Merge branch 'for-4.9/block-irq' of git://git.kernel.dk/linux-block

Pull blk-mq irq/cpu mapping updates from Jens Axboe:
 "This is the block-irq topic branch for 4.9-rc. It's mostly from
  Christoph, and it allows drivers to specify their own mappings, and
  more importantly, to share the blk-mq mappings with the IRQ affinity
  mappings. It's a good step towards making this work better out of the
  box"

* 'for-4.9/block-irq' of git://git.kernel.dk/linux-block:
  blk_mq: linux/blk-mq.h does not include all the headers it depends on
  blk-mq: kill unused blk_mq_create_mq_map()
  blk-mq: get rid of the cpumask in struct blk_mq_tags
  nvme: remove the post_scan callout
  nvme: switch to use pci_alloc_irq_vectors
  blk-mq: provide a default queue mapping for PCI device
  blk-mq: allow the driver to pass in a queue mapping
  blk-mq: remove ->map_queue
  blk-mq: only allocate a single mq_map per tag_set
  blk-mq: don't redistribute hardware queues on a CPU hotplug event

block/Kconfig

@@ -125,4 +125,9 @@ config BLOCK_COMPAT
 	depends on BLOCK && COMPAT
 	default y
 
+config BLK_MQ_PCI
+	bool
+	depends on BLOCK && PCI
+	default y
+
 source block/Kconfig.iosched

block/Makefile

@@ -22,4 +22,4 @@ obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
-
+obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o

block/blk-flush.c

@@ -232,7 +232,7 @@ static void flush_end_io(struct request *flush_rq, int error)
 
 		/* release the tag's ownership to the req cloned from */
 		spin_lock_irqsave(&fq->mq_flush_lock, flags);
-		hctx = q->mq_ops->map_queue(q, flush_rq->mq_ctx->cpu);
+		hctx = blk_mq_map_queue(q, flush_rq->mq_ctx->cpu);
 		blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq);
 		flush_rq->tag = -1;
 	}
@@ -325,7 +325,7 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 		flush_rq->tag = first_rq->tag;
 		fq->orig_rq = first_rq;
 
-		hctx = q->mq_ops->map_queue(q, first_rq->mq_ctx->cpu);
+		hctx = blk_mq_map_queue(q, first_rq->mq_ctx->cpu);
 		blk_mq_tag_set_rq(hctx, first_rq->tag, flush_rq);
 	}
 
@@ -358,7 +358,7 @@ static void mq_flush_data_end_io(struct request *rq, int error)
 	unsigned long flags;
 	struct blk_flush_queue *fq = blk_get_flush_queue(q, ctx);
 
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
+	hctx = blk_mq_map_queue(q, ctx->cpu);
 
 	/*
 	 * After populating an empty queue, kick it to avoid stall.  Read

block/blk-mq-cpumap.c

@@ -31,14 +31,16 @@ static int get_first_sibling(unsigned int cpu)
 	return cpu;
 }
 
-int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
-			    const struct cpumask *online_mask)
+int blk_mq_map_queues(struct blk_mq_tag_set *set)
 {
+	unsigned int *map = set->mq_map;
+	unsigned int nr_queues = set->nr_hw_queues;
+	const struct cpumask *online_mask = cpu_online_mask;
 	unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling;
 	cpumask_var_t cpus;
 
 	if (!alloc_cpumask_var(&cpus, GFP_ATOMIC))
-		return 1;
+		return -ENOMEM;
 
 	cpumask_clear(cpus);
 	nr_cpus = nr_uniq_cpus = 0;
@@ -86,23 +88,6 @@ int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
 	return 0;
 }
 
-unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set)
-{
-	unsigned int *map;
-
-	/* If cpus are offline, map them to first hctx */
-	map = kzalloc_node(sizeof(*map) * nr_cpu_ids, GFP_KERNEL,
-				set->numa_node);
-	if (!map)
-		return NULL;
-
-	if (!blk_mq_update_queue_map(map, set->nr_hw_queues, cpu_online_mask))
-		return map;
-
-	kfree(map);
-	return NULL;
-}
-
 /*
  * We have no quick way of doing reverse lookups. This is only used at
  * queue init time, so runtime isn't important.

