if (tcp_ctask->r2tqueue == ERR_PTR(-ENOMEM)) {
			iscsi_pool_free(&tcp_ctask->r2tpool,
					(void**)tcp_ctask->r2ts);
			goto r2t_alloc_fail;
		}
	}

	return 0;

r2t_alloc_fail:
	for (i = 0; i < cmd_i; i++) {
		struct iscsi_cmd_task *ctask = session->cmds[i];
		struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;