1 files changed, 1021 insertions, 235 deletions

diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 65f168c41d23..755313b766b9 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -40,6 +40,12 @@ static unsigned int disc_threads = IBMVFC_MAX_DISC_THREADS;
 static unsigned int ibmvfc_debug = IBMVFC_DEBUG;
 static unsigned int log_level = IBMVFC_DEFAULT_LOG_LEVEL;
 static unsigned int cls3_error = IBMVFC_CLS3_ERROR;
+static unsigned int mq_enabled = IBMVFC_MQ;
+static unsigned int nr_scsi_hw_queues = IBMVFC_SCSI_HW_QUEUES;
+static unsigned int nr_scsi_channels = IBMVFC_SCSI_CHANNELS;
+static unsigned int mig_channels_only = IBMVFC_MIG_NO_SUB_TO_CRQ;
+static unsigned int mig_no_less_channels = IBMVFC_MIG_NO_N_TO_M;
+
 static LIST_HEAD(ibmvfc_head);
 static DEFINE_SPINLOCK(ibmvfc_driver_lock);
 static struct scsi_transport_template *ibmvfc_transport_template;
@@ -49,6 +55,22 @@ MODULE_AUTHOR("Brian King <brking@linux.vnet.ibm.com>");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(IBMVFC_DRIVER_VERSION);
 
+module_param_named(mq, mq_enabled, uint, S_IRUGO);
+MODULE_PARM_DESC(mq, "Enable multiqueue support. "
+		 "[Default=" __stringify(IBMVFC_MQ) "]");
+module_param_named(scsi_host_queues, nr_scsi_hw_queues, uint, S_IRUGO);
+MODULE_PARM_DESC(scsi_host_queues, "Number of SCSI Host submission queues. "
+		 "[Default=" __stringify(IBMVFC_SCSI_HW_QUEUES) "]");
+module_param_named(scsi_hw_channels, nr_scsi_channels, uint, S_IRUGO);
+MODULE_PARM_DESC(scsi_hw_channels, "Number of hw scsi channels to request. "
+		 "[Default=" __stringify(IBMVFC_SCSI_CHANNELS) "]");
+module_param_named(mig_channels_only, mig_channels_only, uint, S_IRUGO);
+MODULE_PARM_DESC(mig_channels_only, "Prevent migration to non-channelized system. "
+		 "[Default=" __stringify(IBMVFC_MIG_NO_SUB_TO_CRQ) "]");
+module_param_named(mig_no_less_channels, mig_no_less_channels, uint, S_IRUGO);
+MODULE_PARM_DESC(mig_no_less_channels, "Prevent migration to system with less channels. "
+		 "[Default=" __stringify(IBMVFC_MIG_NO_N_TO_M) "]");
+
 module_param_named(init_timeout, init_timeout, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(init_timeout, "Initialization timeout in seconds. "
 		 "[Default=" __stringify(IBMVFC_INIT_TIMEOUT) "]");
@@ -138,6 +160,20 @@ static void ibmvfc_tgt_move_login(struct ibmvfc_target *);
 
 static const char *unknown_error = "unknown error";
 
+static long h_reg_sub_crq(unsigned long unit_address, unsigned long ioba,
+			  unsigned long length, unsigned long *cookie,
+			  unsigned long *irq)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	rc = plpar_hcall(H_REG_SUB_CRQ, retbuf, unit_address, ioba, length);
+	*cookie = retbuf[0];
+	*irq = retbuf[1];
+
+	return rc;
+}
+
 static int ibmvfc_check_caps(struct ibmvfc_host *vhost, unsigned long cap_flags)
 {
 	u64 host_caps = be64_to_cpu(vhost->login_buf->resp.capabilities);
@@ -176,8 +212,9 @@ static void ibmvfc_trc_start(struct ibmvfc_event *evt)
 	struct ibmvfc_mad_common *mad = &evt->iu.mad_common;
 	struct ibmvfc_fcp_cmd_iu *iu = ibmvfc_get_fcp_iu(vhost, vfc_cmd);
 	struct ibmvfc_trace_entry *entry;
+	int index = atomic_inc_return(&vhost->trace_index) & IBMVFC_TRACE_INDEX_MASK;
 
-	entry = &vhost->trace[vhost->trace_index++];
+	entry = &vhost->trace[index];
 	entry->evt = evt;
 	entry->time = jiffies;
 	entry->fmt = evt->crq.format;
@@ -211,8 +248,10 @@ static void ibmvfc_trc_end(struct ibmvfc_event *evt)
 	struct ibmvfc_mad_common *mad = &evt->xfer_iu->mad_common;
 	struct ibmvfc_fcp_cmd_iu *iu = ibmvfc_get_fcp_iu(vhost, vfc_cmd);
 	struct ibmvfc_fcp_rsp *rsp = ibmvfc_get_fcp_rsp(vhost, vfc_cmd);
-	struct ibmvfc_trace_entry *entry = &vhost->trace[vhost->trace_index++];
+	struct ibmvfc_trace_entry *entry;
+	int index = atomic_inc_return(&vhost->trace_index) & IBMVFC_TRACE_INDEX_MASK;
 
+	entry = &vhost->trace[index];
 	entry->evt = evt;
 	entry->time = jiffies;
 	entry->fmt = evt->crq.format;
@@ -660,7 +699,7 @@ static void ibmvfc_init_host(struct ibmvfc_host *vhost)
 	}
 
 	if (!ibmvfc_set_host_state(vhost, IBMVFC_INITIALIZING)) {
-		memset(vhost->async_crq.msgs, 0, PAGE_SIZE);
+		memset(vhost->async_crq.msgs.async, 0, PAGE_SIZE);
 		vhost->async_crq.cur = 0;
 
 		list_for_each_entry(tgt, &vhost->targets, queue)
@@ -687,6 +726,15 @@ static int ibmvfc_send_crq(struct ibmvfc_host *vhost, u64 word1, u64 word2)
 	return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, word1, word2);
 }
 
+static int ibmvfc_send_sub_crq(struct ibmvfc_host *vhost, u64 cookie, u64 word1,
+			       u64 word2, u64 word3, u64 word4)
+{
+	struct vio_dev *vdev = to_vio_dev(vhost->dev);
+
+	return plpar_hcall_norets(H_SEND_SUB_CRQ, vdev->unit_address, cookie,
+				  word1, word2, word3, word4);
+}
+
 /**
  * ibmvfc_send_crq_init - Send a CRQ init message
  * @vhost:	ibmvfc host struct
@@ -714,6 +762,105 @@ static int ibmvfc_send_crq_init_complete(struct ibmvfc_host *vhost)
 }
 
 /**
+ * ibmvfc_init_event_pool - Allocates and initializes the event pool for a host
+ * @vhost:	ibmvfc host who owns the event pool
+ *
+ * Returns zero on success.
+ **/
+static int ibmvfc_init_event_pool(struct ibmvfc_host *vhost,
+				  struct ibmvfc_queue *queue,
+				  unsigned int size)
+{
+	int i;
+	struct ibmvfc_event_pool *pool = &queue->evt_pool;
+
+	ENTER;
+	if (!size)
+		return 0;
+
+	pool->size = size;
+	pool->events = kcalloc(size, sizeof(*pool->events), GFP_KERNEL);
+	if (!pool->events)
+		return -ENOMEM;
+
+	pool->iu_storage = dma_alloc_coherent(vhost->dev,
+					      size * sizeof(*pool->iu_storage),
+					      &pool->iu_token, 0);
+
+	if (!pool->iu_storage) {
+		kfree(pool->events);
+		return -ENOMEM;
+	}
+
+	INIT_LIST_HEAD(&queue->sent);
+	INIT_LIST_HEAD(&queue->free);
+	spin_lock_init(&queue->l_lock);
+
+	for (i = 0; i < size; ++i) {
+		struct ibmvfc_event *evt = &pool->events[i];
+
+		atomic_set(&evt->free, 1);
+		evt->crq.valid = 0x80;
+		evt->crq.ioba = cpu_to_be64(pool->iu_token + (sizeof(*evt->xfer_iu) * i));
+		evt->xfer_iu = pool->iu_storage + i;
+		evt->vhost = vhost;
+		evt->queue = queue;
+		evt->ext_list = NULL;
+		list_add_tail(&evt->queue_list, &queue->free);
+	}
+
+	LEAVE;
+	return 0;
+}
+
+/**
+ * ibmvfc_free_event_pool - Frees memory of the event pool of a host
+ * @vhost:	ibmvfc host who owns the event pool
+ *
+ **/
+static void ibmvfc_free_event_pool(struct ibmvfc_host *vhost,
+				   struct ibmvfc_queue *queue)
+{
+	int i;
+	struct ibmvfc_event_pool *pool = &queue->evt_pool;
+
+	ENTER;
+	for (i = 0; i < pool->size; ++i) {
+		list_del(&pool->events[i].queue_list);
+		BUG_ON(atomic_read(&pool->events[i].free) != 1);
+		if (pool->events[i].ext_list)
+			dma_pool_free(vhost->sg_pool,
+				      pool->events[i].ext_list,
+				      pool->events[i].ext_list_token);
+	}
+
+	kfree(pool->events);
+	dma_free_coherent(vhost->dev,
+			  pool->size * sizeof(*pool->iu_storage),
+			  pool->iu_storage, pool->iu_token);
+	LEAVE;
+}
+
+/**
+ * ibmvfc_free_queue - Deallocate queue
+ * @vhost:	ibmvfc host struct
+ * @queue:	ibmvfc queue struct
+ *
+ * Unmaps dma and deallocates page for messages
+ **/
+static void ibmvfc_free_queue(struct ibmvfc_host *vhost,
+			      struct ibmvfc_queue *queue)
+{
+	struct device *dev = vhost->dev;
+
+	dma_unmap_single(dev, queue->msg_token, PAGE_SIZE, DMA_BIDIRECTIONAL);
+	free_page((unsigned long)queue->msgs.handle);
+	queue->msgs.handle = NULL;
+
+	ibmvfc_free_event_pool(vhost, queue);
+}
+
+/**
  * ibmvfc_release_crq_queue - Deallocates data and unregisters CRQ
  * @vhost:	ibmvfc host struct
  *
@@ -724,7 +871,7 @@ static void ibmvfc_release_crq_queue(struct ibmvfc_host *vhost)
 {
 	long rc = 0;
 	struct vio_dev *vdev = to_vio_dev(vhost->dev);
-	struct ibmvfc_crq_queue *crq = &vhost->crq;
+	struct ibmvfc_queue *crq = &vhost->crq;
 
 	ibmvfc_dbg(vhost, "Releasing CRQ\n");
 	free_irq(vdev->irq, vhost);
@@ -737,8 +884,8 @@ static void ibmvfc_release_crq_queue(struct ibmvfc_host *vhost)
 
 	vhost->state = IBMVFC_NO_CRQ;
 	vhost->logged_in = 0;
-	dma_unmap_single(vhost->dev, crq->msg_token, PAGE_SIZE, DMA_BIDIRECTIONAL);
-	free_page((unsigned long)crq->msgs);
+
+	ibmvfc_free_queue(vhost, crq);
 }
 
