linux-kernel - [PATCH 5.10] block: fix null-deref in percpu_ref

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20220729065243.1786222-1-zhangwensheng@huaweicloud.com>
Date:   Fri, 29 Jul 2022 14:52:43 +0800
From:   Zhang Wensheng <zhangwensheng@...weicloud.com>
To:     stable@...r.kernel.org
Cc:     axboe@...nel.dk, ast@...nel.org, daniel@...earbox.net,
        andrii@...nel.org, kafai@...com, songliubraving@...com, yhs@...com,
        john.fastabend@...il.com, kpsingh@...nel.org,
        linux-block@...r.kernel.org, linux-kernel@...r.kernel.org,
        zhangwensheng5@...wei.com, yukuai3@...wei.com
Subject: [PATCH 5.10] block: fix null-deref in percpu_ref_put

From: Zhang Wensheng <zhangwensheng5@...wei.com>

In the use of q_usage_counter of request_queue, blk_cleanup_queue using
"wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter))"
to wait q_usage_counter becoming zero. however, if the q_usage_counter
becoming zero quickly, and percpu_ref_exit will execute and ref->data
will be freed, maybe another process will cause a null-defef problem
like below:

	CPU0                             CPU1
blk_cleanup_queue
 blk_freeze_queue
  blk_mq_freeze_queue_wait
				scsi_end_request
				 percpu_ref_get
				 ...
				 percpu_ref_put
				  atomic_long_sub_and_test
  percpu_ref_exit
   ref->data -> NULL
   				   ref->data->release(ref) -> null-deref

Fix it by setting flag(QUEUE_FLAG_USAGE_COUNT_SYNC) to add synchronization
mechanism, when ref->data->release is called, the flag will be setted,
and the "wait_event" in blk_mq_freeze_queue_wait must wait flag becoming
true as well, which will limit percpu_ref_exit to execute ahead of time.

Signed-off-by: Zhang Wensheng <zhangwensheng5@...wei.com>
---
 block/blk-core.c       | 4 +++-
 block/blk-mq.c         | 7 +++++++
 include/linux/blk-mq.h | 1 +
 include/linux/blkdev.h | 2 ++
 4 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 26664f2a139e..238d0f3cd279 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -385,7 +385,8 @@ void blk_cleanup_queue(struct request_queue *q)
 	 * prevent that blk_mq_run_hw_queues() accesses the hardware queues
 	 * after draining finished.
 	 */
-	blk_freeze_queue(q);
+	blk_freeze_queue_start(q);
+	blk_mq_freeze_queue_wait_sync(q);
 
 	rq_qos_exit(q);
 
@@ -500,6 +501,7 @@ static void blk_queue_usage_counter_release(struct percpu_ref *ref)
 	struct request_queue *q =
 		container_of(ref, struct request_queue, q_usage_counter);
 
+	blk_queue_flag_set(QUEUE_FLAG_USAGE_COUNT_SYNC, q);
 	wake_up_all(&q->mq_freeze_wq);
 }
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index c5d82b21a1cc..15c4e4530c87 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -134,6 +134,7 @@ void blk_freeze_queue_start(struct request_queue *q)
 {
 	mutex_lock(&q->mq_freeze_lock);
 	if (++q->mq_freeze_depth == 1) {
+		blk_queue_flag_clear(QUEUE_FLAG_USAGE_COUNT_SYNC, q);
 		percpu_ref_kill(&q->q_usage_counter);
 		mutex_unlock(&q->mq_freeze_lock);
 		if (queue_is_mq(q))
@@ -144,6 +145,12 @@ void blk_freeze_queue_start(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_freeze_queue_start);
 
+void blk_mq_freeze_queue_wait_sync(struct request_queue *q)
+{
+	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter) &&
+			test_bit(QUEUE_FLAG_USAGE_COUNT_SYNC, &q->queue_flags));
+}
+
 void blk_mq_freeze_queue_wait(struct request_queue *q)
 {
 	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index f8ea27423d1d..95b2c904375f 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -522,6 +522,7 @@ void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_unfreeze_queue(struct request_queue *q);
 void blk_freeze_queue_start(struct request_queue *q);
 void blk_mq_freeze_queue_wait(struct request_queue *q);
+void blk_mq_freeze_queue_wait_sync(struct request_queue *q);
 int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
 				     unsigned long timeout);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 98fdf5a31fd6..b61461e3a734 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -629,6 +629,8 @@ struct request_queue {
 #define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
 #define QUEUE_FLAG_HCTX_ACTIVE	28	/* at least one blk-mq hctx is active */
 #define QUEUE_FLAG_NOWAIT       29	/* device supports NOWAIT */
+/* sync for q_usage_counter */
+#define QUEUE_FLAG_USAGE_COUNT_SYNC    30
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP) |		\
-- 
2.31.1