4 files changed, 1112 insertions, 317 deletions

diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index f85e42224559..1ff5486213fb 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -106,6 +106,16 @@ struct mmc_blk_data {
 
 static DEFINE_MUTEX(open_lock);
 
+enum mmc_blk_status {
+	MMC_BLK_SUCCESS = 0,
+	MMC_BLK_PARTIAL,
+	MMC_BLK_RETRY,
+	MMC_BLK_RETRY_SINGLE,
+	MMC_BLK_DATA_ERR,
+	MMC_BLK_CMD_ERR,
+	MMC_BLK_ABORT,
+};
+
 module_param(perdev_minors, int, 0444);
 MODULE_PARM_DESC(perdev_minors, "Minors numbers to allocate per device");
 
@@ -427,14 +437,6 @@ static const struct block_device_operations mmc_bdops = {
 #endif
 };
 
-struct mmc_blk_request {
-	struct mmc_request	mrq;
-	struct mmc_command	sbc;
-	struct mmc_command	cmd;
-	struct mmc_command	stop;
-	struct mmc_data		data;
-};
-
 static inline int mmc_blk_part_switch(struct mmc_card *card,
 				      struct mmc_blk_data *md)
 {
@@ -525,7 +527,20 @@ static u32 mmc_sd_num_wr_blocks(struct mmc_card *card)
 	return result;
 }
 
-static u32 get_card_status(struct mmc_card *card, struct request *req)
+static int send_stop(struct mmc_card *card, u32 *status)
+{
+	struct mmc_command cmd = {0};
+	int err;
+
+	cmd.opcode = MMC_STOP_TRANSMISSION;
+	cmd.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC;
+	err = mmc_wait_for_cmd(card->host, &cmd, 5);
+	if (err == 0)
+		*status = cmd.resp[0];
+	return err;
+}
+
+static int get_card_status(struct mmc_card *card, u32 *status, int retries)
 {
 	struct mmc_command cmd = {0};
 	int err;
@@ -534,11 +549,141 @@ static u32 get_card_status(struct mmc_card *card, struct request *req)
 	if (!mmc_host_is_spi(card->host))
 		cmd.arg = card->rca << 16;
 	cmd.flags = MMC_RSP_SPI_R2 | MMC_RSP_R1 | MMC_CMD_AC;
-	err = mmc_wait_for_cmd(card->host, &cmd, 0);
+	err = mmc_wait_for_cmd(card->host, &cmd, retries);
+	if (err == 0)
+		*status = cmd.resp[0];
+	return err;
+}
+
+#define ERR_RETRY	2
+#define ERR_ABORT	1
+#define ERR_CONTINUE	0
+
+static int mmc_blk_cmd_error(struct request *req, const char *name, int error,
+	bool status_valid, u32 status)
+{
+	switch (error) {
+	case -EILSEQ:
+		/* response crc error, retry the r/w cmd */
+		pr_err("%s: %s sending %s command, card status %#x\n",
+			req->rq_disk->disk_name, "response CRC error",
+			name, status);
+		return ERR_RETRY;
+
+	case -ETIMEDOUT:
+		pr_err("%s: %s sending %s command, card status %#x\n",
+			req->rq_disk->disk_name, "timed out", name, status);
+
+		/* If the status cmd initially failed, retry the r/w cmd */
+		if (!status_valid)
+			return ERR_RETRY;
+
+		/*
+		 * If it was a r/w cmd crc error, or illegal command
+		 * (eg, issued in wrong state) then retry - we should
+		 * have corrected the state problem above.
+		 */
+		if (status & (R1_COM_CRC_ERROR | R1_ILLEGAL_COMMAND))
+			return ERR_RETRY;
+
+		/* Otherwise abort the command */
+		return ERR_ABORT;
+
+	default:
+		/* We don't understand the error code the driver gave us */
+		pr_err("%s: unknown error %d sending read/write command, card status %#x\n",
+		       req->rq_disk->disk_name, error, status);
+		return ERR_ABORT;
+	}
+}
+
+/*
+ * Initial r/w and stop cmd error recovery.
+ * We don't know whether the card received the r/w cmd or not, so try to
+ * restore things back to a sane state.  Essentially, we do this as follows:
+ * - Obtain card status.  If the first attempt to obtain card status fails,
+ *   the status word will reflect the failed status cmd, not the failed
+ *   r/w cmd.  If we fail to obtain card status, it suggests we can no
+ *   longer communicate with the card.
+ * - Check the card state.  If the card received the cmd but there was a
+ *   transient problem with the response, it might still be in a data transfer
+ *   mode.  Try to send it a stop command.  If this fails, we can't recover.
+ * - If the r/w cmd failed due to a response CRC error, it was probably
+ *   transient, so retry the cmd.
+ * - If the r/w cmd timed out, but we didn't get the r/w cmd status, retry.
+ * - If the r/w cmd timed out, and the r/w cmd failed due to CRC error or
+ *   illegal cmd, retry.
+ * Otherwise we don't understand what happened, so abort.
+ */
+static int mmc_blk_cmd_recovery(struct mmc_card *card, struct request *req,
+	struct mmc_blk_request *brq)
+{
+	bool prev_cmd_status_valid = true;
+	u32 status, stop_status = 0;
+	int err, retry;
+
+	/*
+	 * Try to get card status which indicates both the card state
+	 * and why there was no response.  If the first attempt fails,
+	 * we can't be sure the returned status is for the r/w command.
+	 */
+	for (retry = 2; retry >= 0; retry--) {
+		err = get_card_status(card, &status, 0);
+		if (!err)
+			break;
+
+		prev_cmd_status_valid = false;
+		pr_err("%s: error %d sending status command, %sing\n",
+		       req->rq_disk->disk_name, err, retry ? "retry" : "abort");
+	}
+
+	/* We couldn't get a response from the card.  Give up. */
 	if (err)
-		printk(KERN_ERR "%s: error %d sending status command",
-		       req->rq_disk->disk_name, err);
-	return cmd.resp[0];
+		return ERR_ABORT;
+
+	/*
+	 * Check the current card state.  If it is in some data transfer
+	 * mode, tell it to stop (and hopefully transition back to TRAN.)
+	 */
+	if (R1_CURRENT_STATE(status) == R1_STATE_DATA ||
+	    R1_CURRENT_STATE(status) == R1_STATE_RCV) {
+		err = send_stop(card, &stop_status);
+		if (err)
+			pr_err("%s: error %d sending stop command\n",
+			       req->rq_disk->disk_name, err);
+
+		/*
+		 * If the stop cmd also timed out, the card is probably
+		 * not present, so abort.  Other errors are bad news too.
+		 */
+		if (err)
+			return ERR_ABORT;
+	}
+
+	/* Check for set block count errors */
+	if (brq->sbc.error)
+		return mmc_blk_cmd_error(req, "SET_BLOCK_COUNT", brq->sbc.error,
+				prev_cmd_status_valid, status);
+
+	/* Check for r/w command errors */
+	if (brq->cmd.error)
+		return mmc_blk_cmd_error(req, "r/w cmd", brq->cmd.error,
+				prev_cmd_status_valid, status);
+
+	/* Now for stop errors.  These aren't fatal to the transfer. */
+	pr_err("%s: error %d sending stop command, original cmd response %#x, card status %#x\n",
+	       req->rq_disk->disk_name, brq->stop.error,
+	       brq->cmd.resp[0], status);
+
+	/*
+	 * Subsitute in our own stop status as this will give the error
+	 * state which happened during the execution of the r/w command.
+	 */
+	if (stop_status) {
+		brq->stop.resp[0] = stop_status;
+		brq->stop.error = 0;
+	}
+	return ERR_CONTINUE;
 }
 
 static int mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req)
@@ -669,240 +814,324 @@ static inline void mmc_apply_rel_rw(struct mmc_blk_request *brq,
 	}
 }
 
-static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req)
+#define CMD_ERRORS							\
+	(R1_OUT_OF_RANGE |	/* Command argument out of range */	\
+	 R1_ADDRESS_ERROR |	/* Misaligned address */		\
+	 R1_BLOCK_LEN_ERROR |	/* Transferred block length incorrect */\
+	 R1_WP_VIOLATION |	/* Tried to write to protected block */	\
+	 R1_CC_ERROR |		/* Card controller error */		\
+	 R1_ERROR)		/* General/unknown error */
+
+static int mmc_blk_err_check(struct mmc_card *card,
+			     struct mmc_async_req *areq)
 {
-	struct mmc_blk_data *md = mq->data;
-	struct mmc_card *card = md->queue.card;
-	struct mmc_blk_request brq;
-	int ret = 1, disable_multi = 0;
+	enum mmc_blk_status ret = MMC_BLK_SUCCESS;
+	struct mmc_queue_req *mq_mrq = container_of(areq, struct mmc_queue_req,
+						    mmc_active);
+	struct mmc_blk_request *brq = &mq_mrq->brq;
+	struct request *req = mq_mrq->req;
 
