Merge tag 'mmc-v4.16' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc

Pull MMC updates from Ulf Hansson:
 "There are two major achievements for MMC in this release, which
  deserves to be specially highlighted.

  First, we have converted the MMC block device from using the legacy
  blk interface into using the modern blkmq interface. Not only do we
  get all the nice effects from using blkmq, but it also means that new
  fresh nice code replaces old rusty code. Great news to everybody that
  cares about MMC/SD!

  It should also be noted that converting to blkmq has not been trivial,
  mostly because of that we have been carrying too much of MMC specific
  optimizations for the I/O request path, rather than striving to move
  these to the generic blk layer. Hopefully we won't be doing that
  mistake, ever again.

  Special thanks to Adrian Hunter (Intel) and to Linus Walleij (Linaro),
  who both have been working on this for quite some time!

  Second, on top of the blkmq deployment, we have enabled full support
  the eMMC command queuing feature, introduced in the eMMC v.5.1 spec.
  This also includes an implementation of a host driver library,
  supporting the corresponding CQHCI HW. Ideally, those controllers that
  supports CQHCI should only need some minor adaptations to make this
  play.

  So far the sdhci-pci driver for the Intel GLKs and the sdhci-of-arasan
  driver used on Rockchip RK3399, have enabled support for eMMC command
  queueing.

  Worth to highlight is also that, implementing the eMMC command queuing
  support has been a collaborative effort, as several people from
  Codeaurora, Rockchip, Intel and Linaro have been involved. However,
  the work has been driven by Adrian Hunter (Intel).

  In some shadow of the above, here are the rest of the highlights:

  MMC core:
   - Don't remove non-removable cards during system suspend
   - Add a slot-gpio helper to check capability of GPIO WP detection

  MMC host:
   - sdhci: Cleanups and improvements of some wakeup related code
   - sdhci-pci-arasan: New variant to support Arasan PCI HW with integrated phy
   - sdhci-acpi: Avoid broken UHS transfer modes on Intel CHT
   - sdhci-acpi: Add support for ACPI HID of AMD Controller with HS400
   - sdhci_f_sdh30: Add ACPI support
   - sdhci-esdhc-imx: Enable/disable clock at runtime suspend/resume
   - sdhci-of-esdhc: A few minor fixes
   - mmci: Add support for new STM32 variant
   - renesas_sdhi: enable R-Car D3 (r8a77995) support
   - tmio/renesas_sdhi: Re-structuring, cleanups and modernizations"

* tag 'mmc-v4.16' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc: (96 commits)
  mmc: mmci: fix error return code in mmci_probe()
  mmc: davinci: suppress error message on EPROBE_DEFER
  mmc: davinci: dont' use module_platform_driver_probe()
  mmc: tmio: hide unused tmio_mmc_clk_disable/tmio_mmc_clk_enable functions
  mmc: mmci: Add STM32 variant
  mmc: mmci: Add support for setting pad type via pinctrl
  mmc: mmci: Don't pretend all variants to have OPENDRAIN bit
  mmc: mmci: Don't pretend all variants to have MCI_STARBITERR flag
  mmc: mmci: Don't pretend all variants to have MMCIMASK1 register
  mmc: tmio: refactor .get_ro hook
  mmc: slot-gpio: add a helper to check capability of GPIO WP detection
  mmc: tmio: remove dma_ops from tmio_mmc_host_probe() argument
  mmc: tmio: move {tmio_}mmc_of_parse() to tmio_mmc_host_alloc()
  mmc: tmio: move clk_enable/disable out of tmio_mmc_host_probe()
  mmc: tmio: ioremap memory resource in tmio_mmc_host_alloc()
  mmc: sh_mmcif: remove redundant initialization of 'opc'
  mmc: sdhci: Rework sdhci_enable_irq_wakeups()
  mmc: sdhci: Handle failure of enable_irq_wake()
  mmc: sdhci: Stop exporting sdhci_enable_irq_wakeups()
  mmc: sdhci-pci: Use device wakeup capability to determine MMC_PM_WAKE_SDIO_IRQ capability
  ...

45 files changed, 3977 insertions, 1443 deletions

diff --git a/Documentation/devicetree/bindings/mmc/mtk-sd.txt b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
index 72d2a734ab85..9b8017670870 100644
--- a/Documentation/devicetree/bindings/mmc/mtk-sd.txt
+++ b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
@@ -12,6 +12,8 @@ Required properties:
 	"mediatek,mt8173-mmc": for mmc host ip compatible with mt8173
 	"mediatek,mt2701-mmc": for mmc host ip compatible with mt2701
 	"mediatek,mt2712-mmc": for mmc host ip compatible with mt2712
+	"mediatek,mt7623-mmc", "mediatek,mt2701-mmc": for MT7623 SoC
+
 - reg: physical base address of the controller and length
 - interrupts: Should contain MSDC interrupt number
 - clocks: Should contain phandle for the clock feeding the MMC controller
diff --git a/Documentation/devicetree/bindings/mmc/tmio_mmc.txt b/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
index 3c6762430fd9..d8685cb83325 100644
--- a/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
@@ -26,6 +26,7 @@ Required properties:
 		"renesas,sdhi-r8a7794" - SDHI IP on R8A7794 SoC
 		"renesas,sdhi-r8a7795" - SDHI IP on R8A7795 SoC
 		"renesas,sdhi-r8a7796" - SDHI IP on R8A7796 SoC
+		"renesas,sdhi-r8a77995" - SDHI IP on R8A77995 SoC
 		"renesas,sdhi-shmobile" - a generic sh-mobile SDHI controller
 		"renesas,rcar-gen1-sdhi" - a generic R-Car Gen1 SDHI controller
 		"renesas,rcar-gen2-sdhi" - a generic R-Car Gen2 or RZ/G1
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index ccfa98af1dd3..20135a5de748 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -63,7 +63,13 @@ MODULE_ALIAS("mmc:block");
 #endif
 #define MODULE_PARAM_PREFIX "mmcblk."
 
-#define MMC_BLK_TIMEOUT_MS  (10 * 60 * 1000)        /* 10 minute timeout */
+/*
+ * Set a 10 second timeout for polling write request busy state. Note, mmc core
+ * is setting a 3 second timeout for SD cards, and SDHCI has long had a 10
+ * second software timer to timeout the whole request, so 10 seconds should be
+ * ample.
+ */
+#define MMC_BLK_TIMEOUT_MS  (10 * 1000)
 #define MMC_SANITIZE_REQ_TIMEOUT 240000
 #define MMC_EXTRACT_INDEX_FROM_ARG(x) ((x & 0x00FF0000) >> 16)
 
@@ -112,6 +118,7 @@ struct mmc_blk_data {
 #define MMC_BLK_WRITE		BIT(1)
 #define MMC_BLK_DISCARD		BIT(2)
 #define MMC_BLK_SECDISCARD	BIT(3)
+#define MMC_BLK_CQE_RECOVERY	BIT(4)
 
