scsi: ufs: ufshpb: Add HPB 2.0 support

Version 2.0 of HBP supports reads of varying sizes from 4KB to 1MB.

A read operation <= 32KB is supported as single HPB read. A read between
36KB and 1MB is supported by a combination of write buffer command and HPB
read command to deliver more PPN. The write buffer commands may not be
issued immediately due to busy tags. To use HPB read more aggressively, the
driver can requeue the write buffer command. The requeue threshold is
implemented as timeout and can be modified with requeue_timeout_ms entry in
sysfs.

[mkp: REQ_OP_DRV_* and blk_rq_is_passthrough()]

Link: https://lore.kernel.org/r/20210712090025epcms2p3b3d94f6f1b2cfa394e3d9ba130ca0fa7@epcms2p3
Tested-by: Can Guo <cang@codeaurora.org>
Tested-by: Stanley Chu <stanley.chu@mediatek.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Can Guo <cang@codeaurora.org>
Reviewed-by: Bean Huo <beanhuo@micron.com>
Reviewed-by: Stanley Chu <stanley.chu@mediatek.com>
Signed-off-by: Daejun Park <daejun7.park@samsung.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 558 insertions, 57 deletions

diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c
index 3d2b8ca8bdb0..9333b670b33f 100644
--- a/drivers/scsi/ufs/ufshpb.c
+++ b/drivers/scsi/ufs/ufshpb.c
@@ -31,6 +31,12 @@ bool ufshpb_is_allowed(struct ufs_hba *hba)
 	return !(hba->ufshpb_dev.hpb_disabled);
 }
 
+/* HPB version 1.0 is called as legacy version. */
+bool ufshpb_is_legacy(struct ufs_hba *hba)
+{
+	return hba->ufshpb_dev.is_legacy;
+}
+
 static struct ufshpb_lu *ufshpb_get_hpb_data(struct scsi_device *sdev)
 {
 	return sdev->hostdata;
@@ -64,9 +70,19 @@ static bool ufshpb_is_write_or_discard(struct scsi_cmnd *cmd)
 	       op_is_discard(req_op(cmd->request));
 }
 
-static bool ufshpb_is_supported_chunk(int transfer_len)
+static bool ufshpb_is_supported_chunk(struct ufshpb_lu *hpb, int transfer_len)
 {
-	return transfer_len <= HPB_MULTI_CHUNK_HIGH;
+	return transfer_len <= hpb->pre_req_max_tr_len;
+}
+
+/*
+ * In this driver, WRITE_BUFFER CMD support 36KB (len=9) ~ 1MB (len=256) as
+ * default. It is possible to change range of transfer_len through sysfs.
+ */
+static inline bool ufshpb_is_required_wb(struct ufshpb_lu *hpb, int len)
+{
+	return len > hpb->pre_req_min_tr_len &&
+	       len <= hpb->pre_req_max_tr_len;
 }
 
 static bool ufshpb_is_general_lun(int lun)
@@ -74,8 +90,7 @@ static bool ufshpb_is_general_lun(int lun)
 	return lun < UFS_UPIU_MAX_UNIT_NUM_ID;
 }
 
-static bool
-ufshpb_is_pinned_region(struct ufshpb_lu *hpb, int rgn_idx)
+static bool ufshpb_is_pinned_region(struct ufshpb_lu *hpb, int rgn_idx)
 {
 	if (hpb->lu_pinned_end != PINNED_NOT_SET &&
 	    rgn_idx >= hpb->lu_pinned_start &&
@@ -264,7 +279,7 @@ ufshpb_get_pos_from_lpn(struct ufshpb_lu *hpb, unsigned long lpn, int *rgn_idx,
 
 static void
 ufshpb_set_hpb_read_to_upiu(struct ufshpb_lu *hpb, struct ufshcd_lrb *lrbp,
-			    u32 lpn, __be64 ppn, u8 transfer_len)
+			    u32 lpn, __be64 ppn, u8 transfer_len, int read_id)
 {
 	unsigned char *cdb = lrbp->cmd->cmnd;
 
@@ -273,15 +288,260 @@ ufshpb_set_hpb_read_to_upiu(struct ufshpb_lu *hpb, struct ufshcd_lrb *lrbp,
 	/* ppn value is stored as big-endian in the host memory */
 	memcpy(&cdb[6], &ppn, sizeof(__be64));
 	cdb[14] = transfer_len;
+	cdb[15] = read_id;
 
