Re: [PATCH v3] scsi: ufs: core: handle PM SSU timeout before SCSI EH

[Bart Van Assche]

On 5/31/26 9:56 PM, Hongjie Fang wrote:
> @@ -9466,7 +9499,7 @@ static enum scsi_timeout_action ufshcd_eh_timed_out(struct scsi_cmnd *scmd)
>   {
>   	struct ufs_hba *hba = shost_priv(scmd->device->host);
>   
> -	if (!hba->system_suspending) {
> +	if (!hba->pm_op_in_progress || !ufshcd_is_scsi_cmd(scmd)) {
>   		/* Activate the error handler in the SCSI core. */
>   		return SCSI_EH_NOT_HANDLED;
>   	}

I think we want to avoid SCSI error handler activation for all commands
that time out while a power management operation is in progress,
including device management commands.

Please consider completing commands from inside the timeout handler
instead of adding force_compl support for the legacy single doorbell
mode. The very lightly tested patch below should realize this.

Thanks,

Bart.


diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 9e0336098e26..63788b187eea 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -9491,22 +9491,23 @@ static enum scsi_timeout_action 
ufshcd_eh_timed_out(struct scsi_cmnd *scmd)
 {
 	struct ufs_hba *hba = shost_priv(scmd->device->host);

-	if (!hba->system_suspending) {
+	if (!hba->pm_op_in_progress) {
 		/* Activate the error handler in the SCSI core. */
 		return SCSI_EH_NOT_HANDLED;
 	}

 	/*
-	 * If we get here we know that no TMFs are outstanding and also that
-	 * the only pending command is a START STOP UNIT command. Handle the
-	 * timeout of that command directly to prevent a deadlock between
+	 * Handle the timeout directly to prevent a deadlock between
 	 * ufshcd_set_dev_pwr_mode() and ufshcd_err_handler().
 	 */
 	ufshcd_link_recovery(hba);
 	dev_info(hba->dev, "%s() finished; outstanding_tasks = %#lx.\n",
 		 __func__, hba->outstanding_tasks);

-	return scsi_host_busy(hba->host) ? SCSI_EH_RESET_TIMER : SCSI_EH_DONE;
+	set_host_byte(scmd, DID_TIME_OUT);
+	ufshcd_release_scsi_cmd(hba, scmd);
+	scsi_done(scmd);
+	return SCSI_EH_DONE;
 }

 static const struct attribute_group *ufshcd_driver_groups[] = {
@@ -10543,7 +10544,6 @@ static int ufshcd_wl_suspend(struct device *dev)

 	hba = shost_priv(sdev->host);
 	down(&hba->host_sem);
-	hba->system_suspending = true;

 	if (pm_runtime_suspended(dev))
 		goto out;
@@ -10585,7 +10585,6 @@ static int ufshcd_wl_resume(struct device *dev)
 		hba->curr_dev_pwr_mode, hba->uic_link_state);
 	if (!ret)
 		hba->is_sys_suspended = false;
-	hba->system_suspending = false;
 	up(&hba->host_sem);
 	return ret;
 }
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index 3eaae082329c..248d0a5bef40 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -1029,8 +1029,6 @@ enum ufshcd_mcq_opr {
  * @caps: bitmask with information about UFS controller capabilities
  * @devfreq: frequency scaling information owned by the devfreq core
  * @clk_scaling: frequency scaling information owned by the UFS driver
- * @system_suspending: system suspend has been started and system 
resume has
- *	not yet finished.
  * @is_sys_suspended: UFS device has been suspended because of system 
suspend
  * @urgent_bkops_lvl: keeps track of urgent bkops level for device
  * @is_urgent_bkops_lvl_checked: keeps track if the urgent bkops level for
@@ -1206,7 +1204,6 @@ struct ufs_hba {

 	struct devfreq *devfreq;
 	struct ufs_clk_scaling clk_scaling;
-	bool system_suspending;
 	bool is_sys_suspended;

 	enum bkops_status urgent_bkops_lvl;