block/blk-mq-pci.c

+/*
+ * Copyright (c) 2016 Christoph Hellwig.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#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>
+
+/**
+ * blk_mq_pci_map_queues - provide a default queue mapping for PCI device
+ * @set:	tagset to provide the mapping for
+ * @pdev:	PCI device associated with @set.
+ *
+ * This function assumes the PCI device @pdev has at least as many available
+ * interrupt vetors as @set has queues.  It will then queuery 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_tag_set *set, struct pci_dev *pdev)
+{
+	const struct cpumask *mask;
+	unsigned int queue, cpu;
+
+	for (queue = 0; queue < set->nr_hw_queues; queue++) {
+		mask = pci_irq_get_affinity(pdev, queue);
+		if (!mask)
+			return -EINVAL;
+
+		for_each_cpu(cpu, mask)
+			set->mq_map[cpu] = queue;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues);

block/blk-mq-tag.c

@@ -141,8 +141,7 @@ static int bt_get(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt,
 		io_schedule();
 
 		data->ctx = blk_mq_get_ctx(data->q);
-		data->hctx = data->q->mq_ops->map_queue(data->q,
-				data->ctx->cpu);
+		data->hctx = blk_mq_map_queue(data->q, data->ctx->cpu);
 		if (data->flags & BLK_MQ_REQ_RESERVED) {
 			bt = &data->hctx->tags->breserved_tags;
 		} else {
@@ -399,11 +398,6 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	if (!tags)
 		return NULL;
 
-	if (!zalloc_cpumask_var(&tags->cpumask, GFP_KERNEL)) {
-		kfree(tags);
-		return NULL;
-	}
-
 	tags->nr_tags = total_tags;
 	tags->nr_reserved_tags = reserved_tags;
 
@@ -414,7 +408,6 @@ void blk_mq_free_tags(struct blk_mq_tags *tags)
 {
 	sbitmap_queue_free(&tags->bitmap_tags);
 	sbitmap_queue_free(&tags->breserved_tags);
-	free_cpumask_var(tags->cpumask);
 	kfree(tags);
 }
 
@@ -453,7 +446,7 @@ u32 blk_mq_unique_tag(struct request *rq)
 	int hwq = 0;
 
 	if (q->mq_ops) {
-		hctx = q->mq_ops->map_queue(q, rq->mq_ctx->cpu);
+		hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
 		hwq = hctx->queue_num;
 	}
 

block/blk-mq-tag.h

@@ -17,8 +17,6 @@ struct blk_mq_tags {
 
 	struct request **rqs;
 	struct list_head page_list;
-
-	cpumask_var_t cpumask;
 };
 
 

block/blk-mq.c

@@ -224,7 +224,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 		return ERR_PTR(ret);
 
 	ctx = blk_mq_get_ctx(q);
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
+	hctx = blk_mq_map_queue(q, ctx->cpu);
 	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
 	rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
 	blk_mq_put_ctx(ctx);
@@ -319,11 +319,7 @@ EXPORT_SYMBOL_GPL(blk_mq_free_hctx_request);
 
 void blk_mq_free_request(struct request *rq)
 {
-	struct blk_mq_hw_ctx *hctx;
-	struct request_queue *q = rq->q;
-
-	hctx = q->mq_ops->map_queue(q, rq->mq_ctx->cpu);
-	blk_mq_free_hctx_request(hctx, rq);
+	blk_mq_free_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
 }
 EXPORT_SYMBOL_GPL(blk_mq_free_request);
 
@@ -1058,9 +1054,7 @@ void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	struct request_queue *q = rq->q;
-	struct blk_mq_hw_ctx *hctx;
-
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
 
 	spin_lock(&ctx->lock);
 	__blk_mq_insert_request(hctx, rq, at_head);
@@ -1077,12 +1071,10 @@ static void blk_mq_insert_requests(struct request_queue *q,
 				     bool from_schedule)
 
 {
-	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
 
 	trace_block_unplug(q, depth, !from_schedule);
 