 	/*
 	 * Only set in main mmc_blk_data associated
@@ -189,7 +196,7 @@ static void mmc_blk_put(struct mmc_blk_data *md)
 	md->usage--;
 	if (md->usage == 0) {
 		int devidx = mmc_get_devidx(md->disk);
-		blk_cleanup_queue(md->queue.queue);
+		blk_put_queue(md->queue.queue);
 		ida_simple_remove(&mmc_blk_ida, devidx);
 		put_disk(md->disk);
 		kfree(md);
@@ -921,14 +928,54 @@ static int mmc_sd_num_wr_blocks(struct mmc_card *card, u32 *written_blocks)
 	return 0;
 }
 
+static unsigned int mmc_blk_clock_khz(struct mmc_host *host)
+{
+	if (host->actual_clock)
+		return host->actual_clock / 1000;
+
+	/* Clock may be subject to a divisor, fudge it by a factor of 2. */
+	if (host->ios.clock)
+		return host->ios.clock / 2000;
+
+	/* How can there be no clock */
+	WARN_ON_ONCE(1);
+	return 100; /* 100 kHz is minimum possible value */
+}
+
+static unsigned int mmc_blk_data_timeout_ms(struct mmc_host *host,
+					    struct mmc_data *data)
+{
+	unsigned int ms = DIV_ROUND_UP(data->timeout_ns, 1000000);
+	unsigned int khz;
+
+	if (data->timeout_clks) {
+		khz = mmc_blk_clock_khz(host);
+		ms += DIV_ROUND_UP(data->timeout_clks, khz);
+	}
+
+	return ms;
+}
+
+static inline bool mmc_blk_in_tran_state(u32 status)
+{
+	/*
+	 * Some cards mishandle the status bits, so make sure to check both the
+	 * busy indication and the card state.
+	 */
+	return status & R1_READY_FOR_DATA &&
+	       (R1_CURRENT_STATE(status) == R1_STATE_TRAN);
+}
+
 static int card_busy_detect(struct mmc_card *card, unsigned int timeout_ms,
-		bool hw_busy_detect, struct request *req, bool *gen_err)
+			    struct request *req, u32 *resp_errs)
 {
 	unsigned long timeout = jiffies + msecs_to_jiffies(timeout_ms);
 	int err = 0;
 	u32 status;
 
 	do {
+		bool done = time_after(jiffies, timeout);
+
 		err = __mmc_send_status(card, &status, 5);
 		if (err) {
 			pr_err("%s: error %d requesting status\n",
@@ -936,25 +983,18 @@ static int card_busy_detect(struct mmc_card *card, unsigned int timeout_ms,
 			return err;
 		}
 
-		if (status & R1_ERROR) {
-			pr_err("%s: %s: error sending status cmd, status %#x\n",
-				req->rq_disk->disk_name, __func__, status);
-			*gen_err = true;
-		}
-
-		/* We may rely on the host hw to handle busy detection.*/
-		if ((card->host->caps & MMC_CAP_WAIT_WHILE_BUSY) &&
-			hw_busy_detect)
-			break;
+		/* Accumulate any response error bits seen */
+		if (resp_errs)
+			*resp_errs |= status;
 
 		/*
 		 * Timeout if the device never becomes ready for data and never
 		 * leaves the program state.
 		 */
-		if (time_after(jiffies, timeout)) {
-			pr_err("%s: Card stuck in programming state! %s %s\n",
+		if (done) {
+			pr_err("%s: Card stuck in wrong state! %s %s status: %#x\n",
 				mmc_hostname(card->host),
-				req->rq_disk->disk_name, __func__);
+				req->rq_disk->disk_name, __func__, status);
 			return -ETIMEDOUT;
 		}
 
@@ -963,229 +1003,11 @@ static int card_busy_detect(struct mmc_card *card, unsigned int timeout_ms,
 		 * 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));
+	} while (!mmc_blk_in_tran_state(status));
 
 	return err;
 }
 
-static int send_stop(struct mmc_card *card, unsigned int timeout_ms,
-		struct request *req, bool *gen_err, u32 *stop_status)
-{
-	struct mmc_host *host = card->host;
-	struct mmc_command cmd = {};
-	int err;
-	bool use_r1b_resp = rq_data_dir(req) == WRITE;
-
-	/*
-	 * Normally we use R1B responses for WRITE, but in cases where the host
-	 * has specified a max_busy_timeout we need to validate it. A failure
-	 * means we need to prevent the host from doing hw busy detection, which
-	 * is done by converting to a R1 response instead.
-	 */
-	if (host->max_busy_timeout && (timeout_ms > host->max_busy_timeout))
-		use_r1b_resp = false;
-
-	cmd.opcode = MMC_STOP_TRANSMISSION;
-	if (use_r1b_resp) {
-		cmd.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC;
-		cmd.busy_timeout = timeout_ms;
-	} else {
-		cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_AC;
-	}
-
-	err = mmc_wait_for_cmd(host, &cmd, 5);
-	if (err)
-		return err;
-
-	*stop_status = cmd.resp[0];
-
-	/* No need to check card status in case of READ. */
-	if (rq_data_dir(req) == READ)
-		return 0;
-
-	if (!mmc_host_is_spi(host) &&
-		(*stop_status & R1_ERROR)) {
-		pr_err("%s: %s: general error sending stop command, resp %#x\n",
-			req->rq_disk->disk_name, __func__, *stop_status);
-		*gen_err = true;
-	}
-
-	return card_busy_detect(card, timeout_ms, use_r1b_resp, req, gen_err);
-}
-
-#define ERR_NOMEDIUM	3
-#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) {
-			pr_err("%s: status not valid, retrying timeout\n",
-				req->rq_disk->disk_name);
-			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)) {
-			pr_err("%s: command error, retrying timeout\n",
-				req->rq_disk->disk_name);
-			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 *ecc_err, bool *gen_err)
-{
-	bool prev_cmd_status_valid = true;
-	u32 status, stop_status = 0;
-	int err, retry;
-
-	if (mmc_card_removed(card))
-		return ERR_NOMEDIUM;
-
-	/*
-	 * 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 = __mmc_send_status(card, &status, 0);
-		if (!err)
-			break;
-
-		/* Re-tune if needed */
-		mmc_retune_recheck(card->host);
-
-		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) {
-		/* Check if the card is removed */
-		if (mmc_detect_card_removed(card->host))
-			return ERR_NOMEDIUM;
-		return ERR_ABORT;
-	}
-
-	/* Flag ECC errors */
-	if ((status & R1_CARD_ECC_FAILED) ||
-	    (brq->stop.resp[0] & R1_CARD_ECC_FAILED) ||
-	    (brq->cmd.resp[0] & R1_CARD_ECC_FAILED))
-		*ecc_err = true;
-
-	/* Flag General errors */
-	if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ)
-		if ((status & R1_ERROR) ||
-			(brq->stop.resp[0] & R1_ERROR)) {
-			pr_err("%s: %s: general error sending stop or status command, stop cmd response %#x, card status %#x\n",
-			       req->rq_disk->disk_name, __func__,
-			       brq->stop.resp[0], status);
-			*gen_err = true;
-		}
-
-	/*
-	 * 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,
-			DIV_ROUND_UP(brq->data.timeout_ns, 1000000),
-			req, gen_err, &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.
-			 */
-			return ERR_ABORT;
-		}
-
-		if (stop_status & R1_CARD_ECC_FAILED)
-			*ecc_err = true;
-	}
-
-	/* 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);
-
-	/* Data errors */
-	if (!brq->stop.error)
-		return ERR_CONTINUE;
-
-	/* Now for stop errors.  These aren't fatal to the transfer. */
-	pr_info("%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_reset(struct mmc_blk_data *md, struct mmc_host *host,
 			 int type)
 {
@@ -1281,7 +1103,7 @@ static void mmc_blk_issue_drv_op(struct mmc_queue *mq, struct request *req)
 		break;
 	}
 	mq_rq->drv_op_result = ret;
-	blk_end_request_all(req, ret ? BLK_STS_IOERR : BLK_STS_OK);
+	blk_mq_end_request(req, ret ? BLK_STS_IOERR : BLK_STS_OK);
 }
 