 	lrbp->cmd->cmd_len = UFS_CDB_SIZE;
 }
 
+static inline void ufshpb_set_write_buf_cmd(unsigned char *cdb,
+					    unsigned long lpn, unsigned int len,
+					    int read_id)
+{
+	cdb[0] = UFSHPB_WRITE_BUFFER;
+	cdb[1] = UFSHPB_WRITE_BUFFER_PREFETCH_ID;
+
+	put_unaligned_be32(lpn, &cdb[2]);
+	cdb[6] = read_id;
+	put_unaligned_be16(len * HPB_ENTRY_SIZE, &cdb[7]);
+
+	cdb[9] = 0x00;	/* Control = 0x00 */
+}
+
+static struct ufshpb_req *ufshpb_get_pre_req(struct ufshpb_lu *hpb)
+{
+	struct ufshpb_req *pre_req;
+
+	if (hpb->num_inflight_pre_req >= hpb->throttle_pre_req) {
+		dev_info(&hpb->sdev_ufs_lu->sdev_dev,
+			 "pre_req throttle. inflight %d throttle %d",
+			 hpb->num_inflight_pre_req, hpb->throttle_pre_req);
+		return NULL;
+	}
+
+	pre_req = list_first_entry_or_null(&hpb->lh_pre_req_free,
+					   struct ufshpb_req, list_req);
+	if (!pre_req) {
+		dev_info(&hpb->sdev_ufs_lu->sdev_dev, "There is no pre_req");
+		return NULL;
+	}
+
+	list_del_init(&pre_req->list_req);
+	hpb->num_inflight_pre_req++;
+
+	return pre_req;
+}
+
+static inline void ufshpb_put_pre_req(struct ufshpb_lu *hpb,
+				      struct ufshpb_req *pre_req)
+{
+	pre_req->req = NULL;
+	bio_reset(pre_req->bio);
+	list_add_tail(&pre_req->list_req, &hpb->lh_pre_req_free);
+	hpb->num_inflight_pre_req--;
+}
+
+static void ufshpb_pre_req_compl_fn(struct request *req, blk_status_t error)
+{
+	struct ufshpb_req *pre_req = (struct ufshpb_req *)req->end_io_data;
+	struct ufshpb_lu *hpb = pre_req->hpb;
+	unsigned long flags;
+
+	if (error) {
+		struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
+		struct scsi_sense_hdr sshdr;
+
+		dev_err(&hpb->sdev_ufs_lu->sdev_dev, "block status %d", error);
+		scsi_command_normalize_sense(cmd, &sshdr);
+		dev_err(&hpb->sdev_ufs_lu->sdev_dev,
+			"code %x sense_key %x asc %x ascq %x",
+			sshdr.response_code,
+			sshdr.sense_key, sshdr.asc, sshdr.ascq);
+		dev_err(&hpb->sdev_ufs_lu->sdev_dev,
+			"byte4 %x byte5 %x byte6 %x additional_len %x",
+			sshdr.byte4, sshdr.byte5,
+			sshdr.byte6, sshdr.additional_length);
+	}
+
+	blk_mq_free_request(req);
+	spin_lock_irqsave(&hpb->rgn_state_lock, flags);
+	ufshpb_put_pre_req(pre_req->hpb, pre_req);
+	spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
+}
+
+static int ufshpb_prep_entry(struct ufshpb_req *pre_req, struct page *page)
+{
+	struct ufshpb_lu *hpb = pre_req->hpb;
+	struct ufshpb_region *rgn;
+	struct ufshpb_subregion *srgn;
+	__be64 *addr;
+	int offset = 0;
+	int copied;
+	unsigned long lpn = pre_req->wb.lpn;
+	int rgn_idx, srgn_idx, srgn_offset;
+	unsigned long flags;
+
+	addr = page_address(page);
+	ufshpb_get_pos_from_lpn(hpb, lpn, &rgn_idx, &srgn_idx, &srgn_offset);
+
+	spin_lock_irqsave(&hpb->rgn_state_lock, flags);
+
+next_offset:
+	rgn = hpb->rgn_tbl + rgn_idx;
+	srgn = rgn->srgn_tbl + srgn_idx;
+
+	if (!ufshpb_is_valid_srgn(rgn, srgn))
+		goto mctx_error;
+
+	if (!srgn->mctx)
+		goto mctx_error;
+
+	copied = ufshpb_fill_ppn_from_page(hpb, srgn->mctx, srgn_offset,
+					   pre_req->wb.len - offset,
+					   &addr[offset]);
+
+	if (copied < 0)
+		goto mctx_error;
+
+	offset += copied;
+	srgn_offset += copied;
+
+	if (srgn_offset == hpb->entries_per_srgn) {
+		srgn_offset = 0;
+
+		if (++srgn_idx == hpb->srgns_per_rgn) {
+			srgn_idx = 0;
+			rgn_idx++;
+		}
+	}
+
+	if (offset < pre_req->wb.len)
+		goto next_offset;
+
+	spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
+	return 0;
+mctx_error:
+	spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
+	return -ENOMEM;
+}
+
+static int ufshpb_pre_req_add_bio_page(struct ufshpb_lu *hpb,
+				       struct request_queue *q,
+				       struct ufshpb_req *pre_req)
+{
+	struct page *page = pre_req->wb.m_page;
+	struct bio *bio = pre_req->bio;
+	int entries_bytes, ret;
+
+	if (!page)
+		return -ENOMEM;
+
+	if (ufshpb_prep_entry(pre_req, page))
+		return -ENOMEM;
+
+	entries_bytes = pre_req->wb.len * sizeof(__be64);
+
+	ret = bio_add_pc_page(q, bio, page, entries_bytes, 0);
+	if (ret != entries_bytes) {
+		dev_err(&hpb->sdev_ufs_lu->sdev_dev,
+			"bio_add_pc_page fail: %d", ret);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static inline int ufshpb_get_read_id(struct ufshpb_lu *hpb)
+{
+	if (++hpb->cur_read_id >= MAX_HPB_READ_ID)
+		hpb->cur_read_id = 1;
+	return hpb->cur_read_id;
+}
+
+static int ufshpb_execute_pre_req(struct ufshpb_lu *hpb, struct scsi_cmnd *cmd,
+				  struct ufshpb_req *pre_req, int read_id)
+{
+	struct scsi_device *sdev = cmd->device;
+	struct request_queue *q = sdev->request_queue;
+	struct request *req;
+	struct scsi_request *rq;
+	struct bio *bio = pre_req->bio;
+
+	pre_req->hpb = hpb;
+	pre_req->wb.lpn = sectors_to_logical(cmd->device,
+					     blk_rq_pos(cmd->request));
+	pre_req->wb.len = sectors_to_logical(cmd->device,
+					     blk_rq_sectors(cmd->request));
+	if (ufshpb_pre_req_add_bio_page(hpb, q, pre_req))
+		return -ENOMEM;
+
+	req = pre_req->req;
+
+	/* 1. request setup */
+	blk_rq_append_bio(req, bio);
+	req->rq_disk = NULL;
+	req->end_io_data = (void *)pre_req;
+	req->end_io = ufshpb_pre_req_compl_fn;
+
+	/* 2. scsi_request setup */
+	rq = scsi_req(req);
+	rq->retries = 1;
+
+	ufshpb_set_write_buf_cmd(rq->cmd, pre_req->wb.lpn, pre_req->wb.len,
+				 read_id);
+	rq->cmd_len = scsi_command_size(rq->cmd);
+
+	if (blk_insert_cloned_request(q, req) != BLK_STS_OK)
+		return -EAGAIN;
+
+	hpb->stats.pre_req_cnt++;
+
+	return 0;
+}
+
+static int ufshpb_issue_pre_req(struct ufshpb_lu *hpb, struct scsi_cmnd *cmd,
+				int *read_id)
+{
+	struct ufshpb_req *pre_req;
+	struct request *req = NULL;
+	unsigned long flags;
+	int _read_id;
+	int ret = 0;
+
+	req = blk_get_request(cmd->device->request_queue,
+			      REQ_OP_DRV_OUT | REQ_SYNC, BLK_MQ_REQ_NOWAIT);
+	if (IS_ERR(req))
+		return -EAGAIN;
+
+	spin_lock_irqsave(&hpb->rgn_state_lock, flags);
+	pre_req = ufshpb_get_pre_req(hpb);
+	if (!pre_req) {
+		ret = -EAGAIN;
+		goto unlock_out;
+	}
+	_read_id = ufshpb_get_read_id(hpb);
+	spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
+
+	pre_req->req = req;
+
+	ret = ufshpb_execute_pre_req(hpb, cmd, pre_req, _read_id);
+	if (ret)
+		goto free_pre_req;
+
+	*read_id = _read_id;
+
+	return ret;
+free_pre_req:
+	spin_lock_irqsave(&hpb->rgn_state_lock, flags);
+	ufshpb_put_pre_req(hpb, pre_req);
+unlock_out:
+	spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
+	blk_put_request(req);
+	return ret;
+}
+
 /*
  * This function will set up HPB read command using host-side L2P map data.
- * In HPB v1.0, maximum size of HPB read command is 4KB.
  */
-void ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
+int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 {
 	struct ufshpb_lu *hpb;
 	struct ufshpb_region *rgn;
@@ -291,30 +551,31 @@ void ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 	__be64 ppn;
 	unsigned long flags;
 	int transfer_len, rgn_idx, srgn_idx, srgn_offset;
+	int read_id = 0;
 	int err = 0;
 