 	/*
-	 * Reliable writes are used to implement Forced Unit Access and
-	 * REQ_META accesses, and are supported only on MMCs.
+	 * sbc.error indicates a problem with the set block count
+	 * command.  No data will have been transferred.
+	 *
+	 * cmd.error indicates a problem with the r/w command.  No
+	 * data will have been transferred.
+	 *
+	 * stop.error indicates a problem with the stop command.  Data
+	 * may have been transferred, or may still be transferring.
 	 */
-	bool do_rel_wr = ((req->cmd_flags & REQ_FUA) ||
-			  (req->cmd_flags & REQ_META)) &&
-		(rq_data_dir(req) == WRITE) &&
-		(md->flags & MMC_BLK_REL_WR);
+	if (brq->sbc.error || brq->cmd.error || brq->stop.error) {
+		switch (mmc_blk_cmd_recovery(card, req, brq)) {
+		case ERR_RETRY:
+			return MMC_BLK_RETRY;
+		case ERR_ABORT:
+			return MMC_BLK_ABORT;
+		case ERR_CONTINUE:
+			break;
+		}
+	}
 
-	do {
-		struct mmc_command cmd = {0};
-		u32 readcmd, writecmd, status = 0;
-
-		memset(&brq, 0, sizeof(struct mmc_blk_request));
-		brq.mrq.cmd = &brq.cmd;
-		brq.mrq.data = &brq.data;
-
-		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.stop.opcode = MMC_STOP_TRANSMISSION;
-		brq.stop.arg = 0;
-		brq.stop.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC;
-		brq.data.blocks = blk_rq_sectors(req);
+	/*
+	 * Check for errors relating to the execution of the
+	 * initial command - such as address errors.  No data
+	 * has been transferred.
+	 */
+	if (brq->cmd.resp[0] & CMD_ERRORS) {
+		pr_err("%s: r/w command failed, status = %#x\n",
+		       req->rq_disk->disk_name, brq->cmd.resp[0]);
+		return MMC_BLK_ABORT;
+	}
 
-		/*
-		 * The block layer doesn't support all sector count
-		 * restrictions, so we need to be prepared for too big
-		 * requests.
-		 */
-		if (brq.data.blocks > card->host->max_blk_count)
-			brq.data.blocks = card->host->max_blk_count;
+	/*
+	 * Everything else is either success, or a data error of some
+	 * 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) {
+		u32 status;
+		do {
+			int err = get_card_status(card, &status, 5);
+			if (err) {
+				printk(KERN_ERR "%s: error %d requesting status\n",
+				       req->rq_disk->disk_name, err);
+				return MMC_BLK_CMD_ERR;
+			}
+			/*
+			 * Some cards mishandle the status bits,
+			 * so make sure to check both the busy
+			 * indication and the card state.
+			 */
+		} while (!(status & R1_READY_FOR_DATA) ||
+			 (R1_CURRENT_STATE(status) == R1_STATE_PRG));
+	}
 
-		/*
-		 * After a read error, we redo the request one sector at a time
-		 * in order to accurately determine which sectors can be read
-		 * successfully.
-		 */
-		if (disable_multi && brq.data.blocks > 1)
-			brq.data.blocks = 1;
+	if (brq->data.error) {
+		pr_err("%s: error %d transferring data, sector %u, nr %u, cmd response %#x, card status %#x\n",
+		       req->rq_disk->disk_name, brq->data.error,
+		       (unsigned)blk_rq_pos(req),
+		       (unsigned)blk_rq_sectors(req),
+		       brq->cmd.resp[0], brq->stop.resp[0]);
 
-		if (brq.data.blocks > 1 || do_rel_wr) {
-			/* SPI multiblock writes terminate using a special
-			 * token, not a STOP_TRANSMISSION request.
-			 */
-			if (!mmc_host_is_spi(card->host) ||
-			    rq_data_dir(req) == READ)
-				brq.mrq.stop = &brq.stop;
-			readcmd = MMC_READ_MULTIPLE_BLOCK;
-			writecmd = MMC_WRITE_MULTIPLE_BLOCK;
-		} else {
-			brq.mrq.stop = NULL;
-			readcmd = MMC_READ_SINGLE_BLOCK;
-			writecmd = MMC_WRITE_BLOCK;
-		}
 		if (rq_data_dir(req) == READ) {
-			brq.cmd.opcode = readcmd;
-			brq.data.flags |= MMC_DATA_READ;
+			if (brq->data.blocks > 1) {
+				/* Redo read one sector at a time */
+				pr_warning("%s: retrying using single block read\n",
+					   req->rq_disk->disk_name);
+				return MMC_BLK_RETRY_SINGLE;
+			}
+			return MMC_BLK_DATA_ERR;
 		} else {
-			brq.cmd.opcode = writecmd;
-			brq.data.flags |= MMC_DATA_WRITE;
+			return MMC_BLK_CMD_ERR;
 		}
+	}
 
-		if (do_rel_wr)
-			mmc_apply_rel_rw(&brq, card, req);
+	if (ret == MMC_BLK_SUCCESS &&
+	    blk_rq_bytes(req) != brq->data.bytes_xfered)
+		ret = MMC_BLK_PARTIAL;
 
-		/*
-		 * Pre-defined multi-block transfers are preferable to
-		 * open ended-ones (and necessary for reliable writes).
-		 * However, it is not sufficient to just send CMD23,
-		 * and avoid the final CMD12, as on an error condition
-		 * CMD12 (stop) needs to be sent anyway. This, coupled
-		 * with Auto-CMD23 enhancements provided by some
-		 * hosts, means that the complexity of dealing
-		 * with this is best left to the host. If CMD23 is
-		 * supported by card and host, we'll fill sbc in and let
-		 * the host deal with handling it correctly. This means
-		 * that for hosts that don't expose MMC_CAP_CMD23, no
-		 * change of behavior will be observed.
-		 *
-		 * N.B: Some MMC cards experience perf degradation.
-		 * We'll avoid using CMD23-bounded multiblock writes for
-		 * these, while retaining features like reliable writes.
-		 */
+	return ret;
+}
 
-		if ((md->flags & MMC_BLK_CMD23) &&
-		    mmc_op_multi(brq.cmd.opcode) &&
-		    (do_rel_wr || !(card->quirks & MMC_QUIRK_BLK_NO_CMD23))) {
-			brq.sbc.opcode = MMC_SET_BLOCK_COUNT;
-			brq.sbc.arg = brq.data.blocks |
-				(do_rel_wr ? (1 << 31) : 0);
-			brq.sbc.flags = MMC_RSP_R1 | MMC_CMD_AC;
-			brq.mrq.sbc = &brq.sbc;
-		}
+static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
+			       struct mmc_card *card,
+			       int disable_multi,
+			       struct mmc_queue *mq)
+{
+	u32 readcmd, writecmd;
+	struct mmc_blk_request *brq = &mqrq->brq;
+	struct request *req = mqrq->req;
+	struct mmc_blk_data *md = mq->data;
 
-		mmc_set_data_timeout(&brq.data, card);
+	/*
+	 * Reliable writes are used to implement Forced Unit Access and
+	 * REQ_META accesses, and are supported only on MMCs.
+	 */
+	bool do_rel_wr = ((req->cmd_flags & REQ_FUA) ||
+			  (req->cmd_flags & REQ_META)) &&
+		(rq_data_dir(req) == WRITE) &&
+		(md->flags & MMC_BLK_REL_WR);
 
-		brq.data.sg = mq->sg;
-		brq.data.sg_len = mmc_queue_map_sg(mq);
+	memset(brq, 0, sizeof(struct mmc_blk_request));
+	brq->mrq.cmd = &brq->cmd;
+	brq->mrq.data = &brq->data;
 