 /**
@@ -778,7 +925,9 @@ static int ibmvfc_reset_crq(struct ibmvfc_host *vhost)
 	int rc = 0;
 	unsigned long flags;
 	struct vio_dev *vdev = to_vio_dev(vhost->dev);
-	struct ibmvfc_crq_queue *crq = &vhost->crq;
+	struct ibmvfc_queue *crq = &vhost->crq;
+	struct ibmvfc_queue *scrq;
+	int i;
 
 	/* Close the CRQ */
 	do {
@@ -788,13 +937,26 @@ static int ibmvfc_reset_crq(struct ibmvfc_host *vhost)
 	} while (rc == H_BUSY || H_IS_LONG_BUSY(rc));
 
 	spin_lock_irqsave(vhost->host->host_lock, flags);
+	spin_lock(vhost->crq.q_lock);
 	vhost->state = IBMVFC_NO_CRQ;
 	vhost->logged_in = 0;
+	vhost->do_enquiry = 1;
+	vhost->using_channels = 0;
 
 	/* Clean out the queue */
-	memset(crq->msgs, 0, PAGE_SIZE);
+	memset(crq->msgs.crq, 0, PAGE_SIZE);
 	crq->cur = 0;
 
+	if (vhost->scsi_scrqs.scrqs) {
+		for (i = 0; i < nr_scsi_hw_queues; i++) {
+			scrq = &vhost->scsi_scrqs.scrqs[i];
+			spin_lock(scrq->q_lock);
+			memset(scrq->msgs.scrq, 0, PAGE_SIZE);
+			scrq->cur = 0;
+			spin_unlock(scrq->q_lock);
+		}
+	}
+
 	/* And re-open it again */
 	rc = plpar_hcall_norets(H_REG_CRQ, vdev->unit_address,
 				crq->msg_token, PAGE_SIZE);
@@ -804,6 +966,7 @@ static int ibmvfc_reset_crq(struct ibmvfc_host *vhost)
 		dev_warn(vhost->dev, "Partner adapter not ready\n");
 	else if (rc != 0)
 		dev_warn(vhost->dev, "Couldn't register crq (rc=%d)\n", rc);
+	spin_unlock(vhost->crq.q_lock);
 	spin_unlock_irqrestore(vhost->host->host_lock, flags);
 
 	return rc;
@@ -835,12 +998,17 @@ static int ibmvfc_valid_event(struct ibmvfc_event_pool *pool,
  **/
 static void ibmvfc_free_event(struct ibmvfc_event *evt)
 {
-	struct ibmvfc_host *vhost = evt->vhost;
-	struct ibmvfc_event_pool *pool = &vhost->pool;
+	struct ibmvfc_event_pool *pool = &evt->queue->evt_pool;
+	unsigned long flags;
 
 	BUG_ON(!ibmvfc_valid_event(pool, evt));
 	BUG_ON(atomic_inc_return(&evt->free) != 1);
-	list_add_tail(&evt->queue, &vhost->free);
+
+	spin_lock_irqsave(&evt->queue->l_lock, flags);
+	list_add_tail(&evt->queue_list, &evt->queue->free);
+	if (evt->eh_comp)
+		complete(evt->eh_comp);
+	spin_unlock_irqrestore(&evt->queue->l_lock, flags);
 }
 
 /**
@@ -859,13 +1027,28 @@ static void ibmvfc_scsi_eh_done(struct ibmvfc_event *evt)
 		cmnd->scsi_done(cmnd);
 	}
 
-	if (evt->eh_comp)
-		complete(evt->eh_comp);
-
 	ibmvfc_free_event(evt);
 }
 
 /**
+ * ibmvfc_complete_purge - Complete failed command list
+ * @purge_list:		list head of failed commands
+ *
+ * This function runs completions on commands to fail as a result of a
+ * host reset or platform migration.
+ **/
+static void ibmvfc_complete_purge(struct list_head *purge_list)
+{
+	struct ibmvfc_event *evt, *pos;
+
+	list_for_each_entry_safe(evt, pos, purge_list, queue_list) {
+		list_del(&evt->queue_list);
+		ibmvfc_trc_end(evt);
+		evt->done(evt);
+	}
+}
+
+/**
  * ibmvfc_fail_request - Fail request with specified error code
  * @evt:		ibmvfc event struct
  * @error_code:	error code to fail request with
@@ -881,10 +1064,7 @@ static void ibmvfc_fail_request(struct ibmvfc_event *evt, int error_code)
 	} else
 		evt->xfer_iu->mad_common.status = cpu_to_be16(IBMVFC_MAD_DRIVER_FAILED);
 
-	list_del(&evt->queue);
 	del_timer(&evt->timer);
-	ibmvfc_trc_end(evt);
-	evt->done(evt);
 }
 
 /**
@@ -898,10 +1078,30 @@ static void ibmvfc_fail_request(struct ibmvfc_event *evt, int error_code)
 static void ibmvfc_purge_requests(struct ibmvfc_host *vhost, int error_code)
 {
 	struct ibmvfc_event *evt, *pos;
+	struct ibmvfc_queue *queues = vhost->scsi_scrqs.scrqs;
+	unsigned long flags;
+	int hwqs = 0;
+	int i;
+
+	if (vhost->using_channels)
+		hwqs = vhost->scsi_scrqs.active_queues;
 
 	ibmvfc_dbg(vhost, "Purging all requests\n");
-	list_for_each_entry_safe(evt, pos, &vhost->sent, queue)
+	spin_lock_irqsave(&vhost->crq.l_lock, flags);
+	list_for_each_entry_safe(evt, pos, &vhost->crq.sent, queue_list)
 		ibmvfc_fail_request(evt, error_code);
+	list_splice_init(&vhost->crq.sent, &vhost->purge);
+	spin_unlock_irqrestore(&vhost->crq.l_lock, flags);
+
+	for (i = 0; i < hwqs; i++) {
+		spin_lock_irqsave(queues[i].q_lock, flags);
+		spin_lock(&queues[i].l_lock);
+		list_for_each_entry_safe(evt, pos, &queues[i].sent, queue_list)
+			ibmvfc_fail_request(evt, error_code);
+		list_splice_init(&queues[i].sent, &vhost->purge);
+		spin_unlock(&queues[i].l_lock);
+		spin_unlock_irqrestore(queues[i].q_lock, flags);
+	}
 }
 
 /**
@@ -1238,6 +1438,7 @@ static void ibmvfc_gather_partition_info(struct ibmvfc_host *vhost)
 static void ibmvfc_set_login_info(struct ibmvfc_host *vhost)
 {
 	struct ibmvfc_npiv_login *login_info = &vhost->login_info;
+	struct ibmvfc_queue *async_crq = &vhost->async_crq;
 	struct device_node *of_node = vhost->dev->of_node;
 	const char *location;
 
@@ -1256,8 +1457,13 @@ static void ibmvfc_set_login_info(struct ibmvfc_host *vhost)
 
 	login_info->max_cmds = cpu_to_be32(max_requests + IBMVFC_NUM_INTERNAL_REQ);
 	login_info->capabilities = cpu_to_be64(IBMVFC_CAN_MIGRATE | IBMVFC_CAN_SEND_VF_WWPN);
+
+	if (vhost->mq_enabled || vhost->using_channels)
+		login_info->capabilities |= cpu_to_be64(IBMVFC_CAN_USE_CHANNELS);
+
 	login_info->async.va = cpu_to_be64(vhost->async_crq.msg_token);
-	login_info->async.len = cpu_to_be32(vhost->async_crq.size * sizeof(*vhost->async_crq.msgs));
+	login_info->async.len = cpu_to_be32(async_crq->size *
+					    sizeof(*async_crq->msgs.async));
 	strncpy(login_info->partition_name, vhost->partition_name, IBMVFC_MAX_NAME);
 	strncpy(login_info->device_name,
 		dev_name(&vhost->host->shost_gendev), IBMVFC_MAX_NAME);
@@ -1268,88 +1474,40 @@ static void ibmvfc_set_login_info(struct ibmvfc_host *vhost)
 }
 
 /**
- * ibmvfc_init_event_pool - Allocates and initializes the event pool for a host
- * @vhost:	ibmvfc host who owns the event pool
- *
- * Returns zero on success.
- **/
-static int ibmvfc_init_event_pool(struct ibmvfc_host *vhost)
-{
-	int i;
-	struct ibmvfc_event_pool *pool = &vhost->pool;
-
-	ENTER;
-	pool->size = max_requests + IBMVFC_NUM_INTERNAL_REQ;
-	pool->events = kcalloc(pool->size, sizeof(*pool->events), GFP_KERNEL);
-	if (!pool->events)
-		return -ENOMEM;
-
-	pool->iu_storage = dma_alloc_coherent(vhost->dev,
-					      pool->size * sizeof(*pool->iu_storage),
-					      &pool->iu_token, 0);
-
-	if (!pool->iu_storage) {
-		kfree(pool->events);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < pool->size; ++i) {
-		struct ibmvfc_event *evt = &pool->events[i];
-		atomic_set(&evt->free, 1);
-		evt->crq.valid = 0x80;
-		evt->crq.ioba = cpu_to_be64(pool->iu_token + (sizeof(*evt->xfer_iu) * i));
-		evt->xfer_iu = pool->iu_storage + i;
-		evt->vhost = vhost;
-		evt->ext_list = NULL;
-		list_add_tail(&evt->queue, &vhost->free);
-	}
-
-	LEAVE;
-	return 0;
-}
-
-/**
- * ibmvfc_free_event_pool - Frees memory of the event pool of a host
- * @vhost:	ibmvfc host who owns the event pool
+ * ibmvfc_get_event - Gets the next free event in pool
+ * @vhost:	ibmvfc host struct
  *
+ * Returns a free event from the pool.
  **/
-static void ibmvfc_free_event_pool(struct ibmvfc_host *vhost)
+static struct ibmvfc_event *ibmvfc_get_event(struct ibmvfc_queue *queue)
 {
-	int i;
-	struct ibmvfc_event_pool *pool = &vhost->pool;
-
-	ENTER;
-	for (i = 0; i < pool->size; ++i) {
-		list_del(&pool->events[i].queue);
-		BUG_ON(atomic_read(&pool->events[i].free) != 1);
-		if (pool->events[i].ext_list)
-			dma_pool_free(vhost->sg_pool,
-				      pool->events[i].ext_list,
-				      pool->events[i].ext_list_token);
-	}
+	struct ibmvfc_event *evt;
+	unsigned long flags;
 
-	kfree(pool->events);
-	dma_free_coherent(vhost->dev,
-			  pool->size * sizeof(*pool->iu_storage),
-			  pool->iu_storage, pool->iu_token);
-	LEAVE;
+	spin_lock_irqsave(&queue->l_lock, flags);
+	BUG_ON(list_empty(&queue->free));
+	evt = list_entry(queue->free.next, struct ibmvfc_event, queue_list);
+	atomic_set(&evt->free, 0);
+	list_del(&evt->queue_list);
+	spin_unlock_irqrestore(&queue->l_lock, flags);
+	return evt;
 }
 
 /**
- * ibmvfc_get_event - Gets the next free event in pool
- * @vhost:	ibmvfc host struct
+ * ibmvfc_locked_done - Calls evt completion with host_lock held
+ * @evt:	ibmvfc evt to complete
  *
- * Returns a free event from the pool.
+ * All non-scsi command completion callbacks have the expectation that the
+ * host_lock is held. This callback is used by ibmvfc_init_event to wrap a
+ * MAD evt with the host_lock.
  **/
-static struct ibmvfc_event *ibmvfc_get_event(struct ibmvfc_host *vhost)
+static void ibmvfc_locked_done(struct ibmvfc_event *evt)
 {
-	struct ibmvfc_event *evt;
+	unsigned long flags;
 