 static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req)
@@ -1324,7 +1146,7 @@ static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req)
 	else
 		mmc_blk_reset_success(md, type);
 fail:
-	blk_end_request(req, status, blk_rq_bytes(req));
+	blk_mq_end_request(req, status);
 }
 
 static void mmc_blk_issue_secdiscard_rq(struct mmc_queue *mq,
@@ -1394,7 +1216,7 @@ out_retry:
 	if (!err)
 		mmc_blk_reset_success(md, type);
 out:
-	blk_end_request(req, status, blk_rq_bytes(req));
+	blk_mq_end_request(req, status);
 }
 
 static void mmc_blk_issue_flush(struct mmc_queue *mq, struct request *req)
@@ -1404,7 +1226,7 @@ static void mmc_blk_issue_flush(struct mmc_queue *mq, struct request *req)
 	int ret = 0;
 
 	ret = mmc_flush_cache(card);
-	blk_end_request_all(req, ret ? BLK_STS_IOERR : BLK_STS_OK);
+	blk_mq_end_request(req, ret ? BLK_STS_IOERR : BLK_STS_OK);
 }
 
 /*
@@ -1430,15 +1252,18 @@ static inline void mmc_apply_rel_rw(struct mmc_blk_request *brq,
 	}
 }
 
-#define CMD_ERRORS							\
-	(R1_OUT_OF_RANGE |	/* Command argument out of range */	\
-	 R1_ADDRESS_ERROR |	/* Misaligned address */		\
+#define CMD_ERRORS_EXCL_OOR						\
+	(R1_ADDRESS_ERROR |	/* Misaligned address */		\
 	 R1_BLOCK_LEN_ERROR |	/* Transferred block length incorrect */\
 	 R1_WP_VIOLATION |	/* Tried to write to protected block */	\
 	 R1_CARD_ECC_FAILED |	/* Card ECC failed */			\
 	 R1_CC_ERROR |		/* Card controller error */		\
 	 R1_ERROR)		/* General/unknown error */
 
+#define CMD_ERRORS							\
+	(CMD_ERRORS_EXCL_OOR |						\
+	 R1_OUT_OF_RANGE)	/* Command argument out of range */	\
+
 static void mmc_blk_eval_resp_error(struct mmc_blk_request *brq)
 {
 	u32 val;
@@ -1481,116 +1306,6 @@ static void mmc_blk_eval_resp_error(struct mmc_blk_request *brq)
 	}
 }
 
-static enum mmc_blk_status mmc_blk_err_check(struct mmc_card *card,
-					     struct mmc_async_req *areq)
-{
-	struct mmc_queue_req *mq_mrq = container_of(areq, struct mmc_queue_req,
-						    areq);
-	struct mmc_blk_request *brq = &mq_mrq->brq;
-	struct request *req = mmc_queue_req_to_req(mq_mrq);
-	int need_retune = card->host->need_retune;
-	bool ecc_err = false;
-	bool gen_err = false;
-
-	/*
-	 * 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.
-	 */
-
-	mmc_blk_eval_resp_error(brq);
-
-	if (brq->sbc.error || brq->cmd.error ||
-	    brq->stop.error || brq->data.error) {
-		switch (mmc_blk_cmd_recovery(card, req, brq, &ecc_err, &gen_err)) {
-		case ERR_RETRY:
-			return MMC_BLK_RETRY;
-		case ERR_ABORT:
-			return MMC_BLK_ABORT;
-		case ERR_NOMEDIUM:
-			return MMC_BLK_NOMEDIUM;
-		case ERR_CONTINUE:
-			break;
-		}
-	}
-
-	/*
-	 * 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;
-	}
-
-	/*
-	 * 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) {
-		int err;
-
-		/* Check stop command response */
-		if (brq->stop.resp[0] & R1_ERROR) {
-			pr_err("%s: %s: general error sending stop command, stop cmd response %#x\n",
-			       req->rq_disk->disk_name, __func__,
-			       brq->stop.resp[0]);
-			gen_err = true;
-		}
-
-		err = card_busy_detect(card, MMC_BLK_TIMEOUT_MS, false, req,
-					&gen_err);
-		if (err)
-			return MMC_BLK_CMD_ERR;
-	}
-
-	/* if general error occurs, retry the write operation. */
-	if (gen_err) {
-		pr_warn("%s: retrying write for general error\n",
-				req->rq_disk->disk_name);
-		return MMC_BLK_RETRY;
-	}
-
-	/* Some errors (ECC) are flagged on the next commmand, so check stop, too */
-	if (brq->data.error || brq->stop.error) {
-		if (need_retune && !brq->retune_retry_done) {
-			pr_debug("%s: retrying because a re-tune was needed\n",
-				 req->rq_disk->disk_name);
-			brq->retune_retry_done = 1;
-			return MMC_BLK_RETRY;
-		}
-		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 ?: brq->stop.error,
-		       (unsigned)blk_rq_pos(req),
-		       (unsigned)blk_rq_sectors(req),
-		       brq->cmd.resp[0], brq->stop.resp[0]);
-
-		if (rq_data_dir(req) == READ) {
-			if (ecc_err)
-				return MMC_BLK_ECC_ERR;
-			return MMC_BLK_DATA_ERR;
-		} else {
-			return MMC_BLK_CMD_ERR;
-		}
-	}
-
-	if (!brq->data.bytes_xfered)
-		return MMC_BLK_RETRY;
-
-	if (blk_rq_bytes(req) != brq->data.bytes_xfered)
-		return MMC_BLK_PARTIAL;
-
-	return MMC_BLK_SUCCESS;
-}
-
 static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq,
 			      int disable_multi, bool *do_rel_wr_p,
 			      bool *do_data_tag_p)
@@ -1706,8 +1421,6 @@ static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq,
 		brq->data.sg_len = i;
 	}
 
-	mqrq->areq.mrq = &brq->mrq;
-
 	if (do_rel_wr_p)
 		*do_rel_wr_p = do_rel_wr;
 
@@ -1715,6 +1428,138 @@ static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq,
 		*do_data_tag_p = do_data_tag;
 }
 
