scsi: ufs: fix livelock on ufshcd_clear_ua_wlun
PATCH 1/1 scsi: ufs: fix livelock on ufshcd_clear_ua_wlun
From: Jaegeuk Kim <[email protected]>
This fixes the below livelock which is caused by calling a scsi command before ufshcd_scsi_unblock_requests() in ufshcd_ungate_work().
Workqueue: ufs_clk_gating_0 ufshcd_ungate_work Call trace: __switch_to+0x298/0x2bc __schedule+0x59c/0x760 schedule+0xac/0xf0 schedule_timeout+0x44/0x1b4 io_schedule_timeout+0x44/0x68 wait_for_common_io+0x7c/0x100 wait_for_completion_io+0x14/0x20 blk_execute_rq+0x94/0xd0 __scsi_execute+0x100/0x1c0 ufshcd_clear_ua_wlun+0x124/0x1c8 ufshcd_host_reset_and_restore+0x1d0/0x2cc ufshcd_link_recovery+0xac/0x134 ufshcd_uic_hibern8_exit+0x1e8/0x1f0 ufshcd_ungate_work+0xac/0x130 process_one_work+0x270/0x47c worker_thread+0x27c/0x4d8 kthread+0x13c/0x320 ret_from_fork+0x10/0x18
--- drivers/scsi/ufs/ufshcd.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/scsi/ufs/ufshcd.c +5 -1
@@ -1603,6 +1603,7 @@ static void ufshcd_ungate_work(struct work_struct *work) } unblock_reqs:ufshcd_scsi_unblock_requests (hba); +ufshcd_clear_ua_wluns (hba); }/**
@@ -6913,7 +6914,7 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba)/* Establish the link again and restore the device */ err =ufshcd_probe_hba (hba, false); -if (!err) +if (!err && !hba->clk_gating.is_suspended)ufshcd_clear_ua_wluns (hba); out:if (err)
@@ -8745,6 +8746,7 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)ufshcd_resume_clkscaling (hba); hba->clk_gating.is_suspended = false; hba->dev_info.b_rpm_dev_flush_capable = false; +ufshcd_clear_ua_wluns (hba);ufshcd_release (hba); out:if (hba->dev_info.b_rpm_dev_flush_capable) {
@@ -8855,6 +8857,8 @@ static int ufshcd_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)cancel_delayed_work (&hba->rpm_dev_flush_recheck_work); } +ufshcd_clear_ua_wluns (hba); +/* Schedule clock gating in case of no access to UFS device yet */ ufshcd_release (hba);
Signature · 1 line
2.29.2.729.g45daf8777d-goog
Hi Jaegeuk,
Quoted 5 lines · Jaegeuk Kim
From: Jaegeuk Kim <[email protected]>
This fixes the below livelock which is caused by calling a scsi command before
ufshcd_scsi_unblock_requests()inufshcd_ungate_work().
Quoted 16 lines
Workqueue: ufs_clk_gating_0 ufshcd_ungate_work Call trace: __switch_to+0x298/0x2bc __schedule+0x59c/0x760 schedule+0xac/0xf0 schedule_timeout+0x44/0x1b4 io_schedule_timeout+0x44/0x68 wait_for_common_io+0x7c/0x100 wait_for_completion_io+0x14/0x20 blk_execute_rq+0x94/0xd0 __scsi_execute+0x100/0x1c0 ufshcd_clear_ua_wlun+0x124/0x1c8 ufshcd_host_reset_and_restore+0x1d0/0x2cc ufshcd_link_recovery+0xac/0x134 ufshcd_uic_hibern8_exit+0x1e8/0x1f0 ufshcd_ungate_work+0xac/0x130
According to the latest mainstream kernel, once ufshcd_uic_hibern8_exit() encounters error, instead, error handler work will be scheduled without blocking ufshcd_uic_hibern8_exit(). In addition, ufshcd_scsi_unblock_requests() would be invoked before leaving ufshcd_uic_hibern8_exit(). So this stack is no longer existed.