-	BUG_ON(list_empty(&vhost->free));
-	evt = list_entry(vhost->free.next, struct ibmvfc_event, queue);
-	atomic_set(&evt->free, 0);
-	list_del(&evt->queue);
-	return evt;
+	spin_lock_irqsave(evt->vhost->host->host_lock, flags);
+	evt->_done(evt);
+	spin_unlock_irqrestore(evt->vhost->host->host_lock, flags);
 }
 
 /**
@@ -1364,9 +1522,15 @@ static void ibmvfc_init_event(struct ibmvfc_event *evt,
 {
 	evt->cmnd = NULL;
 	evt->sync_iu = NULL;
-	evt->crq.format = format;
-	evt->done = done;
 	evt->eh_comp = NULL;
+	evt->crq.format = format;
+	if (format == IBMVFC_CMD_FORMAT)
+		evt->done = done;
+	else {
+		evt->_done = done;
+		evt->done = ibmvfc_locked_done;
+	}
+	evt->hwq = 0;
 }
 
 /**
@@ -1482,6 +1646,7 @@ static int ibmvfc_send_event(struct ibmvfc_event *evt,
 			     struct ibmvfc_host *vhost, unsigned long timeout)
 {
 	__be64 *crq_as_u64 = (__be64 *) &evt->crq;
+	unsigned long flags;
 	int rc;
 
 	/* Copy the IU into the transfer area */
@@ -1493,7 +1658,6 @@ static int ibmvfc_send_event(struct ibmvfc_event *evt,
 	else
 		BUG();
 
-	list_add_tail(&evt->queue, &vhost->sent);
 	timer_setup(&evt->timer, ibmvfc_timeout, 0);
 
 	if (timeout) {
@@ -1501,11 +1665,24 @@ static int ibmvfc_send_event(struct ibmvfc_event *evt,
 		add_timer(&evt->timer);
 	}
 
+	spin_lock_irqsave(&evt->queue->l_lock, flags);
+	list_add_tail(&evt->queue_list, &evt->queue->sent);
+
 	mb();
 
-	if ((rc = ibmvfc_send_crq(vhost, be64_to_cpu(crq_as_u64[0]),
-				  be64_to_cpu(crq_as_u64[1])))) {
-		list_del(&evt->queue);
+	if (evt->queue->fmt == IBMVFC_SUB_CRQ_FMT)
+		rc = ibmvfc_send_sub_crq(vhost,
+					 evt->queue->vios_cookie,
+					 be64_to_cpu(crq_as_u64[0]),
+					 be64_to_cpu(crq_as_u64[1]),
+					 0, 0);
+	else
+		rc = ibmvfc_send_crq(vhost, be64_to_cpu(crq_as_u64[0]),
+				     be64_to_cpu(crq_as_u64[1]));
+
+	if (rc) {
+		list_del(&evt->queue_list);
+		spin_unlock_irqrestore(&evt->queue->l_lock, flags);
 		del_timer(&evt->timer);
 
 		/* If send_crq returns H_CLOSED, return SCSI_MLQUEUE_HOST_BUSY.
@@ -1530,8 +1707,10 @@ static int ibmvfc_send_event(struct ibmvfc_event *evt,
 			evt->xfer_iu->mad_common.status = cpu_to_be16(IBMVFC_MAD_CRQ_ERROR);
 
 		evt->done(evt);
-	} else
+	} else {
+		spin_unlock_irqrestore(&evt->queue->l_lock, flags);
 		ibmvfc_trc_start(evt);
+	}
 
 	return 0;
 }
@@ -1579,7 +1758,9 @@ static void ibmvfc_relogin(struct scsi_device *sdev)
 	struct ibmvfc_host *vhost = shost_priv(sdev->host);
 	struct fc_rport *rport = starget_to_rport(scsi_target(sdev));
 	struct ibmvfc_target *tgt;
+	unsigned long flags;
 
+	spin_lock_irqsave(vhost->host->host_lock, flags);
 	list_for_each_entry(tgt, &vhost->targets, queue) {
 		if (rport == tgt->rport) {
 			ibmvfc_del_tgt(tgt);
@@ -1588,6 +1769,7 @@ static void ibmvfc_relogin(struct scsi_device *sdev)
 	}
 
 	ibmvfc_reinit_host(vhost);
+	spin_unlock_irqrestore(vhost->host->host_lock, flags);
 }
 
 /**
@@ -1639,9 +1821,6 @@ static void ibmvfc_scsi_done(struct ibmvfc_event *evt)
 		cmnd->scsi_done(cmnd);
 	}
 
-	if (evt->eh_comp)
-		complete(evt->eh_comp);
-
 	ibmvfc_free_event(evt);
 }
 
@@ -1710,28 +1889,35 @@ static struct ibmvfc_cmd *ibmvfc_init_vfc_cmd(struct ibmvfc_event *evt, struct s
  * Returns:
  *	0 on success / other on failure
  **/
-static int ibmvfc_queuecommand_lck(struct scsi_cmnd *cmnd,
-			       void (*done) (struct scsi_cmnd *))
+static int ibmvfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 {
-	struct ibmvfc_host *vhost = shost_priv(cmnd->device->host);
+	struct ibmvfc_host *vhost = shost_priv(shost);
 	struct fc_rport *rport = starget_to_rport(scsi_target(cmnd->device));
 	struct ibmvfc_cmd *vfc_cmd;
 	struct ibmvfc_fcp_cmd_iu *iu;
 	struct ibmvfc_event *evt;
+	u32 tag_and_hwq = blk_mq_unique_tag(cmnd->request);
+	u16 hwq = blk_mq_unique_tag_to_hwq(tag_and_hwq);
+	u16 scsi_channel;
 	int rc;
 
 	if (unlikely((rc = fc_remote_port_chkready(rport))) ||
 	    unlikely((rc = ibmvfc_host_chkready(vhost)))) {
 		cmnd->result = rc;
-		done(cmnd);
+		cmnd->scsi_done(cmnd);
 		return 0;
 	}
 
 	cmnd->result = (DID_OK << 16);
-	evt = ibmvfc_get_event(vhost);
+	if (vhost->using_channels) {
+		scsi_channel = hwq % vhost->scsi_scrqs.active_queues;
+		evt = ibmvfc_get_event(&vhost->scsi_scrqs.scrqs[scsi_channel]);
+		evt->hwq = hwq % vhost->scsi_scrqs.active_queues;
+	} else
+		evt = ibmvfc_get_event(&vhost->crq);
+
 	ibmvfc_init_event(evt, ibmvfc_scsi_done, IBMVFC_CMD_FORMAT);
 	evt->cmnd = cmnd;
-	cmnd->scsi_done = done;
 
 	vfc_cmd = ibmvfc_init_vfc_cmd(evt, cmnd->device);
 	iu = ibmvfc_get_fcp_iu(vhost, vfc_cmd);
@@ -1758,12 +1944,10 @@ static int ibmvfc_queuecommand_lck(struct scsi_cmnd *cmnd,
 			    "Failed to map DMA buffer for command. rc=%d\n", rc);
 
 	cmnd->result = DID_ERROR << 16;
-	done(cmnd);
+	cmnd->scsi_done(cmnd);
 	return 0;
 }
 
-static DEF_SCSI_QCMD(ibmvfc_queuecommand)
-
 /**
  * ibmvfc_sync_completion - Signal that a synchronous command has completed
  * @evt:	ibmvfc event struct
@@ -1817,7 +2001,7 @@ static int ibmvfc_bsg_timeout(struct bsg_job *job)
 	}
 
 	vhost->aborting_passthru = 1;
-	evt = ibmvfc_get_event(vhost);
+	evt = ibmvfc_get_event(&vhost->crq);
 	ibmvfc_init_event(evt, ibmvfc_bsg_timeout_done, IBMVFC_MAD_FORMAT);
 
 	tmf = &evt->iu.tmf;
@@ -1875,7 +2059,7 @@ static int ibmvfc_bsg_plogi(struct ibmvfc_host *vhost, unsigned int port_id)
 	if (unlikely((rc = ibmvfc_host_chkready(vhost))))
 		goto unlock_out;
 
-	evt = ibmvfc_get_event(vhost);
+	evt = ibmvfc_get_event(&vhost->crq);
 	ibmvfc_init_event(evt, ibmvfc_sync_completion, IBMVFC_MAD_FORMAT);
 	plogi = &evt->iu.plogi;
 	memset(plogi, 0, sizeof(*plogi));
@@ -1993,7 +2177,7 @@ static int ibmvfc_bsg_request(struct bsg_job *job)
 		goto out;
 	}
 
-	evt = ibmvfc_get_event(vhost);
+	evt = ibmvfc_get_event(&vhost->crq);
 	ibmvfc_init_event(evt, ibmvfc_sync_completion, IBMVFC_MAD_FORMAT);
 	mad = &evt->iu.passthru;
 
@@ -2077,7 +2261,11 @@ static int ibmvfc_reset_device(struct scsi_device *sdev, int type, char *desc)
 
 	spin_lock_irqsave(vhost->host->host_lock, flags);
 	if (vhost->state == IBMVFC_ACTIVE) {
-		evt = ibmvfc_get_event(vhost);
+		if (vhost->using_channels)
+			evt = ibmvfc_get_event(&vhost->scsi_scrqs.scrqs[0]);
+		else
+			evt = ibmvfc_get_event(&vhost->crq);
+
 		ibmvfc_init_event(evt, ibmvfc_sync_completion, IBMVFC_CMD_FORMAT);
 		tmf = ibmvfc_init_vfc_cmd(evt, sdev);
 		iu = ibmvfc_get_fcp_iu(vhost, tmf);
@@ -2195,28 +2383,28 @@ static int ibmvfc_wait_for_ops(struct ibmvfc_host *vhost, void *device,
 	ENTER;
 	do {
 		wait = 0;
-		spin_lock_irqsave(vhost->host->host_lock, flags);
-		list_for_each_entry(evt, &vhost->sent, queue) {
+		spin_lock_irqsave(&vhost->crq.l_lock, flags);
+		list_for_each_entry(evt, &vhost->crq.sent, queue_list) {
 			if (match(evt, device)) {
 				evt->eh_comp = &comp;
 				wait++;
 			}
 		}
-		spin_unlock_irqrestore(vhost->host->host_lock, flags);
+		spin_unlock_irqrestore(&vhost->crq.l_lock, flags);
 
 		if (wait) {
 			timeout = wait_for_completion_timeout(&comp, timeout);
 
 			if (!timeout) {
 				wait = 0;
-				spin_lock_irqsave(vhost->host->host_lock, flags);
-				list_for_each_entry(evt, &vhost->sent, queue) {
+				spin_lock_irqsave(&vhost->crq.l_lock, flags);
+				list_for_each_entry(evt, &vhost->crq.sent, queue_list) {
 					if (match(evt, device)) {
 						evt->eh_comp = NULL;
 						wait++;
 					}
 				}
-				spin_unlock_irqrestore(vhost->host->host_lock, flags);
+				spin_unlock_irqrestore(&vhost->crq.l_lock, flags);
 				if (wait)
 					dev_err(vhost->dev, "Timed out waiting for aborted commands\n");
 				LEAVE;
@@ -2229,23 +2417,123 @@ static int ibmvfc_wait_for_ops(struct ibmvfc_host *vhost, void *device,
 	return SUCCESS;
 }
 