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
-
 	/*
 	 * preemption doesn't flush plug list, so it's possible ctx->cpu is
 	 * offline now
@@ -1216,7 +1208,7 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 
 	blk_queue_enter_live(q);
 	ctx = blk_mq_get_ctx(q);
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
+	hctx = blk_mq_map_queue(q, ctx->cpu);
 
 	if (rw_is_sync(bio_op(bio), bio->bi_opf))
 		op_flags |= REQ_SYNC;
@@ -1235,8 +1227,7 @@ static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie)
 {
 	int ret;
 	struct request_queue *q = rq->q;
-	struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q,
-			rq->mq_ctx->cpu);
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
 	struct blk_mq_queue_data bd = {
 		.rq = rq,
 		.list = NULL,
@@ -1440,15 +1431,6 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	return cookie;
 }
 
-/*
- * Default mapping to a software queue, since we use one per CPU.
- */
-struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, const int cpu)
-{
-	return q->queue_hw_ctx[q->mq_map[cpu]];
-}
-EXPORT_SYMBOL(blk_mq_map_queue);
-
 static void blk_mq_free_rq_map(struct blk_mq_tag_set *set,
 		struct blk_mq_tags *tags, unsigned int hctx_idx)
 {
@@ -1757,7 +1739,7 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 		if (!cpu_online(i))
 			continue;
 
-		hctx = q->mq_ops->map_queue(q, i);
+		hctx = blk_mq_map_queue(q, i);
 
 		/*
 		 * Set local node, IFF we have more than one hw queue. If
@@ -1795,7 +1777,7 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 			continue;
 
 		ctx = per_cpu_ptr(q->queue_ctx, i);
-		hctx = q->mq_ops->map_queue(q, i);
+		hctx = blk_mq_map_queue(q, i);
 
 		cpumask_set_cpu(i, hctx->cpumask);
 		ctx->index_hw = hctx->nr_ctx;
@@ -1824,7 +1806,6 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 		hctx->tags = set->tags[i];
 		WARN_ON(!hctx->tags);
 
-		cpumask_copy(hctx->tags->cpumask, hctx->cpumask);
 		/*
 		 * Set the map size to the number of mapped software queues.
 		 * This is more accurate and more efficient than looping
@@ -1918,7 +1899,6 @@ void blk_mq_release(struct request_queue *q)
 		kfree(hctx);
 	}
 
-	kfree(q->mq_map);
 	q->mq_map = NULL;
 
 	kfree(q->queue_hw_ctx);
@@ -2017,9 +1997,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	if (!q->queue_hw_ctx)
 		goto err_percpu;
 
-	q->mq_map = blk_mq_make_queue_map(set);
-	if (!q->mq_map)
-		goto err_map;
+	q->mq_map = set->mq_map;
 
 	blk_mq_realloc_hw_ctxs(set, q);
 	if (!q->nr_hw_queues)
@@ -2069,8 +2047,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	return q;
 
 err_hctxs:
-	kfree(q->mq_map);
-err_map:
 	kfree(q->queue_hw_ctx);
 err_percpu:
 	free_percpu(q->queue_ctx);
@@ -2102,8 +2078,6 @@ static void blk_mq_queue_reinit(struct request_queue *q,
 
 	blk_mq_sysfs_unregister(q);
 
-	blk_mq_update_queue_map(q->mq_map, q->nr_hw_queues, online_mask);
-
 	/*
 	 * redo blk_mq_init_cpu_queues and blk_mq_init_hw_queues. FIXME: maybe
 	 * we should change hctx numa_node according to new topology (this
@@ -2242,12 +2216,6 @@ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 	return 0;
 }
 
-struct cpumask *blk_mq_tags_cpumask(struct blk_mq_tags *tags)
-{
-	return tags->cpumask;
-}
-EXPORT_SYMBOL_GPL(blk_mq_tags_cpumask);
-
 /*
  * Alloc a tag set to be associated with one or more request queues.
  * May fail with EINVAL for various error conditions. May adjust the
@@ -2256,6 +2224,8 @@ EXPORT_SYMBOL_GPL(blk_mq_tags_cpumask);
  */
 int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 {
+	int ret;
+
 	BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS);
 
 	if (!set->nr_hw_queues)
@@ -2265,7 +2235,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN)
 		return -EINVAL;
 
