scsi: ufs: add reference counting for scsi block requests

Currently we call the scsi_block_requests()/scsi_unblock_requests()
whenever we want to block/unblock scsi requests but as there is no
reference counting, nesting of these calls could leave us in undesired
state sometime. Consider following call flow sequence:

1. func1() calls scsi_block_requests() but calls func2() before
   calling scsi_unblock_requests()
2. func2() calls scsi_block_requests()
3. func2() calls scsi_unblock_requests()
4. func1() calls scsi_unblock_requests()

As there is no reference counting, we will have scsi requests unblocked
after #3 instead of it to be unblocked only after #4. Though we may not
have failures seen with this, we might run into some failures in future.
Better solution would be to fix this by adding reference counting.

Signed-off-by: Subhash Jadavani <subhashj@codeaurora.org>
Signed-off-by: Can Guo <cang@codeaurora.org>
Signed-off-by: Asutosh Das <asutoshd@codeaurora.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/ufs/ufshcd.c

@@ -264,6 +264,18 @@ static inline void ufshcd_disable_irq(struct ufs_hba *hba)
 	}
 }
 
+static void ufshcd_scsi_unblock_requests(struct ufs_hba *hba)
+{
+	if (atomic_dec_and_test(&hba->scsi_block_reqs_cnt))
+		scsi_unblock_requests(hba->host);
+}
+
+static void ufshcd_scsi_block_requests(struct ufs_hba *hba)
+{
+	if (atomic_inc_return(&hba->scsi_block_reqs_cnt) == 1)
+		scsi_block_requests(hba->host);
+}
+
 /* replace non-printable or non-ASCII characters with spaces */
 static inline void ufshcd_remove_non_printable(char *val)
 {
@@ -1074,12 +1086,12 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba)
 	 * make sure that there are no outstanding requests when
 	 * clock scaling is in progress
 	 */
-	scsi_block_requests(hba->host);
+	ufshcd_scsi_block_requests(hba);
 	down_write(&hba->clk_scaling_lock);
 	if (ufshcd_wait_for_doorbell_clr(hba, DOORBELL_CLR_TOUT_US)) {
 		ret = -EBUSY;
 		up_write(&hba->clk_scaling_lock);
-		scsi_unblock_requests(hba->host);
+		ufshcd_scsi_unblock_requests(hba);
 	}
 
 	return ret;
@@ -1088,7 +1100,7 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba)
 static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba)
 {
 	up_write(&hba->clk_scaling_lock);
-	scsi_unblock_requests(hba->host);
+	ufshcd_scsi_unblock_requests(hba);
 }
 
 /**
@@ -1460,7 +1472,7 @@ static void ufshcd_ungate_work(struct work_struct *work)
 		hba->clk_gating.is_suspended = false;
 	}
 unblock_reqs:
-	scsi_unblock_requests(hba->host);
+	ufshcd_scsi_unblock_requests(hba);
 }
 
 /**
@@ -1516,7 +1528,7 @@ start:
 		 * work and to enable clocks.
 		 */
 	case CLKS_OFF:
-		scsi_block_requests(hba->host);
+		ufshcd_scsi_block_requests(hba);
 		hba->clk_gating.state = REQ_CLKS_ON;
 		trace_ufshcd_clk_gating(dev_name(hba->dev),
 					hba->clk_gating.state);
@@ -5298,7 +5310,7 @@ skip_err_handling:
 
 out:
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
-	scsi_unblock_requests(hba->host);
+	ufshcd_scsi_unblock_requests(hba);
 	ufshcd_release(hba);
 	pm_runtime_put_sync(hba->dev);
 }
@@ -5400,7 +5412,7 @@ static void ufshcd_check_errors(struct ufs_hba *hba)
 		/* handle fatal errors only when link is functional */
 		if (hba->ufshcd_state == UFSHCD_STATE_OPERATIONAL) {
 			/* block commands from scsi mid-layer */
-			scsi_block_requests(hba->host);
+			ufshcd_scsi_block_requests(hba);
 
 			hba->ufshcd_state = UFSHCD_STATE_EH_SCHEDULED;
 
@@ -8032,7 +8044,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 
 	/* Hold auto suspend until async scan completes */
 	pm_runtime_get_sync(dev);
-
+	atomic_set(&hba->scsi_block_reqs_cnt, 0);
 	/*
 	 * We are assuming that device wasn't put in sleep/power-down
 	 * state exclusively during the boot stage before kernel.

drivers/scsi/ufs/ufshcd.h

@@ -499,6 +499,7 @@ struct ufs_stats {
  * @urgent_bkops_lvl: keeps track of urgent bkops level for device
  * @is_urgent_bkops_lvl_checked: keeps track if the urgent bkops level for
  *  device is known or not.
+ * @scsi_block_reqs_cnt: reference counting for scsi block requests
  */
 struct ufs_hba {
 	void __iomem *mmio_base;
@@ -699,6 +700,7 @@ struct ufs_hba {
 
 	struct rw_semaphore clk_scaling_lock;
 	struct ufs_desc_size desc_size;
+	atomic_t scsi_block_reqs_cnt;
 };
 
 /* Returns true if clocks can be gated. Otherwise false */