-/**
- * ibmvfc_cancel_all - Cancel all outstanding commands to the device
- * @sdev:	scsi device to cancel commands
- * @type:	type of error recovery being performed
- *
- * This sends a cancel to the VIOS for the specified device. This does
- * NOT send any abort to the actual device. That must be done separately.
- *
- * Returns:
- *	0 on success / other on failure
- **/
-static int ibmvfc_cancel_all(struct scsi_device *sdev, int type)
+static struct ibmvfc_event *ibmvfc_init_tmf(struct ibmvfc_queue *queue,
+					    struct scsi_device *sdev,
+					    int type)
 {
 	struct ibmvfc_host *vhost = shost_priv(sdev->host);
 	struct scsi_target *starget = scsi_target(sdev);
 	struct fc_rport *rport = starget_to_rport(starget);
+	struct ibmvfc_event *evt;
 	struct ibmvfc_tmf *tmf;
+
+	evt = ibmvfc_get_event(queue);
+	ibmvfc_init_event(evt, ibmvfc_sync_completion, IBMVFC_MAD_FORMAT);
+
+	tmf = &evt->iu.tmf;
+	memset(tmf, 0, sizeof(*tmf));
+	if (ibmvfc_check_caps(vhost, IBMVFC_HANDLE_VF_WWPN)) {
+		tmf->common.version = cpu_to_be32(2);
+		tmf->target_wwpn = cpu_to_be64(rport->port_name);
+	} else {
+		tmf->common.version = cpu_to_be32(1);
+	}
+	tmf->common.opcode = cpu_to_be32(IBMVFC_TMF_MAD);
+	tmf->common.length = cpu_to_be16(sizeof(*tmf));
+	tmf->scsi_id = cpu_to_be64(rport->port_id);
+	int_to_scsilun(sdev->lun, &tmf->lun);
+	if (!ibmvfc_check_caps(vhost, IBMVFC_CAN_SUPPRESS_ABTS))
+		type &= ~IBMVFC_TMF_SUPPRESS_ABTS;
+	if (vhost->state == IBMVFC_ACTIVE)
+		tmf->flags = cpu_to_be32((type | IBMVFC_TMF_LUA_VALID));
+	else
+		tmf->flags = cpu_to_be32(((type & IBMVFC_TMF_SUPPRESS_ABTS) | IBMVFC_TMF_LUA_VALID));
+	tmf->cancel_key = cpu_to_be32((unsigned long)sdev->hostdata);
+	tmf->my_cancel_key = cpu_to_be32((unsigned long)starget->hostdata);
+
+	init_completion(&evt->comp);
+
+	return evt;
+}
+
+static int ibmvfc_cancel_all_mq(struct scsi_device *sdev, int type)
+{
+	struct ibmvfc_host *vhost = shost_priv(sdev->host);
+	struct ibmvfc_event *evt, *found_evt, *temp;
+	struct ibmvfc_queue *queues = vhost->scsi_scrqs.scrqs;
+	unsigned long flags;
+	int num_hwq, i;
+	int fail = 0;
+	LIST_HEAD(cancelq);
+	u16 status;
+
+	ENTER;
+	spin_lock_irqsave(vhost->host->host_lock, flags);
+	num_hwq = vhost->scsi_scrqs.active_queues;
+	for (i = 0; i < num_hwq; i++) {
+		spin_lock(queues[i].q_lock);
+		spin_lock(&queues[i].l_lock);
+		found_evt = NULL;
+		list_for_each_entry(evt, &queues[i].sent, queue_list) {
+			if (evt->cmnd && evt->cmnd->device == sdev) {
+				found_evt = evt;
+				break;
+			}
+		}
+		spin_unlock(&queues[i].l_lock);
+
+		if (found_evt && vhost->logged_in) {
+			evt = ibmvfc_init_tmf(&queues[i], sdev, type);
+			evt->sync_iu = &queues[i].cancel_rsp;
+			ibmvfc_send_event(evt, vhost, default_timeout);
+			list_add_tail(&evt->cancel, &cancelq);
+		}
+
+		spin_unlock(queues[i].q_lock);
+	}
+	spin_unlock_irqrestore(vhost->host->host_lock, flags);
+
+	if (list_empty(&cancelq)) {
+		if (vhost->log_level > IBMVFC_DEFAULT_LOG_LEVEL)
+			sdev_printk(KERN_INFO, sdev, "No events found to cancel\n");
+		return 0;
+	}
+
+	sdev_printk(KERN_INFO, sdev, "Cancelling outstanding commands.\n");
+
+	list_for_each_entry_safe(evt, temp, &cancelq, cancel) {
+		wait_for_completion(&evt->comp);
+		status = be16_to_cpu(evt->queue->cancel_rsp.mad_common.status);
+		list_del(&evt->cancel);
+		ibmvfc_free_event(evt);
+
+		if (status != IBMVFC_MAD_SUCCESS) {
+			sdev_printk(KERN_WARNING, sdev, "Cancel failed with rc=%x\n", status);
+			switch (status) {
+			case IBMVFC_MAD_DRIVER_FAILED:
+			case IBMVFC_MAD_CRQ_ERROR:
+			/* Host adapter most likely going through reset, return success to
+			 * the caller will wait for the command being cancelled to get returned
+			 */
+				break;
+			default:
+				fail = 1;
+				break;
+			}
+		}
+	}
+
+	if (fail)
+		return -EIO;
+
+	sdev_printk(KERN_INFO, sdev, "Successfully cancelled outstanding commands\n");
+	LEAVE;
+	return 0;
+}
+
+static int ibmvfc_cancel_all_sq(struct scsi_device *sdev, int type)
+{
+	struct ibmvfc_host *vhost = shost_priv(sdev->host);
 	struct ibmvfc_event *evt, *found_evt;
 	union ibmvfc_iu rsp;
 	int rsp_rc = -EBUSY;
@@ -2253,14 +2541,16 @@ static int ibmvfc_cancel_all(struct scsi_device *sdev, int type)
 	u16 status;
 
 	ENTER;
-	spin_lock_irqsave(vhost->host->host_lock, flags);
 	found_evt = NULL;
-	list_for_each_entry(evt, &vhost->sent, queue) {
+	spin_lock_irqsave(vhost->host->host_lock, flags);
+	spin_lock(&vhost->crq.l_lock);
+	list_for_each_entry(evt, &vhost->crq.sent, queue_list) {
 		if (evt->cmnd && evt->cmnd->device == sdev) {
 			found_evt = evt;
 			break;
 		}
 	}
+	spin_unlock(&vhost->crq.l_lock);
 
 	if (!found_evt) {
 		if (vhost->log_level > IBMVFC_DEFAULT_LOG_LEVEL)
@@ -2270,32 +2560,8 @@ static int ibmvfc_cancel_all(struct scsi_device *sdev, int type)
 	}
 
 	if (vhost->logged_in) {
-		evt = ibmvfc_get_event(vhost);
-		ibmvfc_init_event(evt, ibmvfc_sync_completion, IBMVFC_MAD_FORMAT);
-
-		tmf = &evt->iu.tmf;
-		memset(tmf, 0, sizeof(*tmf));
-		if (ibmvfc_check_caps(vhost, IBMVFC_HANDLE_VF_WWPN)) {
-			tmf->common.version = cpu_to_be32(2);
-			tmf->target_wwpn = cpu_to_be64(rport->port_name);
-		} else {
-			tmf->common.version = cpu_to_be32(1);
-		}
-		tmf->common.opcode = cpu_to_be32(IBMVFC_TMF_MAD);
-		tmf->common.length = cpu_to_be16(sizeof(*tmf));
-		tmf->scsi_id = cpu_to_be64(rport->port_id);
-		int_to_scsilun(sdev->lun, &tmf->lun);
-		if (!ibmvfc_check_caps(vhost, IBMVFC_CAN_SUPPRESS_ABTS))
-			type &= ~IBMVFC_TMF_SUPPRESS_ABTS;
-		if (vhost->state == IBMVFC_ACTIVE)
-			tmf->flags = cpu_to_be32((type | IBMVFC_TMF_LUA_VALID));
-		else
-			tmf->flags = cpu_to_be32(((type & IBMVFC_TMF_SUPPRESS_ABTS) | IBMVFC_TMF_LUA_VALID));
-		tmf->cancel_key = cpu_to_be32((unsigned long)sdev->hostdata);
-		tmf->my_cancel_key = cpu_to_be32((unsigned long)starget->hostdata);
-
+		evt = ibmvfc_init_tmf(&vhost->crq, sdev, type);
 		evt->sync_iu = &rsp;
-		init_completion(&evt->comp);
 		rsp_rc = ibmvfc_send_event(evt, vhost, default_timeout);
 	}
 
@@ -2335,6 +2601,27 @@ static int ibmvfc_cancel_all(struct scsi_device *sdev, int type)
 }
 
 /**
+ * ibmvfc_cancel_all - Cancel all outstanding commands to the device
+ * @sdev:	scsi device to cancel commands
+ * @type:	type of error recovery being performed
+ *
+ * This sends a cancel to the VIOS for the specified device. This does
+ * NOT send any abort to the actual device. That must be done separately.
+ *
+ * Returns:
+ *	0 on success / other on failure
+ **/
+static int ibmvfc_cancel_all(struct scsi_device *sdev, int type)
+{
+	struct ibmvfc_host *vhost = shost_priv(sdev->host);
+
+	if (vhost->mq_enabled && vhost->using_channels)
+		return ibmvfc_cancel_all_mq(sdev, type);
+	else
+		return ibmvfc_cancel_all_sq(sdev, type);
+}
+
+/**
  * ibmvfc_match_key - Match function for specified cancel key
  * @evt:	ibmvfc event struct
  * @key:	cancel key to match
@@ -2390,14 +2677,16 @@ static int ibmvfc_abort_task_set(struct scsi_device *sdev)
 	unsigned long flags, timeout = IBMVFC_ABORT_TIMEOUT;
 	int rsp_code = 0;
 