+#define MMC_CQE_RETRIES 2
+
+static void mmc_blk_cqe_complete_rq(struct mmc_queue *mq, struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_request *mrq = &mqrq->brq.mrq;
+	struct request_queue *q = req->q;
+	struct mmc_host *host = mq->card->host;
+	unsigned long flags;
+	bool put_card;
+	int err;
+
+	mmc_cqe_post_req(host, mrq);
+
+	if (mrq->cmd && mrq->cmd->error)
+		err = mrq->cmd->error;
+	else if (mrq->data && mrq->data->error)
+		err = mrq->data->error;
+	else
+		err = 0;
+
+	if (err) {
+		if (mqrq->retries++ < MMC_CQE_RETRIES)
+			blk_mq_requeue_request(req, true);
+		else
+			blk_mq_end_request(req, BLK_STS_IOERR);
+	} else if (mrq->data) {
+		if (blk_update_request(req, BLK_STS_OK, mrq->data->bytes_xfered))
+			blk_mq_requeue_request(req, true);
+		else
+			__blk_mq_end_request(req, BLK_STS_OK);
+	} else {
+		blk_mq_end_request(req, BLK_STS_OK);
+	}
+
+	spin_lock_irqsave(q->queue_lock, flags);
+
+	mq->in_flight[mmc_issue_type(mq, req)] -= 1;
+
+	put_card = (mmc_tot_in_flight(mq) == 0);
+
+	mmc_cqe_check_busy(mq);
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	if (!mq->cqe_busy)
+		blk_mq_run_hw_queues(q, true);
+
+	if (put_card)
+		mmc_put_card(mq->card, &mq->ctx);
+}
+
+void mmc_blk_cqe_recovery(struct mmc_queue *mq)
+{
+	struct mmc_card *card = mq->card;
+	struct mmc_host *host = card->host;
+	int err;
+
+	pr_debug("%s: CQE recovery start\n", mmc_hostname(host));
+
+	err = mmc_cqe_recovery(host);
+	if (err)
+		mmc_blk_reset(mq->blkdata, host, MMC_BLK_CQE_RECOVERY);
+	else
+		mmc_blk_reset_success(mq->blkdata, MMC_BLK_CQE_RECOVERY);
+
+	pr_debug("%s: CQE recovery done\n", mmc_hostname(host));
+}
+
+static void mmc_blk_cqe_req_done(struct mmc_request *mrq)
+{
+	struct mmc_queue_req *mqrq = container_of(mrq, struct mmc_queue_req,
+						  brq.mrq);
+	struct request *req = mmc_queue_req_to_req(mqrq);
+	struct request_queue *q = req->q;
+	struct mmc_queue *mq = q->queuedata;
+
+	/*
+	 * Block layer timeouts race with completions which means the normal
+	 * completion path cannot be used during recovery.
+	 */
+	if (mq->in_recovery)
+		mmc_blk_cqe_complete_rq(mq, req);
+	else
+		blk_mq_complete_request(req);
+}
+
+static int mmc_blk_cqe_start_req(struct mmc_host *host, struct mmc_request *mrq)
+{
+	mrq->done		= mmc_blk_cqe_req_done;
+	mrq->recovery_notifier	= mmc_cqe_recovery_notifier;
+
+	return mmc_cqe_start_req(host, mrq);
+}
+
+static struct mmc_request *mmc_blk_cqe_prep_dcmd(struct mmc_queue_req *mqrq,
+						 struct request *req)
+{
+	struct mmc_blk_request *brq = &mqrq->brq;
+
+	memset(brq, 0, sizeof(*brq));
+
+	brq->mrq.cmd = &brq->cmd;
+	brq->mrq.tag = req->tag;
+
+	return &brq->mrq;
+}
+
+static int mmc_blk_cqe_issue_flush(struct mmc_queue *mq, struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_request *mrq = mmc_blk_cqe_prep_dcmd(mqrq, req);
+
+	mrq->cmd->opcode = MMC_SWITCH;
+	mrq->cmd->arg = (MMC_SWITCH_MODE_WRITE_BYTE << 24) |
+			(EXT_CSD_FLUSH_CACHE << 16) |
+			(1 << 8) |
+			EXT_CSD_CMD_SET_NORMAL;
+	mrq->cmd->flags = MMC_CMD_AC | MMC_RSP_R1B;
+
+	return mmc_blk_cqe_start_req(mq->card->host, mrq);
+}
+
+static int mmc_blk_cqe_issue_rw_rq(struct mmc_queue *mq, struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+
+	mmc_blk_data_prep(mq, mqrq, 0, NULL, NULL);
+
+	return mmc_blk_cqe_start_req(mq->card->host, &mqrq->brq.mrq);
+}
+
 static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 			       struct mmc_card *card,
 			       int disable_multi,
@@ -1779,318 +1624,637 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 		brq->sbc.flags = MMC_RSP_R1 | MMC_CMD_AC;
 		brq->mrq.sbc = &brq->sbc;
 	}
+}
+
+#define MMC_MAX_RETRIES		5
+#define MMC_DATA_RETRIES	2
+#define MMC_NO_RETRIES		(MMC_MAX_RETRIES + 1)
 
-	mqrq->areq.err_check = mmc_blk_err_check;
+static int mmc_blk_send_stop(struct mmc_card *card, unsigned int timeout)
+{
+	struct mmc_command cmd = {
+		.opcode = MMC_STOP_TRANSMISSION,
+		.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_AC,
+		/* Some hosts wait for busy anyway, so provide a busy timeout */
+		.busy_timeout = timeout,
+	};
+
+	return mmc_wait_for_cmd(card->host, &cmd, 5);
 }
 
-static bool mmc_blk_rw_cmd_err(struct mmc_blk_data *md, struct mmc_card *card,
-			       struct mmc_blk_request *brq, struct request *req,
-			       bool old_req_pending)
+static int mmc_blk_fix_state(struct mmc_card *card, struct request *req)
 {
-	bool req_pending;
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_blk_request *brq = &mqrq->brq;
+	unsigned int timeout = mmc_blk_data_timeout_ms(card->host, &brq->data);
+	int err;
 
-	/*
-	 * If this is an SD card and we're writing, we can first
-	 * mark the known good sectors as ok.
-	 *
-	 * If the card is not SD, we can still ok written sectors
-	 * as reported by the controller (which might be less than
-	 * the real number of written sectors, but never more).
-	 */
-	if (mmc_card_sd(card)) {
-		u32 blocks;
+	mmc_retune_hold_now(card->host);
+
+	mmc_blk_send_stop(card, timeout);
+
+	err = card_busy_detect(card, timeout, req, NULL);
+
+	mmc_retune_release(card->host);
+
+	return err;
+}
+
+#define MMC_READ_SINGLE_RETRIES	2
+
+/* Single sector read during recovery */
+static void mmc_blk_read_single(struct mmc_queue *mq, struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_request *mrq = &mqrq->brq.mrq;
+	struct mmc_card *card = mq->card;
+	struct mmc_host *host = card->host;
+	blk_status_t error = BLK_STS_OK;
+	int retries = 0;
+
+	do {
+		u32 status;
 		int err;
 