-	if (!set->ops->queue_rq || !set->ops->map_queue)
+	if (!set->ops->queue_rq)
 		return -EINVAL;
 
 	if (set->queue_depth > BLK_MQ_MAX_DEPTH) {
@@ -2294,17 +2264,35 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (!set->tags)
 		return -ENOMEM;
 
-	if (blk_mq_alloc_rq_maps(set))
-		goto enomem;
+	ret = -ENOMEM;
+	set->mq_map = kzalloc_node(sizeof(*set->mq_map) * nr_cpu_ids,
+			GFP_KERNEL, set->numa_node);
+	if (!set->mq_map)
+		goto out_free_tags;
+
+	if (set->ops->map_queues)
+		ret = set->ops->map_queues(set);
+	else
+		ret = blk_mq_map_queues(set);
+	if (ret)
+		goto out_free_mq_map;
+
+	ret = blk_mq_alloc_rq_maps(set);
+	if (ret)
+		goto out_free_mq_map;
 
 	mutex_init(&set->tag_list_lock);
 	INIT_LIST_HEAD(&set->tag_list);
 
 	return 0;
-enomem:
+
+out_free_mq_map:
+	kfree(set->mq_map);
+	set->mq_map = NULL;
+out_free_tags:
 	kfree(set->tags);
 	set->tags = NULL;
-	return -ENOMEM;
+	return ret;
 }
 EXPORT_SYMBOL(blk_mq_alloc_tag_set);
 
@@ -2317,6 +2305,9 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 			blk_mq_free_rq_map(set, set->tags[i], i);
 	}
 
+	kfree(set->mq_map);
+	set->mq_map = NULL;
+
 	kfree(set->tags);
 	set->tags = NULL;
 }

block/blk-mq.h

@@ -45,11 +45,15 @@ void blk_mq_disable_hotplug(void);
 /*
  * CPU -> queue mappings
  */
-extern unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set);
-extern int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
-				   const struct cpumask *online_mask);
+int blk_mq_map_queues(struct blk_mq_tag_set *set);
 extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);
 
+static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
+		int cpu)
+{
+	return q->queue_hw_ctx[q->mq_map[cpu]];
+}
+
 /*
  * sysfs helpers
  */

block/blk.h

@@ -39,14 +39,9 @@ extern struct ida blk_queue_ida;
 static inline struct blk_flush_queue *blk_get_flush_queue(
 		struct request_queue *q, struct blk_mq_ctx *ctx)
 {
-	struct blk_mq_hw_ctx *hctx;
-
-	if (!q->mq_ops)
+	if (q->mq_ops)
+		return blk_mq_map_queue(q, ctx->cpu)->fq;
 	return q->fq;
-
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
-
-	return hctx->fq;
 }
 
 static inline void __blk_get_queue(struct request_queue *q)

drivers/block/loop.c

@@ -1703,7 +1703,6 @@ static int loop_init_request(void *data, struct request *rq,
 
 static struct blk_mq_ops loop_mq_ops = {
 	.queue_rq       = loop_queue_rq,
-	.map_queue      = blk_mq_map_queue,
 	.init_request	= loop_init_request,
 };
 

drivers/block/mtip32xx/mtip32xx.c

@@ -3895,7 +3895,6 @@ static enum blk_eh_timer_return mtip_cmd_timeout(struct request *req,
 
 static struct blk_mq_ops mtip_mq_ops = {
 	.queue_rq	= mtip_queue_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_request	= mtip_init_cmd,
 	.exit_request	= mtip_free_cmd,
 	.complete	= mtip_softirq_done_fn,

drivers/block/nbd.c

@@ -881,7 +881,6 @@ static int nbd_init_request(void *data, struct request *rq,
 
 static struct blk_mq_ops nbd_mq_ops = {
 	.queue_rq	= nbd_queue_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_request	= nbd_init_request,
 	.timeout	= nbd_xmit_timeout,
 };

drivers/block/null_blk.c

@@ -394,7 +394,6 @@ static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 
 static struct blk_mq_ops null_mq_ops = {
 	.queue_rq       = null_queue_rq,
-	.map_queue      = blk_mq_map_queue,
 	.init_hctx	= null_init_hctx,
 	.complete	= null_softirq_done_fn,
 };