-		/*
-		 * Adjust the sg list so it is the same size as the
-		 * request.
+	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->stop.opcode = MMC_STOP_TRANSMISSION;
+	brq->stop.arg = 0;
+	brq->stop.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC;
+	brq->data.blocks = blk_rq_sectors(req);
+
+	/*
+	 * The block layer doesn't support all sector count
+	 * restrictions, so we need to be prepared for too big
+	 * requests.
+	 */
+	if (brq->data.blocks > card->host->max_blk_count)
+		brq->data.blocks = card->host->max_blk_count;
+
+	/*
+	 * After a read error, we redo the request one sector at a time
+	 * in order to accurately determine which sectors can be read
+	 * successfully.
+	 */
+	if (disable_multi && brq->data.blocks > 1)
+		brq->data.blocks = 1;
+
+	if (brq->data.blocks > 1 || do_rel_wr) {
+		/* SPI multiblock writes terminate using a special
+		 * token, not a STOP_TRANSMISSION request.
 		 */
-		if (brq.data.blocks != blk_rq_sectors(req)) {
-			int i, data_size = brq.data.blocks << 9;
-			struct scatterlist *sg;
-
-			for_each_sg(brq.data.sg, sg, brq.data.sg_len, i) {
-				data_size -= sg->length;
-				if (data_size <= 0) {
-					sg->length += data_size;
-					i++;
-					break;
-				}
-			}
-			brq.data.sg_len = i;
-		}
+		if (!mmc_host_is_spi(card->host) ||
+		    rq_data_dir(req) == READ)
+			brq->mrq.stop = &brq->stop;
+		readcmd = MMC_READ_MULTIPLE_BLOCK;
+		writecmd = MMC_WRITE_MULTIPLE_BLOCK;
+	} else {
+		brq->mrq.stop = NULL;
+		readcmd = MMC_READ_SINGLE_BLOCK;
+		writecmd = MMC_WRITE_BLOCK;
+	}
+	if (rq_data_dir(req) == READ) {
+		brq->cmd.opcode = readcmd;
+		brq->data.flags |= MMC_DATA_READ;
+	} else {
+		brq->cmd.opcode = writecmd;
+		brq->data.flags |= MMC_DATA_WRITE;
+	}
 
-		mmc_queue_bounce_pre(mq);
+	if (do_rel_wr)
+		mmc_apply_rel_rw(brq, card, req);
 
-		mmc_wait_for_req(card->host, &brq.mrq);
+	/*
+	 * Pre-defined multi-block transfers are preferable to
+	 * open ended-ones (and necessary for reliable writes).
+	 * However, it is not sufficient to just send CMD23,
+	 * and avoid the final CMD12, as on an error condition
+	 * CMD12 (stop) needs to be sent anyway. This, coupled
+	 * with Auto-CMD23 enhancements provided by some
+	 * hosts, means that the complexity of dealing
+	 * with this is best left to the host. If CMD23 is
+	 * supported by card and host, we'll fill sbc in and let
+	 * the host deal with handling it correctly. This means
+	 * that for hosts that don't expose MMC_CAP_CMD23, no
+	 * change of behavior will be observed.
+	 *
+	 * N.B: Some MMC cards experience perf degradation.
+	 * We'll avoid using CMD23-bounded multiblock writes for
+	 * these, while retaining features like reliable writes.
+	 */
 
-		mmc_queue_bounce_post(mq);
+	if ((md->flags & MMC_BLK_CMD23) &&
+	    mmc_op_multi(brq->cmd.opcode) &&
+	    (do_rel_wr || !(card->quirks & MMC_QUIRK_BLK_NO_CMD23))) {
+		brq->sbc.opcode = MMC_SET_BLOCK_COUNT;
+		brq->sbc.arg = brq->data.blocks |
+			(do_rel_wr ? (1 << 31) : 0);
+		brq->sbc.flags = MMC_RSP_R1 | MMC_CMD_AC;
+		brq->mrq.sbc = &brq->sbc;
+	}
 
-		/*
-		 * Check for errors here, but don't jump to cmd_err
-		 * until later as we need to wait for the card to leave
-		 * programming mode even when things go wrong.
-		 */
-		if (brq.sbc.error || brq.cmd.error ||
-		    brq.data.error || brq.stop.error) {
-			if (brq.data.blocks > 1 && rq_data_dir(req) == READ) {
-				/* Redo read one sector at a time */
-				printk(KERN_WARNING "%s: retrying using single "
-				       "block read\n", req->rq_disk->disk_name);
-				disable_multi = 1;
-				continue;
-			}
-			status = get_card_status(card, req);
-		}
+	mmc_set_data_timeout(&brq->data, card);
 
-		if (brq.sbc.error) {
-			printk(KERN_ERR "%s: error %d sending SET_BLOCK_COUNT "
-			       "command, response %#x, card status %#x\n",
-			       req->rq_disk->disk_name, brq.sbc.error,
-			       brq.sbc.resp[0], status);
-		}
+	brq->data.sg = mqrq->sg;
+	brq->data.sg_len = mmc_queue_map_sg(mq, mqrq);
 
-		if (brq.cmd.error) {
-			printk(KERN_ERR "%s: error %d sending read/write "
-			       "command, response %#x, card status %#x\n",
-			       req->rq_disk->disk_name, brq.cmd.error,
-			       brq.cmd.resp[0], status);
+	/*
+	 * Adjust the sg list so it is the same size as the
+	 * request.
+	 */
+	if (brq->data.blocks != blk_rq_sectors(req)) {
+		int i, data_size = brq->data.blocks << 9;
+		struct scatterlist *sg;
+
+		for_each_sg(brq->data.sg, sg, brq->data.sg_len, i) {
+			data_size -= sg->length;
+			if (data_size <= 0) {
+				sg->length += data_size;
+				i++;
+				break;
+			}
 		}
+		brq->data.sg_len = i;
+	}
 
-		if (brq.data.error) {
-			if (brq.data.error == -ETIMEDOUT && brq.mrq.stop)
-				/* 'Stop' response contains card status */
-				status = brq.mrq.stop->resp[0];
-			printk(KERN_ERR "%s: error %d transferring data,"
-			       " sector %u, nr %u, card status %#x\n",
-			       req->rq_disk->disk_name, brq.data.error,
-			       (unsigned)blk_rq_pos(req),
-			       (unsigned)blk_rq_sectors(req), status);
-		}
+	mqrq->mmc_active.mrq = &brq->mrq;
+	mqrq->mmc_active.err_check = mmc_blk_err_check;
 
-		if (brq.stop.error) {
-			printk(KERN_ERR "%s: error %d sending stop command, "
-			       "response %#x, card status %#x\n",
-			       req->rq_disk->disk_name, brq.stop.error,
-			       brq.stop.resp[0], status);
-		}
+	mmc_queue_bounce_pre(mqrq);
+}
 
-		if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ) {
-			do {
-				int err;
-
-				cmd.opcode = MMC_SEND_STATUS;
-				cmd.arg = card->rca << 16;
-				cmd.flags = MMC_RSP_R1 | MMC_CMD_AC;
-				err = mmc_wait_for_cmd(card->host, &cmd, 5);
-				if (err) {
-					printk(KERN_ERR "%s: error %d requesting status\n",
-					       req->rq_disk->disk_name, err);
-					goto cmd_err;
-				}
-				/*
-				 * Some cards mishandle the status bits,
-				 * so make sure to check both the busy
-				 * indication and the card state.
-				 */
-			} while (!(cmd.resp[0] & R1_READY_FOR_DATA) ||
-				(R1_CURRENT_STATE(cmd.resp[0]) == 7));
-
-#if 0
-			if (cmd.resp[0] & ~0x00000900)
-				printk(KERN_ERR "%s: status = %08x\n",
-				       req->rq_disk->disk_name, cmd.resp[0]);
-			if (mmc_decode_status(cmd.resp))
-				goto cmd_err;
-#endif
-		}
+static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
+{
+	struct mmc_blk_data *md = mq->data;
+	struct mmc_card *card = md->queue.card;
+	struct mmc_blk_request *brq = &mq->mqrq_cur->brq;
+	int ret = 1, disable_multi = 0, retry = 0;
+	enum mmc_blk_status status;
+	struct mmc_queue_req *mq_rq;
+	struct request *req;
+	struct mmc_async_req *areq;
+
+	if (!rqc && !mq->mqrq_prev->req)
+		return 0;
 
