Merge tag 'block-6.14-20250131' of git://git.kernel.dk/linux

Pull more block updates from Jens Axboe:

 - MD pull request via Song:
      - Fix a md-cluster regression introduced

 - More sysfs race fixes

 - Mark anything inside queue freezing as not being able to do IO for
   memory allocations

 - Fix for a regression introduced in loop in this merge window

 - Fix for a regression in queue mapping setups introduced in this merge
   window

 - Fix for the block dio fops attempting an iov_iter revert upton
   getting -EIOCBQUEUED on the read side. This one is going to stable as
   well

* tag 'block-6.14-20250131' of git://git.kernel.dk/linux:
  block: force noio scope in blk_mq_freeze_queue
  block: fix nr_hw_queue update racing with disk addition/removal
  block: get rid of request queue ->sysfs_dir_lock
  loop: don't clear LO_FLAGS_PARTSCAN on LOOP_SET_STATUS{,64}
  md/md-bitmap: Synchronize bitmap_get_stats() with bitmap lifetime
  blk-mq: create correct map for fallback case
  block: don't revert iter for -EIOCBQUEUED

Author: torvalds

block/blk-cgroup.c

@@ -1546,6 +1546,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 	struct request_queue *q = disk->queue;
 	struct blkg_policy_data *pd_prealloc = NULL;
 	struct blkcg_gq *blkg, *pinned_blkg = NULL;
+	unsigned int memflags;
 	int ret;
 
 	if (blkcg_policy_enabled(q, pol))
@@ -1560,7 +1561,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 		return -EINVAL;
 
 	if (queue_is_mq(q))
-		blk_mq_freeze_queue(q);
+		memflags = blk_mq_freeze_queue(q);
 retry:
 	spin_lock_irq(&q->queue_lock);
 
@@ -1624,7 +1625,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 	spin_unlock_irq(&q->queue_lock);
 out:
 	if (queue_is_mq(q))
-		blk_mq_unfreeze_queue(q);
+		blk_mq_unfreeze_queue(q, memflags);
 	if (pinned_blkg)
 		blkg_put(pinned_blkg);
 	if (pd_prealloc)
@@ -1668,12 +1669,13 @@ void blkcg_deactivate_policy(struct gendisk *disk,
 {
 	struct request_queue *q = disk->queue;
 	struct blkcg_gq *blkg;
+	unsigned int memflags;
 
 	if (!blkcg_policy_enabled(q, pol))
 		return;
 
 	if (queue_is_mq(q))
-		blk_mq_freeze_queue(q);
+		memflags = blk_mq_freeze_queue(q);
 
 	mutex_lock(&q->blkcg_mutex);
 	spin_lock_irq(&q->queue_lock);
@@ -1697,7 +1699,7 @@ void blkcg_deactivate_policy(struct gendisk *disk,
 	mutex_unlock(&q->blkcg_mutex);
 
 	if (queue_is_mq(q))
-		blk_mq_unfreeze_queue(q);
+		blk_mq_unfreeze_queue(q, memflags);
 }
 EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);
 

block/blk-core.c

@@ -430,7 +430,6 @@ struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id)
 	refcount_set(&q->refs, 1);
 	mutex_init(&q->debugfs_mutex);
 	mutex_init(&q->sysfs_lock);
-	mutex_init(&q->sysfs_dir_lock);
 	mutex_init(&q->limits_lock);
 	mutex_init(&q->rq_qos_mutex);
 	spin_lock_init(&q->queue_lock);

block/blk-ia-ranges.c

@@ -111,7 +111,6 @@ int disk_register_independent_access_ranges(struct gendisk *disk)
 	struct request_queue *q = disk->queue;
 	int i, ret;
 
-	lockdep_assert_held(&q->sysfs_dir_lock);
 	lockdep_assert_held(&q->sysfs_lock);
 
 	if (!iars)
@@ -155,7 +154,6 @@ void disk_unregister_independent_access_ranges(struct gendisk *disk)
 	struct blk_independent_access_ranges *iars = disk->ia_ranges;
 	int i;
 
-	lockdep_assert_held(&q->sysfs_dir_lock);
 	lockdep_assert_held(&q->sysfs_lock);
 
 	if (!iars)
@@ -289,7 +287,6 @@ void disk_set_independent_access_ranges(struct gendisk *disk,
 {
 	struct request_queue *q = disk->queue;
 
