blk-mq: abstract out queue map

This is in preparation for allowing multiple sets of maps per
queue, if so desired.
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NBart Van Assche <bvanassche@acm.org>
Reviewed-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

block/blk-mq-cpumap.c

@@ -30,10 +30,10 @@ static int get_first_sibling(unsigned int cpu)
 	return cpu;
 }
 
-int blk_mq_map_queues(struct blk_mq_tag_set *set)
+int blk_mq_map_queues(struct blk_mq_queue_map *qmap)
 {
-	unsigned int *map = set->mq_map;
-	unsigned int nr_queues = set->nr_hw_queues;
+	unsigned int *map = qmap->mq_map;
+	unsigned int nr_queues = qmap->nr_queues;
 	unsigned int cpu, first_sibling;
 
 	for_each_possible_cpu(cpu) {
@@ -62,12 +62,12 @@ EXPORT_SYMBOL_GPL(blk_mq_map_queues);
  * We have no quick way of doing reverse lookups. This is only used at
  * queue init time, so runtime isn't important.
  */
-int blk_mq_hw_queue_to_node(unsigned int *mq_map, unsigned int index)
+int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int index)
 {
 	int i;
 
 	for_each_possible_cpu(i) {
-		if (index == mq_map[i])
+		if (index == qmap->mq_map[i])
 			return local_memory_node(cpu_to_node(i));
 	}
 

block/blk-mq-pci.c

@@ -31,26 +31,26 @@
  * that maps a queue to the CPUs that have irq affinity for the corresponding
  * vector.
  */
-int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev,
+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 < set->nr_hw_queues; queue++) {
+	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)
-			set->mq_map[cpu] = queue;
+			qmap->mq_map[cpu] = queue;
 	}
 
 	return 0;
 
 fallback:
-	WARN_ON_ONCE(set->nr_hw_queues > 1);
-	blk_mq_clear_mq_map(set);
+	WARN_ON_ONCE(qmap->nr_queues > 1);
+	blk_mq_clear_mq_map(qmap);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues);

block/blk-mq-rdma.c

@@ -41,12 +41,12 @@ int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set,
 			goto fallback;
 
 		for_each_cpu(cpu, mask)
-			set->mq_map[cpu] = queue;
+			set->map[0].mq_map[cpu] = queue;
 	}
 
 	return 0;
 
 fallback:
-	return blk_mq_map_queues(set);
+	return blk_mq_map_queues(&set->map[0]);
 }
 EXPORT_SYMBOL_GPL(blk_mq_rdma_map_queues);

block/blk-mq-virtio.c

@@ -29,7 +29,7 @@
  * that maps a queue to the CPUs that have irq affinity for the corresponding
  * vector.
  */
-int blk_mq_virtio_map_queues(struct blk_mq_tag_set *set,
+int blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap,
 		struct virtio_device *vdev, int first_vec)
 {
 	const struct cpumask *mask;
@@ -38,17 +38,17 @@ int blk_mq_virtio_map_queues(struct blk_mq_tag_set *set,
 	if (!vdev->config->get_vq_affinity)
 		goto fallback;
 
-	for (queue = 0; queue < set->nr_hw_queues; queue++) {
+	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)
-			set->mq_map[cpu] = queue;
+			qmap->mq_map[cpu] = queue;
 	}
 
 	return 0;
 fallback:
-	return blk_mq_map_queues(set);
+	return blk_mq_map_queues(qmap);
 }
 EXPORT_SYMBOL_GPL(blk_mq_virtio_map_queues);

block/blk-mq.c

@@ -1975,7 +1975,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 	struct blk_mq_tags *tags;
 	int node;
 
-	node = blk_mq_hw_queue_to_node(set->mq_map, hctx_idx);
+	node = blk_mq_hw_queue_to_node(&set->map[0], hctx_idx);
 	if (node == NUMA_NO_NODE)
 		node = set->numa_node;
 
@@ -2031,7 +2031,7 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 	size_t rq_size, left;
 	int node;
 
-	node = blk_mq_hw_queue_to_node(set->mq_map, hctx_idx);
+	node = blk_mq_hw_queue_to_node(&set->map[0], hctx_idx);
 	if (node == NUMA_NO_NODE)
 		node = set->numa_node;
 
