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.le...@oracle.com>
Signed-off-by: Ming Lei <ming....@canonical.com>
---
block/blk-mq.c | 29 ++++++++++++++++++++++-------
block/blk-mq.h | 2 ++
block/blk-sysfs.c | 2 ++
3 files changed, 26 insertions(+), 7 deletions(-)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a880b6c..9b250da 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1644,10 +1644,8 @@ 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,
@@ -1872,6 +1870,27 @@ 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;
@@ -2005,12 +2024,8 @@ 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 4f4f943..6a48c4c 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 935ea2a..faaf36a 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);
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
