scsi: qla2xxx: Fix Target mode handling with Multiqueue changes.

- Fix race condition between dpc_thread accessing Multiqueue resources
  and qla2x00_remove_one thread trying to free resource.
- Fix out of order free for Multiqueue resources. Also, Multiqueue
  interrupts needs a workqueue. Interrupt needed to stop before
  the wq can be destroyed.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/qla2xxx/qla_def.h

@@ -2734,7 +2734,8 @@ struct isp_operations {
 
 #define QLA_MSIX_DEFAULT		0x00
 #define QLA_MSIX_RSP_Q			0x01
-#define QLA_MSIX_QPAIR_MULTIQ_RSP_Q	0x02
+#define QLA_ATIO_VECTOR		0x02
+#define QLA_MSIX_QPAIR_MULTIQ_RSP_Q	0x03
 
 #define QLA_MIDX_DEFAULT	0
 #define QLA_MIDX_RSP_Q		1

drivers/scsi/qla2xxx/qla_init.c

@@ -6764,7 +6764,7 @@ struct qla_qpair *qla2xxx_create_qpair(struct scsi_qla_host *vha, int qos, int v
 		qpair->vp_idx = vp_idx;
 
 		for (i = 0; i < ha->msix_count; i++) {
-			msix = &ha->msix_entries[i + 2];
+			msix = &ha->msix_entries[i];
 			if (msix->in_use)
 				continue;
 			qpair->msix = msix;

drivers/scsi/qla2xxx/qla_isr.c

@@ -3005,6 +3005,7 @@ struct qla_init_msix_entry {
 static struct qla_init_msix_entry msix_entries[] = {
 	{ "qla2xxx (default)", qla24xx_msix_default },
 	{ "qla2xxx (rsp_q)", qla24xx_msix_rsp_q },
+	{ "qla2xxx (atio_q)", qla83xx_msix_atio_q },
 	{ "qla2xxx (qpair_multiq)", qla2xxx_msix_rsp_q },
 };
 
@@ -3013,17 +3014,10 @@ static struct qla_init_msix_entry qla82xx_msix_entries[] = {
 	{ "qla2xxx (rsp_q)", qla82xx_msix_rsp_q },
 };
 
-static struct qla_init_msix_entry qla83xx_msix_entries[] = {
-	{ "qla2xxx (default)", qla24xx_msix_default },
-	{ "qla2xxx (rsp_q)", qla24xx_msix_rsp_q },
-	{ "qla2xxx (atio_q)", qla83xx_msix_atio_q },
-};
-
 static int
 qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 {
 #define MIN_MSIX_COUNT	2
-#define ATIO_VECTOR	2
 	int i, ret;
 	struct qla_msix_entry *qentry;
 	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
@@ -3080,7 +3074,7 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 	}
 
 	/* Enable MSI-X vectors for the base queue */
-	for (i = 0; i < 2; i++) {
+	for (i = 0; i < (QLA_MSIX_RSP_Q + 1); i++) {
 		qentry = &ha->msix_entries[i];
 		qentry->handle = rsp;
 		rsp->msix = qentry;
@@ -3097,6 +3091,7 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 		if (ret)
 			goto msix_register_fail;
 		qentry->have_irq = 1;
+		qentry->in_use = 1;
 
 		/* Register for CPU affinity notification. */
 		irq_set_affinity_notifier(qentry->vector, &qentry->irq_notify);
@@ -3116,14 +3111,15 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 	 * queue.
 	 */
 	if (QLA_TGT_MODE_ENABLED() && IS_ATIO_MSIX_CAPABLE(ha)) {
-		qentry = &ha->msix_entries[ATIO_VECTOR];
+		qentry = &ha->msix_entries[QLA_ATIO_VECTOR];
 		rsp->msix = qentry;
 		qentry->handle = rsp;
 		scnprintf(qentry->name, sizeof(qentry->name),
-		    qla83xx_msix_entries[ATIO_VECTOR].name);
+		    msix_entries[QLA_ATIO_VECTOR].name);
+		qentry->in_use = 1;
 		ret = request_irq(qentry->vector,
-			qla83xx_msix_entries[ATIO_VECTOR].handler,
-			0, qla83xx_msix_entries[ATIO_VECTOR].name, rsp);
+			msix_entries[QLA_ATIO_VECTOR].handler,
+			0, msix_entries[QLA_ATIO_VECTOR].name, rsp);
 		qentry->have_irq = 1;
 	}
 

drivers/scsi/qla2xxx/qla_os.c

@@ -439,24 +439,41 @@ static void qla2x00_free_queues(struct qla_hw_data *ha)
 	struct req_que *req;
 	struct rsp_que *rsp;
 	int cnt;
+	unsigned long flags;
 
