[PATCH V3 0/10] blk-mq: cleanup map queues & fix blk_mq_alloc_request_hctx

@@ -7,7 +7,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
-			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
+			blk-mq-sysfs.o blk-mq-map.o blk-mq-sched.o ioctl.o \
 			genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \
 			disk-events.o
 

@@ -94,3 +94,56 @@ int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int index)
 
 	return NUMA_NO_NODE;
 }
+
+/**
+ * blk_mq_dev_map_queues - provide generic queue mapping
+ * @qmap:	CPU to hardware queue map.
+ * @dev_off:	Offset to use for the device
+ * @get_queue_affinity:	Callback to retrieve queue affinity
+ * @dev_data:	Device data passed to get_queue_affinity()
+ * @fallback:	If true, fallback to default blk-mq mapping in case of
+ * any failure
+ *
+ * Generic function to setup each queue mapping in @qmap. It will query
+ * each queue's affinity via @get_queue_affinity and built queue mapping
+ * that maps a queue to the CPUs in the queue affinity.
+ *
+ * Driver has to set correct @dev_data, so that the driver callback
+ * of @get_queue_affinity can work correctly.
+ */
+int blk_mq_dev_map_queues(struct blk_mq_queue_map *qmap, void *dev_data,
+		int dev_off, get_queue_affinty_fn *get_queue_affinity,
+		bool fallback)
+{
+	const struct cpumask *mask;
+	unsigned int queue, cpu;
+
+	/*
+	 * fallback to default mapping if driver doesn't provide
+	 * get_queue_affinity callback
+	 */
+	if (!get_queue_affinity) {
+		fallback = true;
+		goto fallback;
+	}
+
+	for (queue = 0; queue < qmap->nr_queues; queue++) {
+		mask = get_queue_affinity(dev_data, dev_off, queue);
+		if (!mask)
+			goto fallback;
+
+		for_each_cpu(cpu, mask)
+			qmap->mq_map[cpu] = qmap->queue_offset + queue;
+	}
+
+	return 0;
+
+fallback:
+	if (!fallback) {
+		WARN_ON_ONCE(qmap->nr_queues > 1);
+		blk_mq_clear_mq_map(qmap);
+		return 0;
+	}
+	return blk_mq_map_queues(qmap);
+}
+EXPORT_SYMBOL_GPL(blk_mq_dev_map_queues);

@@ -553,7 +553,12 @@ void blk_mq_freeze_queue_wait(struct request_queue *q);
 int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
 				     unsigned long timeout);
 
+typedef const struct cpumask * (get_queue_affinty_fn)(void *dev_data,
+		int dev_off, int queue_idx);
 int blk_mq_map_queues(struct blk_mq_queue_map *qmap);
+int blk_mq_dev_map_queues(struct blk_mq_queue_map *qmap, void *dev_data,
+		int dev_off, get_queue_affinty_fn *get_queue_affinity,
+		bool fallback);
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
 
 void blk_mq_quiesce_queue_nowait(struct request_queue *q);

@@ -103,6 +103,8 @@ int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int index)
  * @dev_data:	Device data passed to get_queue_affinity()
  * @fallback:	If true, fallback to default blk-mq mapping in case of
  * any failure
+ * @managed_irq: If driver is likely to use managed irq, pass @managed_irq
+ * as true.
  *
  * Generic function to setup each queue mapping in @qmap. It will query
  * each queue's affinity via @get_queue_affinity and built queue mapping

@@ -113,7 +115,7 @@ int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int index)
  */
 int blk_mq_dev_map_queues(struct blk_mq_queue_map *qmap, void *dev_data,
 		int dev_off, get_queue_affinty_fn *get_queue_affinity,
-		bool fallback)
+		bool fallback, bool managed_irq)
 {
 	const struct cpumask *mask;
 	unsigned int queue, cpu;

@@ -136,6 +138,8 @@ int blk_mq_dev_map_queues(struct blk_mq_queue_map *qmap, void *dev_data,
 			qmap->mq_map[cpu] = qmap->queue_offset + queue;
 	}
 
