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

@@ -0,0 +1,47 @@
+/*
+ * 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;
 };