+	spin_lock_irqsave(&ha->hardware_lock, flags);
 	for (cnt = 0; cnt < ha->max_req_queues; cnt++) {
 		if (!test_bit(cnt, ha->req_qid_map))
 			continue;
 
 		req = ha->req_q_map[cnt];
+		clear_bit(cnt, ha->req_qid_map);
+		ha->req_q_map[cnt] = NULL;
+
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		qla2x00_free_req_que(ha, req);
+		spin_lock_irqsave(&ha->hardware_lock, flags);
 	}
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
 	kfree(ha->req_q_map);
 	ha->req_q_map = NULL;
 
+
+	spin_lock_irqsave(&ha->hardware_lock, flags);
 	for (cnt = 0; cnt < ha->max_rsp_queues; cnt++) {
 		if (!test_bit(cnt, ha->rsp_qid_map))
 			continue;
 
 		rsp = ha->rsp_q_map[cnt];
+		clear_bit(cnt, ha->req_qid_map);
+		ha->rsp_q_map[cnt] =  NULL;
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		qla2x00_free_rsp_que(ha, rsp);
+		spin_lock_irqsave(&ha->hardware_lock, flags);
 	}
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
 	kfree(ha->rsp_q_map);
 	ha->rsp_q_map = NULL;
 }
@@ -1890,17 +1907,22 @@ qla83xx_iospace_config(struct qla_hw_data *ha)
 		pci_read_config_word(ha->pdev,
 		    QLA_83XX_PCI_MSIX_CONTROL, &msix);
 		ha->msix_count = msix + 1;
-		/* Max queues are bounded by available msix vectors */
-		/* queue 0 uses two msix vectors */
+		/*
+		 * By default, driver uses at least two msix vectors
+		 * (default & rspq)
+		 */
 		if (ql2xmqsupport) {
 			/* MB interrupt uses 1 vector */
 			ha->max_req_queues = ha->msix_count - 1;
 			ha->max_rsp_queues = ha->max_req_queues;
+
+			/* ATIOQ needs 1 vector. That's 1 less QPair */
+			if (QLA_TGT_MODE_ENABLED())
+				ha->max_req_queues--;
+
 			/* Queue pairs is the max value minus
 			 * the base queue pair */
 			ha->max_qpairs = ha->max_req_queues - 1;
-			ql_dbg_pci(ql_dbg_multiq, ha->pdev, 0xc010,
-			    "Max no of queues pairs: %d.\n", ha->max_qpairs);
 			ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0190,
 			    "Max no of queues pairs: %d.\n", ha->max_qpairs);
 		}
@@ -1912,6 +1934,8 @@ qla83xx_iospace_config(struct qla_hw_data *ha)
 
 mqiobase_exit:
 	ha->msix_count = ha->max_rsp_queues + 1;
+	if (QLA_TGT_MODE_ENABLED())
+		ha->msix_count++;
 
 	qlt_83xx_iospace_config(ha);
 
@@ -2989,7 +3013,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    host->can_queue, base_vha->req,
 	    base_vha->mgmt_svr_loop_id, host->sg_tablesize);
 
-	if (ha->mqenable) {
+	if (ha->mqenable && qla_ini_mode_enabled(base_vha)) {
 		ha->wq = alloc_workqueue("qla2xxx_wq", WQ_MEM_RECLAIM, 1);
 		/* Create start of day qpairs for Block MQ */
 		if (shost_use_blk_mq(host)) {
@@ -3263,13 +3287,6 @@ qla2x00_delete_all_vps(struct qla_hw_data *ha, scsi_qla_host_t *base_vha)
 static void
 qla2x00_destroy_deferred_work(struct qla_hw_data *ha)
 {
-	/* Flush the work queue and remove it */
-	if (ha->wq) {
-		flush_workqueue(ha->wq);
-		destroy_workqueue(ha->wq);
-		ha->wq = NULL;
-	}
-
 	/* Cancel all work and destroy DPC workqueues */
 	if (ha->dpc_lp_wq) {
 		cancel_work_sync(&ha->idc_aen);
@@ -3465,9 +3482,17 @@ qla2x00_free_device(scsi_qla_host_t *vha)
 		ha->isp_ops->disable_intrs(ha);
 	}
 
+	qla2x00_free_fcports(vha);
+
 	qla2x00_free_irqs(vha);
 
-	qla2x00_free_fcports(vha);
+	/* Flush the work queue and remove it */
+	if (ha->wq) {
+		flush_workqueue(ha->wq);
+		destroy_workqueue(ha->wq);
+		ha->wq = NULL;
+	}
+
 
 	qla2x00_mem_free(ha);
 
@@ -5187,8 +5212,8 @@ qla2x00_disable_board_on_pci_error(struct work_struct *work)
 
 	base_vha->flags.init_done = 0;
 	qla25xx_delete_queues(base_vha);
-	qla2x00_free_irqs(base_vha);
 	qla2x00_free_fcports(base_vha);
+	qla2x00_free_irqs(base_vha);
 	qla2x00_mem_free(ha);
 	qla82xx_md_free(base_vha);
 	qla2x00_free_queues(ha);