+	qmap->use_managed_irq = managed_irq;
+
 	return 0;
 
 fallback:

@@ -192,7 +192,8 @@ struct blk_mq_hw_ctx {
 struct blk_mq_queue_map {
 	unsigned int *mq_map;
 	unsigned int nr_queues;
-	unsigned int queue_offset;
+	unsigned int queue_offset:31;
+	unsigned int use_managed_irq:1;
 };
 
 /**

@@ -558,7 +559,7 @@ typedef const struct cpumask * (get_queue_affinty_fn)(void *dev_data,
 int blk_mq_map_queues(struct blk_mq_queue_map *qmap);
 int blk_mq_dev_map_queues(struct blk_mq_queue_map *qmap, void *dev_data,
 		int dev_off, get_queue_affinty_fn *get_queue_affinity,
-		bool fallback);
+		bool fallback, bool managed_irq);
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
 
 void blk_mq_quiesce_queue_nowait(struct request_queue *q);

@@ -3547,6 +3547,14 @@ static struct device_attribute *host_attrs_v2_hw[] = {
 	NULL
 };
 
+static inline const struct cpumask *hisi_hba_get_queue_affinity(
+		void *dev_data, int offset, int idx)
+{
+	struct hisi_hba *hba = dev_data;
+
+	return irq_get_affinity_mask(hba->irq_map[offset + idx]);
+}
+
 static int map_queues_v2_hw(struct Scsi_Host *shost)
 {
 	struct hisi_hba *hisi_hba = shost_priv(shost);

@@ -3554,17 +3562,8 @@ static int map_queues_v2_hw(struct Scsi_Host *shost)
 	const struct cpumask *mask;
 	unsigned int queue, cpu;
 
-	for (queue = 0; queue < qmap->nr_queues; queue++) {
-		mask = irq_get_affinity_mask(hisi_hba->irq_map[96 + queue]);
-		if (!mask)
-			continue;
-
-		for_each_cpu(cpu, mask)
-			qmap->mq_map[cpu] = qmap->queue_offset + queue;
-	}
-
-	return 0;
-
+	return blk_mq_dev_map_queues(qmap, hisi_hba, 96,
+			hisi_hba_get_queue_affinity, false, true);
 }
 
 static struct scsi_host_template sht_v2_hw = {

@@ -3132,8 +3132,9 @@ static int hisi_sas_map_queues(struct Scsi_Host *shost)
 	struct hisi_hba *hisi_hba = shost_priv(shost);
 	struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
 
-	return blk_mq_pci_map_queues(qmap, hisi_hba->pci_dev,
-				     BASE_VECTORS_V3_HW);
+	return blk_mq_dev_map_queues(qmap, hisi_hba->pci_dev,
+				     BASE_VECTORS_V3_HW,
+				     scsi_pci_get_queue_affinity, false, true);
 }
 
 static struct scsi_host_template sht_v3_hw = {

@@ -47,6 +47,7 @@
 #include <scsi/scsi_dbg.h>
 #include "megaraid_sas_fusion.h"
 #include "megaraid_sas.h"
+#include "../scsi_priv.h"
 
 /*
  * Number of sectors per IO command

@@ -3185,7 +3186,8 @@ static int megasas_map_queues(struct Scsi_Host *shost)
 	map = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
 	map->nr_queues = instance->msix_vectors - offset;
 	map->queue_offset = 0;
-	blk_mq_pci_map_queues(map, instance->pdev, offset);
+	blk_mq_dev_map_queues(map, instance->pdev, offset,
+			scsi_pci_get_queue_affinity, false, true);
 	qoff += map->nr_queues;
 	offset += map->nr_queues;
 

@@ -2787,17 +2787,18 @@ static int mpi3mr_bios_param(struct scsi_device *sdev,
  * mpi3mr_map_queues - Map queues callback handler
  * @shost: SCSI host reference
  *
- * Call the blk_mq_pci_map_queues with from which operational
+ * Call the blk_mq_dev_map_queues with from which operational
  * queue the mapping has to be done
  *
- * Return: return of blk_mq_pci_map_queues
+ * Return: return of blk_mq_dev_map_queues
  */
 static int mpi3mr_map_queues(struct Scsi_Host *shost)
 {
 	struct mpi3mr_ioc *mrioc = shost_priv(shost);
 