drivers/block/rbd.c

@@ -3621,7 +3621,6 @@ static int rbd_init_request(void *data, struct request *rq,
 
 static struct blk_mq_ops rbd_mq_ops = {
 	.queue_rq	= rbd_queue_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_request	= rbd_init_request,
 };
 

drivers/block/virtio_blk.c

@@ -542,7 +542,6 @@ static int virtblk_init_request(void *data, struct request *rq,
 
 static struct blk_mq_ops virtio_mq_ops = {
 	.queue_rq	= virtio_queue_rq,
-	.map_queue	= blk_mq_map_queue,
 	.complete	= virtblk_request_done,
 	.init_request	= virtblk_init_request,
 };

drivers/block/xen-blkfront.c

@@ -909,7 +909,6 @@ static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 static struct blk_mq_ops blkfront_mq_ops = {
 	.queue_rq = blkif_queue_rq,
-	.map_queue = blk_mq_map_queue,
 };
 
 static void blkif_set_queue_limits(struct blkfront_info *info)

drivers/md/dm-rq.c

@@ -938,7 +938,6 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 static struct blk_mq_ops dm_mq_ops = {
 	.queue_rq = dm_mq_queue_rq,
-	.map_queue = blk_mq_map_queue,
 	.complete = dm_softirq_done,
 	.init_request = dm_mq_init_request,
 };

drivers/mtd/ubi/block.c

@@ -351,7 +351,6 @@ static int ubiblock_init_request(void *data, struct request *req,
 static struct blk_mq_ops ubiblock_mq_ops = {
 	.queue_rq       = ubiblock_queue_rq,
 	.init_request	= ubiblock_init_request,
-	.map_queue      = blk_mq_map_queue,
 };
 
 static DEFINE_IDR(ubiblock_minor_idr);

drivers/nvme/host/core.c

@@ -1851,9 +1851,6 @@ static void nvme_scan_work(struct work_struct *work)
 	list_sort(NULL, &ctrl->namespaces, ns_cmp);
 	mutex_unlock(&ctrl->namespaces_mutex);
 	kfree(id);
-
-	if (ctrl->ops->post_scan)
-		ctrl->ops->post_scan(ctrl);
 }
 
 void nvme_queue_scan(struct nvme_ctrl *ctrl)

drivers/nvme/host/nvme.h

@@ -185,7 +185,6 @@ struct nvme_ctrl_ops {
 	int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
 	int (*reset_ctrl)(struct nvme_ctrl *ctrl);
 	void (*free_ctrl)(struct nvme_ctrl *ctrl);
-	void (*post_scan)(struct nvme_ctrl *ctrl);
 	void (*submit_async_event)(struct nvme_ctrl *ctrl, int aer_idx);
 	int (*delete_ctrl)(struct nvme_ctrl *ctrl);
 	const char *(*get_subsysnqn)(struct nvme_ctrl *ctrl);

drivers/nvme/host/pci.c

@@ -16,6 +16,7 @@
 #include <linux/bitops.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
+#include <linux/blk-mq-pci.h>
 #include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
@@ -88,7 +89,6 @@ struct nvme_dev {
 	unsigned max_qid;
 	int q_depth;
 	u32 db_stride;
-	struct msix_entry *entry;
 	void __iomem *bar;
 	struct work_struct reset_work;
 	struct work_struct remove_work;
@@ -201,6 +201,11 @@ static unsigned int nvme_cmd_size(struct nvme_dev *dev)
 		nvme_iod_alloc_size(dev, NVME_INT_BYTES(dev), NVME_INT_PAGES);
 }
 
+static int nvmeq_irq(struct nvme_queue *nvmeq)
+{
+	return pci_irq_vector(to_pci_dev(nvmeq->dev->dev), nvmeq->cq_vector);
+}
+
 static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 				unsigned int hctx_idx)
 {
@@ -263,6 +268,13 @@ static int nvme_init_request(void *data, struct request *req,
 	return 0;
 }
 
