libiscsi.c

linux 内核源代码

	if (itt < session->cmds_max) {
		ctask = session->cmds[itt];

		if (!ctask->sc) {
			printk(KERN_INFO "iscsi: dropping ctask with "
			       "itt 0x%x\n", ctask->itt);
			/* force drop */
			return ISCSI_ERR_NO_SCSI_CMD;
		}

		if (ctask->sc->SCp.phase != session->age) {
			printk(KERN_ERR "iscsi: ctask's session age %d, "
				"expected %d\n", ctask->sc->SCp.phase,
				session->age);
			return ISCSI_ERR_SESSION_FAILED;
		}
	}

	*ret_itt = itt;
	return 0;
}
EXPORT_SYMBOL_GPL(iscsi_verify_itt);

void iscsi_conn_failure(struct iscsi_conn *conn, enum iscsi_err err)
{
	struct iscsi_session *session = conn->session;
	unsigned long flags;

	spin_lock_irqsave(&session->lock, flags);
	if (session->state == ISCSI_STATE_FAILED) {
		spin_unlock_irqrestore(&session->lock, flags);
		return;
	}

	if (conn->stop_stage == 0)
		session->state = ISCSI_STATE_FAILED;
	spin_unlock_irqrestore(&session->lock, flags);
	set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx);
	set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx);
	iscsi_conn_error(conn->cls_conn, err);
}
EXPORT_SYMBOL_GPL(iscsi_conn_failure);

static void iscsi_prep_mtask(struct iscsi_conn *conn,
			     struct iscsi_mgmt_task *mtask)
{
	struct iscsi_session *session = conn->session;
	struct iscsi_hdr *hdr = mtask->hdr;
	struct iscsi_nopout *nop = (struct iscsi_nopout *)hdr;

	if (hdr->opcode != (ISCSI_OP_LOGIN | ISCSI_OP_IMMEDIATE) &&
	    hdr->opcode != (ISCSI_OP_TEXT | ISCSI_OP_IMMEDIATE))
		nop->exp_statsn = cpu_to_be32(conn->exp_statsn);
	/*
	 * pre-format CmdSN for outgoing PDU.
	 */
	nop->cmdsn = cpu_to_be32(session->cmdsn);
	if (hdr->itt != RESERVED_ITT) {
		hdr->itt = build_itt(mtask->itt, conn->id, session->age);
		/*
		 * TODO: We always use immediate, so we never hit this.
		 * If we start to send tmfs or nops as non-immediate then
		 * we should start checking the cmdsn numbers for mgmt tasks.
		 */
		if (conn->c_stage == ISCSI_CONN_STARTED &&
		    !(hdr->opcode & ISCSI_OP_IMMEDIATE)) {
			session->queued_cmdsn++;
			session->cmdsn++;
		}
	}

	if (session->tt->init_mgmt_task)
		session->tt->init_mgmt_task(conn, mtask);

	debug_scsi("mgmtpdu [op 0x%x hdr->itt 0x%x datalen %d]\n",
		   hdr->opcode, hdr->itt, mtask->data_count);
}

static int iscsi_xmit_mtask(struct iscsi_conn *conn)
{
	struct iscsi_hdr *hdr = conn->mtask->hdr;
	int rc, was_logout = 0;

	spin_unlock_bh(&conn->session->lock);
	if ((hdr->opcode & ISCSI_OPCODE_MASK) == ISCSI_OP_LOGOUT) {
		conn->session->state = ISCSI_STATE_IN_RECOVERY;
		iscsi_block_session(session_to_cls(conn->session));
		was_logout = 1;
	}
	rc = conn->session->tt->xmit_mgmt_task(conn, conn->mtask);
	spin_lock_bh(&conn->session->lock);
	if (rc)
		return rc;