 	hpb = ufshpb_get_hpb_data(cmd->device);
 	if (!hpb)
-		return;
+		return -ENODEV;
 
 	if (ufshpb_get_state(hpb) == HPB_INIT)
-		return;
+		return -ENODEV;
 
 	if (ufshpb_get_state(hpb) != HPB_PRESENT) {
 		dev_notice(&hpb->sdev_ufs_lu->sdev_dev,
 			   "%s: ufshpb state is not PRESENT", __func__);
-		return;
+		return -ENODEV;
 	}
 
 	if (blk_rq_is_passthrough(cmd->request) ||
 	    (!ufshpb_is_write_or_discard(cmd) &&
 	     !ufshpb_is_read_cmd(cmd)))
-		return;
+		return 0;
 
 	transfer_len = sectors_to_logical(cmd->device,
 					  blk_rq_sectors(cmd->request));
 	if (unlikely(!transfer_len))
-		return;
+		return 0;
 
 	lpn = sectors_to_logical(cmd->device, blk_rq_pos(cmd->request));
 	ufshpb_get_pos_from_lpn(hpb, lpn, &rgn_idx, &srgn_idx, &srgn_offset);
@@ -327,11 +588,11 @@ void ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 		ufshpb_set_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset,
 				 transfer_len);
 		spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
-		return;
+		return 0;
 	}
 
-	if (!ufshpb_is_supported_chunk(transfer_len))
-		return;
+	if (!ufshpb_is_supported_chunk(hpb, transfer_len))
+		return 0;
 
 	WARN_ON_ONCE(transfer_len > HPB_MULTI_CHUNK_HIGH);
 
@@ -340,7 +601,7 @@ void ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 				   transfer_len)) {
 		hpb->stats.miss_cnt++;
 		spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
-		return;
+		return 0;
 	}
 
 	err = ufshpb_fill_ppn_from_page(hpb, srgn->mctx, srgn_offset, 1, &ppn);
@@ -353,28 +614,45 @@ void ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 		 * active state.
 		 */
 		dev_err(hba->dev, "get ppn failed. err %d\n", err);
-		return;
+		return err;
 	}
+	if (!ufshpb_is_legacy(hba) &&
+	    ufshpb_is_required_wb(hpb, transfer_len)) {
+		err = ufshpb_issue_pre_req(hpb, cmd, &read_id);
+		if (err) {
+			unsigned long timeout;
+
+			timeout = cmd->jiffies_at_alloc + msecs_to_jiffies(
+				  hpb->params.requeue_timeout_ms);
 
-	ufshpb_set_hpb_read_to_upiu(hpb, lrbp, lpn, ppn, transfer_len);
+			if (time_before(jiffies, timeout))
+				return -EAGAIN;
+
+			hpb->stats.miss_cnt++;
+			return 0;
+		}
+	}
+
+	ufshpb_set_hpb_read_to_upiu(hpb, lrbp, lpn, ppn, transfer_len, read_id);
 
 	hpb->stats.hit_cnt++;
+	return 0;
 }
-static struct ufshpb_req *ufshpb_get_map_req(struct ufshpb_lu *hpb,
-					     struct ufshpb_subregion *srgn)
+
+static struct ufshpb_req *ufshpb_get_req(struct ufshpb_lu *hpb,
+					 int rgn_idx, enum req_opf dir)
 {
-	struct ufshpb_req *map_req;
+	struct ufshpb_req *rq;
 	struct request *req;
-	struct bio *bio;
 	int retries = HPB_MAP_REQ_RETRIES;
 
-	map_req = kmem_cache_alloc(hpb->map_req_cache, GFP_KERNEL);
-	if (!map_req)
+	rq = kmem_cache_alloc(hpb->map_req_cache, GFP_KERNEL);
+	if (!rq)
 		return NULL;
 
 retry:
-	req = blk_get_request(hpb->sdev_ufs_lu->request_queue,
-			      REQ_OP_DRV_IN, BLK_MQ_REQ_NOWAIT);
+	req = blk_get_request(hpb->sdev_ufs_lu->request_queue, dir,
+			      BLK_MQ_REQ_NOWAIT);
 
 	if ((PTR_ERR(req) == -EWOULDBLOCK) && (--retries > 0)) {
 		usleep_range(3000, 3100);
@@ -382,35 +660,54 @@ retry:
 	}
 
 	if (IS_ERR(req))
-		goto free_map_req;
+		goto free_rq;
+
+	rq->hpb = hpb;
+	rq->req = req;
+	rq->rb.rgn_idx = rgn_idx;
+
+	return rq;
+
+free_rq:
+	kmem_cache_free(hpb->map_req_cache, rq);
+	return NULL;
+}
+
+static void ufshpb_put_req(struct ufshpb_lu *hpb, struct ufshpb_req *rq)
+{
+	blk_put_request(rq->req);
+	kmem_cache_free(hpb->map_req_cache, rq);
+}
+
+static struct ufshpb_req *ufshpb_get_map_req(struct ufshpb_lu *hpb,
+					     struct ufshpb_subregion *srgn)
+{
+	struct ufshpb_req *map_req;
+	struct bio *bio;
+
+	map_req = ufshpb_get_req(hpb, srgn->rgn_idx, REQ_OP_DRV_IN);
+	if (!map_req)
+		return NULL;
 
 	bio = bio_alloc(GFP_KERNEL, hpb->pages_per_srgn);
 	if (!bio) {
-		blk_put_request(req);
-		goto free_map_req;
+		ufshpb_put_req(hpb, map_req);
+		return NULL;
 	}
 