-		err = mmc_sd_num_wr_blocks(card, &blocks);
+		mmc_blk_rw_rq_prep(mqrq, card, 1, mq);
+
+		mmc_wait_for_req(host, mrq);
+
+		err = mmc_send_status(card, &status);
 		if (err)
-			req_pending = old_req_pending;
+			goto error_exit;
+
+		if (!mmc_host_is_spi(host) &&
+		    !mmc_blk_in_tran_state(status)) {
+			err = mmc_blk_fix_state(card, req);
+			if (err)
+				goto error_exit;
+		}
+
+		if (mrq->cmd->error && retries++ < MMC_READ_SINGLE_RETRIES)
+			continue;
+
+		retries = 0;
+
+		if (mrq->cmd->error ||
+		    mrq->data->error ||
+		    (!mmc_host_is_spi(host) &&
+		     (mrq->cmd->resp[0] & CMD_ERRORS || status & CMD_ERRORS)))
+			error = BLK_STS_IOERR;
 		else
-			req_pending = blk_end_request(req, BLK_STS_OK, blocks << 9);
-	} else {
-		req_pending = blk_end_request(req, BLK_STS_OK, brq->data.bytes_xfered);
-	}
-	return req_pending;
+			error = BLK_STS_OK;
+
+	} while (blk_update_request(req, error, 512));
+
+	return;
+
+error_exit:
+	mrq->data->bytes_xfered = 0;
+	blk_update_request(req, BLK_STS_IOERR, 512);
+	/* Let it try the remaining request again */
+	if (mqrq->retries > MMC_MAX_RETRIES - 1)
+		mqrq->retries = MMC_MAX_RETRIES - 1;
 }
 
-static void mmc_blk_rw_cmd_abort(struct mmc_queue *mq, struct mmc_card *card,
-				 struct request *req,
-				 struct mmc_queue_req *mqrq)
+static inline bool mmc_blk_oor_valid(struct mmc_blk_request *brq)
 {
-	if (mmc_card_removed(card))
-		req->rq_flags |= RQF_QUIET;
-	while (blk_end_request(req, BLK_STS_IOERR, blk_rq_cur_bytes(req)));
-	mq->qcnt--;
+	return !!brq->mrq.sbc;
 }
 
-/**
- * mmc_blk_rw_try_restart() - tries to restart the current async request
- * @mq: the queue with the card and host to restart
- * @req: a new request that want to be started after the current one
+static inline u32 mmc_blk_stop_err_bits(struct mmc_blk_request *brq)
+{
+	return mmc_blk_oor_valid(brq) ? CMD_ERRORS : CMD_ERRORS_EXCL_OOR;
+}
+
+/*
+ * Check for errors the host controller driver might not have seen such as
+ * response mode errors or invalid card state.
+ */
+static bool mmc_blk_status_error(struct request *req, u32 status)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_blk_request *brq = &mqrq->brq;
+	struct mmc_queue *mq = req->q->queuedata;
+	u32 stop_err_bits;
+
+	if (mmc_host_is_spi(mq->card->host))
+		return false;
+
+	stop_err_bits = mmc_blk_stop_err_bits(brq);
+
+	return brq->cmd.resp[0]  & CMD_ERRORS    ||
+	       brq->stop.resp[0] & stop_err_bits ||
+	       status            & stop_err_bits ||
+	       (rq_data_dir(req) == WRITE && !mmc_blk_in_tran_state(status));
+}
+
+static inline bool mmc_blk_cmd_started(struct mmc_blk_request *brq)
+{
+	return !brq->sbc.error && !brq->cmd.error &&
+	       !(brq->cmd.resp[0] & CMD_ERRORS);
+}
+
+/*
+ * Requests are completed by mmc_blk_mq_complete_rq() which sets simple
+ * policy:
+ * 1. A request that has transferred at least some data is considered
+ * successful and will be requeued if there is remaining data to
+ * transfer.
+ * 2. Otherwise the number of retries is incremented and the request
+ * will be requeued if there are remaining retries.
+ * 3. Otherwise the request will be errored out.
+ * That means mmc_blk_mq_complete_rq() is controlled by bytes_xfered and
+ * mqrq->retries. So there are only 4 possible actions here:
+ *	1. do not accept the bytes_xfered value i.e. set it to zero
+ *	2. change mqrq->retries to determine the number of retries
+ *	3. try to reset the card
+ *	4. read one sector at a time
  */
-static void mmc_blk_rw_try_restart(struct mmc_queue *mq, struct request *req,
-				   struct mmc_queue_req *mqrq)
+static void mmc_blk_mq_rw_recovery(struct mmc_queue *mq, struct request *req)
 {
-	if (!req)
+	int type = rq_data_dir(req) == READ ? MMC_BLK_READ : MMC_BLK_WRITE;
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_blk_request *brq = &mqrq->brq;
+	struct mmc_blk_data *md = mq->blkdata;
+	struct mmc_card *card = mq->card;
+	u32 status;
+	u32 blocks;
+	int err;
+
+	/*
+	 * Some errors the host driver might not have seen. Set the number of
+	 * bytes transferred to zero in that case.
+	 */
+	err = __mmc_send_status(card, &status, 0);
+	if (err || mmc_blk_status_error(req, status))
+		brq->data.bytes_xfered = 0;
+
+	mmc_retune_release(card->host);
+
+	/*
+	 * Try again to get the status. This also provides an opportunity for
+	 * re-tuning.
+	 */
+	if (err)
+		err = __mmc_send_status(card, &status, 0);
+
+	/*
+	 * Nothing more to do after the number of bytes transferred has been
+	 * updated and there is no card.
+	 */
+	if (err && mmc_detect_card_removed(card->host))
 		return;
 
+	/* Try to get back to "tran" state */
+	if (!mmc_host_is_spi(mq->card->host) &&
+	    (err || !mmc_blk_in_tran_state(status)))
+		err = mmc_blk_fix_state(mq->card, req);
+
 	/*
-	 * If the card was removed, just cancel everything and return.
+	 * Special case for SD cards where the card might record the number of
+	 * blocks written.
 	 */
-	if (mmc_card_removed(mq->card)) {
-		req->rq_flags |= RQF_QUIET;
-		blk_end_request_all(req, BLK_STS_IOERR);
-		mq->qcnt--; /* FIXME: just set to 0? */
+	if (!err && mmc_blk_cmd_started(brq) && mmc_card_sd(card) &&
+	    rq_data_dir(req) == WRITE) {
+		if (mmc_sd_num_wr_blocks(card, &blocks))
+			brq->data.bytes_xfered = 0;
+		else
+			brq->data.bytes_xfered = blocks << 9;
+	}
+
+	/* Reset if the card is in a bad state */
+	if (!mmc_host_is_spi(mq->card->host) &&
+	    err && mmc_blk_reset(md, card->host, type)) {
+		pr_err("%s: recovery failed!\n", req->rq_disk->disk_name);
+		mqrq->retries = MMC_NO_RETRIES;
+		return;
+	}
+
+	/*
+	 * If anything was done, just return and if there is anything remaining
+	 * on the request it will get requeued.
+	 */
+	if (brq->data.bytes_xfered)
+		return;
+
+	/* Reset before last retry */
+	if (mqrq->retries + 1 == MMC_MAX_RETRIES)
+		mmc_blk_reset(md, card->host, type);
+
+	/* Command errors fail fast, so use all MMC_MAX_RETRIES */
+	if (brq->sbc.error || brq->cmd.error)
+		return;
+
+	/* Reduce the remaining retries for data errors */
+	if (mqrq->retries < MMC_MAX_RETRIES - MMC_DATA_RETRIES) {
+		mqrq->retries = MMC_MAX_RETRIES - MMC_DATA_RETRIES;
+		return;
+	}
+
+	/* FIXME: Missing single sector read for large sector size */
+	if (!mmc_large_sector(card) && rq_data_dir(req) == READ &&
+	    brq->data.blocks > 1) {
+		/* Read one sector at a time */
+		mmc_blk_read_single(mq, req);
 		return;
 	}
-	/* Else proceed and try to restart the current async request */
-	mmc_blk_rw_rq_prep(mqrq, mq->card, 0, mq);
-	mmc_start_areq(mq->card->host, &mqrq->areq, NULL);
 }
 