-	return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
-	    mrioc->pdev, mrioc->op_reply_q_offset);
+	return blk_mq_dev_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
+	    mrioc->pdev, mrioc->op_reply_q_offset,
+	    scsi_pci_get_queue_affinity, false, true);
 }
 
 /**

@@ -57,6 +57,7 @@
 #include <linux/blk-mq-pci.h>
 #include <asm/unaligned.h>
 
+#include "../scsi_priv.h"
 #include "mpt3sas_base.h"
 
 #define RAID_CHANNEL 1

@@ -11784,8 +11785,9 @@ static int scsih_map_queues(struct Scsi_Host *shost)
 	if (ioc->shost->nr_hw_queues == 1)
 		return 0;
 
-	return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
-	    ioc->pdev, ioc->high_iops_queues);
+	return blk_mq_dev_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
+	    ioc->pdev, ioc->high_iops_queues, scsi_pci_get_queue_affinity,
+	    false, true);
 }
 
 /* shost template for SAS 2.0 HBA devices */

@@ -21,6 +21,7 @@
 #include <scsi/scsi_transport_fc.h>
 
 #include "qla_target.h"
+#include "../scsi_priv.h"
 
 /*
  * Driver version

@@ -7696,7 +7697,8 @@ static int qla2xxx_map_queues(struct Scsi_Host *shost)
 	if (USER_CTRL_IRQ(vha->hw) || !vha->hw->mqiobase)
 		rc = blk_mq_map_queues(qmap);
 	else
-		rc = blk_mq_pci_map_queues(qmap, vha->hw->pdev, vha->irq_offset);
+		rc = blk_mq_dev_map_queues(qmap, vha->hw->pdev, vha->irq_offset,
+				scsi_pci_get_queue_affinity, false, true);
 	return rc;
 }
 

@@ -6,6 +6,7 @@
 #include <linux/async.h>
 #include <scsi/scsi_device.h>
 #include <linux/sbitmap.h>
+#include <linux/pci.h>
 
 struct request_queue;
 struct request;

@@ -190,4 +191,12 @@ extern int scsi_device_max_queue_depth(struct scsi_device *sdev);
 
 #define SCSI_DEVICE_BLOCK_MAX_TIMEOUT	600	/* units in seconds */
 
+static inline const struct cpumask *scsi_pci_get_queue_affinity(
+		void *dev_data, int offset, int queue)
+{
+	struct pci_dev *pdev = dev_data;
+
+	return pci_irq_get_affinity(pdev, offset + queue);
+}
+
 #endif /* _SCSI_PRIV_H */

@@ -26,6 +26,7 @@
 #include <scsi/scsi_eh.h>
 #include <scsi/scsi_transport_sas.h>
 #include <asm/unaligned.h>
+#include "../scsi_priv.h"
 #include "smartpqi.h"
 #include "smartpqi_sis.h"
 

@@ -6104,8 +6105,10 @@ static int pqi_map_queues(struct Scsi_Host *shost)
 {
 	struct pqi_ctrl_info *ctrl_info = shost_to_hba(shost);
 
-	return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
-					ctrl_info->pci_dev, 0);
+	return blk_mq_dev_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
+					ctrl_info->pci_dev, 0,
+					scsi_pci_get_queue_affinity, false,
+					true);
 }
 
 static int pqi_slave_configure(struct scsi_device *sdev)

@@ -433,6 +433,14 @@ static int nvme_init_request(struct blk_mq_tag_set *set, struct request *req,
 	return 0;
 }
 
+static const struct cpumask *nvme_pci_get_queue_affinity(
+		void *dev_data, int offset, int queue)
+{
+	struct pci_dev *pdev = dev_data;
+
+	return pci_irq_get_affinity(pdev, offset + queue);
+}
+
 static int queue_irq_offset(struct nvme_dev *dev)
 {
 	/* if we have more than 1 vec, admin queue offsets us by 1 */

