Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Mon, 21 Dec 2020 07:26:26 -0800
From:   Jaegeuk Kim <jaegeuk@kernel.org>
To:     linux-kernel@vger.kernel.org, linux-scsi@vger.kernel.org,
        kernel-team@android.com
Cc:     cang@codeaurora.org, alim.akhtar@samsung.com, avri.altman@wdc.com,
        bvanassche@acm.org, martin.petersen@oracle.com,
        stanley.chu@mediatek.com
Subject: Re: [PATCH v2] scsi: ufs: fix livelock of ufshcd_clear_ua_wluns
Message-ID: <X+C+oqegC7EI6zDv@google.com>
References: <20201218033131.2624065-1-jaegeuk@kernel.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20201218033131.2624065-1-jaegeuk@kernel.org>
Precedence: bulk

When gate_work/ungate_work gets an error during hibern8_enter or exit,
 ufshcd_err_handler()
   ufshcd_scsi_block_requests()
   ufshcd_reset_and_restore()
     ufshcd_clear_ua_wluns() -> stuck
   ufshcd_scsi_unblock_requests()

In order to avoid it, ufshcd_clear_ua_wluns() can be called per recovery flows
such as suspend/resume, link_recovery, and error_handler.

Fixes: 1918651f2d7e ("scsi: ufs: Clear UAC for RPMB after ufshcd resets")
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---

 Change log from v1:
  - add condition check to call
  - add Fixes tag

 drivers/scsi/ufs/ufshcd.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index e221add25a7e..29a62552f6f1 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -3963,6 +3963,8 @@ int ufshcd_link_recovery(struct ufs_hba *hba)
 	if (ret)
 		dev_err(hba->dev, "%s: link recovery failed, err %d",
 			__func__, ret);
+	else
+		ufshcd_clear_ua_wluns(hba);
 
 	return ret;
 }
@@ -5968,6 +5970,9 @@ static void ufshcd_err_handler(struct work_struct *work)
 	ufshcd_scsi_unblock_requests(hba);
 	ufshcd_err_handling_unprepare(hba);
 	up(&hba->eh_sem);
+
+	if (!err && needs_reset)
+		ufshcd_clear_ua_wluns(hba);
 }
 
 /**
@@ -6908,14 +6913,11 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba)
 	ufshcd_set_clk_freq(hba, true);
 
 	err = ufshcd_hba_enable(hba);
-	if (err)
-		goto out;
 
 	/* Establish the link again and restore the device */
-	err = ufshcd_probe_hba(hba, false);
 	if (!err)
-		ufshcd_clear_ua_wluns(hba);
-out:
+		err = ufshcd_probe_hba(hba, false);
+
 	if (err)
 		dev_err(hba->dev, "%s: Host init failed %d\n", __func__, err);
 	ufshcd_update_evt_hist(hba, UFS_EVT_HOST_RESET, (u32)err);
@@ -8745,6 +8747,7 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 		ufshcd_resume_clkscaling(hba);
 	hba->clk_gating.is_suspended = false;
 	hba->dev_info.b_rpm_dev_flush_capable = false;
+	ufshcd_clear_ua_wluns(hba);
 	ufshcd_release(hba);
 out:
 	if (hba->dev_info.b_rpm_dev_flush_capable) {
@@ -8855,6 +8858,8 @@ static int ufshcd_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 		cancel_delayed_work(&hba->rpm_dev_flush_recheck_work);
 	}
 
+	ufshcd_clear_ua_wluns(hba);
+
 	/* Schedule clock gating in case of no access to UFS device yet */
 	ufshcd_release(hba);
 
-- 
2.29.2.729.g45daf8777d-goog