-static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req)
+static inline bool mmc_blk_rq_error(struct mmc_blk_request *brq)
 {
-	struct mmc_blk_data *md = mq->blkdata;
-	struct mmc_card *card = md->queue.card;
-	struct mmc_blk_request *brq;
-	int disable_multi = 0, retry = 0, type, retune_retry_done = 0;
-	enum mmc_blk_status status;
-	struct mmc_queue_req *mqrq_cur = NULL;
-	struct mmc_queue_req *mq_rq;
-	struct request *old_req;
-	struct mmc_async_req *new_areq;
-	struct mmc_async_req *old_areq;
-	bool req_pending = true;
+	mmc_blk_eval_resp_error(brq);
+
+	return brq->sbc.error || brq->cmd.error || brq->stop.error ||
+	       brq->data.error || brq->cmd.resp[0] & CMD_ERRORS;
+}
+
+static int mmc_blk_card_busy(struct mmc_card *card, struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	u32 status = 0;
+	int err;
+
+	if (mmc_host_is_spi(card->host) || rq_data_dir(req) == READ)
+		return 0;
+
+	err = card_busy_detect(card, MMC_BLK_TIMEOUT_MS, req, &status);
+
+	/*
+	 * Do not assume data transferred correctly if there are any error bits
+	 * set.
+	 */
+	if (status & mmc_blk_stop_err_bits(&mqrq->brq)) {
+		mqrq->brq.data.bytes_xfered = 0;
+		err = err ? err : -EIO;
+	}
+
+	/* Copy the exception bit so it will be seen later on */
+	if (mmc_card_mmc(card) && status & R1_EXCEPTION_EVENT)
+		mqrq->brq.cmd.resp[0] |= R1_EXCEPTION_EVENT;
+
+	return err;
+}
 
-	if (new_req) {
-		mqrq_cur = req_to_mmc_queue_req(new_req);
-		mq->qcnt++;
+static inline void mmc_blk_rw_reset_success(struct mmc_queue *mq,
+					    struct request *req)
+{
+	int type = rq_data_dir(req) == READ ? MMC_BLK_READ : MMC_BLK_WRITE;
+
+	mmc_blk_reset_success(mq->blkdata, type);
+}
+
+static void mmc_blk_mq_complete_rq(struct mmc_queue *mq, struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	unsigned int nr_bytes = mqrq->brq.data.bytes_xfered;
+
+	if (nr_bytes) {
+		if (blk_update_request(req, BLK_STS_OK, nr_bytes))
+			blk_mq_requeue_request(req, true);
+		else
+			__blk_mq_end_request(req, BLK_STS_OK);
+	} else if (!blk_rq_bytes(req)) {
+		__blk_mq_end_request(req, BLK_STS_IOERR);
+	} else if (mqrq->retries++ < MMC_MAX_RETRIES) {
+		blk_mq_requeue_request(req, true);
+	} else {
+		if (mmc_card_removed(mq->card))
+			req->rq_flags |= RQF_QUIET;
+		blk_mq_end_request(req, BLK_STS_IOERR);
+	}
+}
+
+static bool mmc_blk_urgent_bkops_needed(struct mmc_queue *mq,
+					struct mmc_queue_req *mqrq)
+{
+	return mmc_card_mmc(mq->card) && !mmc_host_is_spi(mq->card->host) &&
+	       (mqrq->brq.cmd.resp[0] & R1_EXCEPTION_EVENT ||
+		mqrq->brq.stop.resp[0] & R1_EXCEPTION_EVENT);
+}
+
+static void mmc_blk_urgent_bkops(struct mmc_queue *mq,
+				 struct mmc_queue_req *mqrq)
+{
+	if (mmc_blk_urgent_bkops_needed(mq, mqrq))
+		mmc_start_bkops(mq->card, true);
+}
+
+void mmc_blk_mq_complete(struct request *req)
+{
+	struct mmc_queue *mq = req->q->queuedata;
+
+	if (mq->use_cqe)
+		mmc_blk_cqe_complete_rq(mq, req);
+	else
+		mmc_blk_mq_complete_rq(mq, req);
+}
+
+static void mmc_blk_mq_poll_completion(struct mmc_queue *mq,
+				       struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_host *host = mq->card->host;
+
+	if (mmc_blk_rq_error(&mqrq->brq) ||
+	    mmc_blk_card_busy(mq->card, req)) {
+		mmc_blk_mq_rw_recovery(mq, req);
+	} else {
+		mmc_blk_rw_reset_success(mq, req);
+		mmc_retune_release(host);
+	}
+
+	mmc_blk_urgent_bkops(mq, mqrq);
+}
+
+static void mmc_blk_mq_dec_in_flight(struct mmc_queue *mq, struct request *req)
+{
+	struct request_queue *q = req->q;
+	unsigned long flags;
+	bool put_card;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+
+	mq->in_flight[mmc_issue_type(mq, req)] -= 1;
+
+	put_card = (mmc_tot_in_flight(mq) == 0);
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	if (put_card)
+		mmc_put_card(mq->card, &mq->ctx);
+}
+
+static void mmc_blk_mq_post_req(struct mmc_queue *mq, struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_request *mrq = &mqrq->brq.mrq;
+	struct mmc_host *host = mq->card->host;
+
+	mmc_post_req(host, mrq, 0);
+
+	/*
+	 * Block layer timeouts race with completions which means the normal
+	 * completion path cannot be used during recovery.
+	 */
+	if (mq->in_recovery)
+		mmc_blk_mq_complete_rq(mq, req);
+	else
+		blk_mq_complete_request(req);
+
+	mmc_blk_mq_dec_in_flight(mq, req);
+}
+
+void mmc_blk_mq_recovery(struct mmc_queue *mq)
+{
+	struct request *req = mq->recovery_req;
+	struct mmc_host *host = mq->card->host;
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+
+	mq->recovery_req = NULL;
+	mq->rw_wait = false;
+
+	if (mmc_blk_rq_error(&mqrq->brq)) {
+		mmc_retune_hold_now(host);
+		mmc_blk_mq_rw_recovery(mq, req);
 	}
 
-	if (!mq->qcnt)
+	mmc_blk_urgent_bkops(mq, mqrq);
+
+	mmc_blk_mq_post_req(mq, req);
+}
+
+static void mmc_blk_mq_complete_prev_req(struct mmc_queue *mq,
+					 struct request **prev_req)
+{
+	if (mmc_host_done_complete(mq->card->host))
 		return;
 