	/* done with this in-progress mtask */
	conn->mtask = NULL;

	if (was_logout) {
		set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx);
		return -ENODATA;
	}
	return 0;
}

static int iscsi_check_cmdsn_window_closed(struct iscsi_conn *conn)
{
	struct iscsi_session *session = conn->session;

	/*
	 * Check for iSCSI window and take care of CmdSN wrap-around
	 */
	if (!iscsi_sna_lte(session->queued_cmdsn, session->max_cmdsn)) {
		debug_scsi("iSCSI CmdSN closed. ExpCmdSn %u MaxCmdSN %u "
			   "CmdSN %u/%u\n", session->exp_cmdsn,
			   session->max_cmdsn, session->cmdsn,
			   session->queued_cmdsn);
		return -ENOSPC;
	}
	return 0;
}

static int iscsi_xmit_ctask(struct iscsi_conn *conn)
{
	struct iscsi_cmd_task *ctask = conn->ctask;
	int rc = 0;

	/*
	 * serialize with TMF AbortTask
	 */
	if (ctask->state == ISCSI_TASK_ABORTING)
		goto done;

	__iscsi_get_ctask(ctask);
	spin_unlock_bh(&conn->session->lock);
	rc = conn->session->tt->xmit_cmd_task(conn, ctask);
	spin_lock_bh(&conn->session->lock);
	__iscsi_put_ctask(ctask);

done:
	if (!rc)
		/* done with this ctask */
		conn->ctask = NULL;
	return rc;
}

/**
 * iscsi_data_xmit - xmit any command into the scheduled connection
 * @conn: iscsi connection
 *
 * Notes:
 *	The function can return -EAGAIN in which case the caller must
 *	re-schedule it again later or recover. '0' return code means
 *	successful xmit.
 **/
static int iscsi_data_xmit(struct iscsi_conn *conn)
{
	int rc = 0;

	spin_lock_bh(&conn->session->lock);
	if (unlikely(conn->suspend_tx)) {
		debug_scsi("conn %d Tx suspended!\n", conn->id);
		spin_unlock_bh(&conn->session->lock);
		return -ENODATA;
	}

	if (conn->ctask) {
		rc = iscsi_xmit_ctask(conn);
		if (rc)
			goto again;
	}

	if (conn->mtask) {
		rc = iscsi_xmit_mtask(conn);
	        if (rc)
		        goto again;
	}

	/*
	 * process mgmt pdus like nops before commands since we should
	 * only have one nop-out as a ping from us and targets should not
	 * overflow us with nop-ins
	 */
check_mgmt:
	while (__kfifo_get(conn->mgmtqueue, (void*)&conn->mtask,
			   sizeof(void*))) {
		iscsi_prep_mtask(conn, conn->mtask);
		list_add_tail(&conn->mtask->running, &conn->mgmt_run_list);
		rc = iscsi_xmit_mtask(conn);
		if (rc)
			goto again;
	}

	/* process command queue */
	while (!list_empty(&conn->xmitqueue)) {
		/*
		 * iscsi tcp may readd the task to the xmitqueue to send
		 * write data
		 */
		conn->ctask = list_entry(conn->xmitqueue.next,
					 struct iscsi_cmd_task, running);
		switch (conn->ctask->state) {
		case ISCSI_TASK_ABORTING:
			break;
		case ISCSI_TASK_PENDING:
			iscsi_prep_scsi_cmd_pdu(conn->ctask);
			conn->session->tt->init_cmd_task(conn->ctask);
			/* fall through */
		default:
			conn->ctask->state = ISCSI_TASK_RUNNING;
			break;
		}
		list_move_tail(conn->xmitqueue.next, &conn->run_list);

		rc = iscsi_xmit_ctask(conn);
		if (rc)
			goto again;
		/*
		 * we could continuously get new ctask requests so
		 * we need to check the mgmt queue for nops that need to
		 * be sent to aviod starvation
		 */
		if (__kfifo_len(conn->mgmtqueue))
			goto check_mgmt;
	}
	spin_unlock_bh(&conn->session->lock);
	return -ENODATA;