-	spin_lock_irqsave(vhost->host->host_lock, flags);
 	found_evt = NULL;
-	list_for_each_entry(evt, &vhost->sent, queue) {
+	spin_lock_irqsave(vhost->host->host_lock, flags);
+	spin_lock(&vhost->crq.l_lock);
+	list_for_each_entry(evt, &vhost->crq.sent, queue_list) {
 		if (evt->cmnd && evt->cmnd->device == sdev) {
 			found_evt = evt;
 			break;
 		}
 	}
+	spin_unlock(&vhost->crq.l_lock);
 
 	if (!found_evt) {
 		if (vhost->log_level > IBMVFC_DEFAULT_LOG_LEVEL)
@@ -2407,7 +2696,7 @@ static int ibmvfc_abort_task_set(struct scsi_device *sdev)
 	}
 
 	if (vhost->state == IBMVFC_ACTIVE) {
-		evt = ibmvfc_get_event(vhost);
+		evt = ibmvfc_get_event(&vhost->crq);
 		ibmvfc_init_event(evt, ibmvfc_sync_completion, IBMVFC_CMD_FORMAT);
 		tmf = ibmvfc_init_vfc_cmd(evt, sdev);
 		iu = ibmvfc_get_fcp_iu(vhost, tmf);
@@ -2839,7 +3128,8 @@ static void ibmvfc_handle_async(struct ibmvfc_async_crq *crq,
  * @vhost:	ibmvfc host struct
  *
  **/
-static void ibmvfc_handle_crq(struct ibmvfc_crq *crq, struct ibmvfc_host *vhost)
+static void ibmvfc_handle_crq(struct ibmvfc_crq *crq, struct ibmvfc_host *vhost,
+			      struct list_head *evt_doneq)
 {
 	long rc;
 	struct ibmvfc_event *evt = (struct ibmvfc_event *)be64_to_cpu(crq->ioba);
@@ -2898,7 +3188,7 @@ static void ibmvfc_handle_crq(struct ibmvfc_crq *crq, struct ibmvfc_host *vhost)
 	 * things we send. Make sure this response is to something we
 	 * actually sent
 	 */
-	if (unlikely(!ibmvfc_valid_event(&vhost->pool, evt))) {
+	if (unlikely(!ibmvfc_valid_event(&vhost->crq.evt_pool, evt))) {
 		dev_err(vhost->dev, "Returned correlation_token 0x%08llx is invalid!\n",
 			crq->ioba);
 		return;
@@ -2910,10 +3200,9 @@ static void ibmvfc_handle_crq(struct ibmvfc_crq *crq, struct ibmvfc_host *vhost)
 		return;
 	}
 
-	del_timer(&evt->timer);
-	list_del(&evt->queue);
-	ibmvfc_trc_end(evt);
-	evt->done(evt);
+	spin_lock(&evt->queue->l_lock);
+	list_move_tail(&evt->queue_list, evt_doneq);
+	spin_unlock(&evt->queue->l_lock);
 }
 
 /**
@@ -3132,6 +3421,37 @@ static ssize_t ibmvfc_store_log_level(struct device *dev,
 	return strlen(buf);
 }
 
+static ssize_t ibmvfc_show_scsi_channels(struct device *dev,
+					 struct device_attribute *attr, char *buf)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+	struct ibmvfc_host *vhost = shost_priv(shost);
+	unsigned long flags = 0;
+	int len;
+
+	spin_lock_irqsave(shost->host_lock, flags);
+	len = snprintf(buf, PAGE_SIZE, "%d\n", vhost->client_scsi_channels);
+	spin_unlock_irqrestore(shost->host_lock, flags);
+	return len;
+}
+
+static ssize_t ibmvfc_store_scsi_channels(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf, size_t count)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+	struct ibmvfc_host *vhost = shost_priv(shost);
+	unsigned long flags = 0;
+	unsigned int channels;
+
+	spin_lock_irqsave(shost->host_lock, flags);
+	channels = simple_strtoul(buf, NULL, 10);
+	vhost->client_scsi_channels = min(channels, nr_scsi_hw_queues);
+	ibmvfc_hard_reset_host(vhost);
+	spin_unlock_irqrestore(shost->host_lock, flags);
+	return strlen(buf);
+}
+
 static DEVICE_ATTR(partition_name, S_IRUGO, ibmvfc_show_host_partition_name, NULL);
 static DEVICE_ATTR(device_name, S_IRUGO, ibmvfc_show_host_device_name, NULL);
 static DEVICE_ATTR(port_loc_code, S_IRUGO, ibmvfc_show_host_loc_code, NULL);
@@ -3140,6 +3460,8 @@ static DEVICE_ATTR(npiv_version, S_IRUGO, ibmvfc_show_host_npiv_version, NULL);
 static DEVICE_ATTR(capabilities, S_IRUGO, ibmvfc_show_host_capabilities, NULL);
 static DEVICE_ATTR(log_level, S_IRUGO | S_IWUSR,
 		   ibmvfc_show_log_level, ibmvfc_store_log_level);
+static DEVICE_ATTR(nr_scsi_channels, S_IRUGO | S_IWUSR,
+		   ibmvfc_show_scsi_channels, ibmvfc_store_scsi_channels);
 
 #ifdef CONFIG_SCSI_IBMVFC_TRACE
 /**
@@ -3196,6 +3518,7 @@ static struct device_attribute *ibmvfc_attrs[] = {
 	&dev_attr_npiv_version,
 	&dev_attr_capabilities,
 	&dev_attr_log_level,
+	&dev_attr_nr_scsi_channels,
 	NULL
 };
 
@@ -3221,6 +3544,7 @@ static struct scsi_host_template driver_template = {
 	.max_sectors = IBMVFC_MAX_SECTORS,
 	.shost_attrs = ibmvfc_attrs,
 	.track_queue_depth = 1,
+	.host_tagset = 1,
 };
 
 /**
@@ -3232,10 +3556,10 @@ static struct scsi_host_template driver_template = {
  **/
 static struct ibmvfc_async_crq *ibmvfc_next_async_crq(struct ibmvfc_host *vhost)
 {
-	struct ibmvfc_async_crq_queue *async_crq = &vhost->async_crq;
+	struct ibmvfc_queue *async_crq = &vhost->async_crq;
 	struct ibmvfc_async_crq *crq;
 
-	crq = &async_crq->msgs[async_crq->cur];
+	crq = &async_crq->msgs.async[async_crq->cur];
 	if (crq->valid & 0x80) {
 		if (++async_crq->cur == async_crq->size)
 			async_crq->cur = 0;
@@ -3255,10 +3579,10 @@ static struct ibmvfc_async_crq *ibmvfc_next_async_crq(struct ibmvfc_host *vhost)
  **/
 static struct ibmvfc_crq *ibmvfc_next_crq(struct ibmvfc_host *vhost)
 {
-	struct ibmvfc_crq_queue *queue = &vhost->crq;
+	struct ibmvfc_queue *queue = &vhost->crq;
 	struct ibmvfc_crq *crq;
 
-	crq = &queue->msgs[queue->cur];
+	crq = &queue->msgs.crq[queue->cur];
 	if (crq->valid & 0x80) {
 		if (++queue->cur == queue->size)
 			queue->cur = 0;
@@ -3302,10 +3626,13 @@ static void ibmvfc_tasklet(void *data)
 	struct vio_dev *vdev = to_vio_dev(vhost->dev);
 	struct ibmvfc_crq *crq;
 	struct ibmvfc_async_crq *async;
+	struct ibmvfc_event *evt, *temp;
 	unsigned long flags;
 	int done = 0;
+	LIST_HEAD(evt_doneq);
 
 	spin_lock_irqsave(vhost->host->host_lock, flags);
+	spin_lock(vhost->crq.q_lock);
 	while (!done) {
 		/* Pull all the valid messages off the async CRQ */
 		while ((async = ibmvfc_next_async_crq(vhost)) != NULL) {
@@ -3316,7 +3643,7 @@ static void ibmvfc_tasklet(void *data)
 
 		/* Pull all the valid messages off the CRQ */
 		while ((crq = ibmvfc_next_crq(vhost)) != NULL) {
-			ibmvfc_handle_crq(crq, vhost);
+			ibmvfc_handle_crq(crq, vhost, &evt_doneq);
 			crq->valid = 0;
 			wmb();
 		}
@@ -3329,14 +3656,138 @@ static void ibmvfc_tasklet(void *data)
 			wmb();
 		} else if ((crq = ibmvfc_next_crq(vhost)) != NULL) {
 			vio_disable_interrupts(vdev);
-			ibmvfc_handle_crq(crq, vhost);
+			ibmvfc_handle_crq(crq, vhost, &evt_doneq);
 			crq->valid = 0;
 			wmb();
 		} else
 			done = 1;
 	}
 
+	spin_unlock(vhost->crq.q_lock);
 	spin_unlock_irqrestore(vhost->host->host_lock, flags);
+
+	list_for_each_entry_safe(evt, temp, &evt_doneq, queue_list) {
+		del_timer(&evt->timer);
+		list_del(&evt->queue_list);
+		ibmvfc_trc_end(evt);
+		evt->done(evt);
+	}
+}
+
+static int ibmvfc_toggle_scrq_irq(struct ibmvfc_queue *scrq, int enable)
+{
+	struct device *dev = scrq->vhost->dev;
+	struct vio_dev *vdev = to_vio_dev(dev);
+	unsigned long rc;
+	int irq_action = H_ENABLE_VIO_INTERRUPT;
+
+	if (!enable)
+		irq_action = H_DISABLE_VIO_INTERRUPT;
+
+	rc = plpar_hcall_norets(H_VIOCTL, vdev->unit_address, irq_action,
+				scrq->hw_irq, 0, 0);
+
+	if (rc)
+		dev_err(dev, "Couldn't %s sub-crq[%lu] irq. rc=%ld\n",
+			enable ? "enable" : "disable", scrq->hwq_id, rc);
+
+	return rc;
+}
+
+static void ibmvfc_handle_scrq(struct ibmvfc_crq *crq, struct ibmvfc_host *vhost,
+			       struct list_head *evt_doneq)
+{
+	struct ibmvfc_event *evt = (struct ibmvfc_event *)be64_to_cpu(crq->ioba);
+
+	switch (crq->valid) {
+	case IBMVFC_CRQ_CMD_RSP:
+		break;
+	case IBMVFC_CRQ_XPORT_EVENT:
+		return;
+	default:
+		dev_err(vhost->dev, "Got and invalid message type 0x%02x\n", crq->valid);
+		return;
+	}
+
+	/* The only kind of payload CRQs we should get are responses to
+	 * things we send. Make sure this response is to something we
+	 * actually sent
+	 */
+	if (unlikely(!ibmvfc_valid_event(&evt->queue->evt_pool, evt))) {
+		dev_err(vhost->dev, "Returned correlation_token 0x%08llx is invalid!\n",
+			crq->ioba);
+		return;
+	}
+
+	if (unlikely(atomic_read(&evt->free))) {
+		dev_err(vhost->dev, "Received duplicate correlation_token 0x%08llx!\n",
+			crq->ioba);
+		return;
+	}
+
+	spin_lock(&evt->queue->l_lock);
+	list_move_tail(&evt->queue_list, evt_doneq);
+	spin_unlock(&evt->queue->l_lock);
+}
+
+static struct ibmvfc_crq *ibmvfc_next_scrq(struct ibmvfc_queue *scrq)
+{
+	struct ibmvfc_crq *crq;
+
+	crq = &scrq->msgs.scrq[scrq->cur].crq;
+	if (crq->valid & 0x80) {
+		if (++scrq->cur == scrq->size)
+			scrq->cur = 0;
+		rmb();
+	} else
+		crq = NULL;
+
+	return crq;
+}
+
+static void ibmvfc_drain_sub_crq(struct ibmvfc_queue *scrq)
+{
+	struct ibmvfc_crq *crq;
+	struct ibmvfc_event *evt, *temp;
+	unsigned long flags;
+	int done = 0;
+	LIST_HEAD(evt_doneq);
+
+	spin_lock_irqsave(scrq->q_lock, flags);
+	while (!done) {
+		while ((crq = ibmvfc_next_scrq(scrq)) != NULL) {
+			ibmvfc_handle_scrq(crq, scrq->vhost, &evt_doneq);
+			crq->valid = 0;
+			wmb();
+		}
+
+		ibmvfc_toggle_scrq_irq(scrq, 1);
+		if ((crq = ibmvfc_next_scrq(scrq)) != NULL) {
+			ibmvfc_toggle_scrq_irq(scrq, 0);
+			ibmvfc_handle_scrq(crq, scrq->vhost, &evt_doneq);
+			crq->valid = 0;
+			wmb();
+		} else
+			done = 1;
+	}
+	spin_unlock_irqrestore(scrq->q_lock, flags);
+
+	list_for_each_entry_safe(evt, temp, &evt_doneq, queue_list) {
+		del_timer(&evt->timer);
+		list_del(&evt->queue_list);
+		ibmvfc_trc_end(evt);
+		evt->done(evt);
+	}
+}
+
+static irqreturn_t ibmvfc_interrupt_scsi(int irq, void *scrq_instance)
+{
+	struct ibmvfc_queue *scrq = (struct ibmvfc_queue *)scrq_instance;
+
+	ibmvfc_toggle_scrq_irq(scrq, 0);
+	ibmvfc_drain_sub_crq(scrq);
+
+	return IRQ_HANDLED;
 }
 