-		if (brq.cmd.error || brq.stop.error || brq.data.error) {
-			if (rq_data_dir(req) == READ) {
+	do {
+		if (rqc) {
+			mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq);
+			areq = &mq->mqrq_cur->mmc_active;
+		} else
+			areq = NULL;
+		areq = mmc_start_req(card->host, areq, (int *) &status);
+		if (!areq)
+			return 0;
+
+		mq_rq = container_of(areq, struct mmc_queue_req, mmc_active);
+		brq = &mq_rq->brq;
+		req = mq_rq->req;
+		mmc_queue_bounce_post(mq_rq);
+
+		switch (status) {
+		case MMC_BLK_SUCCESS:
+		case MMC_BLK_PARTIAL:
+			/*
+			 * A block was successfully transferred.
+			 */
+			spin_lock_irq(&md->lock);
+			ret = __blk_end_request(req, 0,
+						brq->data.bytes_xfered);
+			spin_unlock_irq(&md->lock);
+			if (status == MMC_BLK_SUCCESS && ret) {
 				/*
-				 * After an error, we redo I/O one sector at a
-				 * time, so we only reach here after trying to
-				 * read a single sector.
+				 * The blk_end_request has returned non zero
+				 * even though all data is transfered and no
+				 * erros returned by host.
+				 * If this happen it's a bug.
 				 */
-				spin_lock_irq(&md->lock);
-				ret = __blk_end_request(req, -EIO, brq.data.blksz);
-				spin_unlock_irq(&md->lock);
-				continue;
+				printk(KERN_ERR "%s BUG rq_tot %d d_xfer %d\n",
+				       __func__, blk_rq_bytes(req),
+				       brq->data.bytes_xfered);
+				rqc = NULL;
+				goto cmd_abort;
 			}
+			break;
+		case MMC_BLK_CMD_ERR:
 			goto cmd_err;
+		case MMC_BLK_RETRY_SINGLE:
+			disable_multi = 1;
+			break;
+		case MMC_BLK_RETRY:
+			if (retry++ < 5)
+				break;
+		case MMC_BLK_ABORT:
+			goto cmd_abort;
+		case MMC_BLK_DATA_ERR:
+			/*
+			 * After an error, we redo I/O one sector at a
+			 * time, so we only reach here after trying to
+			 * read a single sector.
+			 */
+			spin_lock_irq(&md->lock);
+			ret = __blk_end_request(req, -EIO,
+						brq->data.blksz);
+			spin_unlock_irq(&md->lock);
+			if (!ret)
+				goto start_new_req;
+			break;
 		}
 
-		/*
-		 * A block was successfully transferred.
-		 */
-		spin_lock_irq(&md->lock);
-		ret = __blk_end_request(req, 0, brq.data.bytes_xfered);
-		spin_unlock_irq(&md->lock);
+		if (ret) {
+			/*
+			 * In case of a none complete request
+			 * prepare it again and resend.
+			 */
+			mmc_blk_rw_rq_prep(mq_rq, card, disable_multi, mq);
+			mmc_start_req(card->host, &mq_rq->mmc_active, NULL);
+		}
 	} while (ret);
 
 	return 1;
@@ -927,15 +1156,22 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req)
 		}
 	} else {
 		spin_lock_irq(&md->lock);
-		ret = __blk_end_request(req, 0, brq.data.bytes_xfered);
+		ret = __blk_end_request(req, 0, brq->data.bytes_xfered);
 		spin_unlock_irq(&md->lock);
 	}
 
+ 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);
 
+ start_new_req:
+	if (rqc) {
+		mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq);
+		mmc_start_req(card->host, &mq->mqrq_cur->mmc_active, NULL);
+	}
+
 	return 0;
 }
 
@@ -945,26 +1181,37 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 	struct mmc_blk_data *md = mq->data;
 	struct mmc_card *card = md->queue.card;
 
-	mmc_claim_host(card->host);
+	if (req && !mq->mqrq_prev->req)
+		/* claim host only for the first request */
+		mmc_claim_host(card->host);
+
 	ret = mmc_blk_part_switch(card, md);
 	if (ret) {
 		ret = 0;
 		goto out;
 	}
 
-	if (req->cmd_flags & REQ_DISCARD) {
+	if (req && req->cmd_flags & REQ_DISCARD) {
+		/* complete ongoing async transfer before issuing discard */
+		if (card->host->areq)
+			mmc_blk_issue_rw_rq(mq, NULL);
 		if (req->cmd_flags & REQ_SECURE)
 			ret = mmc_blk_issue_secdiscard_rq(mq, req);
 		else
 			ret = mmc_blk_issue_discard_rq(mq, req);
-	} else if (req->cmd_flags & REQ_FLUSH) {
+	} else if (req && req->cmd_flags & REQ_FLUSH) {
+		/* complete ongoing async transfer before issuing flush */
+		if (card->host->areq)
+			mmc_blk_issue_rw_rq(mq, NULL);
 		ret = mmc_blk_issue_flush(mq, req);
 	} else {
 		ret = mmc_blk_issue_rw_rq(mq, req);
 	}
 
 out:
-	mmc_release_host(card->host);
+	if (!req)
+		/* release host only when there are no more requests */
+		mmc_release_host(card->host);
 	return ret;
 }
 
diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c
index 233cdfae92f4..006a5e9f8ab8 100644
--- a/drivers/mmc/card/mmc_test.c
+++ b/drivers/mmc/card/mmc_test.c
@@ -148,6 +148,27 @@ struct mmc_test_card {
 	struct mmc_test_general_result	*gr;
 };
 
+enum mmc_test_prep_media {
+	MMC_TEST_PREP_NONE = 0,
+	MMC_TEST_PREP_WRITE_FULL = 1 << 0,
+	MMC_TEST_PREP_ERASE = 1 << 1,
+};
+
+struct mmc_test_multiple_rw {
+	unsigned int *sg_len;
+	unsigned int *bs;
+	unsigned int len;
+	unsigned int size;
+	bool do_write;
+	bool do_nonblock_req;
+	enum mmc_test_prep_media prepare;
+};
+
+struct mmc_test_async_req {
+	struct mmc_async_req areq;
+	struct mmc_test_card *test;
+};
+
 /*******************************************************************/
 /*  General helper functions                                       */
 /*******************************************************************/
@@ -367,21 +388,26 @@ out_free:
  * Map memory into a scatterlist.  Optionally allow the same memory to be
  * mapped more than once.
  */
-static int mmc_test_map_sg(struct mmc_test_mem *mem, unsigned long sz,
+static int mmc_test_map_sg(struct mmc_test_mem *mem, unsigned long size,
 			   struct scatterlist *sglist, int repeat,
 			   unsigned int max_segs, unsigned int max_seg_sz,
-			   unsigned int *sg_len)
+			   unsigned int *sg_len, int min_sg_len)
 {
 	struct scatterlist *sg = NULL;
 	unsigned int i;
+	unsigned long sz = size;
 
 	sg_init_table(sglist, max_segs);
+	if (min_sg_len > max_segs)
+		min_sg_len = max_segs;
 
 	*sg_len = 0;
 	do {
 		for (i = 0; i < mem->cnt; i++) {
 			unsigned long len = PAGE_SIZE << mem->arr[i].order;
 
+			if (min_sg_len && (size / min_sg_len < len))
+				len = ALIGN(size / min_sg_len, 512);
 			if (len > sz)
 				len = sz;
 			if (len > max_seg_sz)
@@ -554,11 +580,12 @@ static void mmc_test_print_avg_rate(struct mmc_test_card *test, uint64_t bytes,
 
 	printk(KERN_INFO "%s: Transfer of %u x %u sectors (%u x %u%s KiB) took "
 			 "%lu.%09lu seconds (%u kB/s, %u KiB/s, "
-			 "%u.%02u IOPS)\n",
+			 "%u.%02u IOPS, sg_len %d)\n",
 			 mmc_hostname(test->card->host), count, sectors, count,
 			 sectors >> 1, (sectors & 1 ? ".5" : ""),
 			 (unsigned long)ts.tv_sec, (unsigned long)ts.tv_nsec,
-			 rate / 1000, rate / 1024, iops / 100, iops % 100);
+			 rate / 1000, rate / 1024, iops / 100, iops % 100,
+			 test->area.sg_len);
 
 	mmc_test_save_transfer_result(test, count, sectors, ts, rate, iops);
 }
@@ -661,7 +688,7 @@ static void mmc_test_prepare_broken_mrq(struct mmc_test_card *test,
  * Checks that a normal transfer didn't have any errors
  */
 static int mmc_test_check_result(struct mmc_test_card *test,
-	struct mmc_request *mrq)
+				 struct mmc_request *mrq)
 {
 	int ret;
 
@@ -685,6 +712,17 @@ static int mmc_test_check_result(struct mmc_test_card *test,
 	return ret;
 }
 
+static int mmc_test_check_result_async(struct mmc_card *card,
+				       struct mmc_async_req *areq)
+{
+	struct mmc_test_async_req *test_async =
+		container_of(areq, struct mmc_test_async_req, areq);
+
+	mmc_test_wait_busy(test_async->test);
+
+	return mmc_test_check_result(test_async->test, areq->mrq);
+}
+
 /*
  * Checks that a "short transfer" behaved as expected
  */
@@ -720,6 +758,85 @@ static int mmc_test_check_broken_result(struct mmc_test_card *test,
 }
 