again:
	if (unlikely(conn->suspend_tx))
		rc = -ENODATA;
	spin_unlock_bh(&conn->session->lock);
	return rc;
}

static void iscsi_xmitworker(struct work_struct *work)
{
	struct iscsi_conn *conn =
		container_of(work, struct iscsi_conn, xmitwork);
	int rc;
	/*
	 * serialize Xmit worker on a per-connection basis.
	 */
	do {
		rc = iscsi_data_xmit(conn);
	} while (rc >= 0 || rc == -EAGAIN);
}

enum {
	FAILURE_BAD_HOST = 1,
	FAILURE_SESSION_FAILED,
	FAILURE_SESSION_FREED,
	FAILURE_WINDOW_CLOSED,
	FAILURE_OOM,
	FAILURE_SESSION_TERMINATE,
	FAILURE_SESSION_IN_RECOVERY,
	FAILURE_SESSION_RECOVERY_TIMEOUT,
};

int iscsi_queuecommand(struct scsi_cmnd *sc, void (*done)(struct scsi_cmnd *))
{
	struct Scsi_Host *host;
	int reason = 0;
	struct iscsi_session *session;
	struct iscsi_conn *conn;
	struct iscsi_cmd_task *ctask = NULL;

	sc->scsi_done = done;
	sc->result = 0;
	sc->SCp.ptr = NULL;

	host = sc->device->host;
	session = iscsi_hostdata(host->hostdata);

	spin_lock(&session->lock);

	/*
	 * ISCSI_STATE_FAILED is a temp. state. The recovery
	 * code will decide what is best to do with command queued
	 * during this time
	 */
	if (session->state != ISCSI_STATE_LOGGED_IN &&
	    session->state != ISCSI_STATE_FAILED) {
		/*
		 * to handle the race between when we set the recovery state
		 * and block the session we requeue here (commands could
		 * be entering our queuecommand while a block is starting
		 * up because the block code is not locked)
		 */
		if (session->state == ISCSI_STATE_IN_RECOVERY) {
			reason = FAILURE_SESSION_IN_RECOVERY;
			goto reject;
		}

		if (session->state == ISCSI_STATE_RECOVERY_FAILED)
			reason = FAILURE_SESSION_RECOVERY_TIMEOUT;
		else if (session->state == ISCSI_STATE_TERMINATE)
			reason = FAILURE_SESSION_TERMINATE;
		else
			reason = FAILURE_SESSION_FREED;
		goto fault;
	}

	conn = session->leadconn;
	if (!conn) {
		reason = FAILURE_SESSION_FREED;
		goto fault;
	}

	if (iscsi_check_cmdsn_window_closed(conn)) {
		reason = FAILURE_WINDOW_CLOSED;
		goto reject;
	}

	if (!__kfifo_get(session->cmdpool.queue, (void*)&ctask,
			 sizeof(void*))) {
		reason = FAILURE_OOM;
		goto reject;
	}
	session->queued_cmdsn++;

	sc->SCp.phase = session->age;
	sc->SCp.ptr = (char *)ctask;

	atomic_set(&ctask->refcount, 1);
	ctask->state = ISCSI_TASK_PENDING;
	ctask->mtask = NULL;
	ctask->conn = conn;
	ctask->sc = sc;
	INIT_LIST_HEAD(&ctask->running);

	list_add_tail(&ctask->running, &conn->xmitqueue);
	spin_unlock(&session->lock);

	scsi_queue_work(host, &conn->xmitwork);
	return 0;

reject:
	spin_unlock(&session->lock);
	debug_scsi("cmd 0x%x rejected (%d)\n", sc->cmnd[0], reason);
	return SCSI_MLQUEUE_HOST_BUSY;