 /**
@@ -3491,7 +3942,7 @@ static void ibmvfc_tgt_send_prli(struct ibmvfc_target *tgt)
 		return;
 
 	kref_get(&tgt->kref);
-	evt = ibmvfc_get_event(vhost);
+	evt = ibmvfc_get_event(&vhost->crq);
 	vhost->discovery_threads++;
 	ibmvfc_init_event(evt, ibmvfc_tgt_prli_done, IBMVFC_MAD_FORMAT);
 	evt->tgt = tgt;
@@ -3598,7 +4049,7 @@ static void ibmvfc_tgt_send_plogi(struct ibmvfc_target *tgt)
 
 	kref_get(&tgt->kref);
 	tgt->logo_rcvd = 0;
-	evt = ibmvfc_get_event(vhost);
+	evt = ibmvfc_get_event(&vhost->crq);
 	vhost->discovery_threads++;
 	ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_INIT_WAIT);
 	ibmvfc_init_event(evt, ibmvfc_tgt_plogi_done, IBMVFC_MAD_FORMAT);
@@ -3673,7 +4124,7 @@ static struct ibmvfc_event *__ibmvfc_tgt_get_implicit_logout_evt(struct ibmvfc_t
 	struct ibmvfc_event *evt;
 
 	kref_get(&tgt->kref);
-	evt = ibmvfc_get_event(vhost);
+	evt = ibmvfc_get_event(&vhost->crq);
 	ibmvfc_init_event(evt, done, IBMVFC_MAD_FORMAT);
 	evt->tgt = tgt;
 	mad = &evt->iu.implicit_logout;
@@ -3838,7 +4289,7 @@ static void ibmvfc_tgt_move_login(struct ibmvfc_target *tgt)
 		return;
 
 	kref_get(&tgt->kref);
-	evt = ibmvfc_get_event(vhost);
+	evt = ibmvfc_get_event(&vhost->crq);
 	vhost->discovery_threads++;
 	ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_INIT_WAIT);
 	ibmvfc_init_event(evt, ibmvfc_tgt_move_login_done, IBMVFC_MAD_FORMAT);
@@ -4004,7 +4455,7 @@ static void ibmvfc_adisc_timeout(struct timer_list *t)
 
 	vhost->abort_threads++;
 	kref_get(&tgt->kref);
-	evt = ibmvfc_get_event(vhost);
+	evt = ibmvfc_get_event(&vhost->crq);
 	ibmvfc_init_event(evt, ibmvfc_tgt_adisc_cancel_done, IBMVFC_MAD_FORMAT);
 
 	evt->tgt = tgt;
@@ -4054,7 +4505,7 @@ static void ibmvfc_tgt_adisc(struct ibmvfc_target *tgt)
 		return;
 
 	kref_get(&tgt->kref);
-	evt = ibmvfc_get_event(vhost);
+	evt = ibmvfc_get_event(&vhost->crq);
 	vhost->discovery_threads++;
 	ibmvfc_init_event(evt, ibmvfc_tgt_adisc_done, IBMVFC_MAD_FORMAT);
 	evt->tgt = tgt;
@@ -4157,7 +4608,7 @@ static void ibmvfc_tgt_query_target(struct ibmvfc_target *tgt)
 		return;
 
 	kref_get(&tgt->kref);
-	evt = ibmvfc_get_event(vhost);
+	evt = ibmvfc_get_event(&vhost->crq);
 	vhost->discovery_threads++;
 	evt->tgt = tgt;
 	ibmvfc_init_event(evt, ibmvfc_tgt_query_target_done, IBMVFC_MAD_FORMAT);
@@ -4324,7 +4775,7 @@ static void ibmvfc_discover_targets_done(struct ibmvfc_event *evt)
 static void ibmvfc_discover_targets(struct ibmvfc_host *vhost)
 {
 	struct ibmvfc_discover_targets *mad;
-	struct ibmvfc_event *evt = ibmvfc_get_event(vhost);
+	struct ibmvfc_event *evt = ibmvfc_get_event(&vhost->crq);
 
 	ibmvfc_init_event(evt, ibmvfc_discover_targets_done, IBMVFC_MAD_FORMAT);
 	mad = &evt->iu.discover_targets;
@@ -4344,6 +4795,148 @@ static void ibmvfc_discover_targets(struct ibmvfc_host *vhost)
 		ibmvfc_link_down(vhost, IBMVFC_LINK_DEAD);
 }
 
+static void ibmvfc_channel_setup_done(struct ibmvfc_event *evt)
+{
+	struct ibmvfc_host *vhost = evt->vhost;
+	struct ibmvfc_channel_setup *setup = vhost->channel_setup_buf;
+	struct ibmvfc_scsi_channels *scrqs = &vhost->scsi_scrqs;
+	u32 mad_status = be16_to_cpu(evt->xfer_iu->channel_setup.common.status);
+	int level = IBMVFC_DEFAULT_LOG_LEVEL;
+	int flags, active_queues, i;
+
+	ibmvfc_free_event(evt);
+
+	switch (mad_status) {
+	case IBMVFC_MAD_SUCCESS:
+		ibmvfc_dbg(vhost, "Channel Setup succeeded\n");
+		flags = be32_to_cpu(setup->flags);
+		vhost->do_enquiry = 0;
+		active_queues = be32_to_cpu(setup->num_scsi_subq_channels);
+		scrqs->active_queues = active_queues;
+
+		if (flags & IBMVFC_CHANNELS_CANCELED) {
+			ibmvfc_dbg(vhost, "Channels Canceled\n");
+			vhost->using_channels = 0;
+		} else {
+			if (active_queues)
+				vhost->using_channels = 1;
+			for (i = 0; i < active_queues; i++)
+				scrqs->scrqs[i].vios_cookie =
+					be64_to_cpu(setup->channel_handles[i]);
+
+			ibmvfc_dbg(vhost, "Using %u channels\n",
+				   vhost->scsi_scrqs.active_queues);
+		}
+		break;
+	case IBMVFC_MAD_FAILED:
+		level += ibmvfc_retry_host_init(vhost);
+		ibmvfc_log(vhost, level, "Channel Setup failed\n");
+		fallthrough;
+	case IBMVFC_MAD_DRIVER_FAILED:
+		return;
+	default:
+		dev_err(vhost->dev, "Invalid Channel Setup response: 0x%x\n",
+			mad_status);
+		ibmvfc_link_down(vhost, IBMVFC_LINK_DEAD);
+		return;
+	}
+
+	ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_QUERY);
+	wake_up(&vhost->work_wait_q);
+}
+
+static void ibmvfc_channel_setup(struct ibmvfc_host *vhost)
+{
+	struct ibmvfc_channel_setup_mad *mad;
+	struct ibmvfc_channel_setup *setup_buf = vhost->channel_setup_buf;
+	struct ibmvfc_event *evt = ibmvfc_get_event(&vhost->crq);
+	struct ibmvfc_scsi_channels *scrqs = &vhost->scsi_scrqs;
+	unsigned int num_channels =
+		min(vhost->client_scsi_channels, vhost->max_vios_scsi_channels);
+	int i;
+
+	memset(setup_buf, 0, sizeof(*setup_buf));
+	if (num_channels == 0)
+		setup_buf->flags = cpu_to_be32(IBMVFC_CANCEL_CHANNELS);
+	else {
+		setup_buf->num_scsi_subq_channels = cpu_to_be32(num_channels);
+		for (i = 0; i < num_channels; i++)
+			setup_buf->channel_handles[i] = cpu_to_be64(scrqs->scrqs[i].cookie);
+	}
+
+	ibmvfc_init_event(evt, ibmvfc_channel_setup_done, IBMVFC_MAD_FORMAT);
+	mad = &evt->iu.channel_setup;
+	memset(mad, 0, sizeof(*mad));
+	mad->common.version = cpu_to_be32(1);
+	mad->common.opcode = cpu_to_be32(IBMVFC_CHANNEL_SETUP);
+	mad->common.length = cpu_to_be16(sizeof(*mad));
+	mad->buffer.va = cpu_to_be64(vhost->channel_setup_dma);
+	mad->buffer.len = cpu_to_be32(sizeof(*vhost->channel_setup_buf));
+
+	ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_INIT_WAIT);
+
+	if (!ibmvfc_send_event(evt, vhost, default_timeout))
+		ibmvfc_dbg(vhost, "Sent channel setup\n");
+	else
+		ibmvfc_link_down(vhost, IBMVFC_LINK_DOWN);
+}
+
+static void ibmvfc_channel_enquiry_done(struct ibmvfc_event *evt)
+{
+	struct ibmvfc_host *vhost = evt->vhost;
+	struct ibmvfc_channel_enquiry *rsp = &evt->xfer_iu->channel_enquiry;
+	u32 mad_status = be16_to_cpu(rsp->common.status);
+	int level = IBMVFC_DEFAULT_LOG_LEVEL;
+
+	switch (mad_status) {
+	case IBMVFC_MAD_SUCCESS:
+		ibmvfc_dbg(vhost, "Channel Enquiry succeeded\n");
+		vhost->max_vios_scsi_channels = be32_to_cpu(rsp->num_scsi_subq_channels);
+		ibmvfc_free_event(evt);
+		break;
+	case IBMVFC_MAD_FAILED:
+		level += ibmvfc_retry_host_init(vhost);
+		ibmvfc_log(vhost, level, "Channel Enquiry failed\n");
+		fallthrough;
+	case IBMVFC_MAD_DRIVER_FAILED:
+		ibmvfc_free_event(evt);
+		return;
+	default:
+		dev_err(vhost->dev, "Invalid Channel Enquiry response: 0x%x\n",
+			mad_status);
+		ibmvfc_link_down(vhost, IBMVFC_LINK_DEAD);
+		ibmvfc_free_event(evt);
+		return;
+	}
+
+	ibmvfc_channel_setup(vhost);
+}
+
+static void ibmvfc_channel_enquiry(struct ibmvfc_host *vhost)
+{
+	struct ibmvfc_channel_enquiry *mad;
+	struct ibmvfc_event *evt = ibmvfc_get_event(&vhost->crq);
+
+	ibmvfc_init_event(evt, ibmvfc_channel_enquiry_done, IBMVFC_MAD_FORMAT);
+	mad = &evt->iu.channel_enquiry;
+	memset(mad, 0, sizeof(*mad));
+	mad->common.version = cpu_to_be32(1);
+	mad->common.opcode = cpu_to_be32(IBMVFC_CHANNEL_ENQUIRY);
+	mad->common.length = cpu_to_be16(sizeof(*mad));
+
+	if (mig_channels_only)
+		mad->flags |= cpu_to_be32(IBMVFC_NO_CHANNELS_TO_CRQ_SUPPORT);
+	if (mig_no_less_channels)
+		mad->flags |= cpu_to_be32(IBMVFC_NO_N_TO_M_CHANNELS_SUPPORT);
+
+	ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_INIT_WAIT);
+
+	if (!ibmvfc_send_event(evt, vhost, default_timeout))
+		ibmvfc_dbg(vhost, "Send channel enquiry\n");
+	else
+		ibmvfc_link_down(vhost, IBMVFC_LINK_DEAD);
+}
+
 /**
  * ibmvfc_npiv_login_done - Completion handler for NPIV Login
  * @evt:	ibmvfc event struct
@@ -4425,8 +5018,14 @@ static void ibmvfc_npiv_login_done(struct ibmvfc_event *evt)
 
 	vhost->host->can_queue = be32_to_cpu(rsp->max_cmds) - IBMVFC_NUM_INTERNAL_REQ;
 	vhost->host->max_sectors = npiv_max_sectors;
-	ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_QUERY);
-	wake_up(&vhost->work_wait_q);
+
+	if (ibmvfc_check_caps(vhost, IBMVFC_CAN_SUPPORT_CHANNELS) && vhost->do_enquiry) {
+		ibmvfc_channel_enquiry(vhost);
+	} else {
+		vhost->do_enquiry = 0;
+		ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_QUERY);
+		wake_up(&vhost->work_wait_q);
+	}
 }
 