+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));
+}
+
 /**
  * __nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
  * @nvmeq: The queue to use
@@ -960,7 +972,7 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 		spin_unlock_irq(&nvmeq->q_lock);
 		return 1;
 	}
-	vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
+	vector = nvmeq_irq(nvmeq);
 	nvmeq->dev->online_queues--;
 	nvmeq->cq_vector = -1;
 	spin_unlock_irq(&nvmeq->q_lock);
@@ -968,7 +980,6 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 	if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q)
 		blk_mq_stop_hw_queues(nvmeq->dev->ctrl.admin_q);
 
-	irq_set_affinity_hint(vector, NULL);
 	free_irq(vector, nvmeq);
 
 	return 0;
@@ -1075,15 +1086,14 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	return NULL;
 }
 
-static int queue_request_irq(struct nvme_dev *dev, struct nvme_queue *nvmeq,
-							const char *name)
+static int queue_request_irq(struct nvme_queue *nvmeq)
 {
 	if (use_threaded_interrupts)
-		return request_threaded_irq(dev->entry[nvmeq->cq_vector].vector,
-					nvme_irq_check, nvme_irq, IRQF_SHARED,
-					name, nvmeq);
-	return request_irq(dev->entry[nvmeq->cq_vector].vector, nvme_irq,
-				IRQF_SHARED, name, nvmeq);
+		return request_threaded_irq(nvmeq_irq(nvmeq), nvme_irq_check,
+				nvme_irq, IRQF_SHARED, nvmeq->irqname, nvmeq);
+	else
+		return request_irq(nvmeq_irq(nvmeq), nvme_irq, IRQF_SHARED,
+				nvmeq->irqname, nvmeq);
 }
 
 static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
@@ -1114,7 +1124,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	if (result < 0)
 		goto release_cq;
 
-	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
+	result = queue_request_irq(nvmeq);
 	if (result < 0)
 		goto release_sq;
 
@@ -1131,7 +1141,6 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 static struct blk_mq_ops nvme_mq_admin_ops = {
 	.queue_rq	= nvme_queue_rq,
 	.complete	= nvme_complete_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_hctx	= nvme_admin_init_hctx,
 	.exit_hctx      = nvme_admin_exit_hctx,
 	.init_request	= nvme_admin_init_request,
@@ -1141,9 +1150,9 @@ static struct blk_mq_ops nvme_mq_admin_ops = {
 static struct blk_mq_ops nvme_mq_ops = {
 	.queue_rq	= nvme_queue_rq,
 	.complete	= nvme_complete_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_hctx	= nvme_init_hctx,
 	.init_request	= nvme_init_request,
+	.map_queues	= nvme_pci_map_queues,
 	.timeout	= nvme_timeout,
 	.poll		= nvme_poll,
 };
@@ -1234,7 +1243,7 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 		goto free_nvmeq;
 
 	nvmeq->cq_vector = 0;
-	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
+	result = queue_request_irq(nvmeq);
 	if (result) {
 		nvmeq->cq_vector = -1;
 		goto free_nvmeq;
@@ -1382,7 +1391,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 {
 	struct nvme_queue *adminq = dev->queues[0];
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
-	int result, i, vecs, nr_io_queues, size;
+	int result, nr_io_queues, size;
 
 	nr_io_queues = num_online_cpus();
 	result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
@@ -1417,29 +1426,18 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	}
 
 	/* Deregister the admin queue's interrupt */
-	free_irq(dev->entry[0].vector, adminq);
+	free_irq(pci_irq_vector(pdev, 0), adminq);
 
 	/*
 	 * If we enable msix early due to not intx, disable it again before
 	 * setting up the full range we need.
 	 */
-	if (pdev->msi_enabled)
-		pci_disable_msi(pdev);
-	else if (pdev->msix_enabled)
-		pci_disable_msix(pdev);
-
-	for (i = 0; i < nr_io_queues; i++)
-		dev->entry[i].entry = i;
-	vecs = pci_enable_msix_range(pdev, dev->entry, 1, nr_io_queues);
-	if (vecs < 0) {
-		vecs = pci_enable_msi_range(pdev, 1, min(nr_io_queues, 32));
-		if (vecs < 0) {
-			vecs = 1;
-		} else {
-			for (i = 0; i < vecs; i++)
-				dev->entry[i].vector = i + pdev->irq;
-		}
-	}
+	pci_free_irq_vectors(pdev);
+	nr_io_queues = pci_alloc_irq_vectors(pdev, 1, nr_io_queues,
+			PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY);
+	if (nr_io_queues <= 0)
+		return -EIO;
+	dev->max_qid = nr_io_queues;
 
