scsi: ufs: Utilize Transfer Request List Completion Notification Register

By reading the UTP Transfer Request List Completion Notification Register,
which is added in UFSHCI Ver 3.0, SW can easily get the compeleted transfer
requests. Thus, SW can get rid of host lock, which is used to synchronize
the tr_doorbell and outstanding_reqs, on transfer requests dispatch and
completion paths. This can further benefit random read/write performance.

Link: https://lore.kernel.org/r/1621845419-14194-4-git-send-email-cang@codeaurora.org
Cc: Stanley Chu <stanley.chu@mediatek.com>
Reviewed-by: Stanley Chu <stanley.chu@mediatek.com>
Reviewed-by: Bean Huo <beanhuo@micron.com>
Co-developed-by: Asutosh Das <asutoshd@codeaurora.org>
Signed-off-by: Asutosh Das <asutoshd@codeaurora.org>
Signed-off-by: Can Guo <cang@codeaurora.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/ufs/ufshcd.c

@@ -2106,7 +2106,6 @@ static inline
 void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag)
 {
 	struct ufshcd_lrb *lrbp = &hba->lrb[task_tag];
-	unsigned long flags;
 
 	lrbp->issue_time_stamp = ktime_get();
 	lrbp->compl_time_stamp = ktime_set(0, 0);
@@ -2115,10 +2114,19 @@ void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag)
 	ufshcd_clk_scaling_start_busy(hba);
 	if (unlikely(ufshcd_should_inform_monitor(hba, lrbp)))
 		ufshcd_start_monitor(hba, lrbp);
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	if (ufshcd_has_utrlcnr(hba)) {
-	set_bit(task_tag, &hba->outstanding_reqs);
+		set_bit(task_tag, &hba->outstanding_reqs);
-	ufshcd_writel(hba, 1 << task_tag, REG_UTP_TRANSFER_REQ_DOOR_BELL);
+		ufshcd_writel(hba, 1 << task_tag,
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
+			      REG_UTP_TRANSFER_REQ_DOOR_BELL);
+	} else {
+		unsigned long flags;
+
+		spin_lock_irqsave(hba->host->host_lock, flags);
+		set_bit(task_tag, &hba->outstanding_reqs);
+		ufshcd_writel(hba, 1 << task_tag,
+			      REG_UTP_TRANSFER_REQ_DOOR_BELL);
+		spin_unlock_irqrestore(hba->host->host_lock, flags);
+	}
 	/* Make sure that doorbell is committed immediately */
 	wmb();
 }
@@ -5261,17 +5269,17 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
 }
 
 /**
- * ufshcd_transfer_req_compl - handle SCSI and query command completion
+ * ufshcd_trc_handler - handle transfer requests completion
  * @hba: per adapter instance
+ * @use_utrlcnr: get completed requests from UTRLCNR
  *
  * Returns
  *  IRQ_HANDLED - If interrupt is valid
  *  IRQ_NONE    - If invalid interrupt
  */
-static irqreturn_t ufshcd_transfer_req_compl(struct ufs_hba *hba)
+static irqreturn_t ufshcd_trc_handler(struct ufs_hba *hba, bool use_utrlcnr)
 {
-	unsigned long completed_reqs, flags;
+	unsigned long completed_reqs = 0;
-	u32 tr_doorbell;
 
 	/* Resetting interrupt aggregation counters first and reading the
 	 * DOOR_BELL afterward allows us to handle all the completed requests.
@@ -5284,10 +5292,24 @@ static irqreturn_t ufshcd_transfer_req_compl(struct ufs_hba *hba)
 	    !(hba->quirks & UFSHCI_QUIRK_SKIP_RESET_INTR_AGGR))
 		ufshcd_reset_intr_aggr(hba);
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	if (use_utrlcnr) {
-	tr_doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
+		u32 utrlcnr;
-	completed_reqs = tr_doorbell ^ hba->outstanding_reqs;
+
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
+		utrlcnr = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_LIST_COMPL);
+		if (utrlcnr) {
+			ufshcd_writel(hba, utrlcnr,
+				      REG_UTP_TRANSFER_REQ_LIST_COMPL);
+			completed_reqs = utrlcnr;
+		}
+	} else {
+		unsigned long flags;
+		u32 tr_doorbell;
+
+		spin_lock_irqsave(hba->host->host_lock, flags);
+		tr_doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
+		completed_reqs = tr_doorbell ^ hba->outstanding_reqs;
+		spin_unlock_irqrestore(hba->host->host_lock, flags);
+	}
 
 	if (completed_reqs) {
 		__ufshcd_transfer_req_compl(hba, completed_reqs);
@@ -5769,7 +5791,7 @@ out:
 /* Complete requests that have door-bell cleared */
 static void ufshcd_complete_requests(struct ufs_hba *hba)
 {
-	ufshcd_transfer_req_compl(hba);
+	ufshcd_trc_handler(hba, false);
 	ufshcd_tmc_handler(hba);
 }
 
@@ -6410,7 +6432,7 @@ static irqreturn_t ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status)
 		retval |= ufshcd_tmc_handler(hba);
 
 	if (intr_status & UTP_TRANSFER_REQ_COMPL)
-		retval |= ufshcd_transfer_req_compl(hba);
+		retval |= ufshcd_trc_handler(hba, ufshcd_has_utrlcnr(hba));
 
 	return retval;
 }

drivers/scsi/ufs/ufshcd.h

@@ -1160,6 +1160,11 @@ static inline u32 ufshcd_vops_get_ufs_hci_version(struct ufs_hba *hba)
 	return ufshcd_readl(hba, REG_UFS_VERSION);
 }
 
+static inline bool ufshcd_has_utrlcnr(struct ufs_hba *hba)
+{
+	return (hba->ufs_version >= ufshci_version(3, 0));
+}
+
 static inline int ufshcd_vops_clk_scale_notify(struct ufs_hba *hba,
 			bool up, enum ufs_notify_change_status status)
 {

drivers/scsi/ufs/ufshci.h

@@ -39,6 +39,7 @@ enum {
 	REG_UTP_TRANSFER_REQ_DOOR_BELL		= 0x58,
 	REG_UTP_TRANSFER_REQ_LIST_CLEAR		= 0x5C,
 	REG_UTP_TRANSFER_REQ_LIST_RUN_STOP	= 0x60,
+	REG_UTP_TRANSFER_REQ_LIST_COMPL		= 0x64,
 	REG_UTP_TASK_REQ_LIST_BASE_L		= 0x70,
 	REG_UTP_TASK_REQ_LIST_BASE_H		= 0x74,
 	REG_UTP_TASK_REQ_DOOR_BELL		= 0x78,