 /**
@@ -4437,7 +5036,7 @@ static void ibmvfc_npiv_login_done(struct ibmvfc_event *evt)
 static void ibmvfc_npiv_login(struct ibmvfc_host *vhost)
 {
 	struct ibmvfc_npiv_login_mad *mad;
-	struct ibmvfc_event *evt = ibmvfc_get_event(vhost);
+	struct ibmvfc_event *evt = ibmvfc_get_event(&vhost->crq);
 
 	ibmvfc_gather_partition_info(vhost);
 	ibmvfc_set_login_info(vhost);
@@ -4474,7 +5073,7 @@ static void ibmvfc_npiv_logout_done(struct ibmvfc_event *evt)
 
 	switch (mad_status) {
 	case IBMVFC_MAD_SUCCESS:
-		if (list_empty(&vhost->sent) &&
+		if (list_empty(&vhost->crq.sent) &&
 		    vhost->action == IBMVFC_HOST_ACTION_LOGO_WAIT) {
 			ibmvfc_init_host(vhost);
 			return;
@@ -4502,7 +5101,7 @@ static void ibmvfc_npiv_logout(struct ibmvfc_host *vhost)
 	struct ibmvfc_npiv_logout_mad *mad;
 	struct ibmvfc_event *evt;
 
-	evt = ibmvfc_get_event(vhost);
+	evt = ibmvfc_get_event(&vhost->crq);
 	ibmvfc_init_event(evt, ibmvfc_npiv_logout_done, IBMVFC_MAD_FORMAT);
 
 	mad = &evt->iu.npiv_logout;
@@ -4712,6 +5311,7 @@ static void ibmvfc_do_work(struct ibmvfc_host *vhost)
 	struct ibmvfc_target *tgt;
 	unsigned long flags;
 	struct fc_rport *rport;
+	LIST_HEAD(purge);
 	int rc;
 
 	ibmvfc_log_ae(vhost, vhost->events_to_log);
@@ -4724,7 +5324,9 @@ static void ibmvfc_do_work(struct ibmvfc_host *vhost)
 		break;
 	case IBMVFC_HOST_ACTION_RESET:
 		vhost->action = IBMVFC_HOST_ACTION_TGT_DEL;
+		list_splice_init(&vhost->purge, &purge);
 		spin_unlock_irqrestore(vhost->host->host_lock, flags);
+		ibmvfc_complete_purge(&purge);
 		rc = ibmvfc_reset_crq(vhost);
 		spin_lock_irqsave(vhost->host->host_lock, flags);
 		if (rc == H_CLOSED)
@@ -4737,7 +5339,9 @@ static void ibmvfc_do_work(struct ibmvfc_host *vhost)
 		break;
 	case IBMVFC_HOST_ACTION_REENABLE:
 		vhost->action = IBMVFC_HOST_ACTION_TGT_DEL;
+		list_splice_init(&vhost->purge, &purge);
 		spin_unlock_irqrestore(vhost->host->host_lock, flags);
+		ibmvfc_complete_purge(&purge);
 		rc = ibmvfc_reenable_crq_queue(vhost);
 		spin_lock_irqsave(vhost->host->host_lock, flags);
 		if (rc || (rc = ibmvfc_send_crq_init(vhost))) {
@@ -4898,6 +5502,69 @@ static int ibmvfc_work(void *data)
 }
 
 /**
+ * ibmvfc_alloc_queue - Allocate queue
+ * @vhost:	ibmvfc host struct
+ * @queue:	ibmvfc queue to allocate
+ * @fmt:	queue format to allocate
+ *
+ * Returns:
+ *	0 on success / non-zero on failure
+ **/
+static int ibmvfc_alloc_queue(struct ibmvfc_host *vhost,
+			      struct ibmvfc_queue *queue,
+			      enum ibmvfc_msg_fmt fmt)
+{
+	struct device *dev = vhost->dev;
+	size_t fmt_size;
+	unsigned int pool_size = 0;
+
+	ENTER;
+	spin_lock_init(&queue->_lock);
+	queue->q_lock = &queue->_lock;
+
+	switch (fmt) {
+	case IBMVFC_CRQ_FMT:
+		fmt_size = sizeof(*queue->msgs.crq);
+		pool_size = max_requests + IBMVFC_NUM_INTERNAL_REQ;
+		break;
+	case IBMVFC_ASYNC_FMT:
+		fmt_size = sizeof(*queue->msgs.async);
+		break;
+	case IBMVFC_SUB_CRQ_FMT:
+		fmt_size = sizeof(*queue->msgs.scrq);
+		/* We need one extra event for Cancel Commands */
+		pool_size = max_requests + 1;
+		break;
+	default:
+		dev_warn(dev, "Unknown command/response queue message format: %d\n", fmt);
+		return -EINVAL;
+	}
+
+	if (ibmvfc_init_event_pool(vhost, queue, pool_size)) {
+		dev_err(dev, "Couldn't initialize event pool.\n");
+		return -ENOMEM;
+	}
+
+	queue->msgs.handle = (void *)get_zeroed_page(GFP_KERNEL);
+	if (!queue->msgs.handle)
+		return -ENOMEM;
+
+	queue->msg_token = dma_map_single(dev, queue->msgs.handle, PAGE_SIZE,
+					  DMA_BIDIRECTIONAL);
+
+	if (dma_mapping_error(dev, queue->msg_token)) {
+		free_page((unsigned long)queue->msgs.handle);
+		queue->msgs.handle = NULL;
+		return -ENOMEM;
+	}
+
+	queue->cur = 0;
+	queue->fmt = fmt;
+	queue->size = PAGE_SIZE / fmt_size;
+	return 0;
+}
+
+/**
  * ibmvfc_init_crq - Initializes and registers CRQ with hypervisor
  * @vhost:	ibmvfc host struct
  *
@@ -4912,21 +5579,12 @@ static int ibmvfc_init_crq(struct ibmvfc_host *vhost)
 	int rc, retrc = -ENOMEM;
 	struct device *dev = vhost->dev;
 	struct vio_dev *vdev = to_vio_dev(dev);
-	struct ibmvfc_crq_queue *crq = &vhost->crq;
+	struct ibmvfc_queue *crq = &vhost->crq;
 
 	ENTER;
-	crq->msgs = (struct ibmvfc_crq *)get_zeroed_page(GFP_KERNEL);
-
-	if (!crq->msgs)
+	if (ibmvfc_alloc_queue(vhost, crq, IBMVFC_CRQ_FMT))
 		return -ENOMEM;
 
-	crq->size = PAGE_SIZE / sizeof(*crq->msgs);
-	crq->msg_token = dma_map_single(dev, crq->msgs,
-					PAGE_SIZE, DMA_BIDIRECTIONAL);
-
-	if (dma_mapping_error(dev, crq->msg_token))
-		goto map_failed;
-
 	retrc = rc = plpar_hcall_norets(H_REG_CRQ, vdev->unit_address,
 					crq->msg_token, PAGE_SIZE);
 
@@ -4955,7 +5613,6 @@ static int ibmvfc_init_crq(struct ibmvfc_host *vhost)
 		goto req_irq_failed;
 	}
 
-	crq->cur = 0;
 	LEAVE;
 	return retrc;
 
@@ -4965,12 +5622,136 @@ req_irq_failed:
 		rc = plpar_hcall_norets(H_FREE_CRQ, vdev->unit_address);
 	} while (rc == H_BUSY || H_IS_LONG_BUSY(rc));
 reg_crq_failed:
-	dma_unmap_single(dev, crq->msg_token, PAGE_SIZE, DMA_BIDIRECTIONAL);
-map_failed:
-	free_page((unsigned long)crq->msgs);
+	ibmvfc_free_queue(vhost, crq);
 	return retrc;
 }
 