-	mutex_lock(&q->sysfs_dir_lock);
 	mutex_lock(&q->sysfs_lock);
 	if (iars && !disk_check_ia_ranges(disk, iars)) {
 		kfree(iars);
@@ -313,6 +310,5 @@ void disk_set_independent_access_ranges(struct gendisk *disk,
 		disk_register_independent_access_ranges(disk);
 unlock:
 	mutex_unlock(&q->sysfs_lock);
-	mutex_unlock(&q->sysfs_dir_lock);
 }
 EXPORT_SYMBOL_GPL(disk_set_independent_access_ranges);

block/blk-iocost.c

@@ -3224,6 +3224,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 	u32 qos[NR_QOS_PARAMS];
 	bool enable, user;
 	char *body, *p;
+	unsigned int memflags;
 	int ret;
 
 	blkg_conf_init(&ctx, input);
@@ -3247,7 +3248,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 		ioc = q_to_ioc(disk->queue);
 	}
 
-	blk_mq_freeze_queue(disk->queue);
+	memflags = blk_mq_freeze_queue(disk->queue);
 	blk_mq_quiesce_queue(disk->queue);
 
 	spin_lock_irq(&ioc->lock);
@@ -3347,15 +3348,15 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 		wbt_enable_default(disk);
 
 	blk_mq_unquiesce_queue(disk->queue);
-	blk_mq_unfreeze_queue(disk->queue);
+	blk_mq_unfreeze_queue(disk->queue, memflags);
 
 	blkg_conf_exit(&ctx);
 	return nbytes;
 einval:
 	spin_unlock_irq(&ioc->lock);
 
 	blk_mq_unquiesce_queue(disk->queue);
-	blk_mq_unfreeze_queue(disk->queue);
+	blk_mq_unfreeze_queue(disk->queue, memflags);
 
 	ret = -EINVAL;
 err:
@@ -3414,6 +3415,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 {
 	struct blkg_conf_ctx ctx;
 	struct request_queue *q;
+	unsigned int memflags;
 	struct ioc *ioc;
 	u64 u[NR_I_LCOEFS];
 	bool user;
@@ -3441,7 +3443,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 		ioc = q_to_ioc(q);
 	}
 
-	blk_mq_freeze_queue(q);
+	memflags = blk_mq_freeze_queue(q);
 	blk_mq_quiesce_queue(q);
 
 	spin_lock_irq(&ioc->lock);
@@ -3493,7 +3495,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 	spin_unlock_irq(&ioc->lock);
 
 	blk_mq_unquiesce_queue(q);
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 
 	blkg_conf_exit(&ctx);
 	return nbytes;
@@ -3502,7 +3504,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 	spin_unlock_irq(&ioc->lock);
 
 	blk_mq_unquiesce_queue(q);
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 
 	ret = -EINVAL;
 err:

block/blk-iolatency.c

@@ -749,9 +749,11 @@ static void blkiolatency_enable_work_fn(struct work_struct *work)
 	 */
 	enabled = atomic_read(&blkiolat->enable_cnt);
 	if (enabled != blkiolat->enabled) {
-		blk_mq_freeze_queue(blkiolat->rqos.disk->queue);
+		unsigned int memflags;
+
+		memflags = blk_mq_freeze_queue(blkiolat->rqos.disk->queue);
 		blkiolat->enabled = enabled;
-		blk_mq_unfreeze_queue(blkiolat->rqos.disk->queue);
+		blk_mq_unfreeze_queue(blkiolat->rqos.disk->queue, memflags);
 	}
 }
 

block/blk-mq-cpumap.c

@@ -87,7 +87,6 @@ void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap,
 	return;
 
 fallback:
-	WARN_ON_ONCE(qmap->nr_queues > 1);
-	blk_mq_clear_mq_map(qmap);
+	blk_mq_map_queues(qmap);
 }
 EXPORT_SYMBOL_GPL(blk_mq_map_hw_queues);

block/blk-mq-sysfs.c

@@ -223,30 +223,27 @@ int blk_mq_sysfs_register(struct gendisk *disk)
 	unsigned long i, j;
 	int ret;
 
-	lockdep_assert_held(&q->sysfs_dir_lock);
-
 	ret = kobject_add(q->mq_kobj, &disk_to_dev(disk)->kobj, "mq");
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	kobject_uevent(q->mq_kobj, KOBJ_ADD);
 
+	mutex_lock(&q->tag_set->tag_list_lock);
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
 		if (ret)
-			goto unreg;
+			goto out_unreg;
 	}
+	mutex_unlock(&q->tag_set->tag_list_lock);
+	return 0;
 
