[PATCH 5/9] scsi: ufs: core: Disable W-LUN runtime PM in ufshcd_err_handling_prepare()

[Stanley Jhu <stanleyjhu@google.com>]

ufshcd_err_handling_prepare() calls ufshcd_rpm_get_sync() to power up
the host. Since commit eef1d74bf88f ("PM: runtime: Only set
runtime_error on suspend callback failures"), a failed W-LUN resume no
longer sets runtime_error, so this call runs the W-LUN resume again:

1. A request to a runtime-suspended logical unit resumes its W-LUN
   supplier, and __ufshcd_wl_resume() sends START STOP UNIT.
2. A fatal error sets UFSHCD_STATE_EH_SCHEDULED_FATAL, and
   ufshcd_queuecommand() fails START STOP UNIT with DID_BAD_TARGET.
3. sdev_runtime_resume() fails and clears pm_only on the W-LUN queue
   while rpm_resume() leaves the W-LUN RPM_SUSPENDED.
4. ufshcd_err_handling_prepare() calls ufshcd_rpm_get_sync() while the
   state is still UFSHCD_STATE_EH_SCHEDULED_FATAL. START STOP UNIT
   fails the same way, and blk_clear_pm_only() underflows pm_only
   to -1.

Instead, have the error handler power up the host itself by taking
ufshcd_rpm_get_noresume() and disabling W-LUN runtime PM in
ufshcd_err_handling_prepare(), then re-enabling it in
ufshcd_err_handling_unprepare(). Not resuming the W-LUN in
ufshcd_err_handling_prepare() needs two more changes.

First, force a host reset when the W-LUN is runtime suspended. On a
non-fatal UIC error with the link active in runtime suspend, a logical
unit resuming during error handling ignores the disabled W-LUN.
Skipping reset then leaves the device asleep, and I/O after unquiesce
fails with NOT READY.

Second, block non-W-LUN commands before blk_mq_quiesce_tagset() freezes
the queues. Once W-LUN runtime PM is disabled, another logical unit
resuming in that gap ignores the disabled W-LUN and sends commands that
hit a sleeping device or fail with DID_BAD_TARGET. Add
UFSHCD_EH_WLUN_FENCE to return SCSI_MLQUEUE_HOST_BUSY for non-W-LUN
commands while letting in-flight W-LUN PM commands finish.

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 | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 5563d28ef92e..7e3f9abc7e7c 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -215,6 +215,7 @@ static const char *const ufshcd_state_name[] = {
 /* UFSHCD error handling flags */
 enum {
 	UFSHCD_EH_IN_PROGRESS = (1 << 0),
+	UFSHCD_EH_WLUN_FENCE = (1 << 1),
 };
 
 /* UFSHCD UIC layer error flags */
@@ -235,6 +236,13 @@ enum {
 #define ufshcd_clear_eh_in_progress(h) \
 	((h)->eh_flags &= ~UFSHCD_EH_IN_PROGRESS)
 
+#define ufshcd_set_eh_wlun_fence(h) \
+	((h)->eh_flags |= UFSHCD_EH_WLUN_FENCE)
+#define ufshcd_eh_wlun_fence(h) \
+	((h)->eh_flags & UFSHCD_EH_WLUN_FENCE)
+#define ufshcd_clear_eh_wlun_fence(h) \
+	((h)->eh_flags &= ~UFSHCD_EH_WLUN_FENCE)
+
 const struct ufs_pm_lvl_states ufs_pm_lvl_states[] = {
 	[UFS_PM_LVL_0] = {UFS_ACTIVE_PWR_MODE, UIC_LINK_ACTIVE_STATE},
 	[UFS_PM_LVL_1] = {UFS_ACTIVE_PWR_MODE, UIC_LINK_HIBERN8_STATE},
@@ -3134,12 +3142,19 @@ static enum scsi_qc_status ufshcd_queuecommand(struct Scsi_Host *host,
 		 * UFSHCD_STATE_EH_SCHEDULED_NON_FATAL. Prevent requests
 		 * being issued in that case.
 		 */
-		if (ufshcd_eh_in_progress(hba)) {
+		if (ufshcd_eh_in_progress(hba) ||
+		    (ufshcd_eh_wlun_fence(hba) &&
+		     cmd->device != hba->ufs_device_wlun)) {
 			err = SCSI_MLQUEUE_HOST_BUSY;
 			goto out;
 		}
 		break;
 	case UFSHCD_STATE_EH_SCHEDULED_FATAL:
+		if (ufshcd_eh_wlun_fence(hba) &&
+		    cmd->device != hba->ufs_device_wlun) {
+			err = SCSI_MLQUEUE_HOST_BUSY;
+			goto out;
+		}
 		/*
 		 * pm_runtime_get_sync() is used at error handling preparation
 		 * stage. If a scsi cmd, e.g. the SSU cmd, is sent from hba's
@@ -6899,7 +6914,8 @@ static void ufshcd_err_handling_prepare(struct ufs_hba *hba)
 	 * runtime suspended, so take an extra reference on hba->dev.
 	 */
 	pm_runtime_get_sync(hba->dev);
-	ufshcd_rpm_get_sync(hba);
+	ufshcd_rpm_get_noresume(hba);
+	__pm_runtime_disable(&hba->ufs_device_wlun->sdev_gendev, false);
 	if (pm_runtime_status_suspended(&hba->ufs_device_wlun->sdev_gendev) ||
 	    hba->is_sys_suspended) {
 		enum ufs_pm_op pm_op;
@@ -6943,6 +6959,7 @@ static void ufshcd_err_handling_unprepare(struct ufs_hba *hba)
 	ufshcd_release(hba);
 	if (ufshcd_is_clkscaling_supported(hba))
 		ufshcd_clk_scaling_suspend(hba, false);
+	pm_runtime_enable(&hba->ufs_device_wlun->sdev_gendev);
 	ufshcd_rpm_put(hba);
 	pm_runtime_put(hba->dev);
 }
@@ -7146,6 +7163,7 @@ static void ufshcd_err_handler(struct work_struct *work)
 		up(&hba->host_sem);
 		return;
 	}
+	ufshcd_set_eh_wlun_fence(hba);
 	spin_unlock_irqrestore(&hba->host->host_lock, flags);
 
 	ufshcd_err_handling_prepare(hba);
@@ -7166,6 +7184,8 @@ static void ufshcd_err_handler(struct work_struct *work)
 
 	if (hba->ufshcd_state != UFSHCD_STATE_ERROR)
 		hba->ufshcd_state = UFSHCD_STATE_RESET;
+	if (pm_runtime_status_suspended(&hba->ufs_device_wlun->sdev_gendev))
+		hba->force_reset = true;
 	/*
 	 * A full reset and restore might have happened after preparation
 	 * is finished, double check whether we should stop.
@@ -7295,6 +7315,7 @@ static void ufshcd_err_handler(struct work_struct *work)
 			goto again;
 		hba->ufshcd_state = UFSHCD_STATE_ERROR;
 	}
+	ufshcd_clear_eh_wlun_fence(hba);
 	ufshcd_clear_eh_in_progress(hba);
 	spin_unlock_irqrestore(&hba->host->host_lock, flags);
 	ufshcd_err_handling_unprepare(hba);
-- 
2.56.0.567.gdb80ae8cd5-goog