 /*
+ * Tests nonblock transfer with certain parameters
+ */
+static void mmc_test_nonblock_reset(struct mmc_request *mrq,
+				    struct mmc_command *cmd,
+				    struct mmc_command *stop,
+				    struct mmc_data *data)
+{
+	memset(mrq, 0, sizeof(struct mmc_request));
+	memset(cmd, 0, sizeof(struct mmc_command));
+	memset(data, 0, sizeof(struct mmc_data));
+	memset(stop, 0, sizeof(struct mmc_command));
+
+	mrq->cmd = cmd;
+	mrq->data = data;
+	mrq->stop = stop;
+}
+static int mmc_test_nonblock_transfer(struct mmc_test_card *test,
+				      struct scatterlist *sg, unsigned sg_len,
+				      unsigned dev_addr, unsigned blocks,
+				      unsigned blksz, int write, int count)
+{
+	struct mmc_request mrq1;
+	struct mmc_command cmd1;
+	struct mmc_command stop1;
+	struct mmc_data data1;
+
+	struct mmc_request mrq2;
+	struct mmc_command cmd2;
+	struct mmc_command stop2;
+	struct mmc_data data2;
+
+	struct mmc_test_async_req test_areq[2];
+	struct mmc_async_req *done_areq;
+	struct mmc_async_req *cur_areq = &test_areq[0].areq;
+	struct mmc_async_req *other_areq = &test_areq[1].areq;
+	int i;
+	int ret;
+
+	test_areq[0].test = test;
+	test_areq[1].test = test;
+
+	mmc_test_nonblock_reset(&mrq1, &cmd1, &stop1, &data1);
+	mmc_test_nonblock_reset(&mrq2, &cmd2, &stop2, &data2);
+
+	cur_areq->mrq = &mrq1;
+	cur_areq->err_check = mmc_test_check_result_async;
+	other_areq->mrq = &mrq2;
+	other_areq->err_check = mmc_test_check_result_async;
+
+	for (i = 0; i < count; i++) {
+		mmc_test_prepare_mrq(test, cur_areq->mrq, sg, sg_len, dev_addr,
+				     blocks, blksz, write);
+		done_areq = mmc_start_req(test->card->host, cur_areq, &ret);
+
+		if (ret || (!done_areq && i > 0))
+			goto err;
+
+		if (done_areq) {
+			if (done_areq->mrq == &mrq2)
+				mmc_test_nonblock_reset(&mrq2, &cmd2,
+							&stop2, &data2);
+			else
+				mmc_test_nonblock_reset(&mrq1, &cmd1,
+							&stop1, &data1);
+		}
+		done_areq = cur_areq;
+		cur_areq = other_areq;
+		other_areq = done_areq;
+		dev_addr += blocks;
+	}
+
+	done_areq = mmc_start_req(test->card->host, NULL, &ret);
+
+	return ret;
+err:
+	return ret;
+}
+
+/*
  * Tests a basic transfer with certain parameters
  */
 static int mmc_test_simple_transfer(struct mmc_test_card *test,
@@ -1302,7 +1419,7 @@ static int mmc_test_no_highmem(struct mmc_test_card *test)
  * Map sz bytes so that it can be transferred.
  */
 static int mmc_test_area_map(struct mmc_test_card *test, unsigned long sz,
-			     int max_scatter)
+			     int max_scatter, int min_sg_len)
 {
 	struct mmc_test_area *t = &test->area;
 	int err;
@@ -1315,7 +1432,7 @@ static int mmc_test_area_map(struct mmc_test_card *test, unsigned long sz,
 				       &t->sg_len);
 	} else {
 		err = mmc_test_map_sg(t->mem, sz, t->sg, 1, t->max_segs,
-				      t->max_seg_sz, &t->sg_len);
+				      t->max_seg_sz, &t->sg_len, min_sg_len);
 	}
 	if (err)
 		printk(KERN_INFO "%s: Failed to map sg list\n",
@@ -1336,14 +1453,17 @@ static int mmc_test_area_transfer(struct mmc_test_card *test,
 }
 
 /*
- * Map and transfer bytes.
+ * Map and transfer bytes for multiple transfers.
  */
-static int mmc_test_area_io(struct mmc_test_card *test, unsigned long sz,
-			    unsigned int dev_addr, int write, int max_scatter,
-			    int timed)
+static int mmc_test_area_io_seq(struct mmc_test_card *test, unsigned long sz,
+				unsigned int dev_addr, int write,
+				int max_scatter, int timed, int count,
+				bool nonblock, int min_sg_len)
 {
 	struct timespec ts1, ts2;
-	int ret;
+	int ret = 0;
+	int i;
+	struct mmc_test_area *t = &test->area;
 
 	/*
 	 * In the case of a maximally scattered transfer, the maximum transfer
@@ -1361,14 +1481,21 @@ static int mmc_test_area_io(struct mmc_test_card *test, unsigned long sz,
 			sz = max_tfr;
 	}
 
-	ret = mmc_test_area_map(test, sz, max_scatter);
+	ret = mmc_test_area_map(test, sz, max_scatter, min_sg_len);
 	if (ret)
 		return ret;
 
 	if (timed)
 		getnstimeofday(&ts1);
+	if (nonblock)
+		ret = mmc_test_nonblock_transfer(test, t->sg, t->sg_len,
+				 dev_addr, t->blocks, 512, write, count);
+	else
+		for (i = 0; i < count && ret == 0; i++) {
+			ret = mmc_test_area_transfer(test, dev_addr, write);
+			dev_addr += sz >> 9;
+		}
 
-	ret = mmc_test_area_transfer(test, dev_addr, write);
 	if (ret)
 		return ret;
 
@@ -1376,11 +1503,19 @@ static int mmc_test_area_io(struct mmc_test_card *test, unsigned long sz,
 		getnstimeofday(&ts2);
 
 	if (timed)
-		mmc_test_print_rate(test, sz, &ts1, &ts2);
+		mmc_test_print_avg_rate(test, sz, count, &ts1, &ts2);
 
 	return 0;
 }
 
+static int mmc_test_area_io(struct mmc_test_card *test, unsigned long sz,
+			    unsigned int dev_addr, int write, int max_scatter,
+			    int timed)
+{
+	return mmc_test_area_io_seq(test, sz, dev_addr, write, max_scatter,
+				    timed, 1, false, 0);
+}
+
 /*
  * Write the test area entirely.
  */
@@ -1954,6 +2089,245 @@ static int mmc_test_large_seq_write_perf(struct mmc_test_card *test)
 	return mmc_test_large_seq_perf(test, 1);
 }
 