-	map_req->hpb = hpb;
-	map_req->req = req;
 	map_req->bio = bio;
 
-	map_req->rgn_idx = srgn->rgn_idx;
-	map_req->srgn_idx = srgn->srgn_idx;
-	map_req->mctx = srgn->mctx;
+	map_req->rb.srgn_idx = srgn->srgn_idx;
+	map_req->rb.mctx = srgn->mctx;
 
 	return map_req;
-
-free_map_req:
-	kmem_cache_free(hpb->map_req_cache, map_req);
-	return NULL;
 }
 
 static void ufshpb_put_map_req(struct ufshpb_lu *hpb,
 			       struct ufshpb_req *map_req)
 {
 	bio_put(map_req->bio);
-	blk_put_request(map_req->req);
-	kmem_cache_free(hpb->map_req_cache, map_req);
+	ufshpb_put_req(hpb, map_req);
 }
 
 static int ufshpb_clear_dirty_bitmap(struct ufshpb_lu *hpb,
@@ -493,6 +790,13 @@ static void ufshpb_activate_subregion(struct ufshpb_lu *hpb,
 	srgn->srgn_state = HPB_SRGN_VALID;
 }
 
+static void ufshpb_umap_req_compl_fn(struct request *req, blk_status_t error)
+{
+	struct ufshpb_req *umap_req = (struct ufshpb_req *)req->end_io_data;
+
+	ufshpb_put_req(umap_req->hpb, umap_req);
+}
+
 static void ufshpb_map_req_compl_fn(struct request *req, blk_status_t error)
 {
 	struct ufshpb_req *map_req = (struct ufshpb_req *) req->end_io_data;
@@ -500,8 +804,8 @@ static void ufshpb_map_req_compl_fn(struct request *req, blk_status_t error)
 	struct ufshpb_subregion *srgn;
 	unsigned long flags;
 
-	srgn = hpb->rgn_tbl[map_req->rgn_idx].srgn_tbl +
-		map_req->srgn_idx;
+	srgn = hpb->rgn_tbl[map_req->rb.rgn_idx].srgn_tbl +
+		map_req->rb.srgn_idx;
 
 	ufshpb_clear_dirty_bitmap(hpb, srgn);
 	spin_lock_irqsave(&hpb->rgn_state_lock, flags);
@@ -511,6 +815,16 @@ static void ufshpb_map_req_compl_fn(struct request *req, blk_status_t error)
 	ufshpb_put_map_req(map_req->hpb, map_req);
 }
 
+static void ufshpb_set_unmap_cmd(unsigned char *cdb, struct ufshpb_region *rgn)
+{
+	cdb[0] = UFSHPB_WRITE_BUFFER;
+	cdb[1] = rgn ? UFSHPB_WRITE_BUFFER_INACT_SINGLE_ID :
+			  UFSHPB_WRITE_BUFFER_INACT_ALL_ID;
+	if (rgn)
+		put_unaligned_be16(rgn->rgn_idx, &cdb[2]);
+	cdb[9] = 0x00;
+}
+
 static void ufshpb_set_read_buf_cmd(unsigned char *cdb, int rgn_idx,
 				    int srgn_idx, int srgn_mem_size)
 {
@@ -524,6 +838,23 @@ static void ufshpb_set_read_buf_cmd(unsigned char *cdb, int rgn_idx,
 	cdb[9] = 0x00;
 }
 
+static void ufshpb_execute_umap_req(struct ufshpb_lu *hpb,
+				   struct ufshpb_req *umap_req,
+				   struct ufshpb_region *rgn)
+{
+	struct request *req;
+	struct scsi_request *rq;
+
+	req = umap_req->req;
+	req->timeout = 0;
+	req->end_io_data = (void *)umap_req;
+	rq = scsi_req(req);
+	ufshpb_set_unmap_cmd(rq->cmd, rgn);
+	rq->cmd_len = HPB_WRITE_BUFFER_CMD_LENGTH;
+
+	blk_execute_rq_nowait(NULL, req, 1, ufshpb_umap_req_compl_fn);
+}
+
 static int ufshpb_execute_map_req(struct ufshpb_lu *hpb,
 				  struct ufshpb_req *map_req, bool last)
 {
@@ -536,12 +867,12 @@ static int ufshpb_execute_map_req(struct ufshpb_lu *hpb,
 
 	q = hpb->sdev_ufs_lu->request_queue;
 	for (i = 0; i < hpb->pages_per_srgn; i++) {
-		ret = bio_add_pc_page(q, map_req->bio, map_req->mctx->m_page[i],
+		ret = bio_add_pc_page(q, map_req->bio, map_req->rb.mctx->m_page[i],
 				      PAGE_SIZE, 0);
 		if (ret != PAGE_SIZE) {
 			dev_err(&hpb->sdev_ufs_lu->sdev_dev,
 				   "bio_add_pc_page fail %d - %d\n",
-				   map_req->rgn_idx, map_req->srgn_idx);
+				   map_req->rb.rgn_idx, map_req->rb.srgn_idx);
 			return ret;
 		}
 	}
@@ -557,8 +888,8 @@ static int ufshpb_execute_map_req(struct ufshpb_lu *hpb,
 	if (unlikely(last))
 		mem_size = hpb->last_srgn_entries * HPB_ENTRY_SIZE;
 
