[PATCH 2/2] mmc: core: Support packed command for eMMC4.5 device

[Seungwon Jeon]

This patch supports packed command of eMMC4.5 device.
Several reads(or writes) can be grouped in packed command
and all data of the individual commands can be sent in a
single transfer on the bus.

Signed-off-by: Seungwon Jeon <tgih.jun@xxxxxxxxxxx>
---
 drivers/mmc/card/block.c |  355 ++++++++++++++++++++++++++++++++++++++++++++--
 drivers/mmc/card/queue.c |   48 ++++++-
 drivers/mmc/card/queue.h |   12 ++
 include/linux/mmc/core.h |    3 +
 4 files changed, 404 insertions(+), 14 deletions(-)

diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index a1cb21f..6c49656 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -59,6 +59,13 @@ MODULE_ALIAS("mmc:block");
 #define INAND_CMD38_ARG_SECTRIM1 0x81
 #define INAND_CMD38_ARG_SECTRIM2 0x88

+#define mmc_req_rel_wr(req)	(((req->cmd_flags & REQ_FUA) || \
+			(req->cmd_flags & REQ_META)) && \
+			(rq_data_dir(req) == WRITE))
+#define PACKED_CMD_VER		0x01
+#define PACKED_CMD_RD		0x01
+#define PACKED_CMD_WR		0x02
+
 static DEFINE_MUTEX(block_mutex);

 /*
@@ -943,7 +950,8 @@ static int mmc_blk_err_check(struct mmc_card *card,
 	 * kind.  If it was a write, we may have transitioned to
 	 * program mode, which we have to wait for it to complete.
 	 */
-	if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ) {
+	if ((!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ) ||
+			(mq_mrq->packed_cmd == MMC_PACKED_WR_HDR)) {
 		u32 status;
 		do {
 			int err = get_card_status(card, &status, 5);
@@ -980,12 +988,67 @@ static int mmc_blk_err_check(struct mmc_card *card,
 	if (!brq->data.bytes_xfered)
 		return MMC_BLK_RETRY;

+	if (mq_mrq->packed_cmd != MMC_PACKED_NONE) {
+		if (unlikely(brq->data.blocks << 9 != brq->data.bytes_xfered))
+			return MMC_BLK_PARTIAL;
+		else
+			return MMC_BLK_SUCCESS;
+	}
+
 	if (blk_rq_bytes(req) != brq->data.bytes_xfered)
 		return MMC_BLK_PARTIAL;

 	return MMC_BLK_SUCCESS;
 }

+static int mmc_blk_packed_err_check(struct mmc_card *card,
+			     struct mmc_async_req *areq)
+{
+	struct mmc_queue_req *mq_mrq = container_of(areq, struct mmc_queue_req,
+						    mmc_active);
+	int err, check, status;
+	u8 ext_csd[512];
+
+	check = mmc_blk_err_check(card, areq);
+
+	if (check == MMC_BLK_SUCCESS)
+		return check;
+
+	if (check == MMC_BLK_PARTIAL) {
+		err = get_card_status(card, &status, 0);
+		if (err)
+			return MMC_BLK_ABORT;
+
+		if (status & R1_EXP_EVENT) {
+			err = mmc_send_ext_csd(card, ext_csd);
+			if (err)
+				return MMC_BLK_ABORT;
+
+			if ((ext_csd[EXT_CSD_EXP_EVENTS_STATUS + 0] &
+						EXT_CSD_PACKED_FAILURE) &&
+					(ext_csd[EXT_CSD_PACKED_CMD_STATUS] &
+					 EXT_CSD_PACKED_GENERIC_ERROR)) {
+				if (ext_csd[EXT_CSD_PACKED_CMD_STATUS] &
+						EXT_CSD_PACKED_INDEXED_ERROR) {
+					/* Make be 0-based */
+					mq_mrq->packed_fail_idx =
+						ext_csd[EXT_CSD_PACKED_FAILURE_INDEX] - 1;
+					return MMC_BLK_PARTIAL;
+				} else {
+					return MMC_BLK_RETRY;
+				}
+			}
+		} else {
+			return MMC_BLK_RETRY;
+		}
+	}
+
+	if (check != MMC_BLK_ABORT)
+		return MMC_BLK_RETRY;
+	else
+		return MMC_BLK_ABORT;
+}
+
 static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 			       struct mmc_card *card,
 			       int disable_multi,
@@ -1129,6 +1192,211 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 	mmc_queue_bounce_pre(mqrq);
 }