+static int mmc_test_rw_multiple(struct mmc_test_card *test,
+				struct mmc_test_multiple_rw *tdata,
+				unsigned int reqsize, unsigned int size,
+				int min_sg_len)
+{
+	unsigned int dev_addr;
+	struct mmc_test_area *t = &test->area;
+	int ret = 0;
+
+	/* Set up test area */
+	if (size > mmc_test_capacity(test->card) / 2 * 512)
+		size = mmc_test_capacity(test->card) / 2 * 512;
+	if (reqsize > t->max_tfr)
+		reqsize = t->max_tfr;
+	dev_addr = mmc_test_capacity(test->card) / 4;
+	if ((dev_addr & 0xffff0000))
+		dev_addr &= 0xffff0000; /* Round to 64MiB boundary */
+	else
+		dev_addr &= 0xfffff800; /* Round to 1MiB boundary */
+	if (!dev_addr)
+		goto err;
+
+	if (reqsize > size)
+		return 0;
+
+	/* prepare test area */
+	if (mmc_can_erase(test->card) &&
+	    tdata->prepare & MMC_TEST_PREP_ERASE) {
+		ret = mmc_erase(test->card, dev_addr,
+				size / 512, MMC_SECURE_ERASE_ARG);
+		if (ret)
+			ret = mmc_erase(test->card, dev_addr,
+					size / 512, MMC_ERASE_ARG);
+		if (ret)
+			goto err;
+	}
+
+	/* Run test */
+	ret = mmc_test_area_io_seq(test, reqsize, dev_addr,
+				   tdata->do_write, 0, 1, size / reqsize,
+				   tdata->do_nonblock_req, min_sg_len);
+	if (ret)
+		goto err;
+
+	return ret;
+ err:
+	printk(KERN_INFO "[%s] error\n", __func__);
+	return ret;
+}
+
+static int mmc_test_rw_multiple_size(struct mmc_test_card *test,
+				     struct mmc_test_multiple_rw *rw)
+{
+	int ret = 0;
+	int i;
+	void *pre_req = test->card->host->ops->pre_req;
+	void *post_req = test->card->host->ops->post_req;
+
+	if (rw->do_nonblock_req &&
+	    ((!pre_req && post_req) || (pre_req && !post_req))) {
+		printk(KERN_INFO "error: only one of pre/post is defined\n");
+		return -EINVAL;
+	}
+
+	for (i = 0 ; i < rw->len && ret == 0; i++) {
+		ret = mmc_test_rw_multiple(test, rw, rw->bs[i], rw->size, 0);
+		if (ret)
+			break;
+	}
+	return ret;
+}
+
+static int mmc_test_rw_multiple_sg_len(struct mmc_test_card *test,
+				       struct mmc_test_multiple_rw *rw)
+{
+	int ret = 0;
+	int i;
+
+	for (i = 0 ; i < rw->len && ret == 0; i++) {
+		ret = mmc_test_rw_multiple(test, rw, 512*1024, rw->size,
+					   rw->sg_len[i]);
+		if (ret)
+			break;
+	}
+	return ret;
+}
+
+/*
+ * Multiple blocking write 4k to 4 MB chunks
+ */
+static int mmc_test_profile_mult_write_blocking_perf(struct mmc_test_card *test)
+{
+	unsigned int bs[] = {1 << 12, 1 << 13, 1 << 14, 1 << 15, 1 << 16,
+			     1 << 17, 1 << 18, 1 << 19, 1 << 20, 1 << 22};
+	struct mmc_test_multiple_rw test_data = {
+		.bs = bs,
+		.size = TEST_AREA_MAX_SIZE,
+		.len = ARRAY_SIZE(bs),
+		.do_write = true,
+		.do_nonblock_req = false,
+		.prepare = MMC_TEST_PREP_ERASE,
+	};
+
+	return mmc_test_rw_multiple_size(test, &test_data);
+};
+
+/*
+ * Multiple non-blocking write 4k to 4 MB chunks
+ */
+static int mmc_test_profile_mult_write_nonblock_perf(struct mmc_test_card *test)
+{
+	unsigned int bs[] = {1 << 12, 1 << 13, 1 << 14, 1 << 15, 1 << 16,
+			     1 << 17, 1 << 18, 1 << 19, 1 << 20, 1 << 22};
+	struct mmc_test_multiple_rw test_data = {
+		.bs = bs,
+		.size = TEST_AREA_MAX_SIZE,
+		.len = ARRAY_SIZE(bs),
+		.do_write = true,
+		.do_nonblock_req = true,
+		.prepare = MMC_TEST_PREP_ERASE,
+	};
+
+	return mmc_test_rw_multiple_size(test, &test_data);
+}
+
+/*
+ * Multiple blocking read 4k to 4 MB chunks
+ */
+static int mmc_test_profile_mult_read_blocking_perf(struct mmc_test_card *test)
+{
+	unsigned int bs[] = {1 << 12, 1 << 13, 1 << 14, 1 << 15, 1 << 16,
+			     1 << 17, 1 << 18, 1 << 19, 1 << 20, 1 << 22};
+	struct mmc_test_multiple_rw test_data = {
+		.bs = bs,
+		.size = TEST_AREA_MAX_SIZE,
+		.len = ARRAY_SIZE(bs),
+		.do_write = false,
+		.do_nonblock_req = false,
+		.prepare = MMC_TEST_PREP_NONE,
+	};
+
+	return mmc_test_rw_multiple_size(test, &test_data);
+}
+
+/*
+ * Multiple non-blocking read 4k to 4 MB chunks
+ */
+static int mmc_test_profile_mult_read_nonblock_perf(struct mmc_test_card *test)
+{
+	unsigned int bs[] = {1 << 12, 1 << 13, 1 << 14, 1 << 15, 1 << 16,
+			     1 << 17, 1 << 18, 1 << 19, 1 << 20, 1 << 22};
+	struct mmc_test_multiple_rw test_data = {
+		.bs = bs,
+		.size = TEST_AREA_MAX_SIZE,
+		.len = ARRAY_SIZE(bs),
+		.do_write = false,
+		.do_nonblock_req = true,
+		.prepare = MMC_TEST_PREP_NONE,
+	};
+
+	return mmc_test_rw_multiple_size(test, &test_data);
+}
+
+/*
+ * Multiple blocking write 1 to 512 sg elements
+ */
+static int mmc_test_profile_sglen_wr_blocking_perf(struct mmc_test_card *test)
+{
+	unsigned int sg_len[] = {1, 1 << 3, 1 << 4, 1 << 5, 1 << 6,
+				 1 << 7, 1 << 8, 1 << 9};
+	struct mmc_test_multiple_rw test_data = {
+		.sg_len = sg_len,
+		.size = TEST_AREA_MAX_SIZE,
+		.len = ARRAY_SIZE(sg_len),
+		.do_write = true,
+		.do_nonblock_req = false,
+		.prepare = MMC_TEST_PREP_ERASE,
+	};
+
+	return mmc_test_rw_multiple_sg_len(test, &test_data);
+};
+
+/*
+ * Multiple non-blocking write 1 to 512 sg elements
+ */
+static int mmc_test_profile_sglen_wr_nonblock_perf(struct mmc_test_card *test)
+{
+	unsigned int sg_len[] = {1, 1 << 3, 1 << 4, 1 << 5, 1 << 6,
+				 1 << 7, 1 << 8, 1 << 9};
+	struct mmc_test_multiple_rw test_data = {
+		.sg_len = sg_len,
+		.size = TEST_AREA_MAX_SIZE,
+		.len = ARRAY_SIZE(sg_len),
+		.do_write = true,
+		.do_nonblock_req = true,
+		.prepare = MMC_TEST_PREP_ERASE,
+	};
+
+	return mmc_test_rw_multiple_sg_len(test, &test_data);
+}
+
+/*
+ * Multiple blocking read 1 to 512 sg elements
+ */
+static int mmc_test_profile_sglen_r_blocking_perf(struct mmc_test_card *test)
+{
+	unsigned int sg_len[] = {1, 1 << 3, 1 << 4, 1 << 5, 1 << 6,
+				 1 << 7, 1 << 8, 1 << 9};
+	struct mmc_test_multiple_rw test_data = {
+		.sg_len = sg_len,
+		.size = TEST_AREA_MAX_SIZE,
+		.len = ARRAY_SIZE(sg_len),
+		.do_write = false,
+		.do_nonblock_req = false,
+		.prepare = MMC_TEST_PREP_NONE,
+	};
+
+	return mmc_test_rw_multiple_sg_len(test, &test_data);
+}
+
+/*
+ * Multiple non-blocking read 1 to 512 sg elements
+ */
+static int mmc_test_profile_sglen_r_nonblock_perf(struct mmc_test_card *test)
+{
+	unsigned int sg_len[] = {1, 1 << 3, 1 << 4, 1 << 5, 1 << 6,
+				 1 << 7, 1 << 8, 1 << 9};
+	struct mmc_test_multiple_rw test_data = {
+		.sg_len = sg_len,
+		.size = TEST_AREA_MAX_SIZE,
+		.len = ARRAY_SIZE(sg_len),
+		.do_write = false,
+		.do_nonblock_req = true,
+		.prepare = MMC_TEST_PREP_NONE,
+	};
+
+	return mmc_test_rw_multiple_sg_len(test, &test_data);
+}
+
 static const struct mmc_test_case mmc_test_cases[] = {
 	{
 		.name = "Basic write (no data verification)",
@@ -2221,6 +2595,61 @@ static const struct mmc_test_case mmc_test_cases[] = {
 		.cleanup = mmc_test_area_cleanup,
 	},
 
+	{
+		.name = "Write performance with blocking req 4k to 4MB",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_profile_mult_write_blocking_perf,
+		.cleanup = mmc_test_area_cleanup,
+	},
+
+	{
+		.name = "Write performance with non-blocking req 4k to 4MB",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_profile_mult_write_nonblock_perf,
+		.cleanup = mmc_test_area_cleanup,
+	},
+
+	{
+		.name = "Read performance with blocking req 4k to 4MB",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_profile_mult_read_blocking_perf,
+		.cleanup = mmc_test_area_cleanup,
+	},
+
+	{
+		.name = "Read performance with non-blocking req 4k to 4MB",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_profile_mult_read_nonblock_perf,
+		.cleanup = mmc_test_area_cleanup,
+	},
+
+	{
+		.name = "Write performance blocking req 1 to 512 sg elems",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_profile_sglen_wr_blocking_perf,
+		.cleanup = mmc_test_area_cleanup,
+	},
+
+	{
+		.name = "Write performance non-blocking req 1 to 512 sg elems",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_profile_sglen_wr_nonblock_perf,
+		.cleanup = mmc_test_area_cleanup,
+	},
+
+	{
+		.name = "Read performance blocking req 1 to 512 sg elems",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_profile_sglen_r_blocking_perf,
+		.cleanup = mmc_test_area_cleanup,
+	},
+
+	{
+		.name = "Read performance non-blocking req 1 to 512 sg elems",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_profile_sglen_r_nonblock_perf,
+		.cleanup = mmc_test_area_cleanup,
+	},
 };
 
 static DEFINE_MUTEX(mmc_test_lock);
@@ -2445,6 +2874,32 @@ static const struct file_operations mmc_test_fops_test = {
 	.release	= single_release,
 };
 
