block: don't grab elevator lock during queue initialization

->elevator_lock depends on queue freeze lock, see block/blk-sysfs.c.

queue freeze lock depends on fs_reclaim.

So don't grab elevator lock during queue initialization which needs to
call kmalloc(GFP_KERNEL), and we can cut the dependency between
->elevator_lock and fs_reclaim, then the lockdep warning can be killed.

This way is safe because elevator setting isn't ready to run during
queue initialization.

There isn't such issue in __blk_mq_update_nr_hw_queues() because
memalloc_noio_save() is called before acquiring elevator lock.

Fixes the following lockdep warning:

https://lore.kernel.org/linux-block/67e6b425.050a0220.2f068f.007b.GAE@google.com/

Reported-by: syzbot+4c7e0f9b94ad65811efb@syzkaller.appspotmail.com
Cc: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250403105402.1334206-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 0cfd1a149f643944196b926924d0e0cf96f09d8b..c2697db591091200cdb9f6e082e472b829701e4c 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4464,14 +4464,12 @@ static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx(
        return NULL;
 }
 
-static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
-                                               struct request_queue *q)
+static void __blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
+                                    struct request_queue *q)
 {
        struct blk_mq_hw_ctx *hctx;
        unsigned long i, j;
 
-       /* protect against switching io scheduler  */
-       mutex_lock(&q->elevator_lock);
        for (i = 0; i < set->nr_hw_queues; i++) {
                int old_node;
                int node = blk_mq_get_hctx_node(set, i);
@@ -4504,7 +4502,19 @@ 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->elevator_lock);
+}
+
+static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
+                                  struct request_queue *q, bool lock)
+{
+       if (lock) {
+               /* protect against switching io scheduler  */
+               mutex_lock(&q->elevator_lock);
+               __blk_mq_realloc_hw_ctxs(set, q);
+               mutex_unlock(&q->elevator_lock);
+       } else {
+               __blk_mq_realloc_hw_ctxs(set, q);
+       }
 
        /* unregister cpuhp callbacks for exited hctxs */
        blk_mq_remove_hw_queues_cpuhp(q);
@@ -4536,7 +4546,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 
        xa_init(&q->hctx_table);
 
-       blk_mq_realloc_hw_ctxs(set, q);
+       blk_mq_realloc_hw_ctxs(set, q, false);
        if (!q->nr_hw_queues)
                goto err_hctxs;
 
@@ -5032,7 +5042,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 fallback:
        blk_mq_update_queue_map(set);
        list_for_each_entry(q, &set->tag_list, tag_set_list) {
-               blk_mq_realloc_hw_ctxs(set, q);
+               blk_mq_realloc_hw_ctxs(set, q, true);
 
                if (q->nr_hw_queues != set->nr_hw_queues) {
                        int i = prev_nr_hw_queues;