blk-mq: release mq's kobjects in blk_release_queue()

The kobject memory inside blk-mq hctx/ctx shouldn't have been freed
before the kobject is released because driver core can access it freely
before its release.

We can't do that in all ctx/hctx/mq_kobj's release handler because
it can be run before blk_cleanup_queue().

Given mq_kobj shouldn't have been introduced, this patch simply moves
mq's release into blk_release_queue().

Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

3 files changed, 26 insertions, 7 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 2f95747c287e..2390c5541e71 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1641,10 +1641,8 @@ static void blk_mq_free_hw_queues(struct request_queue *q,
         struct blk_mq_hw_ctx *hctx;
         unsigned int i;
 
-        queue_for_each_hw_ctx(q, hctx, i) {
+        queue_for_each_hw_ctx(q, hctx, i)
                 free_cpumask_var(hctx->cpumask);
-                kfree(hctx);
-        }
 }
 
 static int blk_mq_init_hctx(struct request_queue *q,
@@ -1869,6 +1867,27 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
         mutex_unlock(&set->tag_list_lock);
 }
 
+/*
+ * It is the actual release handler for mq, but we do it from
+ * request queue's release handler for avoiding use-after-free
+ * and headache because q->mq_kobj shouldn't have been introduced,
+ * but we can't group ctx/kctx kobj without it.
+ */
+void blk_mq_release(struct request_queue *q)
+{
+        struct blk_mq_hw_ctx *hctx;
+        unsigned int i;
+
+        /* hctx kobj stays in hctx */
+        queue_for_each_hw_ctx(q, hctx, i)
+                kfree(hctx);
+
+        kfree(q->queue_hw_ctx);
+
+        /* ctx kobj stays in queue_ctx */
+        free_percpu(q->queue_ctx);
+}
+
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 {
         struct blk_mq_hw_ctx **hctxs;
@@ -2002,12 +2021,8 @@ void blk_mq_free_queue(struct request_queue *q)
 
         percpu_ref_exit(&q->mq_usage_counter);
 
-        free_percpu(q->queue_ctx);
-        kfree(q->queue_hw_ctx);
         kfree(q->mq_map);
 
-        q->queue_ctx = NULL;
-        q->queue_hw_ctx = NULL;
         q->mq_map = NULL;
 
         mutex_lock(&all_q_mutex);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 4f4f943c22c3..6a48c4c0d8a2 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -62,6 +62,8 @@ extern void blk_mq_sysfs_unregister(struct request_queue *q);
 
 extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
 
+void blk_mq_release(struct request_queue *q);
+
 /*
  * Basic implementation of sparser bitmap, allowing the user to spread
  * the bits over more cachelines.
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 935ea2aa0730..faaf36ade7eb 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -517,6 +517,8 @@ static void blk_release_queue(struct kobject *kobj)
 
         if (!q->mq_ops)
                 blk_free_flush_queue(q->fq);
+        else
+                blk_mq_release(q);
 
         blk_trace_shutdown(q);