+static int mtf_testlist_show(struct seq_file *sf, void *data)
+{
+	int i;
+
+	mutex_lock(&mmc_test_lock);
+
+	for (i = 0; i < ARRAY_SIZE(mmc_test_cases); i++)
+		seq_printf(sf, "%d:\t%s\n", i+1, mmc_test_cases[i].name);
+
+	mutex_unlock(&mmc_test_lock);
+
+	return 0;
+}
+
+static int mtf_testlist_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mtf_testlist_show, inode->i_private);
+}
+
+static const struct file_operations mmc_test_fops_testlist = {
+	.open		= mtf_testlist_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static void mmc_test_free_file_test(struct mmc_card *card)
 {
 	struct mmc_test_dbgfs_file *df, *dfs;
@@ -2476,7 +2931,18 @@ static int mmc_test_register_file_test(struct mmc_card *card)
 
 	if (IS_ERR_OR_NULL(file)) {
 		dev_err(&card->dev,
-			"Can't create file. Perhaps debugfs is disabled.\n");
+			"Can't create test. Perhaps debugfs is disabled.\n");
+		ret = -ENODEV;
+		goto err;
+	}
+
+	if (card->debugfs_root)
+		file = debugfs_create_file("testlist", S_IRUGO,
+			card->debugfs_root, card, &mmc_test_fops_testlist);
+
+	if (IS_ERR_OR_NULL(file)) {
+		dev_err(&card->dev,
+			"Can't create testlist. Perhaps debugfs is disabled.\n");
 		ret = -ENODEV;
 		goto err;
 	}
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index 6413afa318d2..45fb362e3f01 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -52,14 +52,18 @@ static int mmc_queue_thread(void *d)
 	down(&mq->thread_sem);
 	do {
 		struct request *req = NULL;
+		struct mmc_queue_req *tmp;
 
 		spin_lock_irq(q->queue_lock);
 		set_current_state(TASK_INTERRUPTIBLE);
 		req = blk_fetch_request(q);
-		mq->req = req;
+		mq->mqrq_cur->req = req;
 		spin_unlock_irq(q->queue_lock);
 
-		if (!req) {
+		if (req || mq->mqrq_prev->req) {
+			set_current_state(TASK_RUNNING);
+			mq->issue_fn(mq, req);
+		} else {
 			if (kthread_should_stop()) {
 				set_current_state(TASK_RUNNING);
 				break;
@@ -67,11 +71,14 @@ static int mmc_queue_thread(void *d)
 			up(&mq->thread_sem);
 			schedule();
 			down(&mq->thread_sem);
-			continue;
 		}
-		set_current_state(TASK_RUNNING);
 
-		mq->issue_fn(mq, req);
+		/* Current request becomes previous request and vice versa. */
+		mq->mqrq_prev->brq.mrq.data = NULL;
+		mq->mqrq_prev->req = NULL;
+		tmp = mq->mqrq_prev;
+		mq->mqrq_prev = mq->mqrq_cur;
+		mq->mqrq_cur = tmp;
 	} while (1);
 	up(&mq->thread_sem);
 
@@ -97,10 +104,46 @@ static void mmc_request(struct request_queue *q)
 		return;
 	}
 
-	if (!mq->req)
+	if (!mq->mqrq_cur->req && !mq->mqrq_prev->req)
 		wake_up_process(mq->thread);
 }
 
+struct scatterlist *mmc_alloc_sg(int sg_len, int *err)
+{
+	struct scatterlist *sg;
+
+	sg = kmalloc(sizeof(struct scatterlist)*sg_len, GFP_KERNEL);
+	if (!sg)
+		*err = -ENOMEM;
+	else {
+		*err = 0;
+		sg_init_table(sg, sg_len);
+	}
+
+	return sg;
+}
+
+static void mmc_queue_setup_discard(struct request_queue *q,
+				    struct mmc_card *card)
+{
+	unsigned max_discard;
+
+	max_discard = mmc_calc_max_discard(card);
+	if (!max_discard)
+		return;
+
+	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
+	q->limits.max_discard_sectors = max_discard;
+	if (card->erased_byte == 0)
+		q->limits.discard_zeroes_data = 1;
+	q->limits.discard_granularity = card->pref_erase << 9;
+	/* granularity must not be greater than max. discard */
+	if (card->pref_erase > max_discard)
+		q->limits.discard_granularity = 0;
+	if (mmc_can_secure_erase_trim(card))
+		queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, q);
+}
+
 /**
  * mmc_init_queue - initialise a queue structure.
  * @mq: mmc queue
@@ -116,6 +159,8 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 	struct mmc_host *host = card->host;
 	u64 limit = BLK_BOUNCE_HIGH;
 	int ret;
+	struct mmc_queue_req *mqrq_cur = &mq->mqrq[0];
+	struct mmc_queue_req *mqrq_prev = &mq->mqrq[1];
 
 	if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask)
 		limit = *mmc_dev(host)->dma_mask;
@@ -125,21 +170,16 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 	if (!mq->queue)
 		return -ENOMEM;
 
+	memset(&mq->mqrq_cur, 0, sizeof(mq->mqrq_cur));
+	memset(&mq->mqrq_prev, 0, sizeof(mq->mqrq_prev));
+	mq->mqrq_cur = mqrq_cur;
+	mq->mqrq_prev = mqrq_prev;
 	mq->queue->queuedata = mq;
-	mq->req = NULL;
 
 	blk_queue_prep_rq(mq->queue, mmc_prep_request);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mq->queue);
-	if (mmc_can_erase(card)) {
-		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mq->queue);
-		mq->queue->limits.max_discard_sectors = UINT_MAX;
-		if (card->erased_byte == 0)
-			mq->queue->limits.discard_zeroes_data = 1;
-		mq->queue->limits.discard_granularity = card->pref_erase << 9;
-		if (mmc_can_secure_erase_trim(card))
-			queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD,
-						mq->queue);
-	}
+	if (mmc_can_erase(card))
+		mmc_queue_setup_discard(mq->queue, card);
 
 #ifdef CONFIG_MMC_BLOCK_BOUNCE
 	if (host->max_segs == 1) {
@@ -155,53 +195,64 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 			bouncesz = host->max_blk_count * 512;
 
 		if (bouncesz > 512) {
-			mq->bounce_buf = kmalloc(bouncesz, GFP_KERNEL);
-			if (!mq->bounce_buf) {
+			mqrq_cur->bounce_buf = kmalloc(bouncesz, GFP_KERNEL);
+			if (!mqrq_cur->bounce_buf) {
+				printk(KERN_WARNING "%s: unable to "
+					"allocate bounce cur buffer\n",
+					mmc_card_name(card));
+			}
+			mqrq_prev->bounce_buf = kmalloc(bouncesz, GFP_KERNEL);
+			if (!mqrq_prev->bounce_buf) {
 				printk(KERN_WARNING "%s: unable to "
-					"allocate bounce buffer\n",
+					"allocate bounce prev buffer\n",
 					mmc_card_name(card));
+				kfree(mqrq_cur->bounce_buf);
+				mqrq_cur->bounce_buf = NULL;
 			}
 		}
 
-		if (mq->bounce_buf) {
+		if (mqrq_cur->bounce_buf && mqrq_prev->bounce_buf) {
 			blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_ANY);
 			blk_queue_max_hw_sectors(mq->queue, bouncesz / 512);
 			blk_queue_max_segments(mq->queue, bouncesz / 512);
 			blk_queue_max_segment_size(mq->queue, bouncesz);
 
-			mq->sg = kmalloc(sizeof(struct scatterlist),
-				GFP_KERNEL);
-			if (!mq->sg) {
-				ret = -ENOMEM;
+			mqrq_cur->sg = mmc_alloc_sg(1, &ret);
+			if (ret)
 				goto cleanup_queue;
-			}
-			sg_init_table(mq->sg, 1);
 
-			mq->bounce_sg = kmalloc(sizeof(struct scatterlist) *
-				bouncesz / 512, GFP_KERNEL);
-			if (!mq->bounce_sg) {
-				ret = -ENOMEM;
+			mqrq_cur->bounce_sg =
+				mmc_alloc_sg(bouncesz / 512, &ret);
+			if (ret)
+				goto cleanup_queue;
+
+			mqrq_prev->sg = mmc_alloc_sg(1, &ret);
+			if (ret)
+				goto cleanup_queue;
+
+			mqrq_prev->bounce_sg =
+				mmc_alloc_sg(bouncesz / 512, &ret);
+			if (ret)
 				goto cleanup_queue;
-			}
-			sg_init_table(mq->bounce_sg, bouncesz / 512);
 		}
 	}
 #endif
 
-	if (!mq->bounce_buf) {
+	if (!mqrq_cur->bounce_buf && !mqrq_prev->bounce_buf) {
 		blk_queue_bounce_limit(mq->queue, limit);
 		blk_queue_max_hw_sectors(mq->queue,
 			min(host->max_blk_count, host->max_req_size / 512));
 		blk_queue_max_segments(mq->queue, host->max_segs);
 		blk_queue_max_segment_size(mq->queue, host->max_seg_size);
 