+static u8 mmc_blk_chk_packable(struct mmc_queue *mq, struct request *req)
+{
+	struct request_queue *q = mq->queue;
+	struct mmc_card *card = mq->card;
+	struct request *cur = req, *next = NULL;
+	struct mmc_blk_data *md = mq->data;
+	bool en_rel_wr = card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN;
+	unsigned int req_sectors = 0, phys_segments = 0;
+	unsigned int max_blk_count, max_phys_segs;
+	u8 max_packed_rw = 0;
+	u8 reqs = 0;
+
+	if (!(md->flags & MMC_BLK_CMD23) &&
+			!card->ext_csd.packed_event_en)
+		goto no_packed;
+
+	if (rq_data_dir(cur) == READ)
+		max_packed_rw = card->ext_csd.max_packed_reads;
+	else
+		max_packed_rw = card->ext_csd.max_packed_writes;
+
+	if (max_packed_rw == 0)
+		goto no_packed;
+
+	if (mmc_req_rel_wr(cur) &&
+			(md->flags & MMC_BLK_REL_WR) &&
+			!en_rel_wr) {
+		goto no_packed;
+	}
+
+	max_blk_count = min(card->host->max_blk_count,
+			card->host->max_req_size >> 9);
+	if (unlikely(max_blk_count > 0xffff))
+		max_blk_count = 0xffff;
+
+	max_phys_segs = queue_max_segments(q);
+	req_sectors += blk_rq_sectors(cur);
+	phys_segments += req->nr_phys_segments;
+
+	if (rq_data_dir(cur) == WRITE) {
+		req_sectors++;
+		phys_segments++;
+	}
+
+	while (reqs < max_packed_rw - 1) {
+		next = blk_fetch_request(q);
+		if (!next)
+			break;
+
+		if (rq_data_dir(cur) != rq_data_dir(next)) {
+			blk_requeue_request(q, next);
+			break;
+		}
+
+		if (mmc_req_rel_wr(next) &&
+				(md->flags & MMC_BLK_REL_WR) &&
+				!en_rel_wr) {
+			blk_requeue_request(q, next);
+			break;
+		}
+
+		req_sectors += blk_rq_sectors(next);
+		if (req_sectors > max_blk_count) {
+			blk_requeue_request(q, next);
+			break;
+		}
+
+		phys_segments +=  next->nr_phys_segments;
+		if (phys_segments > max_phys_segs) {
+			blk_requeue_request(q, next);
+			break;
+		}
+
+		list_add_tail(&next->queuelist, &mq->mqrq_cur->packed_list);
+		cur = next;
+		reqs++;
+	}
+
+	if (reqs > 0) {
+		list_add(&req->queuelist, &mq->mqrq_cur->packed_list);
+		return (reqs + 1);
+	}
+
+no_packed:
+	mq->mqrq_cur->packed_cmd = MMC_PACKED_NONE;
+	return reqs;
+}
+
+static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq,
+			       struct mmc_card *card,
+			       struct mmc_queue *mq,
+			       u8 reqs)
+{
+	struct mmc_blk_request *brq = &mqrq->brq;
+	struct request *req = mqrq->req;
+	struct request *prq;
+	struct mmc_blk_data *md = mq->data;
+	bool do_rel_wr;
+	u32 *packed_cmd_hdr = mqrq->packed_cmd_hdr;
+	u8 i =1;
+
+	mqrq->packed_cmd = (rq_data_dir(req) == READ) ?
+		MMC_PACKED_WR_HDR : MMC_PACKED_WRITE;
+	mqrq->packed_blocks = 0;
+	mqrq->packed_fail_idx = -1;
+
+	memset(packed_cmd_hdr, 0, sizeof(mqrq->packed_cmd_hdr));
+	packed_cmd_hdr[0] = (reqs << 16) |
+		(((rq_data_dir(req) == READ) ? PACKED_CMD_RD: PACKED_CMD_WR) << 8) |
+		PACKED_CMD_VER;
+
+	/*
+	 * Argument for each entry of packed group
+	 */
+	list_for_each_entry(prq, &mqrq->packed_list, queuelist) {
+		do_rel_wr = mmc_req_rel_wr(prq) && (md->flags & MMC_BLK_REL_WR);
+		/* Argument of CMD23*/
