Merge tag 'block-6.13-20241213' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - Series from Damien fixing issues with the zoned write plugging

 - Fix for a potential UAF in block cgroups

 - Fix deadlock around queue freezing and the sysfs lock

 - Various little cleanups and fixes

* tag 'block-6.13-20241213' of git://git.kernel.dk/linux:
  block: Fix potential deadlock while freezing queue and acquiring sysfs_lock
  block: Fix queue_iostats_passthrough_show()
  blk-mq: Clean up blk_mq_requeue_work()
  mq-deadline: Remove a local variable
  blk-iocost: Avoid using clamp() on inuse in __propagate_weights()
  block: Make bio_iov_bvec_set() accept pointer to const iov_iter
  block: get wp_offset by bdev_offset_from_zone_start
  blk-cgroup: Fix UAF in blkcg_unpin_online()
  MAINTAINERS: update Coly Li's email address
  block: Prevent potential deadlocks in zone write plug error recovery
  dm: Fix dm-zoned-reclaim zone write pointer alignment
  block: Ignore REQ_NOWAIT for zone reset and zone finish operations
  block: Use a zone write plug BIO work for REQ_NOWAIT BIOs

Author: torvalds

MAINTAINERS

@@ -3893,7 +3893,7 @@ W:	http://www.baycom.org/~tom/ham/ham.html
 F:	drivers/net/hamradio/baycom*
 
 BCACHE (BLOCK LAYER CACHE)
-M:	Coly Li <colyli@suse.de>
+M:	Coly Li <colyli@kernel.org>
 M:	Kent Overstreet <[email protected]>
 L:	[email protected]
 S:	Maintained

block/bio.c

@@ -1171,7 +1171,7 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
 }
 EXPORT_SYMBOL_GPL(__bio_release_pages);
 
-void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
+void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter)
 {
 	WARN_ON_ONCE(bio->bi_max_vecs);
 

block/blk-cgroup.c

@@ -1324,10 +1324,14 @@ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css)
 	struct blkcg *blkcg = css_to_blkcg(blkcg_css);
 
 	do {
+		struct blkcg *parent;
+
 		if (!refcount_dec_and_test(&blkcg->online_pin))
 			break;
+
+		parent = blkcg_parent(blkcg);
 		blkcg_destroy_blkgs(blkcg);
-		blkcg = blkcg_parent(blkcg);
+		blkcg = parent;
 	} while (blkcg);
 }
 

block/blk-iocost.c

@@ -1098,7 +1098,14 @@ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse,
 		inuse = DIV64_U64_ROUND_UP(active * iocg->child_inuse_sum,
 					   iocg->child_active_sum);
 	} else {
-		inuse = clamp_t(u32, inuse, 1, active);
+		/*
+		 * It may be tempting to turn this into a clamp expression with
+		 * a lower limit of 1 but active may be 0, which cannot be used
+		 * as an upper limit in that situation. This expression allows
+		 * active to clamp inuse unless it is 0, in which case inuse
+		 * becomes 1.
+		 */
+		inuse = min(inuse, active) ?: 1;
 	}
 
 	iocg->last_inuse = iocg->inuse;

block/blk-map.c

@@ -574,7 +574,7 @@ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter)
 	bio = blk_rq_map_bio_alloc(rq, 0, GFP_KERNEL);
 	if (!bio)
 		return -ENOMEM;
-	bio_iov_bvec_set(bio, (struct iov_iter *)iter);
+	bio_iov_bvec_set(bio, iter);
 
 	/* check that the data layout matches the hardware restrictions */
 	ret = bio_split_rw_at(bio, lim, &nsegs, max_bytes);

block/blk-mq-sysfs.c

@@ -275,15 +275,13 @@ 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);
+	lockdep_assert_held(&q->sysfs_dir_lock);
+
 	if (!q->mq_sysfs_init_done)
-		goto unlock;
+		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 +290,16 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q)
 	unsigned long i;
 	int ret = 0;
 
-	mutex_lock(&q->sysfs_dir_lock);
+	lockdep_assert_held(&q->sysfs_dir_lock);
+
 	if (!q->mq_sysfs_init_done)
-		goto unlock;
+		return ret;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
 		if (ret)
 			break;
 	}
 
-unlock:
-	mutex_unlock(&q->sysfs_dir_lock);
-
 	return ret;
 }

block/blk-mq.c

@@ -1544,19 +1544,17 @@ static void blk_mq_requeue_work(struct work_struct *work)
 
 	while (!list_empty(&rq_list)) {
 		rq = list_entry(rq_list.next, struct request, queuelist);
+		list_del_init(&rq->queuelist);
 		/*
-		 * If RQF_DONTPREP ist set, the request has been started by the
+		 * If RQF_DONTPREP is set, the request has been started by the
 		 * driver already and might have driver-specific data allocated
 		 * already.  Insert it into the hctx dispatch list to avoid
 		 * block layer merges for the request.
 		 */
-		if (rq->rq_flags & RQF_DONTPREP) {
-			list_del_init(&rq->queuelist);
+		if (rq->rq_flags & RQF_DONTPREP)
 			blk_mq_request_bypass_insert(rq, 0);
-		} else {
-			list_del_init(&rq->queuelist);
+		else
 			blk_mq_insert_request(rq, BLK_MQ_INSERT_AT_HEAD);
-		}
 	}
 
 	while (!list_empty(&flush_list)) {
@@ -4455,7 +4453,8 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	unsigned long i, j;
 