-		mq->sg = kmalloc(sizeof(struct scatterlist) *
-			host->max_segs, GFP_KERNEL);
-		if (!mq->sg) {
-			ret = -ENOMEM;
+		mqrq_cur->sg = mmc_alloc_sg(host->max_segs, &ret);
+		if (ret)
+			goto cleanup_queue;
+
+
+		mqrq_prev->sg = mmc_alloc_sg(host->max_segs, &ret);
+		if (ret)
 			goto cleanup_queue;
-		}
-		sg_init_table(mq->sg, host->max_segs);
 	}
 
 	sema_init(&mq->thread_sem, 1);
@@ -216,16 +267,22 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 
 	return 0;
  free_bounce_sg:
- 	if (mq->bounce_sg)
- 		kfree(mq->bounce_sg);
- 	mq->bounce_sg = NULL;
+	kfree(mqrq_cur->bounce_sg);
+	mqrq_cur->bounce_sg = NULL;
+	kfree(mqrq_prev->bounce_sg);
+	mqrq_prev->bounce_sg = NULL;
+
  cleanup_queue:
- 	if (mq->sg)
-		kfree(mq->sg);
-	mq->sg = NULL;
-	if (mq->bounce_buf)
-		kfree(mq->bounce_buf);
-	mq->bounce_buf = NULL;
+	kfree(mqrq_cur->sg);
+	mqrq_cur->sg = NULL;
+	kfree(mqrq_cur->bounce_buf);
+	mqrq_cur->bounce_buf = NULL;
+
+	kfree(mqrq_prev->sg);
+	mqrq_prev->sg = NULL;
+	kfree(mqrq_prev->bounce_buf);
+	mqrq_prev->bounce_buf = NULL;
+
 	blk_cleanup_queue(mq->queue);
 	return ret;
 }
@@ -234,6 +291,8 @@ void mmc_cleanup_queue(struct mmc_queue *mq)
 {
 	struct request_queue *q = mq->queue;
 	unsigned long flags;
+	struct mmc_queue_req *mqrq_cur = mq->mqrq_cur;
+	struct mmc_queue_req *mqrq_prev = mq->mqrq_prev;
 
 	/* Make sure the queue isn't suspended, as that will deadlock */
 	mmc_queue_resume(mq);
@@ -247,16 +306,23 @@ void mmc_cleanup_queue(struct mmc_queue *mq)
 	blk_start_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
- 	if (mq->bounce_sg)
- 		kfree(mq->bounce_sg);
- 	mq->bounce_sg = NULL;
+	kfree(mqrq_cur->bounce_sg);
+	mqrq_cur->bounce_sg = NULL;
 
-	kfree(mq->sg);
-	mq->sg = NULL;
+	kfree(mqrq_cur->sg);
+	mqrq_cur->sg = NULL;
 
-	if (mq->bounce_buf)
-		kfree(mq->bounce_buf);
-	mq->bounce_buf = NULL;
+	kfree(mqrq_cur->bounce_buf);
+	mqrq_cur->bounce_buf = NULL;
+
+	kfree(mqrq_prev->bounce_sg);
+	mqrq_prev->bounce_sg = NULL;
+
+	kfree(mqrq_prev->sg);
+	mqrq_prev->sg = NULL;
+
+	kfree(mqrq_prev->bounce_buf);
+	mqrq_prev->bounce_buf = NULL;
 
 	mq->card = NULL;
 }
@@ -309,27 +375,27 @@ void mmc_queue_resume(struct mmc_queue *mq)
 /*
  * Prepare the sg list(s) to be handed of to the host driver
  */
-unsigned int mmc_queue_map_sg(struct mmc_queue *mq)
+unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq)
 {
 	unsigned int sg_len;
 	size_t buflen;
 	struct scatterlist *sg;
 	int i;
 
-	if (!mq->bounce_buf)
-		return blk_rq_map_sg(mq->queue, mq->req, mq->sg);
+	if (!mqrq->bounce_buf)
+		return blk_rq_map_sg(mq->queue, mqrq->req, mqrq->sg);
 
-	BUG_ON(!mq->bounce_sg);
+	BUG_ON(!mqrq->bounce_sg);
 
-	sg_len = blk_rq_map_sg(mq->queue, mq->req, mq->bounce_sg);
+	sg_len = blk_rq_map_sg(mq->queue, mqrq->req, mqrq->bounce_sg);
 
-	mq->bounce_sg_len = sg_len;
+	mqrq->bounce_sg_len = sg_len;
 
 	buflen = 0;
-	for_each_sg(mq->bounce_sg, sg, sg_len, i)
+	for_each_sg(mqrq->bounce_sg, sg, sg_len, i)
 		buflen += sg->length;
 
-	sg_init_one(mq->sg, mq->bounce_buf, buflen);
+	sg_init_one(mqrq->sg, mqrq->bounce_buf, buflen);
 
 	return 1;
 }
@@ -338,31 +404,30 @@ unsigned int mmc_queue_map_sg(struct mmc_queue *mq)
  * If writing, bounce the data to the buffer before the request
  * is sent to the host driver
  */
-void mmc_queue_bounce_pre(struct mmc_queue *mq)
+void mmc_queue_bounce_pre(struct mmc_queue_req *mqrq)
 {
-	if (!mq->bounce_buf)
+	if (!mqrq->bounce_buf)
 		return;
 
-	if (rq_data_dir(mq->req) != WRITE)
+	if (rq_data_dir(mqrq->req) != WRITE)
 		return;
 
-	sg_copy_to_buffer(mq->bounce_sg, mq->bounce_sg_len,
-		mq->bounce_buf, mq->sg[0].length);
+	sg_copy_to_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len,
+		mqrq->bounce_buf, mqrq->sg[0].length);
 }
 
 /*
  * If reading, bounce the data from the buffer after the request
  * has been handled by the host driver
  */
-void mmc_queue_bounce_post(struct mmc_queue *mq)
+void mmc_queue_bounce_post(struct mmc_queue_req *mqrq)
 {
-	if (!mq->bounce_buf)
+	if (!mqrq->bounce_buf)
 		return;
 
-	if (rq_data_dir(mq->req) != READ)
+	if (rq_data_dir(mqrq->req) != READ)
 		return;
 
-	sg_copy_from_buffer(mq->bounce_sg, mq->bounce_sg_len,
-		mq->bounce_buf, mq->sg[0].length);
+	sg_copy_from_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len,
+		mqrq->bounce_buf, mqrq->sg[0].length);
 }
-
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index 6223ef8dc9cd..d2a1eb4b9f9f 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -4,19 +4,35 @@
 struct request;
 struct task_struct;
 
+struct mmc_blk_request {
+	struct mmc_request	mrq;
+	struct mmc_command	sbc;
+	struct mmc_command	cmd;
+	struct mmc_command	stop;
+	struct mmc_data		data;
+};
+
+struct mmc_queue_req {
+	struct request		*req;
+	struct mmc_blk_request	brq;
+	struct scatterlist	*sg;
+	char			*bounce_buf;
+	struct scatterlist	*bounce_sg;
+	unsigned int		bounce_sg_len;
+	struct mmc_async_req	mmc_active;
+};
+
 struct mmc_queue {
 	struct mmc_card		*card;
 	struct task_struct	*thread;
 	struct semaphore	thread_sem;
 	unsigned int		flags;
-	struct request		*req;
 	int			(*issue_fn)(struct mmc_queue *, struct request *);
 	void			*data;
 	struct request_queue	*queue;
-	struct scatterlist	*sg;
-	char			*bounce_buf;
-	struct scatterlist	*bounce_sg;
-	unsigned int		bounce_sg_len;
+	struct mmc_queue_req	mqrq[2];
+	struct mmc_queue_req	*mqrq_cur;
+	struct mmc_queue_req	*mqrq_prev;
 };
 
 extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *,
@@ -25,8 +41,9 @@ extern void mmc_cleanup_queue(struct mmc_queue *);
 extern void mmc_queue_suspend(struct mmc_queue *);
 extern void mmc_queue_resume(struct mmc_queue *);
 
-extern unsigned int mmc_queue_map_sg(struct mmc_queue *);
-extern void mmc_queue_bounce_pre(struct mmc_queue *);
-extern void mmc_queue_bounce_post(struct mmc_queue *);
+extern unsigned int mmc_queue_map_sg(struct mmc_queue *,
+				     struct mmc_queue_req *);
+extern void mmc_queue_bounce_pre(struct mmc_queue_req *);
+extern void mmc_queue_bounce_post(struct mmc_queue_req *);
 
 #endif