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

10 files changed, 110 insertions, 92 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 5136ad4bb6d55..1d4d624492fcd 100644
--- a/block/Kconfig
+++ b/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
diff --git a/block/Makefile b/block/Makefile
index 9eda2322b2d40..37a0d93f97bb6 100644
--- a/block/Makefile
+++ b/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
diff --git a/block/blk-flush.c b/block/blk-flush.c
index d308def812db9..6a14b68b91358 100644
--- a/block/blk-flush.c
+++ b/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
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index d0634bcf322f1..19b1d9c5f07e1 100644
--- a/block/blk-mq-cpumap.c
+++ b/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.
diff --git a/block/blk-mq-pci.c b/block/blk-mq-pci.c
new file mode 100644
index 0000000000000..966c2169762eb
--- /dev/null
+++ b/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);
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index cef618f6fc921..dcf5ce3ba4bff 100644
--- a/block/blk-mq-tag.c
+++ b/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;
 	}
 
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 09f4cc0aaa84c..d1662734dc539 100644
--- a/block/blk-mq-tag.h
+++ b/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;
 };
 
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index dc5f47f609316..b65f572a4faf1 100644
--- a/block/blk-mq.c
+++ b/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 @@ run_queue:
 	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;
 }
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 9b15d2ef7f7bf..df6474cb5a4ce 100644
--- a/block/blk-mq.h
+++ b/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
  */
diff --git a/block/blk.h b/block/blk.h
index c37492f5edaae..74444c49078fc 100644
--- a/block/blk.h
+++ b/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)
-		return q->fq;
-
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
-
-	return hctx->fq;
+	if (q->mq_ops)
+		return blk_mq_map_queue(q, ctx->cpu)->fq;
+	return q->fq;
 }
 
 static inline void __blk_get_queue(struct request_queue *q)