[PATCH v7 09/14] scsi: ufs: fix error recovery after the hibern8 exit failure

[Yaniv Gardi]

Hibern8 exit can be called from 3 different context:
    - ufshcd_hibern8_exit_work
    - ufshcd_ungate_work
    - runtime/system resume

If hibern8 exit fails for some reason then we try to bring the link to
active state by link startup but this recovery mechanism results into
deadlock or errors from first 2 context listed above. This change fixes
the recovery by adding proper error handling mechanism.

Reviewed-by: Gilad Broner <gbroner@xxxxxxxxxxxxxx>
Reviewed-by: Dolev Raviv <draviv@xxxxxxxxxxxxxx>
Signed-off-by: Subhash Jadavani <subhashj@xxxxxxxxxxxxxx>
Signed-off-by: Yaniv Gardi <ygardi@xxxxxxxxxxxxxx>

---
 drivers/scsi/ufs/ufshcd.c | 58 +++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 53 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 1581d03..da08a40 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -608,6 +608,11 @@ int ufshcd_hold(struct ufs_hba *hba, bool async)
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	hba->clk_gating.active_reqs++;
 
+	if (ufshcd_eh_in_progress(hba)) {
+		spin_unlock_irqrestore(hba->host->host_lock, flags);
+		return 0;
+	}
+
 start:
 	switch (hba->clk_gating.state) {
 	case CLKS_ON:
@@ -723,7 +728,8 @@ static void __ufshcd_release(struct ufs_hba *hba)
 	if (hba->clk_gating.active_reqs || hba->clk_gating.is_suspended
 		|| hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL
 		|| hba->lrb_in_use || hba->outstanding_tasks
-		|| hba->active_uic_cmd || hba->uic_async_done)
+		|| hba->active_uic_cmd || hba->uic_async_done
+		|| ufshcd_eh_in_progress(hba))
 		return;
 
 	hba->clk_gating.state = REQ_CLKS_OFF;
@@ -1360,6 +1366,13 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 		cmd->scsi_done(cmd);
 		goto out_unlock;
 	}
+
+	/* if error handling is in progress, don't issue commands */
+	if (ufshcd_eh_in_progress(hba)) {
+		set_host_byte(cmd, DID_ERROR);
+		cmd->scsi_done(cmd);
+		goto out_unlock;
+	}
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
 	/* acquire the tag to make sure device cmds don't use it */
@@ -2390,6 +2403,31 @@ out:
 	return ret;
 }
 
+static int ufshcd_link_recovery(struct ufs_hba *hba)
+{
+	int ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	hba->ufshcd_state = UFSHCD_STATE_RESET;
+	ufshcd_set_eh_in_progress(hba);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	ret = ufshcd_host_reset_and_restore(hba);
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	if (ret)
+		hba->ufshcd_state = UFSHCD_STATE_ERROR;
+	ufshcd_clear_eh_in_progress(hba);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	if (ret)
+		dev_err(hba->dev, "%s: link recovery failed, err %d",
+			__func__, ret);
+
+	return ret;
+}
+
 static int __ufshcd_uic_hibern8_enter(struct ufs_hba *hba)
 {
 	int ret;
@@ -2398,10 +2436,18 @@ static int __ufshcd_uic_hibern8_enter(struct ufs_hba *hba)
 	uic_cmd.command = UIC_CMD_DME_HIBER_ENTER;
 	ret = ufshcd_uic_pwr_ctrl(hba, &uic_cmd);
 
-	if (ret)
+	if (ret) {
 		dev_err(hba->dev, "%s: hibern8 enter failed. ret = %d\n",
 			__func__, ret);
 
+		/*
+		 * If link recovery fails then return error so that caller
+		 * don't retry the hibern8 enter again.
+		 */
+		if (ufshcd_link_recovery(hba))
+			ret = -ENOLINK;
+	}
+
 	return ret;
 }
 
@@ -2426,8 +2472,9 @@ static int ufshcd_uic_hibern8_exit(struct ufs_hba *hba)
 	uic_cmd.command = UIC_CMD_DME_HIBER_EXIT;
 	ret = ufshcd_uic_pwr_ctrl(hba, &uic_cmd);
 	if (ret) {
-		ufshcd_set_link_off(hba);
-		ret = ufshcd_host_reset_and_restore(hba);
+		dev_err(hba->dev, "%s: hibern8 exit failed. ret = %d\n",
+			__func__, ret);
+		ret = ufshcd_link_recovery(hba);
 	}
 
 	return ret;
@@ -4379,7 +4426,6 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 	/* UFS device is also active now */
 	ufshcd_set_ufs_dev_active(hba);
 	ufshcd_force_reset_auto_bkops(hba);
-	hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
 	hba->wlun_dev_clr_ua = true;
 
 	if (ufshcd_get_max_pwr_mode(hba)) {
@@ -4393,6 +4439,8 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 					__func__, ret);
 	}
 
+	/* set the state as operational after switching to desired gear */
+	hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
 	/*
 	 * If we are in error handling context or in power management callbacks
 	 * context, no need to scan the host
-- 
1.8.5.2

-- 
QUALCOMM ISRAEL, on behalf of Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, hosted by The Linux Foundation