 	/*
 	 * Should investigate if there's a performance win from allocating
@@ -1447,10 +1445,8 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	 * path to scale better, even if the receive path is limited by the
 	 * number of interrupts.
 	 */
-	nr_io_queues = vecs;
-	dev->max_qid = nr_io_queues;
 
-	result = queue_request_irq(dev, adminq, adminq->irqname);
+	result = queue_request_irq(adminq);
 	if (result) {
 		adminq->cq_vector = -1;
 		goto free_queues;
@@ -1462,23 +1458,6 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	return result;
 }
 
-static void nvme_pci_post_scan(struct nvme_ctrl *ctrl)
-{
-	struct nvme_dev *dev = to_nvme_dev(ctrl);
-	struct nvme_queue *nvmeq;
-	int i;
-
-	for (i = 0; i < dev->online_queues; i++) {
-		nvmeq = dev->queues[i];
-
-		if (!nvmeq->tags || !(*nvmeq->tags))
-			continue;
-
-		irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
-					blk_mq_tags_cpumask(*nvmeq->tags));
-	}
-}
-
 static void nvme_del_queue_end(struct request *req, int error)
 {
 	struct nvme_queue *nvmeq = req->end_io_data;
@@ -1615,15 +1594,9 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 	 * interrupts. Pre-enable a single MSIX or MSI vec for setup. We'll
 	 * adjust this later.
 	 */
-	if (pci_enable_msix(pdev, dev->entry, 1)) {
-		pci_enable_msi(pdev);
-		dev->entry[0].vector = pdev->irq;
-	}
-
-	if (!dev->entry[0].vector) {
-		result = -ENODEV;
-		goto disable;
-	}
+	result = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
+	if (result < 0)
+		return result;
 
 	cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
 
@@ -1665,10 +1638,7 @@ static void nvme_pci_disable(struct nvme_dev *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
-	if (pdev->msi_enabled)
-		pci_disable_msi(pdev);
-	else if (pdev->msix_enabled)
-		pci_disable_msix(pdev);
+	pci_free_irq_vectors(pdev);
 
 	if (pci_is_enabled(pdev)) {
 		pci_disable_pcie_error_reporting(pdev);
@@ -1743,7 +1713,6 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 	if (dev->ctrl.admin_q)
 		blk_put_queue(dev->ctrl.admin_q);
 	kfree(dev->queues);
-	kfree(dev->entry);
 	kfree(dev);
 }
 
@@ -1887,7 +1856,6 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.reg_read64		= nvme_pci_reg_read64,
 	.reset_ctrl		= nvme_pci_reset_ctrl,
 	.free_ctrl		= nvme_pci_free_ctrl,
-	.post_scan		= nvme_pci_post_scan,
 	.submit_async_event	= nvme_pci_submit_async_event,
 };
 
@@ -1920,10 +1888,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
 	if (!dev)
 		return -ENOMEM;
-	dev->entry = kzalloc_node(num_possible_cpus() * sizeof(*dev->entry),
-							GFP_KERNEL, node);
-	if (!dev->entry)
-		goto free;
 	dev->queues = kzalloc_node((num_possible_cpus() + 1) * sizeof(void *),
 							GFP_KERNEL, node);
 	if (!dev->queues)
@@ -1964,7 +1928,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	nvme_dev_unmap(dev);
  free:
 	kfree(dev->queues);
-	kfree(dev->entry);
 	kfree(dev);
 	return result;
 }

drivers/nvme/host/rdma.c

@@ -1480,7 +1480,6 @@ static void nvme_rdma_complete_rq(struct request *rq)
 static struct blk_mq_ops nvme_rdma_mq_ops = {
 	.queue_rq	= nvme_rdma_queue_rq,
 	.complete	= nvme_rdma_complete_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_request	= nvme_rdma_init_request,
 	.exit_request	= nvme_rdma_exit_request,
 	.reinit_request	= nvme_rdma_reinit_request,
@@ -1492,7 +1491,6 @@ static struct blk_mq_ops nvme_rdma_mq_ops = {
 static struct blk_mq_ops nvme_rdma_admin_mq_ops = {
 	.queue_rq	= nvme_rdma_queue_rq,
 	.complete	= nvme_rdma_complete_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_request	= nvme_rdma_init_admin_request,
 	.exit_request	= nvme_rdma_exit_admin_request,
 	.reinit_request	= nvme_rdma_reinit_request,