-	do {
-		if (new_req) {
-			/*
-			 * When 4KB native sector is enabled, only 8 blocks
-			 * multiple read or write is allowed
-			 */
-			if (mmc_large_sector(card) &&
-				!IS_ALIGNED(blk_rq_sectors(new_req), 8)) {
-				pr_err("%s: Transfer size is not 4KB sector size aligned\n",
-					new_req->rq_disk->disk_name);
-				mmc_blk_rw_cmd_abort(mq, card, new_req, mqrq_cur);
-				return;
-			}
+	mutex_lock(&mq->complete_lock);
 
-			mmc_blk_rw_rq_prep(mqrq_cur, card, 0, mq);
-			new_areq = &mqrq_cur->areq;
-		} else
-			new_areq = NULL;
+	if (!mq->complete_req)
+		goto out_unlock;
 
-		old_areq = mmc_start_areq(card->host, new_areq, &status);
-		if (!old_areq) {
-			/*
-			 * We have just put the first request into the pipeline
-			 * and there is nothing more to do until it is
-			 * complete.
-			 */
-			return;
-		}
+	mmc_blk_mq_poll_completion(mq, mq->complete_req);
+
+	if (prev_req)
+		*prev_req = mq->complete_req;
+	else
+		mmc_blk_mq_post_req(mq, mq->complete_req);
+
+	mq->complete_req = NULL;
+
+out_unlock:
+	mutex_unlock(&mq->complete_lock);
+}
+
+void mmc_blk_mq_complete_work(struct work_struct *work)
+{
+	struct mmc_queue *mq = container_of(work, struct mmc_queue,
+					    complete_work);
+
+	mmc_blk_mq_complete_prev_req(mq, NULL);
+}
+
+static void mmc_blk_mq_req_done(struct mmc_request *mrq)
+{
+	struct mmc_queue_req *mqrq = container_of(mrq, struct mmc_queue_req,
+						  brq.mrq);
+	struct request *req = mmc_queue_req_to_req(mqrq);
+	struct request_queue *q = req->q;
+	struct mmc_queue *mq = q->queuedata;
+	struct mmc_host *host = mq->card->host;
+	unsigned long flags;
+
+	if (!mmc_host_done_complete(host)) {
+		bool waiting;
 
 		/*
-		 * An asynchronous request has been completed and we proceed
-		 * to handle the result of it.
+		 * We cannot complete the request in this context, so record
+		 * that there is a request to complete, and that a following
+		 * request does not need to wait (although it does need to
+		 * complete complete_req first).
 		 */
-		mq_rq =	container_of(old_areq, struct mmc_queue_req, areq);
-		brq = &mq_rq->brq;
-		old_req = mmc_queue_req_to_req(mq_rq);
-		type = rq_data_dir(old_req) == READ ? MMC_BLK_READ : MMC_BLK_WRITE;
-
-		switch (status) {
-		case MMC_BLK_SUCCESS:
-		case MMC_BLK_PARTIAL:
-			/*
-			 * A block was successfully transferred.
-			 */
-			mmc_blk_reset_success(md, type);
+		spin_lock_irqsave(q->queue_lock, flags);
+		mq->complete_req = req;
+		mq->rw_wait = false;
+		waiting = mq->waiting;
+		spin_unlock_irqrestore(q->queue_lock, flags);
 
-			req_pending = blk_end_request(old_req, BLK_STS_OK,
-						      brq->data.bytes_xfered);
-			/*
-			 * If the blk_end_request function returns non-zero even
-			 * though all data has been transferred and no errors
-			 * were returned by the host controller, it's a bug.
-			 */
-			if (status == MMC_BLK_SUCCESS && req_pending) {
-				pr_err("%s BUG rq_tot %d d_xfer %d\n",
-				       __func__, blk_rq_bytes(old_req),
-				       brq->data.bytes_xfered);
-				mmc_blk_rw_cmd_abort(mq, card, old_req, mq_rq);
-				return;
-			}
-			break;
-		case MMC_BLK_CMD_ERR:
-			req_pending = mmc_blk_rw_cmd_err(md, card, brq, old_req, req_pending);
-			if (mmc_blk_reset(md, card->host, type)) {
-				if (req_pending)
-					mmc_blk_rw_cmd_abort(mq, card, old_req, mq_rq);
-				else
-					mq->qcnt--;
-				mmc_blk_rw_try_restart(mq, new_req, mqrq_cur);
-				return;
-			}
-			if (!req_pending) {
-				mq->qcnt--;
-				mmc_blk_rw_try_restart(mq, new_req, mqrq_cur);
-				return;
-			}
-			break;
-		case MMC_BLK_RETRY:
-			retune_retry_done = brq->retune_retry_done;
-			if (retry++ < 5)
-				break;
-			/* Fall through */
-		case MMC_BLK_ABORT:
-			if (!mmc_blk_reset(md, card->host, type))
-				break;
-			mmc_blk_rw_cmd_abort(mq, card, old_req, mq_rq);
-			mmc_blk_rw_try_restart(mq, new_req, mqrq_cur);
-			return;
-		case MMC_BLK_DATA_ERR: {
-			int err;
-
-			err = mmc_blk_reset(md, card->host, type);
-			if (!err)
-				break;
-			if (err == -ENODEV) {
-				mmc_blk_rw_cmd_abort(mq, card, old_req, mq_rq);
-				mmc_blk_rw_try_restart(mq, new_req, mqrq_cur);
-				return;
-			}
-			/* Fall through */
-		}
-		case MMC_BLK_ECC_ERR:
-			if (brq->data.blocks > 1) {
-				/* Redo read one sector at a time */
-				pr_warn("%s: retrying using single block read\n",
-					old_req->rq_disk->disk_name);
-				disable_multi = 1;
-				break;
-			}
-			/*
-			 * After an error, we redo I/O one sector at a
-			 * time, so we only reach here after trying to
-			 * read a single sector.
-			 */
-			req_pending = blk_end_request(old_req, BLK_STS_IOERR,
-						      brq->data.blksz);
-			if (!req_pending) {
-				mq->qcnt--;
-				mmc_blk_rw_try_restart(mq, new_req, mqrq_cur);
-				return;
-			}
-			break;
-		case MMC_BLK_NOMEDIUM:
-			mmc_blk_rw_cmd_abort(mq, card, old_req, mq_rq);
-			mmc_blk_rw_try_restart(mq, new_req, mqrq_cur);
-			return;
-		default:
-			pr_err("%s: Unhandled return value (%d)",
-					old_req->rq_disk->disk_name, status);
-			mmc_blk_rw_cmd_abort(mq, card, old_req, mq_rq);
-			mmc_blk_rw_try_restart(mq, new_req, mqrq_cur);
-			return;
-		}
+		/*
+		 * If 'waiting' then the waiting task will complete this
+		 * request, otherwise queue a work to do it. Note that
+		 * complete_work may still race with the dispatch of a following
+		 * request.
+		 */
+		if (waiting)
+			wake_up(&mq->wait);
+		else
+			kblockd_schedule_work(&mq->complete_work);
 