@@ -463,7 +471,9 @@ static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
 		 */
 		map->queue_offset = qoff;
 		if (i != HCTX_TYPE_POLL && offset)
-			blk_mq_pci_map_queues(map, to_pci_dev(dev->dev), offset);
+			blk_mq_dev_map_queues(map, to_pci_dev(dev->dev), offset,
+					nvme_pci_get_queue_affinity, false,
+					true);
 		else
 			blk_mq_map_queues(map);
 		qoff += map->nr_queues;

@@ -448,6 +448,16 @@ int virtio_device_restore(struct virtio_device *dev)
 EXPORT_SYMBOL_GPL(virtio_device_restore);
 #endif
 
+const struct cpumask *virtio_get_vq_affinity(struct virtio_device *dev,
+		int index)
+{
+	if (!dev->config->get_vq_affinity)
+		return NULL;
+
+	return dev->config->get_vq_affinity(dev, index);
+}
+EXPORT_SYMBOL_GPL(virtio_get_vq_affinity);
+
 static int virtio_init(void)
 {
 	if (bus_register(&virtio_bus) != 0)

@@ -139,6 +139,8 @@ int virtio_device_restore(struct virtio_device *dev);
 #endif
 
 size_t virtio_max_dma_size(struct virtio_device *vdev);
+const struct cpumask *virtio_get_vq_affinity(struct virtio_device *dev,
+		int index);
 
 #define virtio_device_for_each_vq(vdev, vq) \
 	list_for_each_entry(vq, &vdev->vqs, list)

@@ -677,12 +677,20 @@ static int virtblk_init_request(struct blk_mq_tag_set *set, struct request *rq,
 	return 0;
 }
 
+static const struct cpumask *virtblk_get_vq_affinity(void *dev_data,
+		int offset, int queue)
+{
+	struct virtio_device *vdev = dev_data;
+
+	return virtio_get_vq_affinity(vdev, offset + queue);
+}
+
 static int virtblk_map_queues(struct blk_mq_tag_set *set)
 {
 	struct virtio_blk *vblk = set->driver_data;
 
-	return blk_mq_virtio_map_queues(&set->map[HCTX_TYPE_DEFAULT],
-					vblk->vdev, 0);
+	return blk_mq_dev_map_queues(&set->map[HCTX_TYPE_DEFAULT], vblk->vdev,
+				     0, virtblk_get_vq_affinity, true, true);
 }
 
 static const struct blk_mq_ops virtio_mq_ops = {

@@ -712,12 +712,21 @@ static int virtscsi_abort(struct scsi_cmnd *sc)
 	return virtscsi_tmf(vscsi, cmd);
 }
 
+static const struct cpumask *virtscsi_get_vq_affinity(void *dev_data,
+		int offset, int queue)
+{
+	struct virtio_device *vdev = dev_data;
+
+	return virtio_get_vq_affinity(vdev, offset + queue);
+}
+
 static int virtscsi_map_queues(struct Scsi_Host *shost)
 {
 	struct virtio_scsi *vscsi = shost_priv(shost);
 	struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
 
-	return blk_mq_virtio_map_queues(qmap, vscsi->vdev, 2);
+	return blk_mq_dev_map_queues(qmap, vscsi->vdev, 2,
+			virtscsi_get_vq_affinity, true, true);
 }
 
 static void virtscsi_commit_rqs(struct Scsi_Host *shost, u16 hwq)

@@ -2169,6 +2169,14 @@ static void nvme_rdma_complete_rq(struct request *rq)
 	nvme_complete_rq(rq);
 }
 
+static const struct cpumask *nvme_rdma_get_queue_affinity(
+		void *dev_data, int offset, int queue)
+{
+	struct ib_device *dev = dev_data;
+
+	return ib_get_vector_affinity(dev, offset + queue);
+}
+
 static int nvme_rdma_map_queues(struct blk_mq_tag_set *set)
 {
 	struct nvme_rdma_ctrl *ctrl = set->driver_data;