-	q->mq_sysfs_init_done = true;
-
-out:
-	return ret;
-
-unreg:
+out_unreg:
 	queue_for_each_hw_ctx(q, hctx, j) {
 		if (j < i)
 			blk_mq_unregister_hctx(hctx);
 	}
+	mutex_unlock(&q->tag_set->tag_list_lock);
 
 	kobject_uevent(q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(q->mq_kobj);
@@ -259,31 +256,25 @@ void blk_mq_sysfs_unregister(struct gendisk *disk)
 	struct blk_mq_hw_ctx *hctx;
 	unsigned long i;
 
-	lockdep_assert_held(&q->sysfs_dir_lock);
-
+	mutex_lock(&q->tag_set->tag_list_lock);
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
+	mutex_unlock(&q->tag_set->tag_list_lock);
 
 	kobject_uevent(q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(q->mq_kobj);
-
-	q->mq_sysfs_init_done = false;
 }
 
 void blk_mq_sysfs_unregister_hctxs(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	unsigned long i;
 
-	mutex_lock(&q->sysfs_dir_lock);
-	if (!q->mq_sysfs_init_done)
-		goto unlock;
+	if (!blk_queue_registered(q))
+		return;
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
-
-unlock:
-	mutex_unlock(&q->sysfs_dir_lock);
 }
 
 int blk_mq_sysfs_register_hctxs(struct request_queue *q)
@@ -292,18 +283,15 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q)
 	unsigned long i;
 	int ret = 0;
 
-	mutex_lock(&q->sysfs_dir_lock);
-	if (!q->mq_sysfs_init_done)
-		goto unlock;
+	if (!blk_queue_registered(q))
+		goto out;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
 		if (ret)
 			break;
 	}
 
-unlock:
-	mutex_unlock(&q->sysfs_dir_lock);
-
+out:
 	return ret;
 }

block/blk-mq.c

@@ -210,12 +210,12 @@ int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout);
 
-void blk_mq_freeze_queue(struct request_queue *q)
+void blk_mq_freeze_queue_nomemsave(struct request_queue *q)
 {
 	blk_freeze_queue_start(q);
 	blk_mq_freeze_queue_wait(q);
 }
-EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
+EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_nomemsave);
 
 bool __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic)
 {
@@ -236,12 +236,12 @@ bool __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic)
 	return unfreeze;
 }
 
-void blk_mq_unfreeze_queue(struct request_queue *q)
+void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q)
 {
 	if (__blk_mq_unfreeze_queue(q, false))
 		blk_unfreeze_release_lock(q);
 }
-EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
+EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue_nomemrestore);
 
 /*
  * non_owner variant of blk_freeze_queue_start
@@ -4223,13 +4223,14 @@ static void blk_mq_update_tag_set_shared(struct blk_mq_tag_set *set,
 					 bool shared)
 {
 	struct request_queue *q;
+	unsigned int memflags;
 
 	lockdep_assert_held(&set->tag_list_lock);
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
-		blk_mq_freeze_queue(q);
+		memflags = blk_mq_freeze_queue(q);
 		queue_set_hctx_shared(q, shared);
-		blk_mq_unfreeze_queue(q);
+		blk_mq_unfreeze_queue(q, memflags);
 	}
 }
 
@@ -4992,6 +4993,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	struct request_queue *q;
 	LIST_HEAD(head);
 	int prev_nr_hw_queues = set->nr_hw_queues;
+	unsigned int memflags;
 	int i;
 
 	lockdep_assert_held(&set->tag_list_lock);
@@ -5003,8 +5005,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues)
 		return;
 
+	memflags = memalloc_noio_save();
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
-		blk_mq_freeze_queue(q);
+		blk_mq_freeze_queue_nomemsave(q);
+
 	/*
 	 * Switch IO scheduler to 'none', cleaning up the data associated
 	 * with the previous scheduler. We will switch back once we are done
@@ -5052,7 +5056,8 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		blk_mq_elv_switch_back(&head, q);
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
-		blk_mq_unfreeze_queue(q);
+		blk_mq_unfreeze_queue_nomemrestore(q);
+	memalloc_noio_restore(memflags);
 
 	/* Free the excess tags when nr_hw_queues shrink. */
 	for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++)

block/blk-pm.c

@@ -89,7 +89,7 @@ int blk_pre_runtime_suspend(struct request_queue *q)
 	if (percpu_ref_is_zero(&q->q_usage_counter))
 		ret = 0;
 	/* Switch q_usage_counter back to per-cpu mode. */
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue_nomemrestore(q);
 
 	if (ret < 0) {
 		spin_lock_irq(&q->queue_lock);