Thanks,
Stanley Chu
Quoted 49 lines
process_one_work+0x270/0x47c worker_thread+0x27c/0x4d8 kthread+0x13c/0x320 ret_from_fork+0x10/0x18Fixes 1918651f2d7e ("scsi: ufs: Clear UAC for RPMB after ufshcd resets")Signed-off-by Jaegeuk Kim <[email protected]>--- drivers/scsi/ufs/ufshcd.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)drivers/scsi/ufs/ufshcd.c +5
-1@@ -1603,6 +1603,7 @@ static void ufshcd_ungate_work(struct work_struct *work) } unblock_reqs:ufshcd_scsi_unblock_requests (hba); +ufshcd_clear_ua_wluns (hba); }/** @@ -6913,7 +6914,7 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba)/* Establish the link again and restore the device */ err =ufshcd_probe_hba (hba, false); -if (!err) +if (!err && !hba->clk_gating.is_suspended)ufshcd_clear_ua_wluns (hba); out:if (err)@@ -8745,6 +8746,7 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)ufshcd_resume_clkscaling (hba); hba->clk_gating.is_suspended = false; hba->dev_info.b_rpm_dev_flush_capable = false; +ufshcd_clear_ua_wluns (hba);ufshcd_release (hba); out:if (hba->dev_info.b_rpm_dev_flush_capable) {@@ -8855,6 +8857,8 @@ static int ufshcd_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)cancel_delayed_work (&hba->rpm_dev_flush_recheck_work); } +ufshcd_clear_ua_wluns (hba); +/* Schedule clock gating in case of no access to UFS device yet */ ufshcd_release (hba);
Quoted 25 lines · Stanley Chu
Hi Jaegeuk,
Quoted 5 lines · Jaegeuk Kim
From: Jaegeuk Kim <[email protected]>
This fixes the below livelock which is caused by calling a scsi command before
ufshcd_scsi_unblock_requests()inufshcd_ungate_work().Quoted 16 lines
Workqueue: ufs_clk_gating_0 ufshcd_ungate_work Call trace: __switch_to+0x298/0x2bc __schedule+0x59c/0x760 schedule+0xac/0xf0 schedule_timeout+0x44/0x1b4 io_schedule_timeout+0x44/0x68 wait_for_common_io+0x7c/0x100 wait_for_completion_io+0x14/0x20 blk_execute_rq+0x94/0xd0 __scsi_execute+0x100/0x1c0 ufshcd_clear_ua_wlun+0x124/0x1c8 ufshcd_host_reset_and_restore+0x1d0/0x2cc ufshcd_link_recovery+0xac/0x134 ufshcd_uic_hibern8_exit+0x1e8/0x1f0 ufshcd_ungate_work+0xac/0x130
Quoted 5 lines
According to the latest mainstream kernel, once
ufshcd_uic_hibern8_exit()encounters error, instead, error handler work will be scheduled without blockingufshcd_uic_hibern8_exit(). In addition,ufshcd_scsi_unblock_requests()would be invoked before leavingufshcd_uic_hibern8_exit(). So this stack is no longer existed.
Oh, thank you for pointing this out. It seems the below patch made it. 4db7a2360597 ("scsi: ufs: Fix concurrency of error handler and other error recovery paths")
Next time, I need to check upstream more carefully. :P
Quoted 54 lines
Thanks,
Stanley ChuQuoted 49 lines
process_one_work+0x270/0x47c worker_thread+0x27c/0x4d8 kthread+0x13c/0x320 ret_from_fork+0x10/0x18Fixes 1918651f2d7e ("scsi: ufs: Clear UAC for RPMB after ufshcd resets")Signed-off-by Jaegeuk Kim <[email protected]>--- drivers/scsi/ufs/ufshcd.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)drivers/scsi/ufs/ufshcd.c +5
-1@@ -1603,6 +1603,7 @@ static void ufshcd_ungate_work(struct work_struct *work) } unblock_reqs:ufshcd_scsi_unblock_requests (hba); +ufshcd_clear_ua_wluns (hba); }/** @@ -6913,7 +6914,7 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba)/* Establish the link again and restore the device */ err =ufshcd_probe_hba (hba, false); -if (!err) +if (!err && !hba->clk_gating.is_suspended)ufshcd_clear_ua_wluns (hba); out:if (err)@@ -8745,6 +8746,7 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)ufshcd_resume_clkscaling (hba); hba->clk_gating.is_suspended = false; hba->dev_info.b_rpm_dev_flush_capable = false; +ufshcd_clear_ua_wluns (hba);ufshcd_release (hba); out:if (hba->dev_info.b_rpm_dev_flush_capable) {@@ -8855,6 +8857,8 @@ static int ufshcd_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)cancel_delayed_work (&hba->rpm_dev_flush_recheck_work); } +ufshcd_clear_ua_wluns (hba); +/* Schedule clock gating in case of no access to UFS device yet */ ufshcd_release (hba);