@@ -2192,10 +2200,12 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set)
 			ctrl->io_queues[HCTX_TYPE_DEFAULT];
 		set->map[HCTX_TYPE_READ].queue_offset = 0;
 	}
-	blk_mq_rdma_map_queues(&set->map[HCTX_TYPE_DEFAULT],
-			ctrl->device->dev, 0);
-	blk_mq_rdma_map_queues(&set->map[HCTX_TYPE_READ],
-			ctrl->device->dev, 0);
+	blk_mq_dev_map_queues(&set->map[HCTX_TYPE_DEFAULT],
+			ctrl->device->dev, 0, nvme_rdma_get_queue_affinity,
+			true, false);
+	blk_mq_dev_map_queues(&set->map[HCTX_TYPE_READ],
+			ctrl->device->dev, 0, nvme_rdma_get_queue_affinity,
+			true, false);
 
 	if (opts->nr_poll_queues && ctrl->io_queues[HCTX_TYPE_POLL]) {
 		/* map dedicated poll queues only if we have queues left */

@@ -31,9 +31,6 @@ obj-$(CONFIG_IOSCHED_BFQ)	+= bfq.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY_T10)	+= t10-pi.o
-obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o
-obj-$(CONFIG_BLK_MQ_VIRTIO)	+= blk-mq-virtio.o
-obj-$(CONFIG_BLK_MQ_RDMA)	+= blk-mq-rdma.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
 obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o

@@ -1,48 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (c) 2016 Christoph Hellwig.
- */
-#include <linux/kobject.h>
-#include <linux/blkdev.h>
-#include <linux/blk-mq.h>
-#include <linux/blk-mq-pci.h>
-#include <linux/pci.h>
-#include <linux/module.h>
-
-#include "blk-mq.h"
-
-/**
- * blk_mq_pci_map_queues - provide a default queue mapping for PCI device
- * @qmap:	CPU to hardware queue map.
- * @pdev:	PCI device associated with @set.
- * @offset:	Offset to use for the pci irq vector
- *
- * This function assumes the PCI device @pdev has at least as many available
- * interrupt vectors as @set has queues.  It will then query the vector
- * corresponding to each queue for it's affinity mask and built queue mapping
- * that maps a queue to the CPUs that have irq affinity for the corresponding
- * vector.
- */
-int blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev,
-			    int offset)
-{
-	const struct cpumask *mask;
-	unsigned int queue, cpu;
-
-	for (queue = 0; queue < qmap->nr_queues; queue++) {
-		mask = pci_irq_get_affinity(pdev, queue + offset);
-		if (!mask)
-			goto fallback;
-
-		for_each_cpu(cpu, mask)
-			qmap->mq_map[cpu] = qmap->queue_offset + queue;
-	}
-
-	return 0;
-
-fallback:
-	WARN_ON_ONCE(qmap->nr_queues > 1);
-	blk_mq_clear_mq_map(qmap);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues);

@@ -1,44 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (c) 2017 Sagi Grimberg.
- */
-#include <linux/blk-mq.h>
-#include <linux/blk-mq-rdma.h>
-#include <rdma/ib_verbs.h>
-
-/**
- * blk_mq_rdma_map_queues - provide a default queue mapping for rdma device
- * @map:	CPU to hardware queue map.
- * @dev:	rdma device to provide a mapping for.
- * @first_vec:	first interrupt vectors to use for queues (usually 0)
- *
- * This function assumes the rdma device @dev has at least as many available
- * interrupt vetors as @set has queues.  It will then query it's affinity mask
- * and built queue mapping that maps a queue to the CPUs that have irq affinity
- * for the corresponding vector.
- *
- * In case either the driver passed a @dev with less vectors than
- * @set->nr_hw_queues, or @dev does not provide an affinity mask for a
- * vector, we fallback to the naive mapping.
- */
-int blk_mq_rdma_map_queues(struct blk_mq_queue_map *map,
-		struct ib_device *dev, int first_vec)
-{
-	const struct cpumask *mask;
-	unsigned int queue, cpu;
-
-	for (queue = 0; queue < map->nr_queues; queue++) {
-		mask = ib_get_vector_affinity(dev, first_vec + queue);
-		if (!mask)
-			goto fallback;
-
-		for_each_cpu(cpu, mask)
-			map->mq_map[cpu] = map->queue_offset + queue;
-	}
-
-	return 0;
-
-fallback:
-	return blk_mq_map_queues(map);
-}
-EXPORT_SYMBOL_GPL(blk_mq_rdma_map_queues);