+static int ibmvfc_register_scsi_channel(struct ibmvfc_host *vhost,
+				  int index)
+{
+	struct device *dev = vhost->dev;
+	struct vio_dev *vdev = to_vio_dev(dev);
+	struct ibmvfc_queue *scrq = &vhost->scsi_scrqs.scrqs[index];
+	int rc = -ENOMEM;
+
+	ENTER;
+
+	if (ibmvfc_alloc_queue(vhost, scrq, IBMVFC_SUB_CRQ_FMT))
+		return -ENOMEM;
+
+	rc = h_reg_sub_crq(vdev->unit_address, scrq->msg_token, PAGE_SIZE,
+			   &scrq->cookie, &scrq->hw_irq);
+
+	if (rc) {
+		dev_warn(dev, "Error registering sub-crq: %d\n", rc);
+		if (rc == H_PARAMETER)
+			dev_warn_once(dev, "Firmware may not support MQ\n");
+		goto reg_failed;
+	}
+
+	scrq->irq = irq_create_mapping(NULL, scrq->hw_irq);
+
+	if (!scrq->irq) {
+		rc = -EINVAL;
+		dev_err(dev, "Error mapping sub-crq[%d] irq\n", index);
+		goto irq_failed;
+	}
+
+	snprintf(scrq->name, sizeof(scrq->name), "ibmvfc-%x-scsi%d",
+		 vdev->unit_address, index);
+	rc = request_irq(scrq->irq, ibmvfc_interrupt_scsi, 0, scrq->name, scrq);
+
+	if (rc) {
+		dev_err(dev, "Couldn't register sub-crq[%d] irq\n", index);
+		irq_dispose_mapping(scrq->irq);
+		goto irq_failed;
+	}
+
+	scrq->hwq_id = index;
+	scrq->vhost = vhost;
+
+	LEAVE;
+	return 0;
+
+irq_failed:
+	do {
+		plpar_hcall_norets(H_FREE_SUB_CRQ, vdev->unit_address, scrq->cookie);
+	} while (rc == H_BUSY || H_IS_LONG_BUSY(rc));
+reg_failed:
+	ibmvfc_free_queue(vhost, scrq);
+	LEAVE;
+	return rc;
+}
+
+static void ibmvfc_deregister_scsi_channel(struct ibmvfc_host *vhost, int index)
+{
+	struct device *dev = vhost->dev;
+	struct vio_dev *vdev = to_vio_dev(dev);
+	struct ibmvfc_queue *scrq = &vhost->scsi_scrqs.scrqs[index];
+	long rc;
+
+	ENTER;
+
+	free_irq(scrq->irq, scrq);
+	irq_dispose_mapping(scrq->irq);
+
+	do {
+		rc = plpar_hcall_norets(H_FREE_SUB_CRQ, vdev->unit_address,
+					scrq->cookie);
+	} while (rc == H_BUSY || H_IS_LONG_BUSY(rc));
+
+	if (rc)
+		dev_err(dev, "Failed to free sub-crq[%d]: rc=%ld\n", index, rc);
+
+	ibmvfc_free_queue(vhost, scrq);
+	LEAVE;
+}
+
+static int ibmvfc_init_sub_crqs(struct ibmvfc_host *vhost)
+{
+	int i, j;
+
+	ENTER;
+
+	vhost->scsi_scrqs.scrqs = kcalloc(nr_scsi_hw_queues,
+					  sizeof(*vhost->scsi_scrqs.scrqs),
+					  GFP_KERNEL);
+	if (!vhost->scsi_scrqs.scrqs)
+		return -1;
+
+	for (i = 0; i < nr_scsi_hw_queues; i++) {
+		if (ibmvfc_register_scsi_channel(vhost, i)) {
+			for (j = i; j > 0; j--)
+				ibmvfc_deregister_scsi_channel(vhost, j - 1);
+			kfree(vhost->scsi_scrqs.scrqs);
+			vhost->scsi_scrqs.scrqs = NULL;
+			vhost->scsi_scrqs.active_queues = 0;
+			LEAVE;
+			return -1;
+		}
+	}
+
+	LEAVE;
+	return 0;
+}
+
+static void ibmvfc_release_sub_crqs(struct ibmvfc_host *vhost)
+{
+	int i;
+
+	ENTER;
+	if (!vhost->scsi_scrqs.scrqs)
+		return;
+
+	for (i = 0; i < nr_scsi_hw_queues; i++)
+		ibmvfc_deregister_scsi_channel(vhost, i);
+
+	kfree(vhost->scsi_scrqs.scrqs);
+	vhost->scsi_scrqs.scrqs = NULL;
+	vhost->scsi_scrqs.active_queues = 0;
+	LEAVE;
+}
+
 /**
  * ibmvfc_free_mem - Free memory for vhost
  * @vhost:	ibmvfc host struct
@@ -4980,7 +5761,7 @@ map_failed:
  **/
 static void ibmvfc_free_mem(struct ibmvfc_host *vhost)
 {
-	struct ibmvfc_async_crq_queue *async_q = &vhost->async_crq;
+	struct ibmvfc_queue *async_q = &vhost->async_crq;
 
 	ENTER;
 	mempool_destroy(vhost->tgt_pool);
@@ -4990,9 +5771,7 @@ static void ibmvfc_free_mem(struct ibmvfc_host *vhost)
 	dma_free_coherent(vhost->dev, sizeof(*vhost->login_buf),
 			  vhost->login_buf, vhost->login_buf_dma);
 	dma_pool_destroy(vhost->sg_pool);
-	dma_unmap_single(vhost->dev, async_q->msg_token,
-			 async_q->size * sizeof(*async_q->msgs), DMA_BIDIRECTIONAL);
-	free_page((unsigned long)async_q->msgs);
+	ibmvfc_free_queue(vhost, async_q);
 	LEAVE;
 }
 
@@ -5005,26 +5784,15 @@ static void ibmvfc_free_mem(struct ibmvfc_host *vhost)
  **/
 static int ibmvfc_alloc_mem(struct ibmvfc_host *vhost)
 {
-	struct ibmvfc_async_crq_queue *async_q = &vhost->async_crq;
+	struct ibmvfc_queue *async_q = &vhost->async_crq;
 	struct device *dev = vhost->dev;
 
 	ENTER;
-	async_q->msgs = (struct ibmvfc_async_crq *)get_zeroed_page(GFP_KERNEL);
-	if (!async_q->msgs) {
-		dev_err(dev, "Couldn't allocate async queue.\n");
+	if (ibmvfc_alloc_queue(vhost, async_q, IBMVFC_ASYNC_FMT)) {
+		dev_err(dev, "Couldn't allocate/map async queue.\n");
 		goto nomem;
 	}
 
-	async_q->size = PAGE_SIZE / sizeof(struct ibmvfc_async_crq);
-	async_q->msg_token = dma_map_single(dev, async_q->msgs,
-					    async_q->size * sizeof(*async_q->msgs),
-					    DMA_BIDIRECTIONAL);
-
-	if (dma_mapping_error(dev, async_q->msg_token)) {
-		dev_err(dev, "Failed to map async queue\n");
-		goto free_async_crq;
-	}
-
 	vhost->sg_pool = dma_pool_create(IBMVFC_NAME, dev,
 					 SG_ALL * sizeof(struct srp_direct_buf),
 					 sizeof(struct srp_direct_buf), 0);
@@ -5053,6 +5821,7 @@ static int ibmvfc_alloc_mem(struct ibmvfc_host *vhost)
 
 	vhost->trace = kcalloc(IBMVFC_NUM_TRACE_ENTRIES,
 			       sizeof(struct ibmvfc_trace_entry), GFP_KERNEL);
+	atomic_set(&vhost->trace_index, -1);
 
 	if (!vhost->trace)
 		goto free_disc_buffer;
@@ -5065,9 +5834,20 @@ static int ibmvfc_alloc_mem(struct ibmvfc_host *vhost)
 		goto free_trace;
 	}
 
+	vhost->channel_setup_buf = dma_alloc_coherent(dev, sizeof(*vhost->channel_setup_buf),
+						      &vhost->channel_setup_dma,
+						      GFP_KERNEL);
+
+	if (!vhost->channel_setup_buf) {
+		dev_err(dev, "Couldn't allocate Channel Setup buffer\n");
+		goto free_tgt_pool;
+	}
+
 	LEAVE;
 	return 0;
 
+free_tgt_pool:
+	mempool_destroy(vhost->tgt_pool);
 free_trace:
 	kfree(vhost->trace);
 free_disc_buffer:
@@ -5079,10 +5859,7 @@ free_login_buffer:
 free_sg_pool:
 	dma_pool_destroy(vhost->sg_pool);
 unmap_async_crq:
-	dma_unmap_single(dev, async_q->msg_token,
-			 async_q->size * sizeof(*async_q->msgs), DMA_BIDIRECTIONAL);
-free_async_crq:
-	free_page((unsigned long)async_q->msgs);
+	ibmvfc_free_queue(vhost, async_q);
 nomem:
 	LEAVE;
 	return -ENOMEM;
@@ -5154,6 +5931,7 @@ static int ibmvfc_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	struct Scsi_Host *shost;
 	struct device *dev = &vdev->dev;
 	int rc = -ENOMEM;
+	unsigned int max_scsi_queues = IBMVFC_MAX_SCSI_QUEUES;
 
 	ENTER;
 	shost = scsi_host_alloc(&driver_template, sizeof(*vhost));
@@ -5169,17 +5947,23 @@ static int ibmvfc_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	shost->max_sectors = IBMVFC_MAX_SECTORS;
 	shost->max_cmd_len = IBMVFC_MAX_CDB_LEN;
 	shost->unique_id = shost->host_no;
+	shost->nr_hw_queues = mq_enabled ? min(max_scsi_queues, nr_scsi_hw_queues) : 1;
 
 	vhost = shost_priv(shost);
-	INIT_LIST_HEAD(&vhost->sent);
-	INIT_LIST_HEAD(&vhost->free);
 	INIT_LIST_HEAD(&vhost->targets);
+	INIT_LIST_HEAD(&vhost->purge);
 	sprintf(vhost->name, IBMVFC_NAME);
 	vhost->host = shost;
 	vhost->dev = dev;
 	vhost->partition_number = -1;
 	vhost->log_level = log_level;
 	vhost->task_set = 1;
+
+	vhost->mq_enabled = mq_enabled;
+	vhost->client_scsi_channels = min(shost->nr_hw_queues, nr_scsi_channels);
+	vhost->using_channels = 0;
+	vhost->do_enquiry = 1;
+
 	strcpy(vhost->partition_name, "UNKNOWN");
 	init_waitqueue_head(&vhost->work_wait_q);
 	init_waitqueue_head(&vhost->init_wait_q);
@@ -5204,13 +5988,8 @@ static int ibmvfc_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 		goto kill_kthread;
 	}
 
-	if ((rc = ibmvfc_init_event_pool(vhost))) {
-		dev_err(dev, "Couldn't initialize event pool. rc=%d\n", rc);
-		goto release_crq;
-	}
-
 	if ((rc = scsi_add_host(shost, dev)))
-		goto release_event_pool;
+		goto release_crq;
 
 	fc_host_dev_loss_tmo(shost) = IBMVFC_DEV_LOSS_TMO;
 
@@ -5220,6 +5999,12 @@ static int ibmvfc_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 		goto remove_shost;
 	}
 
+	if (vhost->mq_enabled) {
+		rc = ibmvfc_init_sub_crqs(vhost);
+		if (rc)
+			dev_warn(dev, "Failed to allocate Sub-CRQs. rc=%d\n", rc);
+	}
+
 	if (shost_to_fc_host(shost)->rqst_q)
 		blk_queue_max_segments(shost_to_fc_host(shost)->rqst_q, 1);
 	dev_set_drvdata(dev, vhost);
@@ -5233,8 +6018,6 @@ static int ibmvfc_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 
 remove_shost:
 	scsi_remove_host(shost);
-release_event_pool:
-	ibmvfc_free_event_pool(vhost);
 release_crq:
 	ibmvfc_release_crq_queue(vhost);
 kill_kthread:
@@ -5258,6 +6041,7 @@ out:
 static int ibmvfc_remove(struct vio_dev *vdev)
 {
 	struct ibmvfc_host *vhost = dev_get_drvdata(&vdev->dev);
+	LIST_HEAD(purge);
 	unsigned long flags;
 
 	ENTER;
@@ -5268,15 +6052,17 @@ static int ibmvfc_remove(struct vio_dev *vdev)
 	spin_unlock_irqrestore(vhost->host->host_lock, flags);
 
 	ibmvfc_wait_while_resetting(vhost);
-	ibmvfc_release_crq_queue(vhost);
 	kthread_stop(vhost->work_thread);
 	fc_remove_host(vhost->host);
 	scsi_remove_host(vhost->host);
 
 	spin_lock_irqsave(vhost->host->host_lock, flags);
 	ibmvfc_purge_requests(vhost, DID_ERROR);
+	list_splice_init(&vhost->purge, &purge);
 	spin_unlock_irqrestore(vhost->host->host_lock, flags);
-	ibmvfc_free_event_pool(vhost);
+	ibmvfc_complete_purge(&purge);
+	ibmvfc_release_sub_crqs(vhost);
+	ibmvfc_release_crq_queue(vhost);
 
 	ibmvfc_free_mem(vhost);
 	spin_lock(&ibmvfc_driver_lock);