-	ufshpb_set_read_buf_cmd(rq->cmd, map_req->rgn_idx,
-				map_req->srgn_idx, mem_size);
+	ufshpb_set_read_buf_cmd(rq->cmd, map_req->rb.rgn_idx,
+				map_req->rb.srgn_idx, mem_size);
 	rq->cmd_len = HPB_READ_BUFFER_CMD_LENGTH;
 
 	blk_execute_rq_nowait(NULL, req, 1, ufshpb_map_req_compl_fn);
@@ -690,6 +1021,26 @@ static void ufshpb_purge_active_subregion(struct ufshpb_lu *hpb,
 	}
 }
 
+static int ufshpb_issue_umap_req(struct ufshpb_lu *hpb,
+				 struct ufshpb_region *rgn)
+{
+	struct ufshpb_req *umap_req;
+	int rgn_idx = rgn ? rgn->rgn_idx : 0;
+
+	umap_req = ufshpb_get_req(hpb, rgn_idx, REQ_OP_DRV_OUT);
+	if (!umap_req)
+		return -ENOMEM;
+
+	ufshpb_execute_umap_req(hpb, umap_req, rgn);
+
+	return 0;
+}
+
+static int ufshpb_issue_umap_all_req(struct ufshpb_lu *hpb)
+{
+	return ufshpb_issue_umap_req(hpb, NULL);
+}
+
 static void __ufshpb_evict_region(struct ufshpb_lu *hpb,
 				  struct ufshpb_region *rgn)
 {
@@ -1212,6 +1563,16 @@ static void ufshpb_lu_parameter_init(struct ufs_hba *hba,
 	u32 entries_per_rgn;
 	u64 rgn_mem_size, tmp;
 
+	/* for pre_req */
+	hpb->pre_req_min_tr_len = hpb_dev_info->max_hpb_single_cmd + 1;
+
+	if (ufshpb_is_legacy(hba))
+		hpb->pre_req_max_tr_len = HPB_LEGACY_CHUNK_HIGH;
+	else
+		hpb->pre_req_max_tr_len = HPB_MULTI_CHUNK_HIGH;
+
+	hpb->cur_read_id = 0;
+
 	hpb->lu_pinned_start = hpb_lu_info->pinned_start;
 	hpb->lu_pinned_end = hpb_lu_info->num_pinned ?
 		(hpb_lu_info->pinned_start + hpb_lu_info->num_pinned - 1)
@@ -1358,7 +1719,7 @@ ufshpb_sysfs_attr_show_func(rb_active_cnt);
 ufshpb_sysfs_attr_show_func(rb_inactive_cnt);
 ufshpb_sysfs_attr_show_func(map_req_cnt);
 
-static struct attribute *hpb_dev_attrs[] = {
+static struct attribute *hpb_dev_stat_attrs[] = {
 	&dev_attr_hit_cnt.attr,
 	&dev_attr_miss_cnt.attr,
 	&dev_attr_rb_noti_cnt.attr,
@@ -1370,9 +1731,118 @@ static struct attribute *hpb_dev_attrs[] = {
 
 struct attribute_group ufs_sysfs_hpb_stat_group = {
 	.name = "hpb_stats",
-	.attrs = hpb_dev_attrs,
+	.attrs = hpb_dev_stat_attrs,
+};
+
+/* SYSFS functions */
+#define ufshpb_sysfs_param_show_func(__name)				\
+static ssize_t __name##_show(struct device *dev,			\
+	struct device_attribute *attr, char *buf)			\
+{									\
+	struct scsi_device *sdev = to_scsi_device(dev);			\
+	struct ufshpb_lu *hpb = ufshpb_get_hpb_data(sdev);		\
+									\
+	if (!hpb)							\
+		return -ENODEV;						\
+									\
+	return sysfs_emit(buf, "%d\n", hpb->params.__name);		\
+}
+
+ufshpb_sysfs_param_show_func(requeue_timeout_ms);
+static ssize_t
+requeue_timeout_ms_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
+{
+	struct scsi_device *sdev = to_scsi_device(dev);
+	struct ufshpb_lu *hpb = ufshpb_get_hpb_data(sdev);
+	int val;
+
+	if (!hpb)
+		return -ENODEV;
+
+	if (kstrtouint(buf, 0, &val))
+		return -EINVAL;
+
+	if (val < 0)
+		return -EINVAL;
+
+	hpb->params.requeue_timeout_ms = val;
+
+	return count;
+}
+static DEVICE_ATTR_RW(requeue_timeout_ms);
+
+static struct attribute *hpb_dev_param_attrs[] = {
+	&dev_attr_requeue_timeout_ms.attr,
+	NULL,
 };
 