@@ -2322,7 +2322,7 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	 * If the cpu isn't present, the cpu is mapped to first hctx.
 	 */
 	for_each_possible_cpu(i) {
-		hctx_idx = set->mq_map[i];
+		hctx_idx = set->map[0].mq_map[i];
 		/* unmapped hw queue can be remapped after CPU topo changed */
 		if (!set->tags[hctx_idx] &&
 		    !__blk_mq_alloc_rq_map(set, hctx_idx)) {
@@ -2332,7 +2332,7 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 			 * case, remap the current ctx to hctx[0] which
 			 * is guaranteed to always have tags allocated
 			 */
-			set->mq_map[i] = 0;
+			set->map[0].mq_map[i] = 0;
 		}
 
 		ctx = per_cpu_ptr(q->queue_ctx, i);
@@ -2585,7 +2585,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 		int node;
 		struct blk_mq_hw_ctx *hctx;
 
-		node = blk_mq_hw_queue_to_node(set->mq_map, i);
+		node = blk_mq_hw_queue_to_node(&set->map[0], i);
 		/*
 		 * If the hw queue has been mapped to another numa node,
 		 * we need to realloc the hctx. If allocation fails, fallback
@@ -2791,18 +2791,18 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 		 * for (queue = 0; queue < set->nr_hw_queues; queue++) {
 		 * 	mask = get_cpu_mask(queue)
 		 * 	for_each_cpu(cpu, mask)
-		 * 		set->mq_map[cpu] = queue;
+		 * 		set->map.mq_map[cpu] = queue;
 		 * }
 		 *
 		 * When we need to remap, the table has to be cleared for
 		 * killing stale mapping since one CPU may not be mapped
 		 * to any hw queue.
 		 */
-		blk_mq_clear_mq_map(set);
+		blk_mq_clear_mq_map(&set->map[0]);
 
 		return set->ops->map_queues(set);
 	} else
-		return blk_mq_map_queues(set);
+		return blk_mq_map_queues(&set->map[0]);
 }
 
 /*
@@ -2857,10 +2857,12 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 		return -ENOMEM;
 
 	ret = -ENOMEM;
-	set->mq_map = kcalloc_node(nr_cpu_ids, sizeof(*set->mq_map),
-				   GFP_KERNEL, set->numa_node);
-	if (!set->mq_map)
+	set->map[0].mq_map = kcalloc_node(nr_cpu_ids,
+					  sizeof(*set->map[0].mq_map),
+					  GFP_KERNEL, set->numa_node);
+	if (!set->map[0].mq_map)
 		goto out_free_tags;
+	set->map[0].nr_queues = set->nr_hw_queues;
 
 	ret = blk_mq_update_queue_map(set);
 	if (ret)
@@ -2876,8 +2878,8 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	return 0;
 
 out_free_mq_map:
-	kfree(set->mq_map);
-	set->mq_map = NULL;
+	kfree(set->map[0].mq_map);
+	set->map[0].mq_map = NULL;
 out_free_tags:
 	kfree(set->tags);
 	set->tags = NULL;
@@ -2892,8 +2894,8 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 	for (i = 0; i < nr_cpu_ids; i++)
 		blk_mq_free_map_and_requests(set, i);
 
-	kfree(set->mq_map);
-	set->mq_map = NULL;
+	kfree(set->map[0].mq_map);
+	set->map[0].mq_map = NULL;
 
 	kfree(set->tags);
 	set->tags = NULL;
@@ -3054,7 +3056,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 			pr_warn("Increasing nr_hw_queues to %d fails, fallback to %d\n",
 					nr_hw_queues, prev_nr_hw_queues);
 			set->nr_hw_queues = prev_nr_hw_queues;
-			blk_mq_map_queues(set);
+			blk_mq_map_queues(&set->map[0]);
 			goto fallback;
 		}
 		blk_mq_map_swqueue(q);

block/blk-mq.h

@@ -70,14 +70,14 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 /*
  * CPU -> queue mappings
  */
-extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);
+extern int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int);
 
 static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
 		int cpu)
 {
 	struct blk_mq_tag_set *set = q->tag_set;
 
-	return q->queue_hw_ctx[set->mq_map[cpu]];
+	return q->queue_hw_ctx[set->map[0].mq_map[cpu]];
 }
 
 /*
@@ -206,12 +206,12 @@ static inline void blk_mq_put_driver_tag(struct request *rq)
 	__blk_mq_put_driver_tag(hctx, rq);
 }
 
-static inline void blk_mq_clear_mq_map(struct blk_mq_tag_set *set)
+static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap)
 {
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		set->mq_map[cpu] = 0;
+		qmap->mq_map[cpu] = 0;
 }
 
 #endif

drivers/block/virtio_blk.c

@@ -624,7 +624,7 @@ 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, vblk->vdev, 0);
+	return blk_mq_virtio_map_queues(&set->map[0], vblk->vdev, 0);
 }
 
