block: correct locking order for protecting blk-wbt parameters

The commit '245618f8e45f ("block: protect wbt_lat_usec using q->
elevator_lock")' introduced q->elevator_lock to protect updates
to blk-wbt parameters when writing to the sysfs attribute wbt_
lat_usec and the cgroup attribute io.cost.qos. However, both
these attributes also acquire q->rq_qos_mutex, leading to the
following lockdep warning:

======================================================
WARNING: possible circular locking dependency detected
6.14.0-rc5+ #138 Not tainted
------------------------------------------------------
bash/5902 is trying to acquire lock:
c000000085d495a0 (&q->rq_qos_mutex){+.+.}-{4:4}, at: wbt_init+0x164/0x238

but task is already holding lock:
c000000085d498c8 (&q->elevator_lock){+.+.}-{4:4}, at: queue_wb_lat_store+0xb0/0x20c

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (&q->elevator_lock){+.+.}-{4:4}:
__mutex_lock+0xf0/0xa58
ioc_qos_write+0x16c/0x85c
cgroup_file_write+0xc4/0x32c
kernfs_fop_write_iter+0x1b8/0x29c
vfs_write+0x410/0x584
ksys_write+0x84/0x140
system_call_exception+0x134/0x360
system_call_vectored_common+0x15c/0x2ec

-> #0 (&q->rq_qos_mutex){+.+.}-{4:4}:
__lock_acquire+0x1b6c/0x2ae0
lock_acquire+0x140/0x430
__mutex_lock+0xf0/0xa58
wbt_init+0x164/0x238
queue_wb_lat_store+0x1dc/0x20c
queue_attr_store+0x12c/0x164
sysfs_kf_write+0x6c/0xb0
kernfs_fop_write_iter+0x1b8/0x29c
vfs_write+0x410/0x584
ksys_write+0x84/0x140
system_call_exception+0x134/0x360
system_call_vectored_common+0x15c/0x2ec

other info that might help us debug this:

Possible unsafe locking scenario:

CPU0 CPU1
---- ----
lock(&q->elevator_lock);
lock(&q->rq_qos_mutex);
lock(&q->elevator_lock);
lock(&q->rq_qos_mutex);

*** DEADLOCK ***

6 locks held by bash/5902:
#0: c000000051122400 (sb_writers#3){.+.+}-{0:0}, at: ksys_write+0x84/0x140
#1: c00000007383f088 (&of->mutex#2){+.+.}-{4:4}, at: kernfs_fop_write_iter+0x174/0x29c
#2: c000000008550428 (kn->active#182){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x180/0x29c
#3: c000000085d493a8 (&q->q_usage_counter(io)#5){++++}-{0:0}, at: blk_mq_freeze_queue_nomemsave+0x28/0x40
#4: c000000085d493e0 (&q->q_usage_counter(queue)#5){++++}-{0:0}, at: blk_mq_freeze_queue_nomemsave+0x28/0x40
#5: c000000085d498c8 (&q->elevator_lock){+.+.}-{4:4}, at: queue_wb_lat_store+0xb0/0x20c

stack backtrace:
CPU: 17 UID: 0 PID: 5902 Comm: bash Kdump: loaded Not tainted 6.14.0-rc5+ #138
Hardware name: IBM,9043-MRX POWER10 (architected) 0x800200 0xf000006 of:IBM,FW1060.00 (NM1060_028) hv:phyp pSeries
Call Trace:
[c0000000721ef590] [c00000000118f8a8] dump_stack_lvl+0x108/0x18c (unreliable)
[c0000000721ef5c0] [c00000000022563c] print_circular_bug+0x448/0x604
[c0000000721ef670] [c000000000225a44] check_noncircular+0x24c/0x26c
[c0000000721ef740] [c00000000022bf28] __lock_acquire+0x1b6c/0x2ae0
[c0000000721ef870] [c000000000229240] lock_acquire+0x140/0x430
[c0000000721ef970] [c0000000011cfbec] __mutex_lock+0xf0/0xa58
[c0000000721efaa0] [c00000000096c46c] wbt_init+0x164/0x238
[c0000000721efaf0] [c0000000008f8cd8] queue_wb_lat_store+0x1dc/0x20c
[c0000000721efb50] [c0000000008f8fa0] queue_attr_store+0x12c/0x164
[c0000000721efc60] [c0000000007c11cc] sysfs_kf_write+0x6c/0xb0
[c0000000721efca0] [c0000000007bfa4c] kernfs_fop_write_iter+0x1b8/0x29c
[c0000000721efcf0] [c0000000006a281c] vfs_write+0x410/0x584
[c0000000721efdc0] [c0000000006a2cc8] ksys_write+0x84/0x140
[c0000000721efe10] [c000000000031b64] system_call_exception+0x134/0x360
[c0000000721efe50] [c00000000000cedc] system_call_vectored_common+0x15c/0x2ec

>From the above log it's apparent that method which writes to sysfs attr
wbt_lat_usec acquires q->elevator_lock first, and then acquires q->rq_
qos_mutex. However the another method which writes to io.cost.qos,
acquires q->rq_qos_mutex first, and then acquires q->rq_qos_mutex. So
this could potentially cause the deadlock.

A closer look at ioc_qos_write shows that correcting the lock order is
non-trivial because q->rq_qos_mutex is acquired in blkg_conf_open_bdev
and released in blkg_conf_exit. The function blkg_conf_open_bdev is
responsible for parsing user input and finding the corresponding block
device (bdev) from the user provided major:minor number.

Since we do not know the bdev until blkg_conf_open_bdev completes, we
cannot simply move q->elevator_lock acquisition before blkg_conf_open_
bdev. So to address this, we intoduce new helpers blkg_conf_open_bdev_
frozen and blkg_conf_exit_frozen which are just wrappers around blkg_
conf_open_bdev and blkg_conf_exit respectively. The helper blkg_conf_
open_bdev_frozen is similar to blkg_conf_open_bdev, but additionally
freezes the queue, acquires q->elevator_lock and ensures the correct
locking order is followed between q->elevator_lock and q->rq_qos_mutex.
Similarly another helper blkg_conf_exit_frozen in addition to unfreezing
the queue ensures that we release the locks in correct order.

By using these helpers, now we maintain the same locking order in all
code paths where we update blk-wbt parameters.

Fixes: 245618f8e45f ("block: protect wbt_lat_usec using q->elevator_lock")
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202503171650.cc082b66-lkp@intel.com
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Link: https://lore.kernel.org/r/20250319105518.468941-3-nilay@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>