[RFC PATCH] scsi: ufs: core: Allow error recovery before the device W-LUN exists

[Asdlerto Korry]

ufshcd_err_handling_should_stop() returns true while hba->ufs_device_wlun
is NULL, i.e. until the first probe has added the device W-LUN. If the
link fails during that first probe (for example NOP OUT failing after
link startup), the error handler therefore never resets the host or the
link: it only marks the state operational and returns, and the probe
keeps failing until it gives up.

On a Samsung Galaxy M52 5G (SM7325) the first link startup regularly
ends in PA errors (LINERESET). With the W-LUN check removed, the error
handler performs a real host reset and restore and the device comes up;
without it, it never does.

Removing the check exposes three places that dereference
hba->ufs_device_wlun unconditionally on this path:
ufshcd_rpm_get_sync()/ufshcd_rpm_put(), ufshcd_err_handling_prepare()
and ufshcd_recover_pm_error(). Skip the W-LUN runtime PM handling there
when the W-LUN does not exist yet; there is nothing to resume and no
regular SCSI I/O before it is added.

Note: the error handler then calls ufshcd_verify_dev_init() through
ufshcd_reset_and_restore() while the tag set is quiesced. This needs the
pseudo SCSI device queue to be unquiesced in ufshcd_err_handling_prepare()
(as done upstream), otherwise blk_execute_rq() waits forever.

Signed-off-by: Asdlerto Korry <korryasdlerto@xxxxxxxxx>
---
 drivers/ufs/core/ufshcd-priv.h |  4 ++++
 drivers/ufs/core/ufshcd.c      | 13 +++++++++----
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/ufs/core/ufshcd-priv.h b/drivers/ufs/core/ufshcd-priv.h
index e55c2a02c1f5..2cb0d542d114 100644
--- a/drivers/ufs/core/ufshcd-priv.h
+++ b/drivers/ufs/core/ufshcd-priv.h
@@ -385,6 +385,8 @@ static inline int ufshcd_update_ee_usr_mask(struct ufs_hba *hba,
 
 static inline int ufshcd_rpm_get_sync(struct ufs_hba *hba)
 {
+	if (!hba->ufs_device_wlun)
+		return 0;
 	return pm_runtime_get_sync(&hba->ufs_device_wlun->sdev_gendev);
 }
 
@@ -410,6 +412,8 @@ static inline int ufshcd_rpm_resume(struct ufs_hba *hba)
 
 static inline void ufshcd_rpm_put(struct ufs_hba *hba)
 {
+	if (!hba->ufs_device_wlun)
+		return;
 	pm_runtime_put(&hba->ufs_device_wlun->sdev_gendev);
 }
 
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index fd52deb72d21..9767fbc7b870 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -6876,8 +6876,9 @@ static void ufshcd_err_handling_prepare(struct ufs_hba *hba)
 	 */
 	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) {
+	if (hba->ufs_device_wlun &&
+	    (pm_runtime_status_suspended(&hba->ufs_device_wlun->sdev_gendev) ||
+	     hba->is_sys_suspended)) {
 		enum ufs_pm_op pm_op;
 
 		/*
@@ -6926,7 +6927,6 @@ static void ufshcd_err_handling_unprepare(struct ufs_hba *hba)
 static inline bool ufshcd_err_handling_should_stop(struct ufs_hba *hba)
 {
 	return (!hba->is_powered || hba->shutting_down ||
-		!hba->ufs_device_wlun ||
 		hba->ufshcd_state == UFSHCD_STATE_ERROR ||
 		(!(hba->saved_err || hba->saved_uic_err || hba->force_reset ||
 		   ufshcd_is_link_broken(hba))));
@@ -6935,12 +6935,17 @@ 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_target *starget;
 	struct Scsi_Host *shost = hba->host;
 	struct scsi_device *sdev;
 	struct request_queue *q;
 	bool resume_sdev_queues = false;
 
+	/* Nothing to recover before the device W-LUN has been added */
+	if (!hba->ufs_device_wlun)
+		return;
+	starget = hba->ufs_device_wlun->sdev_target;
+
 	hba->is_sys_suspended = false;
 
 	/*
-- 
2.25.1