mirrors/linux
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-12-27 13:30:45 -05:00
Code Issues Packages Projects Releases Wiki Activity

scsi: ufs: core: Fix EH failure after W-LUN resume error

Browse Source 
When a W-LUN resume fails, its parent devices in the SCSI hierarchy,
including the scsi_target, may be runtime suspended. Subsequently, the
error handler in ufshcd_recover_pm_error() fails to set the W-LUN device
back to active because the parent target is not active.  This results in
the following errors:

  google-ufshcd 3c2d0000.ufs: ufshcd_err_handler started; HBA state eh_fatal; ...
  ufs_device_wlun 0:0:0:49488: START_STOP failed for power mode: 1, result 40000
  ufs_device_wlun 0:0:0:49488: ufshcd_wl_runtime_resume failed: -5
  ...
  ufs_device_wlun 0:0:0:49488: runtime PM trying to activate child device 0:0:0:49488 but parent (target0:0:0) is not active

Address this by:

 1. Ensuring the W-LUN's parent scsi_target is runtime resumed before
    attempting to set the W-LUN to active within
    ufshcd_recover_pm_error().

 2. Explicitly checking for power.runtime_error on the HBA and W-LUN
    devices before calling pm_runtime_set_active() to clear the error
    state.

 3. Adding pm_runtime_get_sync(hba->dev) in
    ufshcd_err_handling_prepare() to ensure the HBA itself is active
    during error recovery, even if a child device resume failed.

These changes ensure the device power states are managed correctly
during error recovery.

Signed-off-by: Brian Kao <powenkao@google.com>
Tested-by: Brian Kao <powenkao@google.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20251112063214.1195761-1-powenkao@google.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This commit is contained in:
Brian Kao
2025-11-12 06:32:02 +00:00
committed by Martin K. Petersen
parent 82f78acd5a
commit b4bb6daf4a
1 changed files with 30 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
drivers/ufs/core/ufshcd.c
View File

@@ -6504,6 +6504,11 @@ static void ufshcd_clk_scaling_suspend(struct ufs_hba *hba, bool suspend)
static void ufshcd_err_handling_prepare(struct ufs_hba *hba)
{
/*
* A WLUN resume failure could potentially lead to the HBA being
* runtime suspended, so take an extra reference on hba->dev.
*/
pm_runtime_get_sync(hba->dev);
ufshcd_rpm_get_sync(hba);
if (pm_runtime_status_suspended(&hba->ufs_device_wlun->sdev_gendev) ||
hba->is_sys_suspended) {
@@ -6543,6 +6548,7 @@ static void ufshcd_err_handling_unprepare(struct ufs_hba *hba)
if (ufshcd_is_clkscaling_supported(hba))
ufshcd_clk_scaling_suspend(hba, false);
ufshcd_rpm_put(hba);
pm_runtime_put(hba->dev);
}
static inline bool ufshcd_err_handling_should_stop(struct ufs_hba *hba)
@@ -6557,28 +6563,42 @@ static inline bool ufshcd_err_handling_should_stop(struct ufs_hba *hba)
#ifdef CONFIG_PM
static void ufshcd_recover_pm_error(struct ufs_hba *hba)
{
struct scsi_target *starget = hba->ufs_device_wlun->sdev_target;
struct Scsi_Host *shost = hba->host;
struct scsi_device *sdev;
struct request_queue *q;
int ret;
bool resume_sdev_queues = false;
hba->is_sys_suspended = false;
/*
* Set RPM status of wlun device to RPM_ACTIVE,
* this also clears its runtime error.
*/
ret = pm_runtime_set_active(&hba->ufs_device_wlun->sdev_gendev);
/* hba device might have a runtime error otherwise */
if (ret)
ret = pm_runtime_set_active(hba->dev);
/*
* Ensure the parent's error status is cleared before proceeding
* to the child, as the parent must be active to activate the child.
*/
if (hba->dev->power.runtime_error) {
/* hba->dev has no functional parent thus simplily set RPM_ACTIVE */
pm_runtime_set_active(hba->dev);
resume_sdev_queues = true;
}
if (hba->ufs_device_wlun->sdev_gendev.power.runtime_error) {
/*
* starget, parent of wlun, might be suspended if wlun resume failed.
* Make sure parent is resumed before set child (wlun) active.
*/
pm_runtime_get_sync(&starget->dev);
pm_runtime_set_active(&hba->ufs_device_wlun->sdev_gendev);
pm_runtime_put_sync(&starget->dev);
resume_sdev_queues = true;
}
/*
* If wlun device had runtime error, we also need to resume those
* consumer scsi devices in case any of them has failed to be
* resumed due to supplier runtime resume failure. This is to unblock
* blk_queue_enter in case there are bios waiting inside it.
*/
if (!ret) {
if (resume_sdev_queues) {
shost_for_each_device(sdev, shost) {
q = sdev->request_queue;
if (q->dev && (q->rpm_status == RPM_SUSPENDED ||