fault:
	spin_unlock(&session->lock);
	printk(KERN_ERR "iscsi: cmd 0x%x is not queued (%d)\n",
	       sc->cmnd[0], reason);
	sc->result = (DID_NO_CONNECT << 16);
	scsi_set_resid(sc, scsi_bufflen(sc));
	sc->scsi_done(sc);
	return 0;
}
EXPORT_SYMBOL_GPL(iscsi_queuecommand);

int iscsi_change_queue_depth(struct scsi_device *sdev, int depth)
{
	if (depth > ISCSI_MAX_CMD_PER_LUN)
		depth = ISCSI_MAX_CMD_PER_LUN;
	scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), depth);
	return sdev->queue_depth;
}
EXPORT_SYMBOL_GPL(iscsi_change_queue_depth);

static struct iscsi_mgmt_task *
__iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
		      char *data, uint32_t data_size)
{
	struct iscsi_session *session = conn->session;
	struct iscsi_mgmt_task *mtask;

	if (session->state == ISCSI_STATE_TERMINATE)
		return NULL;

	if (hdr->opcode == (ISCSI_OP_LOGIN | ISCSI_OP_IMMEDIATE) ||
	    hdr->opcode == (ISCSI_OP_TEXT | ISCSI_OP_IMMEDIATE))
		/*
		 * Login and Text are sent serially, in
		 * request-followed-by-response sequence.
		 * Same mtask can be used. Same ITT must be used.
		 * Note that login_mtask is preallocated at conn_create().
		 */
		mtask = conn->login_mtask;
	else {
		BUG_ON(conn->c_stage == ISCSI_CONN_INITIAL_STAGE);
		BUG_ON(conn->c_stage == ISCSI_CONN_STOPPED);

		if (!__kfifo_get(session->mgmtpool.queue,
				 (void*)&mtask, sizeof(void*)))
			return NULL;
	}

	if (data_size) {
		memcpy(mtask->data, data, data_size);
		mtask->data_count = data_size;
	} else
		mtask->data_count = 0;

	INIT_LIST_HEAD(&mtask->running);
	memcpy(mtask->hdr, hdr, sizeof(struct iscsi_hdr));
	__kfifo_put(conn->mgmtqueue, (void*)&mtask, sizeof(void*));
	return mtask;
}

int iscsi_conn_send_pdu(struct iscsi_cls_conn *cls_conn, struct iscsi_hdr *hdr,
			char *data, uint32_t data_size)
{
	struct iscsi_conn *conn = cls_conn->dd_data;
	struct iscsi_session *session = conn->session;
	int err = 0;

	spin_lock_bh(&session->lock);
	if (!__iscsi_conn_send_pdu(conn, hdr, data, data_size))
		err = -EPERM;
	spin_unlock_bh(&session->lock);
	scsi_queue_work(session->host, &conn->xmitwork);
	return err;
}
EXPORT_SYMBOL_GPL(iscsi_conn_send_pdu);

void iscsi_session_recovery_timedout(struct iscsi_cls_session *cls_session)
{
	struct iscsi_session *session = class_to_transport_session(cls_session);
	struct iscsi_conn *conn = session->leadconn;

	spin_lock_bh(&session->lock);
	if (session->state != ISCSI_STATE_LOGGED_IN) {
		session->state = ISCSI_STATE_RECOVERY_FAILED;
		if (conn)
			wake_up(&conn->ehwait);
	}
	spin_unlock_bh(&session->lock);
}
EXPORT_SYMBOL_GPL(iscsi_session_recovery_timedout);

int iscsi_eh_host_reset(struct scsi_cmnd *sc)
{
	struct Scsi_Host *host = sc->device->host;
	struct iscsi_session *session = iscsi_hostdata(host->hostdata);
	struct iscsi_conn *conn = session->leadconn;
	int fail_session = 0;

	spin_lock_bh(&session->lock);
	if (session->state == ISCSI_STATE_TERMINATE) {
failed:
		debug_scsi("failing host reset: session terminated "
			   "[CID %d age %d]\n", conn->id, session->age);
		spin_unlock_bh(&session->lock);
		return FAILED;
	}

	if (sc->SCp.phase == session->age) {
		debug_scsi("failing connection CID %d due to SCSI host reset\n",
			   conn->id);
		fail_session = 1;
	}
	spin_unlock_bh(&session->lock);