drivers/nvme/target/loop.c

@@ -273,7 +273,6 @@ static int nvme_loop_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 static struct blk_mq_ops nvme_loop_mq_ops = {
 	.queue_rq	= nvme_loop_queue_rq,
 	.complete	= nvme_loop_complete_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_request	= nvme_loop_init_request,
 	.init_hctx	= nvme_loop_init_hctx,
 	.timeout	= nvme_loop_timeout,
@@ -282,7 +281,6 @@ static struct blk_mq_ops nvme_loop_mq_ops = {
 static struct blk_mq_ops nvme_loop_admin_mq_ops = {
 	.queue_rq	= nvme_loop_queue_rq,
 	.complete	= nvme_loop_complete_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_request	= nvme_loop_init_admin_request,
 	.init_hctx	= nvme_loop_init_admin_hctx,
 	.timeout	= nvme_loop_timeout,

drivers/scsi/scsi_lib.c

@@ -2077,7 +2077,6 @@ struct request_queue *scsi_alloc_queue(struct scsi_device *sdev)
 }
 
 static struct blk_mq_ops scsi_mq_ops = {
-	.map_queue	= blk_mq_map_queue,
 	.queue_rq	= scsi_queue_rq,
 	.complete	= scsi_softirq_done,
 	.timeout	= scsi_timeout,

include/linux/blk-mq-pci.h

+#ifndef _LINUX_BLK_MQ_PCI_H
+#define _LINUX_BLK_MQ_PCI_H
+
+struct blk_mq_tag_set;
+struct pci_dev;
+
+int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev);
+
+#endif /* _LINUX_BLK_MQ_PCI_H */

include/linux/blk-mq.h

@@ -62,6 +62,7 @@ struct blk_mq_hw_ctx {
 };
 
 struct blk_mq_tag_set {
+	unsigned int		*mq_map;
 	struct blk_mq_ops	*ops;
 	unsigned int		nr_hw_queues;
 	unsigned int		queue_depth;	/* max hw supported */
@@ -85,7 +86,6 @@ struct blk_mq_queue_data {
 };
 
 typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *);
-typedef struct blk_mq_hw_ctx *(map_queue_fn)(struct request_queue *, const int);
 typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool);
 typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
 typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
@@ -99,6 +99,7 @@ typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
 		bool);
 typedef void (busy_tag_iter_fn)(struct request *, void *, bool);
 typedef int (poll_fn)(struct blk_mq_hw_ctx *, unsigned int);
+typedef int (map_queues_fn)(struct blk_mq_tag_set *set);
 
 
 struct blk_mq_ops {
@@ -107,11 +108,6 @@ struct blk_mq_ops {
 	 */
 	queue_rq_fn		*queue_rq;
 
-	/*
-	 * Map to specific hardware queue
-	 */
-	map_queue_fn		*map_queue;
-
 	/*
 	 * Called on request timeout
 	 */
@@ -144,6 +140,8 @@ struct blk_mq_ops {
 	init_request_fn		*init_request;
 	exit_request_fn		*exit_request;
 	reinit_request_fn	*reinit_request;
+
+	map_queues_fn		*map_queues;
 };
 
 enum {
@@ -199,7 +197,6 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int op,
 		unsigned int flags, unsigned int hctx_idx);
 struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
-struct cpumask *blk_mq_tags_cpumask(struct blk_mq_tags *tags);
 
 enum {
 	BLK_MQ_UNIQUE_TAG_BITS = 16,
@@ -218,7 +215,6 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
 	return unique_tag & BLK_MQ_UNIQUE_TAG_MASK;
 }
 
-struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
 
 int blk_mq_request_started(struct request *rq);
 void blk_mq_start_request(struct request *rq);