@@ -1,46 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (c) 2016 Christoph Hellwig.
- */
-#include <linux/device.h>
-#include <linux/blk-mq.h>
-#include <linux/blk-mq-virtio.h>
-#include <linux/virtio_config.h>
-#include <linux/module.h>
-#include "blk-mq.h"
-
-/**
- * blk_mq_virtio_map_queues - provide a default queue mapping for virtio device
- * @qmap:	CPU to hardware queue map.
- * @vdev:	virtio device to provide a mapping for.
- * @first_vec:	first interrupt vectors to use for queues (usually 0)
- *
- * This function assumes the virtio device @vdev has at least as many available
- * interrupt vectors as @set has queues.  It will then query the vector
- * corresponding to each queue for it's affinity mask and built queue mapping
- * that maps a queue to the CPUs that have irq affinity for the corresponding
- * vector.
- */
-int blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap,
-		struct virtio_device *vdev, int first_vec)
-{
-	const struct cpumask *mask;
-	unsigned int queue, cpu;
-
-	if (!vdev->config->get_vq_affinity)
-		goto fallback;
-
-	for (queue = 0; queue < qmap->nr_queues; queue++) {
-		mask = vdev->config->get_vq_affinity(vdev, first_vec + queue);
-		if (!mask)
-			goto fallback;
-
-		for_each_cpu(cpu, mask)
-			qmap->mq_map[cpu] = qmap->queue_offset + queue;
-	}
-
-	return 0;
-fallback:
-	return blk_mq_map_queues(qmap);
-}
-EXPORT_SYMBOL_GPL(blk_mq_virtio_map_queues);

@@ -427,6 +427,15 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
 }
 EXPORT_SYMBOL(blk_mq_alloc_request);
 
+static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
+{
+	int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);
+
+	if (cpu >= nr_cpu_ids)
+		cpu = cpumask_first(hctx->cpumask);
+	return cpu;
+}
+
 struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx)
 {

@@ -468,7 +477,10 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	data.hctx = q->queue_hw_ctx[hctx_idx];
 	if (!blk_mq_hw_queue_mapped(data.hctx))
 		goto out_queue_exit;
-	cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask);
+
+	WARN_ON_ONCE(blk_mq_hctx_use_managed_irq(data.hctx));
+
+	cpu = blk_mq_first_mapped_cpu(data.hctx);
 	data.ctx = __blk_mq_get_ctx(q, cpu);
 
 	if (!q->elevator)

@@ -1501,15 +1513,6 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	hctx_unlock(hctx, srcu_idx);
 }
 
-static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
-{
-	int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);
-
-	if (cpu >= nr_cpu_ids)
-		cpu = cpumask_first(hctx->cpumask);
-	return cpu;
-}
-
 /*
  * It'd be great if the workqueue API had a way to pass
  * in a mask and had some smarts for more clever placement.

@@ -2556,6 +2559,10 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
 	struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
 			struct blk_mq_hw_ctx, cpuhp_online);
 
+	/* hctx needn't to be deactivated in case managed irq isn't used */
+	if (!blk_mq_hctx_use_managed_irq(hctx))
+		return 0;
+
 	if (!cpumask_test_cpu(cpu, hctx->cpumask) ||
 	    !blk_mq_last_cpu_in_hctx(cpu, hctx))
 		return 0;

@@ -119,6 +119,11 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
 	return ctx->hctxs[type];
 }
 
+static inline bool blk_mq_hctx_use_managed_irq(struct blk_mq_hw_ctx *hctx)
+{
+	return hctx->queue->tag_set->map[hctx->type].use_managed_irq;
+}
+
 /*
  * sysfs helpers
  */