 #ifdef CONFIG_VIRTIO_BLK_SCSI

drivers/nvme/host/pci.c

@@ -435,7 +435,7 @@ static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
 {
 	struct nvme_dev *dev = set->driver_data;
 
-	return blk_mq_pci_map_queues(set, to_pci_dev(dev->dev),
+	return blk_mq_pci_map_queues(&set->map[0], to_pci_dev(dev->dev),
 			dev->num_vecs > 1 ? 1 /* admin queue */ : 0);
 }
 

drivers/scsi/qla2xxx/qla_os.c

@@ -6934,11 +6934,12 @@ static int qla2xxx_map_queues(struct Scsi_Host *shost)
 {
 	int rc;
 	scsi_qla_host_t *vha = (scsi_qla_host_t *)shost->hostdata;
+	struct blk_mq_queue_map *qmap = &shost->tag_set.map[0];
 
 	if (USER_CTRL_IRQ(vha->hw))
-		rc = blk_mq_map_queues(&shost->tag_set);
+		rc = blk_mq_map_queues(qmap);
 	else
-		rc = blk_mq_pci_map_queues(&shost->tag_set, vha->hw->pdev, 0);
+		rc = blk_mq_pci_map_queues(qmap, vha->hw->pdev, 0);
 	return rc;
 }
 

drivers/scsi/scsi_lib.c

@@ -1812,7 +1812,7 @@ static int scsi_map_queues(struct blk_mq_tag_set *set)
 
 	if (shost->hostt->map_queues)
 		return shost->hostt->map_queues(shost);
-	return blk_mq_map_queues(set);
+	return blk_mq_map_queues(&set->map[0]);
 }
 
 void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)

drivers/scsi/smartpqi/smartpqi_init.c

@@ -5319,7 +5319,8 @@ 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, ctrl_info->pci_dev, 0);
+	return blk_mq_pci_map_queues(&shost->tag_set.map[0],
+					ctrl_info->pci_dev, 0);
 }
 
 static int pqi_getpciinfo_ioctl(struct pqi_ctrl_info *ctrl_info,

drivers/scsi/virtio_scsi.c

@@ -719,8 +719,9 @@ static void virtscsi_target_destroy(struct scsi_target *starget)
 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[0];
 
-	return blk_mq_virtio_map_queues(&shost->tag_set, vscsi->vdev, 2);
+	return blk_mq_virtio_map_queues(qmap, vscsi->vdev, 2);
 }
 
 /*

include/linux/blk-mq-pci.h

@@ -2,10 +2,10 @@
 #ifndef _LINUX_BLK_MQ_PCI_H
 #define _LINUX_BLK_MQ_PCI_H
 
-struct blk_mq_tag_set;
+struct blk_mq_queue_map;
 struct pci_dev;
 
-int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev,
+int blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev,
 			  int offset);
 
 #endif /* _LINUX_BLK_MQ_PCI_H */

include/linux/blk-mq-virtio.h

@@ -2,10 +2,10 @@
 #ifndef _LINUX_BLK_MQ_VIRTIO_H
 #define _LINUX_BLK_MQ_VIRTIO_H
 
-struct blk_mq_tag_set;
+struct blk_mq_queue_map;
 struct virtio_device;
 
-int blk_mq_virtio_map_queues(struct blk_mq_tag_set *set,
+int blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap,
 		struct virtio_device *vdev, int first_vec);
 
 #endif /* _LINUX_BLK_MQ_VIRTIO_H */

include/linux/blk-mq.h

@@ -74,10 +74,19 @@ struct blk_mq_hw_ctx {
 	struct srcu_struct	srcu[0];
 };
 
+struct blk_mq_queue_map {
+	unsigned int *mq_map;
+	unsigned int nr_queues;
+};
+
+enum {
+	HCTX_MAX_TYPES = 1,
+};
+
 struct blk_mq_tag_set {
-	unsigned int		*mq_map;
+	struct blk_mq_queue_map	map[HCTX_MAX_TYPES];
 	const struct blk_mq_ops	*ops;
-	unsigned int		nr_hw_queues;
+	unsigned int		nr_hw_queues;	/* nr hw queues across maps */
 	unsigned int		queue_depth;	/* max hw supported */
 	unsigned int		reserved_tags;
 	unsigned int		cmd_size;	/* per-request extra data */
@@ -295,7 +304,7 @@ void blk_mq_freeze_queue_wait(struct request_queue *q);
 int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
 				     unsigned long timeout);
 
-int blk_mq_map_queues(struct blk_mq_tag_set *set);
+int blk_mq_map_queues(struct blk_mq_queue_map *qmap);
 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);