	/*
	 * we drop the lock here but the leadconn cannot be destoyed while
	 * we are in the scsi eh
	 */
	if (fail_session)
		iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);

	debug_scsi("iscsi_eh_host_reset wait for relogin\n");
	wait_event_interruptible(conn->ehwait,
				 session->state == ISCSI_STATE_TERMINATE ||
				 session->state == ISCSI_STATE_LOGGED_IN ||
				 session->state == ISCSI_STATE_RECOVERY_FAILED);
	if (signal_pending(current))
		flush_signals(current);

	spin_lock_bh(&session->lock);
	if (session->state == ISCSI_STATE_LOGGED_IN)
		printk(KERN_INFO "iscsi: host reset succeeded\n");
	else
		goto failed;
	spin_unlock_bh(&session->lock);

	return SUCCESS;
}
EXPORT_SYMBOL_GPL(iscsi_eh_host_reset);

static void iscsi_tmabort_timedout(unsigned long data)
{
	struct iscsi_cmd_task *ctask = (struct iscsi_cmd_task *)data;
	struct iscsi_conn *conn = ctask->conn;
	struct iscsi_session *session = conn->session;

	spin_lock(&session->lock);
	if (conn->tmabort_state == TMABORT_INITIAL) {
		conn->tmabort_state = TMABORT_TIMEDOUT;
		debug_scsi("tmabort timedout [sc %p itt 0x%x]\n",
			ctask->sc, ctask->itt);
		/* unblock eh_abort() */
		wake_up(&conn->ehwait);
	}
	spin_unlock(&session->lock);
}

static int iscsi_exec_abort_task(struct scsi_cmnd *sc,
				 struct iscsi_cmd_task *ctask)
{
	struct iscsi_conn *conn = ctask->conn;
	struct iscsi_session *session = conn->session;
	struct iscsi_tm *hdr = &conn->tmhdr;

	/*
	 * ctask timed out but session is OK requests must be serialized.
	 */
	memset(hdr, 0, sizeof(struct iscsi_tm));
	hdr->opcode = ISCSI_OP_SCSI_TMFUNC | ISCSI_OP_IMMEDIATE;
	hdr->flags = ISCSI_TM_FUNC_ABORT_TASK;
	hdr->flags |= ISCSI_FLAG_CMD_FINAL;
	memcpy(hdr->lun, ctask->hdr->lun, sizeof(hdr->lun));
	hdr->rtt = ctask->hdr->itt;
	hdr->refcmdsn = ctask->hdr->cmdsn;

	ctask->mtask = __iscsi_conn_send_pdu(conn, (struct iscsi_hdr *)hdr,
					    NULL, 0);
	if (!ctask->mtask) {
		spin_unlock_bh(&session->lock);
		iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
		spin_lock_bh(&session->lock)
		debug_scsi("abort sent failure [itt 0x%x]\n", ctask->itt);
		return -EPERM;
	}
	ctask->state = ISCSI_TASK_ABORTING;

	debug_scsi("abort sent [itt 0x%x]\n", ctask->itt);

	if (conn->tmabort_state == TMABORT_INITIAL) {
		conn->tmfcmd_pdus_cnt++;
		conn->tmabort_timer.expires = 20*HZ + jiffies;
		conn->tmabort_timer.function = iscsi_tmabort_timedout;
		conn->tmabort_timer.data = (unsigned long)ctask;
		add_timer(&conn->tmabort_timer);
		debug_scsi("abort set timeout [itt 0x%x]\n", ctask->itt);