blk-mq: use quiesced elevator switch when reinitializing queues

mainline inclusion
from mainline-v6.1-rc1
commit 8237c01f
category: bugfix
bugzilla: https://gitee.com/openeuler/kernel/issues/I6GI6F
CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit?id=8237c01f1696bc53c470493bf1fe092a107648a6

--------------------------------

The hctx's run_work may be racing with the elevator switch when
reinitializing hardware queues. The queue is merely frozen in this
context, but that only prevents requests from allocating and doesn't
stop the hctx work from running. The work may get an elevator pointer
that's being torn down, and can result in use-after-free errors and
kernel panics (example below). Use the quiesced elevator switch instead,
and make the previous one static since it is now only used locally.

  nvme nvme0: resetting controller
  nvme nvme0: 32/0/0 default/read/poll queues
  BUG: kernel NULL pointer dereference, address: 0000000000000008
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 80000020c8861067 P4D 80000020c8861067 PUD 250f8c8067 PMD 0
  Oops: 0000 [#1] SMP PTI
  Workqueue: kblockd blk_mq_run_work_fn
  RIP: 0010:kyber_has_work+0x29/0x70

...

  Call Trace:
   __blk_mq_do_dispatch_sched+0x83/0x2b0
   __blk_mq_sched_dispatch_requests+0x12e/0x170
   blk_mq_sched_dispatch_requests+0x30/0x60
   __blk_mq_run_hw_queue+0x2b/0x50
   process_one_work+0x1ef/0x380
   worker_thread+0x2d/0x3e0
Signed-off-by: NKeith Busch <kbusch@kernel.org>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220927155652.3260724-1-kbusch@fb.comSigned-off-by: NJens Axboe <axboe@kernel.dk>

Conflicts:
	block/blk-mq.c
	block/blk.h
Signed-off-by: NYu Kuai <yukuai3@huawei.com>
Reviewed-by: NHou Tao <houtao1@huawei.com>
Signed-off-by: NJialin Zhang <zhangjialin11@huawei.com>

block/blk-mq.c

@@ -3873,14 +3873,14 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
 
 	mutex_lock(&q->sysfs_lock);
 	/*
-	 * After elevator_switch_mq, the previous elevator_queue will be
+	 * After elevator_switch, the previous elevator_queue will be
 	 * released by elevator_release. The reference of the io scheduler
 	 * module get by elevator_get will also be put. So we need to get
 	 * a reference of the io scheduler module here to prevent it to be
 	 * removed.
 	 */
 	__module_get(qe->type->elevator_owner);
-	elevator_switch_mq(q, NULL);
+	elevator_switch(q, NULL);
 	mutex_unlock(&q->sysfs_lock);
 
 	return true;
@@ -3905,7 +3905,7 @@ static void blk_mq_elv_switch_back(struct list_head *head,
 	kfree(qe);
 
 	mutex_lock(&q->sysfs_lock);
-	elevator_switch_mq(q, t);
+	elevator_switch(q, t);
 	mutex_unlock(&q->sysfs_lock);
 }
 

block/blk.h

@@ -201,8 +201,7 @@ void blk_account_io_done(struct request *req, u64 now);
 void blk_insert_flush(struct request *rq);
 
 void elevator_init_mq(struct request_queue *q);
-int elevator_switch_mq(struct request_queue *q,
-			      struct elevator_type *new_e);
+int elevator_switch(struct request_queue *q, struct elevator_type *new_e);
 void __elevator_exit(struct request_queue *, struct elevator_queue *);
 int elv_register_queue(struct request_queue *q, bool uevent);
 void elv_unregister_queue(struct request_queue *q);

block/elevator.c

@@ -577,7 +577,7 @@ void elv_unregister(struct elevator_type *e)
 }
 EXPORT_SYMBOL_GPL(elv_unregister);
 
-int elevator_switch_mq(struct request_queue *q,
+static int elevator_switch_mq(struct request_queue *q,
 			      struct elevator_type *new_e)
 {
 	int ret;
@@ -716,7 +716,7 @@ void elevator_init_mq(struct request_queue *q)
  * need for the new one. this way we have a chance of going back to the old
  * one, if the new one fails init for some reason.
  */
-static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
+int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 {
 	int err;