+		packed_cmd_hdr[(i * 2)] = (do_rel_wr ? MMC_CMD23_ARG_REL_WR : 0) |
+			blk_rq_sectors(prq);
+		/* Argument of CMD18 or CMD25 */
+		packed_cmd_hdr[((i * 2)) + 1] = mmc_card_blockaddr(card) ?
+			blk_rq_pos(prq) : blk_rq_pos(prq) << 9;
+		mqrq->packed_blocks += blk_rq_sectors(prq);
+		i++;
+	}
+
+	memset(brq, 0, sizeof(struct mmc_blk_request));
+	brq->mrq.cmd = &brq->cmd;
+	brq->mrq.data = &brq->data;
+	brq->mrq.sbc = &brq->sbc;
+	brq->mrq.stop = &brq->stop;
+
+	brq->sbc.opcode = MMC_SET_BLOCK_COUNT;
+	brq->sbc.arg = MMC_CMD23_ARG_PACKED |
+		((rq_data_dir(req) == READ) ? 1 : mqrq->packed_blocks + 1);
+	brq->sbc.flags = MMC_RSP_R1 | MMC_CMD_AC;
+
+	brq->cmd.opcode = MMC_WRITE_MULTIPLE_BLOCK;
+	brq->cmd.arg = blk_rq_pos(req);
+	if (!mmc_card_blockaddr(card))
+		brq->cmd.arg <<= 9;
+	brq->cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_ADTC;
+
+	brq->data.blksz = 512;
+	/*
+	 * Write separately the packd command header only for packed read.
+	 * In case of packed write, header is sent with blocks of data.
+	 */
+	brq->data.blocks = (rq_data_dir(req) == READ) ?
+		1 : mqrq->packed_blocks + 1;
+	brq->data.flags |= MMC_DATA_WRITE;
+
+	brq->stop.opcode = MMC_STOP_TRANSMISSION;
+	brq->stop.arg = 0;
+	brq->stop.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC;
+
+	mmc_set_data_timeout(&brq->data, card);
+
+	brq->data.sg = mqrq->sg;
+	brq->data.sg_len = mmc_queue_map_sg(mq, mqrq);
+
+	mqrq->mmc_active.mrq = &brq->mrq;
+	mqrq->mmc_active.err_check = mmc_blk_packed_err_check;
+
+	mmc_queue_bounce_pre(mqrq);
+}
+
+static void mmc_blk_packed_rrq_prep(struct mmc_queue_req *mqrq,
+			       struct mmc_card *card,
+			       struct mmc_queue *mq)
+{
+	struct mmc_blk_request *brq = &mqrq->brq;
+	struct request *req = mqrq->req;
+
+	mqrq->packed_cmd = MMC_PACKED_READ;
+
+	memset(brq, 0, sizeof(struct mmc_blk_request));
+	brq->mrq.cmd = &brq->cmd;
+	brq->mrq.data = &brq->data;
+	brq->mrq.stop = &brq->stop;
+
+	brq->cmd.opcode = MMC_READ_MULTIPLE_BLOCK;
+	brq->cmd.arg = blk_rq_pos(req);
+	if (!mmc_card_blockaddr(card))
+		brq->cmd.arg <<= 9;
+	brq->cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_ADTC;
+	brq->data.blksz = 512;
+	brq->data.blocks = mqrq->packed_blocks;
+	brq->data.flags |= MMC_DATA_READ;
+
+	brq->stop.opcode = MMC_STOP_TRANSMISSION;
+	brq->stop.arg = 0;
+	brq->stop.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC;
+
+	mmc_set_data_timeout(&brq->data, card);
+
+	brq->data.sg = mqrq->sg;
+	brq->data.sg_len = mmc_queue_map_sg(mq, mqrq);
+
+	mqrq->mmc_active.mrq = &brq->mrq;
+	mqrq->mmc_active.err_check = mmc_blk_packed_err_check;
+
+	mmc_queue_bounce_pre(mqrq);
+}
+
 static int mmc_blk_cmd_err(struct mmc_blk_data *md, struct mmc_card *card,
 			   struct mmc_blk_request *brq, struct request *req,
 			   int ret)
@@ -1166,15 +1434,33 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 	int ret = 1, disable_multi = 0, retry = 0, type;
 	enum mmc_blk_status status;
 	struct mmc_queue_req *mq_rq;
-	struct request *req;
+	struct request *req, *prq;
 	struct mmc_async_req *areq;
+	u8 reqs = 0;

