> There is a history of dead lock as reboot is performed at the beginning of
> booting. SDEV_QUIESCE was set for all lu's scsi_devices by ufs shutdown,
> and at that time the audio driver was waiting on blk_mq_submit_bio holding
> a mutex_lock while reading the fw binary. After that, a deadlock issue
> occurred while audio driver shutdown was waiting for mutex_unlock of
> blk_mq_submit_bio. To solve this, set SDEV_OFFLINE for all lus except wlun,
> so that any i/o that comes down after a ufs shutdown will return an error.
>
> [ 31.907781]I[0: swapper/0: 0] 1 130705007 1651079834
> 11289729804 0 D( 2) 3 ffffff882e208000 * init
> [device_shutdown]
> [ 31.907793]I[0: swapper/0: 0] Mutex: 0xffffff8849a2b8b0:
> owner[0xffffff882e28cb00 kworker/6:0 :49]
> [ 31.907806]I[0: swapper/0: 0] Call trace:
> [ 31.907810]I[0: swapper/0: 0] __switch_to+0x174/0x338
> [ 31.907819]I[0: swapper/0: 0] __schedule+0x5ec/0x9cc
> [ 31.907826]I[0: swapper/0: 0] schedule+0x7c/0xe8
> [ 31.907834]I[0: swapper/0: 0] schedule_preempt_disabled+0x24/0x40
> [ 31.907842]I[0: swapper/0: 0] __mutex_lock+0x408/0xdac
> [ 31.907849]I[0: swapper/0: 0] __mutex_lock_slowpath+0x14/0x24
> [ 31.907858]I[0: swapper/0: 0] mutex_lock+0x40/0xec
> [ 31.907866]I[0: swapper/0: 0] device_shutdown+0x108/0x280
> [ 31.907875]I[0: swapper/0: 0] kernel_restart+0x4c/0x11c
> [ 31.907883]I[0: swapper/0: 0] __arm64_sys_reboot+0x15c/0x280
> [ 31.907890]I[0: swapper/0: 0] invoke_syscall+0x70/0x158
> [ 31.907899]I[0: swapper/0: 0] el0_svc_common+0xb4/0xf4
> [ 31.907909]I[0: swapper/0: 0] do_el0_svc+0x2c/0xb0
> [ 31.907918]I[0: swapper/0: 0] el0_svc+0x34/0xe0
> [ 31.907928]I[0: swapper/0: 0] el0t_64_sync_handler+0x68/0xb4
> [ 31.907937]I[0: swapper/0: 0] el0t_64_sync+0x1a0/0x1a4
>
> [ 31.908774]I[0: swapper/0: 0] 49 0 11960702
> 11236868007 0 D( 2) 6 ffffff882e28cb00 * kworker/6:0
> [__bio_queue_enter]
> [ 31.908783]I[0: swapper/0: 0] Call trace:
> [ 31.908788]I[0: swapper/0: 0] __switch_to+0x174/0x338
> [ 31.908796]I[0: swapper/0: 0] __schedule+0x5ec/0x9cc
> [ 31.908803]I[0: swapper/0: 0] schedule+0x7c/0xe8
> [ 31.908811]I[0: swapper/0: 0] __bio_queue_enter+0xb8/0x178
> [ 31.908818]I[0: swapper/0: 0] blk_mq_submit_bio+0x194/0x67c
> [ 31.908827]I[0: swapper/0: 0] __submit_bio+0xb8/0x19c
>
> Fixes: b294ff3e3449 ("scsi: ufs: core: Enable power management for wlun")
> Cc: stable@xxxxxxxxxxxxxxx
> Signed-off-by: Seunghwan Baek <sh8267.baek@xxxxxxxxxxx>
> ---
> drivers/ufs/core/ufshcd.c | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
> index a6f818cdef0e..4ac1492787c2 100644
> --- a/drivers/ufs/core/ufshcd.c
> +++ b/drivers/ufs/core/ufshcd.c
> @@ -10215,7 +10215,9 @@ static void ufshcd_wl_shutdown(struct device *dev)
> shost_for_each_device(sdev, hba->host) {
> if (sdev == hba->ufs_device_wlun)
> continue;
> - scsi_device_quiesce(sdev);
> + mutex_lock(&sdev->state_mutex);
> + scsi_device_set_state(sdev, SDEV_OFFLINE);
> + mutex_unlock(&sdev->state_mutex);
> }
> __ufshcd_wl_suspend(hba, UFS_SHUTDOWN_PM);
>
> --
> 2.17.1
>
Dear all.
Could you please review this patch? It's been almost a month.
If you have any opinions about this patch, share and comment it.
Thanks.
BRs.
