[PATCH 8/9] scsi: ufs: core: Wake suspended consumer queues after host reset

[Stanley Jhu <stanleyjhu@google.com>]

ufshcd_err_handling_prepare() now disables runtime PM of the UFS device
W-LUN, and ufshcd_err_handling_unprepare() enables it again and learns
whether a host reset in the error handler run succeeded.
ufshcd_recover_pm_error() wakes the runtime-suspended logical units
after a host reset only when hba->dev or the W-LUN has
power.runtime_error set, so I/O waiting on a runtime-suspended logical
unit stays blocked when both flags are clear:

1. I/O to a runtime-suspended logical unit blocks in
   __bio_queue_enter() and queues a runtime resume of the logical unit.
2. START STOP UNIT fails in the resume of the W-LUN supplier, and
   rpm_resume() rolls the logical unit back to RPM_SUSPENDED with
   power.runtime_error clear.
3. A later W-LUN runtime resume succeeds.
4. A fatal error makes ufshcd_err_handler() reset the host.
5. ufshcd_recover_pm_error() finds power.runtime_error clear on both
   devices and skips the wake loop.
6. The I/O stays blocked in __bio_queue_enter() until another request
   reaches the same queue.

Request a runtime resume of every runtime-suspended logical unit from
ufshcd_err_handling_unprepare() after every successful host reset,
whether or not power.runtime_error is set. Waking an idle logical unit
sends no SCSI command, and the logical unit returns to runtime suspend
after its autosuspend delay.

Requesting the resumes from ufshcd_err_handling_unprepare() needs two
more changes. First, issue them after pm_runtime_enable() on the W-LUN.
ufshcd_recover_pm_error() runs while W-LUN runtime PM is disabled, and
rpm_get_suppliers() ignores -EACCES from a disabled supplier. A logical
unit woken there resumes while its W-LUN supplier stays RPM_SUSPENDED.
Second, also runtime resume the UFS device W-LUN, synchronously and
before the logical units. ufshcd_err_handling_prepare() disables W-LUN
runtime PM without resuming the W-LUN, so the W-LUN stays RPM_SUSPENDED
after the reset when no logical unit is left runtime suspended to resume
it through the runtime PM device link. pm_request_resume() takes no
reference on hba->dev, so the pm_runtime_put(hba->dev) that follows
can runtime suspend hba->dev while the link is active and every
logical unit is runtime suspended.

Fixes: eef1d74bf88f ("PM: runtime: Only set runtime_error on suspend callback failures")
Cc: stable@vger.kernel.org # 7.3.x
Signed-off-by: Stanley Jhu <stanleyjhu@google.com>
---
 drivers/ufs/core/ufshcd.c | 51 +++++++++++++++++++++++----------------
 1 file changed, 30 insertions(+), 21 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 286ffb44772d..87d475e323b1 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -6961,6 +6961,33 @@ static bool ufshcd_err_handling_prepare(struct ufs_hba *hba)
 	return vops_resumed;
 }
 
+#ifdef CONFIG_PM
+/*
+ * A logical unit whose runtime resume failed against the W-LUN may still have
+ * bios waiting in blk_queue_enter(). Request a runtime resume for every
+ * suspended logical unit to unblock them. Resume the W-LUN first and
+ * synchronously. ufshcd_err_handling_prepare() disabled its runtime PM
+ * without resuming it, and the caller drops its hba->dev reference next.
+ */
+static void ufshcd_resume_sdevs_after_reset(struct ufs_hba *hba)
+{
+	struct scsi_device *sdev;
+	struct request_queue *q;
+
+	ufshcd_rpm_resume(hba);
+	shost_for_each_device(sdev, hba->host) {
+		q = sdev->request_queue;
+		if (q->dev && (q->rpm_status == RPM_SUSPENDED ||
+			       q->rpm_status == RPM_SUSPENDING))
+			pm_request_resume(q->dev);
+	}
+}
+#else
+static inline void ufshcd_resume_sdevs_after_reset(struct ufs_hba *hba)
+{
+}
+#endif
+
 static void ufshcd_err_handling_unprepare(struct ufs_hba *hba,
 					  bool vops_resumed, bool pm_recovered)
 {
@@ -6981,6 +7008,9 @@ static void ufshcd_err_handling_unprepare(struct ufs_hba *hba,
 	if (ufshcd_is_clkscaling_supported(hba))
 		ufshcd_clk_scaling_suspend(hba, false);
 	pm_runtime_enable(&hba->ufs_device_wlun->sdev_gendev);
+	/* The W-LUN and logical units resume only after pm_runtime_enable(). */
+	if (pm_recovered)
+		ufshcd_resume_sdevs_after_reset(hba);
 	ufshcd_rpm_put(hba);
 	pm_runtime_put(hba->dev);
 }
@@ -6998,10 +7028,6 @@ static inline bool ufshcd_err_handling_should_stop(struct ufs_hba *hba)
 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;
-	bool resume_sdev_queues = false;
 
 	hba->is_sys_suspended = false;
 
@@ -7012,7 +7038,6 @@ static void ufshcd_recover_pm_error(struct ufs_hba *hba)
 	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) {
@@ -7023,22 +7048,6 @@ static void ufshcd_recover_pm_error(struct ufs_hba *hba)
 		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 (resume_sdev_queues) {
-		shost_for_each_device(sdev, shost) {
-			q = sdev->request_queue;
-			if (q->dev && (q->rpm_status == RPM_SUSPENDED ||
-				       q->rpm_status == RPM_SUSPENDING))
-				pm_request_resume(q->dev);
-		}
 	}
 }
 #else
-- 
2.56.0.567.gdb80ae8cd5-goog