 	if (!rqc && !mq->mqrq_prev->req)
 		return 0;

+	if (rqc)
+		reqs = mmc_blk_chk_packable(mq, rqc);
+
 	do {
 		if (rqc) {
-			mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq);
+			if (reqs >= 2) {
+				mmc_blk_packed_hdr_wrq_prep(mq->mqrq_cur, card, mq, reqs);
+				if (rq_data_dir(rqc) == READ) {
+					areq = &mq->mqrq_cur->mmc_active;
+					mmc_wait_for_req(card->host, areq->mrq);
+					status = mmc_blk_packed_err_check(card, areq);
+					if (status == MMC_BLK_SUCCESS) {
+						mmc_blk_packed_rrq_prep(mq->mqrq_cur, card, mq);
+					} else {
+						goto check_status;
+					}
+				}
+			} else {
+				mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq);
+			}
 			areq = &mq->mqrq_cur->mmc_active;
 		} else
 			areq = NULL;
@@ -1182,6 +1468,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 		if (!areq)
 			return 0;

+check_status:
 		mq_rq = container_of(areq, struct mmc_queue_req, mmc_active);
 		brq = &mq_rq->brq;
 		req = mq_rq->req;
@@ -1195,10 +1482,32 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 			 * A block was successfully transferred.
 			 */
 			mmc_blk_reset_success(md, type);
-			spin_lock_irq(&md->lock);
-			ret = __blk_end_request(req, 0,
+
+			if (mq_rq->packed_cmd != MMC_PACKED_NONE) {
+				int idx = mq_rq->packed_fail_idx, i = 0;
+				while (!list_empty(&mq_rq->packed_list)) {
+					prq = list_entry_rq(mq_rq->packed_list.next);
+					if (idx == i) {
+						/* retry from error index */
+						reqs -= idx;
+						mq_rq->req = prq;
+						ret = 1;
+						break;
+					}
+					list_del_init(&prq->queuelist);
+					spin_lock_irq(&md->lock);
+					ret = __blk_end_request(prq, 0, blk_rq_bytes(prq));
+					spin_unlock_irq(&md->lock);
+					i++;
+				}
+				break;
+			} else {
+				spin_lock_irq(&md->lock);
+				ret = __blk_end_request(req, 0,
 						brq->data.bytes_xfered);
-			spin_unlock_irq(&md->lock);
+				spin_unlock_irq(&md->lock);
+			}
+
 			/*
 			 * If the blk_end_request function returns non-zero even
 			 * though all data has been transferred and no errors
@@ -1257,7 +1566,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 			break;
 		}

-		if (ret) {
+		if (ret && (mq_rq->packed_cmd == MMC_PACKED_NONE)) {
 			/*
 			 * In case of a incomplete request
 			 * prepare it again and resend.
@@ -1270,13 +1579,37 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 	return 1;

  cmd_abort:
-	spin_lock_irq(&md->lock);
-	while (ret)
-		ret = __blk_end_request(req, -EIO, blk_rq_cur_bytes(req));
-	spin_unlock_irq(&md->lock);
+	if (mq_rq->packed_cmd != MMC_PACKED_NONE) {
+		spin_lock_irq(&md->lock);
+		while (ret)
+			ret = __blk_end_request(req, -EIO, blk_rq_cur_bytes(req));
+		spin_unlock_irq(&md->lock);
+	} else {
+		while (!list_empty(&mq_rq->packed_list)) {
+			prq = list_entry_rq(mq_rq->packed_list.next);
+			list_del_init(&prq->queuelist);
+			spin_lock_irq(&md->lock);
+			__blk_end_request(prq, -EIO, blk_rq_bytes(prq));
+			spin_unlock_irq(&md->lock);
+		}
+	}

  start_new_req:
 	if (rqc) {
+		/*
+		 * If current request is packed, it need to put back.
+		 */
+		if (mq->mqrq_cur->packed_cmd != MMC_PACKED_NONE) {
+			while (!list_empty(&mq->mqrq_cur->packed_list)) {
+				prq = list_entry_rq(mq->mqrq_cur->packed_list.prev);
+				if (prq->queuelist.prev != &mq->mqrq_cur->packed_list) {
+					list_del_init(&prq->queuelist);
+					blk_requeue_request(mq->queue, prq);
+				} else {
+					list_del_init(&prq->queuelist);
+				}
+			}
+		}
 		mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq);
 		mmc_start_req(card->host, &mq->mqrq_cur->mmc_active, NULL);
 	}
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index dcad59c..3a4542e 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -172,6 +172,8 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,

 	memset(&mq->mqrq_cur, 0, sizeof(mq->mqrq_cur));
 	memset(&mq->mqrq_prev, 0, sizeof(mq->mqrq_prev));
+	INIT_LIST_HEAD(&mqrq_cur->packed_list);
+	INIT_LIST_HEAD(&mqrq_prev->packed_list);
 	mq->mqrq_cur = mqrq_cur;
 	mq->mqrq_prev = mqrq_prev;
 	mq->queue->queuedata = mq;
@@ -372,6 +374,39 @@ void mmc_queue_resume(struct mmc_queue *mq)
 	}
 }

