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

Pull block fixes from Jens Axboe:
 "Another week, another round of fixes.

  These have been brewing for a bit and in various iterations, but I
  feel pretty comfortable about the quality of them.  They fix real
  issues.  The pull request is mostly blk-mq related, and the only one
  not fixing a real bug, is the tag iterator abstraction from Christoph.
  But it's pretty trivial, and we'll need it for another fix soon.

  Apart from the blk-mq fixes, there's an NVMe affinity fix from Keith,
  and a single fix for xen-blkback from Roger fixing failure to free
  requests on disconnect"

* 'for-linus' of git://git.kernel.dk/linux-block:
  blk-mq: factor out a helper to iterate all tags for a request_queue
  blk-mq: fix racy updates of rq->errors
  blk-mq: fix deadlock when reading cpu_list
  blk-mq: avoid inserting requests before establishing new mapping
  blk-mq: fix q->mq_usage_counter access race
  blk-mq: Fix use after of free q->mq_map
  blk-mq: fix sysfs registration/unregistration race
  blk-mq: avoid setting hctx->tags->cpumask before allocation
  NVMe: Set affinity after allocating request queues
  xen/blkback: free requests on disconnection

block/blk-mq-cpumap.c

@@ -31,7 +31,8 @@ static int get_first_sibling(unsigned int cpu)
 	return cpu;
 }
 
-int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues)
+int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
+			    const struct cpumask *online_mask)
 {
 	unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling;
 	cpumask_var_t cpus;
@@ -41,7 +42,7 @@ int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues)
 
 	cpumask_clear(cpus);
 	nr_cpus = nr_uniq_cpus = 0;
-	for_each_online_cpu(i) {
+	for_each_cpu(i, online_mask) {
 		nr_cpus++;
 		first_sibling = get_first_sibling(i);
 		if (!cpumask_test_cpu(first_sibling, cpus))
@@ -51,7 +52,7 @@ int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues)
 
 	queue = 0;
 	for_each_possible_cpu(i) {
-		if (!cpu_online(i)) {
+		if (!cpumask_test_cpu(i, online_mask)) {
 			map[i] = 0;
 			continue;
 		}
@@ -95,7 +96,7 @@ unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set)
 	if (!map)
 		return NULL;
 
-	if (!blk_mq_update_queue_map(map, set->nr_hw_queues))
+	if (!blk_mq_update_queue_map(map, set->nr_hw_queues, cpu_online_mask))
 		return map;
 
 	kfree(map);

block/blk-mq-sysfs.c

@@ -229,8 +229,6 @@ static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
 	unsigned int i, first = 1;
 	ssize_t ret = 0;
 
-	blk_mq_disable_hotplug();
-
 	for_each_cpu(i, hctx->cpumask) {
 		if (first)
 			ret += sprintf(ret + page, "%u", i);
@@ -240,8 +238,6 @@ static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
 		first = 0;
 	}
 
-	blk_mq_enable_hotplug();
-
 	ret += sprintf(ret + page, "\n");
 	return ret;
 }
@@ -343,7 +339,7 @@ static void blk_mq_unregister_hctx(struct blk_mq_hw_ctx *hctx)
 	struct blk_mq_ctx *ctx;
 	int i;
 
-	if (!hctx->nr_ctx || !(hctx->flags & BLK_MQ_F_SYSFS_UP))
+	if (!hctx->nr_ctx)
 		return;
 
 	hctx_for_each_ctx(hctx, ctx, i)
@@ -358,7 +354,7 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)
 	struct blk_mq_ctx *ctx;
 	int i, ret;
 
-	if (!hctx->nr_ctx || !(hctx->flags & BLK_MQ_F_SYSFS_UP))
+	if (!hctx->nr_ctx)
 		return 0;
 
 	ret = kobject_add(&hctx->kobj, &q->mq_kobj, "%u", hctx->queue_num);
@@ -381,6 +377,8 @@ void blk_mq_unregister_disk(struct gendisk *disk)
 	struct blk_mq_ctx *ctx;
 	int i, j;
 
+	blk_mq_disable_hotplug();
+
 	queue_for_each_hw_ctx(q, hctx, i) {
 		blk_mq_unregister_hctx(hctx);
 
@@ -395,6 +393,9 @@ void blk_mq_unregister_disk(struct gendisk *disk)
 	kobject_put(&q->mq_kobj);
 
 	kobject_put(&disk_to_dev(disk)->kobj);
+
+	q->mq_sysfs_init_done = false;
+	blk_mq_enable_hotplug();
 }
 
 static void blk_mq_sysfs_init(struct request_queue *q)
@@ -425,27 +426,30 @@ int blk_mq_register_disk(struct gendisk *disk)
 	struct blk_mq_hw_ctx *hctx;
 	int ret, i;
 
+	blk_mq_disable_hotplug();
+
 	blk_mq_sysfs_init(q);
 
 	ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	kobject_uevent(&q->mq_kobj, KOBJ_ADD);
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		hctx->flags |= BLK_MQ_F_SYSFS_UP;
 		ret = blk_mq_register_hctx(hctx);
 		if (ret)
 			break;
 	}
 
-	if (ret) {
+	if (ret)
 		blk_mq_unregister_disk(disk);
-		return ret;
-	}
+	else
+		q->mq_sysfs_init_done = true;
+out:
+	blk_mq_enable_hotplug();
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_mq_register_disk);
 
@@ -454,6 +458,9 @@ void blk_mq_sysfs_unregister(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
+	if (!q->mq_sysfs_init_done)
+		return;
+
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
 }
@@ -463,6 +470,9 @@ int blk_mq_sysfs_register(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i, ret = 0;
 
+	if (!q->mq_sysfs_init_done)
+		return ret;
+
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
 		if (ret)

block/blk-mq-tag.c

@@ -471,17 +471,30 @@ void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
 }
 EXPORT_SYMBOL(blk_mq_all_tag_busy_iter);
 
-void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
+void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv)
 {
-	struct blk_mq_tags *tags = hctx->tags;
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		struct blk_mq_tags *tags = hctx->tags;
+
+		/*
+		 * If not software queues are currently mapped to this
+		 * hardware queue, there's nothing to check
+		 */
+		if (!blk_mq_hw_queue_mapped(hctx))
+			continue;
+
+		if (tags->nr_reserved_tags)
+			bt_for_each(hctx, &tags->breserved_tags, 0, fn, priv, true);
+		bt_for_each(hctx, &tags->bitmap_tags, tags->nr_reserved_tags, fn, priv,
+		      false);
+	}
 
-	if (tags->nr_reserved_tags)
-		bt_for_each(hctx, &tags->breserved_tags, 0, fn, priv, true);
-	bt_for_each(hctx, &tags->bitmap_tags, tags->nr_reserved_tags, fn, priv,
-			false);
 }
-EXPORT_SYMBOL(blk_mq_tag_busy_iter);
 
 static unsigned int bt_unused_tags(struct blk_mq_bitmap_tags *bt)
 {

block/blk-mq-tag.h

@@ -58,6 +58,8 @@ extern ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page);
 extern void blk_mq_tag_init_last_tag(struct blk_mq_tags *tags, unsigned int *last_tag);
 extern int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int depth);
 extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
+void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
+		void *priv);
 
 enum {
 	BLK_MQ_TAG_CACHE_MIN	= 1,