diff mbox series

[v14,19/19] scsi: ufs: Inform the block layer about write ordering

Message ID 20231023215638.3405959-20-bvanassche@acm.org (mailing list archive)
State Superseded
Headers show
Series Improve write performance for zoned UFS devices​ | expand

Commit Message

Bart Van Assche Oct. 23, 2023, 9:54 p.m. UTC 
From the UFSHCI 4.0 specification, about the legacy (single queue) mode:
"The host controller always process transfer requests in-order according
to the order submitted to the list. In case of multiple commands with
single doorbell register ringing (batch mode), The dispatch order for
these transfer requests by host controller will base on their index in
the List. A transfer request with lower index value will be executed
before a transfer request with higher index value."

From the UFSHCI 4.0 specification, about the MCQ mode:
"Command Submission
1. Host SW writes an Entry to SQ
2. Host SW updates SQ doorbell tail pointer

Command Processing
3. After fetching the Entry, Host Controller updates SQ doorbell head
   pointer
4. Host controller sends COMMAND UPIU to UFS device"

In other words, for both legacy and MCQ mode, UFS controllers are
required to forward commands to the UFS device in the order these
commands have been received from the host.

Notes:
- For legacy mode this is only correct if the host submits one
  command at a time. The UFS driver does this.
- Also in legacy mode, the command order is not preserved if
  auto-hibernation is enabled in the UFS controller. Hence, enable
  zone write locking if auto-hibernation is enabled.

This patch improves performance as follows on my test setup:
- With the mq-deadline scheduler: 2.5x more IOPS for small writes.
- When not using an I/O scheduler compared to using mq-deadline with
  zone locking: 4x more IOPS for small writes.

Reviewed-by: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Reviewed-by: Can Guo <quic_cang@quicinc.com>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
---
 drivers/ufs/core/ufshcd.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 0a21ea9d7576..70bf62ed414c 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -4325,6 +4325,20 @@  static int ufshcd_update_preserves_write_order(struct ufs_hba *hba,
 				return -EPERM;
 		}
 	}
+	shost_for_each_device(sdev, hba->host)
+		blk_freeze_queue_start(sdev->request_queue);
+	shost_for_each_device(sdev, hba->host) {
+		struct request_queue *q = sdev->request_queue;
+
+		blk_mq_freeze_queue_wait(q);
+		q->limits.driver_preserves_write_order = preserves_write_order;
+		blk_queue_required_elevator_features(q,
+			!preserves_write_order && blk_queue_is_zoned(q) ?
+			ELEVATOR_F_ZBD_SEQ_WRITE : 0);
+		if (q->disk)
+			disk_set_zoned(q->disk, q->limits.zoned);
+		blk_mq_unfreeze_queue(q);
+	}
 
 	return 0;
 }
@@ -4367,7 +4381,8 @@  int ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit)
 
 	if (!is_mcq_enabled(hba) && !prev_state && new_state) {
 		/*
-		 * Auto-hibernation will be enabled for legacy UFSHCI mode.
+		 * Auto-hibernation will be enabled for legacy UFSHCI mode. Tell
+		 * the block layer that write requests may be reordered.
 		 */
 		ret = ufshcd_update_preserves_write_order(hba, false);
 		if (ret)
@@ -4383,7 +4398,8 @@  int ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit)
 	}
 	if (!is_mcq_enabled(hba) && prev_state && !new_state) {
 		/*
-		 * Auto-hibernation has been disabled.
+		 * Auto-hibernation has been disabled. Tell the block layer that
+		 * the order of write requests is preserved.
 		 */
 		ret = ufshcd_update_preserves_write_order(hba, true);
 		WARN_ON_ONCE(ret);
@@ -5151,6 +5167,10 @@  static int ufshcd_slave_configure(struct scsi_device *sdev)
 	struct ufs_hba *hba = shost_priv(sdev->host);
 	struct request_queue *q = sdev->request_queue;
 
+	q->limits.driver_preserves_write_order =
+		!ufshcd_is_auto_hibern8_supported(hba) ||
+		FIELD_GET(UFSHCI_AHIBERN8_TIMER_MASK, hba->ahit) == 0;
+
 	blk_queue_update_dma_pad(q, PRDT_DATA_BYTE_COUNT_PAD - 1);
 	if (hba->quirks & UFSHCD_QUIRK_4KB_DMA_ALIGNMENT)
 		blk_queue_update_dma_alignment(q, SZ_4K - 1);
@@ -8919,6 +8939,7 @@  static const struct scsi_host_template ufshcd_driver_template = {
 	.max_host_blocked	= 1,
 	.track_queue_depth	= 1,
 	.skip_settle_delay	= 1,
+	.needs_prepare_resubmit	= 1,
 	.sdev_groups		= ufshcd_driver_groups,
 	.rpm_autosuspend_delay	= RPM_AUTOSUSPEND_DELAY_MS,
 };