+static unsigned int mmc_queue_packed_map_sg(struct mmc_queue *mq,
+				struct mmc_queue_req *mqrq,
+				struct scatterlist *sg)
+{
+	struct scatterlist *__sg;
+	unsigned int sg_len = 0;
+	struct request *req;
+	enum mmc_packed_cmd cmd;
+
+	cmd = mqrq->packed_cmd;
+
+	if (cmd == MMC_PACKED_WR_HDR || cmd == MMC_PACKED_WRITE) {
+		__sg =sg;
+		sg_set_buf(__sg, mqrq->packed_cmd_hdr,
+				sizeof(mqrq->packed_cmd_hdr));
+		sg_len++;
+		if (cmd == MMC_PACKED_WR_HDR) {
+			sg_mark_end(__sg);
+			return sg_len;
+		}
+		__sg->page_link &= ~0x02;
+	}
+
+	__sg = sg + sg_len;
+	list_for_each_entry(req, &mqrq->packed_list, queuelist) {
+		sg_len += blk_rq_map_sg(mq->queue, req, __sg);
+		__sg = sg + (sg_len - 1);
+		(__sg++)->page_link &= ~0x02;
+	}
+	sg_mark_end(sg + (sg_len - 1));
+	return sg_len;
+}
+
 /*
  * Prepare the sg list(s) to be handed of to the host driver
  */
@@ -382,12 +417,19 @@ unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq)
 	struct scatterlist *sg;
 	int i;

-	if (!mqrq->bounce_buf)
-		return blk_rq_map_sg(mq->queue, mqrq->req, mqrq->sg);
+	if (!mqrq->bounce_buf) {
+		if (!list_empty(&mqrq->packed_list))
+			return mmc_queue_packed_map_sg(mq, mqrq, mqrq->sg);
+		else
+			return blk_rq_map_sg(mq->queue, mqrq->req, mqrq->sg);
+	}

 	BUG_ON(!mqrq->bounce_sg);

-	sg_len = blk_rq_map_sg(mq->queue, mqrq->req, mqrq->bounce_sg);
+	if (!list_empty(&mqrq->packed_list))
+		sg_len = mmc_queue_packed_map_sg(mq, mqrq, mqrq->bounce_sg);
+	else
+		sg_len = blk_rq_map_sg(mq->queue, mqrq->req, mqrq->bounce_sg);

 	mqrq->bounce_sg_len = sg_len;

diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index d2a1eb4..5d0131e 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -12,6 +12,13 @@ struct mmc_blk_request {
 	struct mmc_data		data;
 };

+enum mmc_packed_cmd {
+	MMC_PACKED_NONE = 0,
+	MMC_PACKED_WR_HDR,
+	MMC_PACKED_WRITE,
+	MMC_PACKED_READ,
+};
+
 struct mmc_queue_req {
 	struct request		*req;
 	struct mmc_blk_request	brq;
@@ -20,6 +27,11 @@ struct mmc_queue_req {
 	struct scatterlist	*bounce_sg;
 	unsigned int		bounce_sg_len;
 	struct mmc_async_req	mmc_active;
+	struct list_head	packed_list;
+	u32			packed_cmd_hdr[128];
+	unsigned int		packed_blocks;
+	enum mmc_packed_cmd	packed_cmd;
+	int		packed_fail_idx;
 };

 struct mmc_queue {
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index 174a844..3c61d5a 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -18,6 +18,8 @@ struct mmc_request;
 struct mmc_command {
 	u32			opcode;
 	u32			arg;
+#define MMC_CMD23_ARG_REL_WR	(1 << 31)
+#define MMC_CMD23_ARG_PACKED	((0 << 31) | (1 << 30))
 	u32			resp[4];
 	unsigned int		flags;		/* expected response type */
 #define MMC_RSP_PRESENT	(1 << 0)
@@ -143,6 +145,7 @@ extern int mmc_app_cmd(struct mmc_host *, struct mmc_card *);
 extern int mmc_wait_for_app_cmd(struct mmc_host *, struct mmc_card *,
 	struct mmc_command *, int);
 extern int mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int);
+extern int mmc_send_ext_csd(struct mmc_card *card, u8 *ext_csd);

 #define MMC_ERASE_ARG		0x00000000
 #define MMC_SECURE_ERASE_ARG	0x80000000
--
1.7.0.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/