diff mbox series

[v9,8/9] scsi: ufs: Fix a racing problem btw error handler and runtime PM ops

Message ID 1596445485-19834-9-git-send-email-cang@codeaurora.org
State New
Headers show
Series [v9,1/9] scsi: ufs: Add checks before setting clk-gating states | expand

Commit Message

Can Guo Aug. 3, 2020, 9:04 a.m. UTC 
Current IRQ handler blocks scsi requests before scheduling eh_work, when
error handler calls pm_runtime_get_sync, if ufshcd_suspend/resume sends a
scsi cmd, most likely the SSU cmd, since scsi requests are blocked,
pm_runtime_get_sync() will never return because ufshcd_suspend/reusme is
blocked by the scsi cmd. Some changes and code re-arrangement can be made
to resolve it.

o In queuecommand path, hba->ufshcd_state check and ufshcd_send_command
  should stay into the same spin lock. This is to make sure that no more
  commands leak into doorbell after hba->ufshcd_state is changed.
o Don't block scsi requests before scheduling eh_work, let error handler
  block scsi requests when it is ready to start error recovery.
o Don't let scsi layer keep requeuing the scsi cmds sent from hba runtime
  PM ops, let them pass or fail them. Let them pass if eh_work is scheduled
  due to non-fatal errors. Fail them if eh_work is scheduled due to fatal
  errors, otherwise the cmds may eventually time out since UFS is in bad
  state, which gets error handler blocked for too long. If we fail the scsi
  cmds sent from hba runtime PM ops, hba runtime PM ops fails too, but it
  does not hurt since error handler can recover hba runtime PM error.

Signed-off-by: Can Guo <cang@codeaurora.org>
Reviewed-by: Bean Huo <beanhuo@micron.com>
---
 drivers/scsi/ufs/ufshcd.c | 84 ++++++++++++++++++++++++++++-------------------
 1 file changed, 50 insertions(+), 34 deletions(-)
diff mbox series

Patch

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index a79fbbd..d7d2758 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -126,7 +126,8 @@  enum {
 	UFSHCD_STATE_RESET,
 	UFSHCD_STATE_ERROR,
 	UFSHCD_STATE_OPERATIONAL,
-	UFSHCD_STATE_EH_SCHEDULED,
+	UFSHCD_STATE_EH_SCHEDULED_FATAL,
+	UFSHCD_STATE_EH_SCHEDULED_NON_FATAL,
 };
 
 /* UFSHCD error handling flags */
@@ -2515,34 +2516,6 @@  static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	if (!down_read_trylock(&hba->clk_scaling_lock))
 		return SCSI_MLQUEUE_HOST_BUSY;
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	switch (hba->ufshcd_state) {
-	case UFSHCD_STATE_OPERATIONAL:
-		break;
-	case UFSHCD_STATE_EH_SCHEDULED:
-	case UFSHCD_STATE_RESET:
-		err = SCSI_MLQUEUE_HOST_BUSY;
-		goto out_unlock;
-	case UFSHCD_STATE_ERROR:
-		set_host_byte(cmd, DID_ERROR);
-		cmd->scsi_done(cmd);
-		goto out_unlock;
-	default:
-		dev_WARN_ONCE(hba->dev, 1, "%s: invalid state %d\n",
-				__func__, hba->ufshcd_state);
-		set_host_byte(cmd, DID_BAD_TARGET);
-		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);
-
 	hba->req_abort_count = 0;
 
 	err = ufshcd_hold(hba, true);
@@ -2578,11 +2551,50 @@  static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	/* Make sure descriptors are ready before ringing the doorbell */
 	wmb();
 
-	/* issue command to the controller */
 	spin_lock_irqsave(hba->host->host_lock, flags);
+	switch (hba->ufshcd_state) {
+	case UFSHCD_STATE_OPERATIONAL:
+	case UFSHCD_STATE_EH_SCHEDULED_NON_FATAL:
+		break;
+	case UFSHCD_STATE_EH_SCHEDULED_FATAL:
+		/*
+		 * 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
+		 * PM ops, it can never be finished if we let SCSI layer keep
+		 * retrying it, which gets err handler stuck forever. Neither
+		 * can we let the scsi cmd pass through, because UFS is in bad
+		 * state, the scsi cmd may eventually time out, which will get
+		 * err handler blocked for too long. So, just fail the scsi cmd
+		 * sent from PM ops, err handler can recover PM error anyways.
+		 */
+		if (hba->pm_op_in_progress) {
+			hba->force_reset = true;
+			set_host_byte(cmd, DID_BAD_TARGET);
+			goto out_compl_cmd;
+		}
+	case UFSHCD_STATE_RESET:
+		err = SCSI_MLQUEUE_HOST_BUSY;
+		goto out_compl_cmd;
+	case UFSHCD_STATE_ERROR:
+		set_host_byte(cmd, DID_ERROR);
+		goto out_compl_cmd;
+	default:
+		dev_WARN_ONCE(hba->dev, 1, "%s: invalid state %d\n",
+				__func__, hba->ufshcd_state);
+		set_host_byte(cmd, DID_BAD_TARGET);
+		goto out_compl_cmd;
+	}
 	ufshcd_send_command(hba, tag);
-out_unlock:
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	goto out;
+
+out_compl_cmd:
+	scsi_dma_unmap(lrbp->cmd);
+	lrbp->cmd = NULL;
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	ufshcd_release(hba);
+	if (!err)
+		cmd->scsi_done(cmd);
 out:
 	up_read(&hba->clk_scaling_lock);
 	return err;
@@ -5552,9 +5564,12 @@  static inline void ufshcd_schedule_eh_work(struct ufs_hba *hba)
 {
 	/* handle fatal errors only when link is not in error state */
 	if (hba->ufshcd_state != UFSHCD_STATE_ERROR) {
-		hba->ufshcd_state = UFSHCD_STATE_EH_SCHEDULED;
-		if (queue_work(hba->eh_wq, &hba->eh_work))
-			ufshcd_scsi_block_requests(hba);
+		if (hba->force_reset || ufshcd_is_link_broken(hba) ||
+		    ufshcd_is_saved_err_fatal(hba))
+			hba->ufshcd_state = UFSHCD_STATE_EH_SCHEDULED_FATAL;
+		else
+			hba->ufshcd_state = UFSHCD_STATE_EH_SCHEDULED_NON_FATAL;
+		queue_work(hba->eh_wq, &hba->eh_work);
 	}
 }
 
@@ -5664,6 +5679,7 @@  static void ufshcd_err_handler(struct work_struct *work)
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	ufshcd_err_handling_prepare(hba);
 	spin_lock_irqsave(hba->host->host_lock, flags);
+	ufshcd_scsi_block_requests(hba);
 	/*
 	 * A full reset and restore might have happened after preparation
 	 * is finished, double check whether we should stop.