1 files changed, 45 insertions, 23 deletions

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 040a0ceb170a..80c0b49f30b0 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -1455,15 +1455,14 @@ out:
 static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, int err)
 {
 	up_write(&hba->clk_scaling_lock);
+	mutex_unlock(&hba->wb_mutex);
+	blk_mq_unquiesce_tagset(&hba->host->tag_set);
+	mutex_unlock(&hba->host->scan_mutex);
 
 	/* Enable Write Booster if current gear requires it else disable it */
 	if (ufshcd_enable_wb_if_scaling_up(hba) && !err)
 		ufshcd_wb_toggle(hba, hba->pwr_info.gear_rx >= hba->clk_scaling.wb_gear);
 
-	mutex_unlock(&hba->wb_mutex);
-
-	blk_mq_unquiesce_tagset(&hba->host->tag_set);
-	mutex_unlock(&hba->host->scan_mutex);
 	ufshcd_release(hba);
 }
 
@@ -6504,6 +6503,11 @@ 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 +6547,7 @@ 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 +6562,42 @@ 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.
+	 * Ensure the parent's error status is cleared before proceeding
+	 * to the child, as the parent must be active to activate the child.
 	 */
-	ret = pm_runtime_set_active(&hba->ufs_device_wlun->sdev_gendev);
+	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;
+	}
 
-	/* hba device might have a runtime error otherwise */
-	if (ret)
-		ret = pm_runtime_set_active(hba->dev);
 	/*
 	 * 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 ||
@@ -6679,19 +6698,22 @@ static void ufshcd_err_handler(struct work_struct *work)
 		 hba->saved_uic_err, hba->force_reset,
 		 ufshcd_is_link_broken(hba) ? "; link is broken" : "");
 
-	/*
-	 * Use ufshcd_rpm_get_noresume() here to safely perform link recovery
-	 * even if an error occurs during runtime suspend or runtime resume.
-	 * This avoids potential deadlocks that could happen if we tried to
-	 * resume the device while a PM operation is already in progress.
-	 */
-	ufshcd_rpm_get_noresume(hba);
-	if (hba->pm_op_in_progress) {
-		ufshcd_link_recovery(hba);
+	if (hba->ufs_device_wlun) {
+		/*
+		 * Use ufshcd_rpm_get_noresume() here to safely perform link
+		 * recovery even if an error occurs during runtime suspend or
+		 * runtime resume. This avoids potential deadlocks that could
+		 * happen if we tried to resume the device while a PM operation
+		 * is already in progress.
+		 */
+		ufshcd_rpm_get_noresume(hba);
+		if (hba->pm_op_in_progress) {
+			ufshcd_link_recovery(hba);
+			ufshcd_rpm_put(hba);
+			return;
+		}
 		ufshcd_rpm_put(hba);
-		return;
 	}
-	ufshcd_rpm_put(hba);
 
 	down(&hba->host_sem);
 	spin_lock_irqsave(hba->host->host_lock, flags);