+struct attribute_group ufs_sysfs_hpb_param_group = {
+	.name = "hpb_params",
+	.attrs = hpb_dev_param_attrs,
+};
+
+static int ufshpb_pre_req_mempool_init(struct ufshpb_lu *hpb)
+{
+	struct ufshpb_req *pre_req = NULL, *t;
+	int qd = hpb->sdev_ufs_lu->queue_depth / 2;
+	int i;
+
+	INIT_LIST_HEAD(&hpb->lh_pre_req_free);
+
+	hpb->pre_req = kcalloc(qd, sizeof(struct ufshpb_req), GFP_KERNEL);
+	hpb->throttle_pre_req = qd;
+	hpb->num_inflight_pre_req = 0;
+
+	if (!hpb->pre_req)
+		goto release_mem;
+
+	for (i = 0; i < qd; i++) {
+		pre_req = hpb->pre_req + i;
+		INIT_LIST_HEAD(&pre_req->list_req);
+		pre_req->req = NULL;
+
+		pre_req->bio = bio_alloc(GFP_KERNEL, 1);
+		if (!pre_req->bio)
+			goto release_mem;
+
+		pre_req->wb.m_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!pre_req->wb.m_page) {
+			bio_put(pre_req->bio);
+			goto release_mem;
+		}
+
+		list_add_tail(&pre_req->list_req, &hpb->lh_pre_req_free);
+	}
+
+	return 0;
+release_mem:
+	list_for_each_entry_safe(pre_req, t, &hpb->lh_pre_req_free, list_req) {
+		list_del_init(&pre_req->list_req);
+		bio_put(pre_req->bio);
+		__free_page(pre_req->wb.m_page);
+	}
+
+	kfree(hpb->pre_req);
+	return -ENOMEM;
+}
+
+static void ufshpb_pre_req_mempool_destroy(struct ufshpb_lu *hpb)
+{
+	struct ufshpb_req *pre_req = NULL;
+	int i;
+
+	for (i = 0; i < hpb->throttle_pre_req; i++) {
+		pre_req = hpb->pre_req + i;
+		bio_put(hpb->pre_req[i].bio);
+		if (!pre_req->wb.m_page)
+			__free_page(hpb->pre_req[i].wb.m_page);
+		list_del_init(&pre_req->list_req);
+	}
+
+	kfree(hpb->pre_req);
+}
+
 static void ufshpb_stat_init(struct ufshpb_lu *hpb)
 {
 	hpb->stats.hit_cnt = 0;
@@ -1383,6 +1853,11 @@ static void ufshpb_stat_init(struct ufshpb_lu *hpb)
 	hpb->stats.map_req_cnt = 0;
 }
 
+static void ufshpb_param_init(struct ufshpb_lu *hpb)
+{
+	hpb->params.requeue_timeout_ms = HPB_REQUEUE_TIME_MS;
+}
+
 static int ufshpb_lu_hpb_init(struct ufs_hba *hba, struct ufshpb_lu *hpb)
 {
 	int ret;
@@ -1415,14 +1890,24 @@ static int ufshpb_lu_hpb_init(struct ufs_hba *hba, struct ufshpb_lu *hpb)
 		goto release_req_cache;
 	}
 
+	ret = ufshpb_pre_req_mempool_init(hpb);
+	if (ret) {
+		dev_err(hba->dev, "ufshpb(%d) pre_req_mempool init fail",
+			hpb->lun);
+		goto release_m_page_cache;
+	}
+
 	ret = ufshpb_alloc_region_tbl(hba, hpb);
 	if (ret)
-		goto release_m_page_cache;
+		goto release_pre_req_mempool;
 
 	ufshpb_stat_init(hpb);
+	ufshpb_param_init(hpb);
 
 	return 0;
 
+release_pre_req_mempool:
+	ufshpb_pre_req_mempool_destroy(hpb);
 release_m_page_cache:
 	kmem_cache_destroy(hpb->m_page_cache);
 release_req_cache:
@@ -1431,7 +1916,7 @@ release_req_cache:
 }
 
 static struct ufshpb_lu *
-ufshpb_alloc_hpb_lu(struct ufs_hba *hba, int lun,
+ufshpb_alloc_hpb_lu(struct ufs_hba *hba, struct scsi_device *sdev,
 		    struct ufshpb_dev_info *hpb_dev_info,
 		    struct ufshpb_lu_info *hpb_lu_info)
 {
@@ -1442,7 +1927,8 @@ ufshpb_alloc_hpb_lu(struct ufs_hba *hba, int lun,
 	if (!hpb)
 		return NULL;
 