 	/* protect against switching io scheduler  */
-	mutex_lock(&q->sysfs_lock);
+	lockdep_assert_held(&q->sysfs_lock);
+
 	for (i = 0; i < set->nr_hw_queues; i++) {
 		int old_node;
 		int node = blk_mq_get_hctx_node(set, i);
@@ -4488,7 +4487,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 
 	xa_for_each_start(&q->hctx_table, j, hctx, j)
 		blk_mq_exit_hctx(q, set, hctx, j);
-	mutex_unlock(&q->sysfs_lock);
 
 	/* unregister cpuhp callbacks for exited hctxs */
 	blk_mq_remove_hw_queues_cpuhp(q);
@@ -4520,10 +4518,14 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 
 	xa_init(&q->hctx_table);
 
+	mutex_lock(&q->sysfs_lock);
+
 	blk_mq_realloc_hw_ctxs(set, q);
 	if (!q->nr_hw_queues)
 		goto err_hctxs;
 
+	mutex_unlock(&q->sysfs_lock);
+
 	INIT_WORK(&q->timeout_work, blk_mq_timeout_work);
 	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);
 
@@ -4542,6 +4544,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	return 0;
 
 err_hctxs:
+	mutex_unlock(&q->sysfs_lock);
 	blk_mq_release(q);
 err_exit:
 	q->mq_ops = NULL;
@@ -4922,12 +4925,12 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
 		return false;
 
 	/* q->elevator needs protection from ->sysfs_lock */
-	mutex_lock(&q->sysfs_lock);
+	lockdep_assert_held(&q->sysfs_lock);
 
 	/* the check has to be done with holding sysfs_lock */
 	if (!q->elevator) {
 		kfree(qe);
-		goto unlock;
+		goto out;
 	}
 
 	INIT_LIST_HEAD(&qe->node);
@@ -4937,9 +4940,7 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
 	__elevator_get(qe->type);
 	list_add(&qe->node, head);
 	elevator_disable(q);
-unlock:
-	mutex_unlock(&q->sysfs_lock);
-
+out:
 	return true;
 }
 
@@ -4968,11 +4969,9 @@ static void blk_mq_elv_switch_back(struct list_head *head,
 	list_del(&qe->node);
 	kfree(qe);
 
-	mutex_lock(&q->sysfs_lock);
 	elevator_switch(q, t);
 	/* drop the reference acquired in blk_mq_elv_switch_none */
 	elevator_put(t);
-	mutex_unlock(&q->sysfs_lock);
 }
 
 static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
@@ -4992,8 +4991,11 @@ 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;
 
-	list_for_each_entry(q, &set->tag_list, tag_set_list)
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		mutex_lock(&q->sysfs_dir_lock);
+		mutex_lock(&q->sysfs_lock);
 		blk_mq_freeze_queue(q);
+	}
 	/*
 	 * Switch IO scheduler to 'none', cleaning up the data associated
 	 * with the previous scheduler. We will switch back once we are done
@@ -5049,8 +5051,11 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_elv_switch_back(&head, q);
 
-	list_for_each_entry(q, &set->tag_list, tag_set_list)
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_unfreeze_queue(q);
+		mutex_unlock(&q->sysfs_lock);
+		mutex_unlock(&q->sysfs_dir_lock);
+	}
 
 	/* Free the excess tags when nr_hw_queues shrink. */
 	for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++)

block/blk-sysfs.c

@@ -263,7 +263,7 @@ static ssize_t queue_nr_zones_show(struct gendisk *disk, char *page)
 
 static ssize_t queue_iostats_passthrough_show(struct gendisk *disk, char *page)
 {
-	return queue_var_show(blk_queue_passthrough_stat(disk->queue), page);
+	return queue_var_show(!!blk_queue_passthrough_stat(disk->queue), page);
 }
 
 static ssize_t queue_iostats_passthrough_store(struct gendisk *disk,
@@ -706,11 +706,11 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
 	if (entry->load_module)
 		entry->load_module(disk, page, length);
 
-	blk_mq_freeze_queue(q);
 	mutex_lock(&q->sysfs_lock);
+	blk_mq_freeze_queue(q);
 	res = entry->store(disk, page, length);
-	mutex_unlock(&q->sysfs_lock);
 	blk_mq_unfreeze_queue(q);
+	mutex_unlock(&q->sysfs_lock);
 	return res;
 }