-	hpb->lun = lun;
+	hpb->lun = sdev->lun;
+	hpb->sdev_ufs_lu = sdev;
 
 	ufshpb_lu_parameter_init(hba, hpb, hpb_dev_info, hpb_lu_info);
 
@@ -1452,6 +1938,7 @@ ufshpb_alloc_hpb_lu(struct ufs_hba *hba, int lun,
 		goto release_hpb;
 	}
 
+	sdev->hostdata = hpb;
 	return hpb;
 
 release_hpb:
@@ -1654,6 +2141,7 @@ void ufshpb_destroy_lu(struct ufs_hba *hba, struct scsi_device *sdev)
 
 	ufshpb_cancel_jobs(hpb);
 
+	ufshpb_pre_req_mempool_destroy(hpb);
 	ufshpb_destroy_region_tbl(hpb);
 
 	kmem_cache_destroy(hpb->map_req_cache);
@@ -1693,6 +2181,7 @@ static void ufshpb_hpb_lu_prepared(struct ufs_hba *hba)
 			ufshpb_set_state(hpb, HPB_PRESENT);
 			if ((hpb->lu_pinned_end - hpb->lu_pinned_start) > 0)
 				queue_work(ufshpb_wq, &hpb->map_work);
+			ufshpb_issue_umap_all_req(hpb);
 		} else {
 			dev_err(hba->dev, "destroy HPB lu %d\n", hpb->lun);
 			ufshpb_destroy_lu(hba, sdev);
@@ -1717,7 +2206,7 @@ void ufshpb_init_hpb_lu(struct ufs_hba *hba, struct scsi_device *sdev)
 	if (ret)
 		goto out;
 
-	hpb = ufshpb_alloc_hpb_lu(hba, lun, &hba->ufshpb_dev,
+	hpb = ufshpb_alloc_hpb_lu(hba, sdev, &hba->ufshpb_dev,
 				  &hpb_lu_info);
 	if (!hpb)
 		goto out;
@@ -1725,9 +2214,6 @@ void ufshpb_init_hpb_lu(struct ufs_hba *hba, struct scsi_device *sdev)
 	tot_active_srgn_pages += hpb_lu_info.max_active_rgns *
 			hpb->srgns_per_rgn * hpb->pages_per_srgn;
 
-	hpb->sdev_ufs_lu = sdev;
-	sdev->hostdata = hpb;
-
 out:
 	/* All LUs are initialized */
 	if (atomic_dec_and_test(&hba->ufshpb_dev.slave_conf_cnt))
@@ -1814,8 +2300,9 @@ void ufshpb_get_geo_info(struct ufs_hba *hba, u8 *geo_buf)
 void ufshpb_get_dev_info(struct ufs_hba *hba, u8 *desc_buf)
 {
 	struct ufshpb_dev_info *hpb_dev_info = &hba->ufshpb_dev;
-	int version;
+	int version, ret;
 	u8 hpb_mode;
+	u32 max_hpb_single_cmd = HPB_MULTI_CHUNK_LOW;
 
 	hpb_mode = desc_buf[DEVICE_DESC_PARAM_HPB_CONTROL];
 	if (hpb_mode == HPB_HOST_CONTROL) {
@@ -1826,13 +2313,27 @@ void ufshpb_get_dev_info(struct ufs_hba *hba, u8 *desc_buf)
 	}
 
 	version = get_unaligned_be16(desc_buf + DEVICE_DESC_PARAM_HPB_VER);
-	if (version != HPB_SUPPORT_VERSION) {
+	if ((version != HPB_SUPPORT_VERSION) &&
+	    (version != HPB_SUPPORT_LEGACY_VERSION)) {
 		dev_err(hba->dev, "%s: HPB %x version is not supported.\n",
 			__func__, version);
 		hpb_dev_info->hpb_disabled = true;
 		return;
 	}
 
+	if (version == HPB_SUPPORT_LEGACY_VERSION)
+		hpb_dev_info->is_legacy = true;
+
+	pm_runtime_get_sync(hba->dev);
+	ret = ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_READ_ATTR,
+		QUERY_ATTR_IDN_MAX_HPB_SINGLE_CMD, 0, 0, &max_hpb_single_cmd);
+	pm_runtime_put_sync(hba->dev);
+
+	if (ret)
+		dev_err(hba->dev, "%s: idn: read max size of single hpb cmd query request failed",
+			__func__);
+	hpb_dev_info->max_hpb_single_cmd = max_hpb_single_cmd;
+
 	/*
 	 * Get the number of user logical unit to check whether all
 	 * scsi_device finish initialization