-		if (req_pending) {
-			/*
-			 * In case of a incomplete request
-			 * prepare it again and resend.
-			 */
-			mmc_blk_rw_rq_prep(mq_rq, card,
-					disable_multi, mq);
-			mmc_start_areq(card->host,
-					&mq_rq->areq, NULL);
-			mq_rq->brq.retune_retry_done = retune_retry_done;
-		}
-	} while (req_pending);
+		return;
+	}
+
+	/* Take the recovery path for errors or urgent background operations */
+	if (mmc_blk_rq_error(&mqrq->brq) ||
+	    mmc_blk_urgent_bkops_needed(mq, mqrq)) {
+		spin_lock_irqsave(q->queue_lock, flags);
+		mq->recovery_needed = true;
+		mq->recovery_req = req;
+		spin_unlock_irqrestore(q->queue_lock, flags);
+		wake_up(&mq->wait);
+		schedule_work(&mq->recovery_work);
+		return;
+	}
+
+	mmc_blk_rw_reset_success(mq, req);
 
-	mq->qcnt--;
+	mq->rw_wait = false;
+	wake_up(&mq->wait);
+
+	mmc_blk_mq_post_req(mq, req);
 }
 
-void mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
+static bool mmc_blk_rw_wait_cond(struct mmc_queue *mq, int *err)
+{
+	struct request_queue *q = mq->queue;
+	unsigned long flags;
+	bool done;
+
+	/*
+	 * Wait while there is another request in progress, but not if recovery
+	 * is needed. Also indicate whether there is a request waiting to start.
+	 */
+	spin_lock_irqsave(q->queue_lock, flags);
+	if (mq->recovery_needed) {
+		*err = -EBUSY;
+		done = true;
+	} else {
+		done = !mq->rw_wait;
+	}
+	mq->waiting = !done;
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	return done;
+}
+
+static int mmc_blk_rw_wait(struct mmc_queue *mq, struct request **prev_req)
+{
+	int err = 0;
+
+	wait_event(mq->wait, mmc_blk_rw_wait_cond(mq, &err));
+
+	/* Always complete the previous request if there is one */
+	mmc_blk_mq_complete_prev_req(mq, prev_req);
+
+	return err;
+}
+
+static int mmc_blk_mq_issue_rw_rq(struct mmc_queue *mq,
+				  struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_host *host = mq->card->host;
+	struct request *prev_req = NULL;
+	int err = 0;
+
+	mmc_blk_rw_rq_prep(mqrq, mq->card, 0, mq);
+
+	mqrq->brq.mrq.done = mmc_blk_mq_req_done;
+
+	mmc_pre_req(host, &mqrq->brq.mrq);
+
+	err = mmc_blk_rw_wait(mq, &prev_req);
+	if (err)
+		goto out_post_req;
+
+	mq->rw_wait = true;
+
+	err = mmc_start_request(host, &mqrq->brq.mrq);
+
+	if (prev_req)
+		mmc_blk_mq_post_req(mq, prev_req);
+
+	if (err)
+		mq->rw_wait = false;
+
+	/* Release re-tuning here where there is no synchronization required */
+	if (err || mmc_host_done_complete(host))
+		mmc_retune_release(host);
+
+out_post_req:
+	if (err)
+		mmc_post_req(host, &mqrq->brq.mrq, err);
+
+	return err;
+}
+
+static int mmc_blk_wait_for_idle(struct mmc_queue *mq, struct mmc_host *host)
+{
+	if (mq->use_cqe)
+		return host->cqe_ops->cqe_wait_for_idle(host);
+
+	return mmc_blk_rw_wait(mq, NULL);
+}
+
+enum mmc_issued mmc_blk_mq_issue_rq(struct mmc_queue *mq, struct request *req)
 {
-	int ret;
 	struct mmc_blk_data *md = mq->blkdata;
 	struct mmc_card *card = md->queue.card;
-
-	if (req && !mq->qcnt)
-		/* claim host only for the first request */
-		mmc_get_card(card, NULL);
+	struct mmc_host *host = card->host;
+	int ret;
 
 	ret = mmc_blk_part_switch(card, md->part_type);
-	if (ret) {
-		if (req) {
-			blk_end_request_all(req, BLK_STS_IOERR);
-		}
-		goto out;
-	}
+	if (ret)
+		return MMC_REQ_FAILED_TO_START;
 
-	if (req) {
+	switch (mmc_issue_type(mq, req)) {
+	case MMC_ISSUE_SYNC:
+		ret = mmc_blk_wait_for_idle(mq, host);
+		if (ret)
+			return MMC_REQ_BUSY;
 		switch (req_op(req)) {
 		case REQ_OP_DRV_IN:
 		case REQ_OP_DRV_OUT:
-			/*
-			 * Complete ongoing async transfer before issuing
-			 * ioctl()s
-			 */
-			if (mq->qcnt)
-				mmc_blk_issue_rw_rq(mq, NULL);
 			mmc_blk_issue_drv_op(mq, req);
 			break;
 		case REQ_OP_DISCARD:
-			/*
-			 * Complete ongoing async transfer before issuing
-			 * discard.
-			 */
-			if (mq->qcnt)
-				mmc_blk_issue_rw_rq(mq, NULL);
 			mmc_blk_issue_discard_rq(mq, req);
 			break;
 		case REQ_OP_SECURE_ERASE:
-			/*
-			 * Complete ongoing async transfer before issuing
-			 * secure erase.
-			 */
-			if (mq->qcnt)
-				mmc_blk_issue_rw_rq(mq, NULL);
 			mmc_blk_issue_secdiscard_rq(mq, req);
 			break;
 		case REQ_OP_FLUSH:
-			/*
-			 * Complete ongoing async transfer before issuing
-			 * flush.
-			 */
-			if (mq->qcnt)
-				mmc_blk_issue_rw_rq(mq, NULL);
 			mmc_blk_issue_flush(mq, req);
 			break;
 		default:
-			/* Normal request, just issue it */
-			mmc_blk_issue_rw_rq(mq, req);
-			card->host->context_info.is_waiting_last_req = false;
+			WARN_ON_ONCE(1);
+			return MMC_REQ_FAILED_TO_START;
+		}
+		return MMC_REQ_FINISHED;
+	case MMC_ISSUE_DCMD:
+	case MMC_ISSUE_ASYNC:
+		switch (req_op(req)) {
+		case REQ_OP_FLUSH:
+			ret = mmc_blk_cqe_issue_flush(mq, req);
 			break;
+		case REQ_OP_READ:
+		case REQ_OP_WRITE:
+			if (mq->use_cqe)
+				ret = mmc_blk_cqe_issue_rw_rq(mq, req);
+			else
+				ret = mmc_blk_mq_issue_rw_rq(mq, req);
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			ret = -EINVAL;
 		}
-	} else {
-		/* No request, flushing the pipeline with NULL */
-		mmc_blk_issue_rw_rq(mq, NULL);
-		card->host->context_info.is_waiting_last_req = false;
+		if (!ret)
+			return MMC_REQ_STARTED;
+		return ret == -EBUSY ? MMC_REQ_BUSY : MMC_REQ_FAILED_TO_START;
+	default:
+		WARN_ON_ONCE(1);
+		return MMC_REQ_FAILED_TO_START;
 	}
-
-out:
-	if (!mq->qcnt)
-		mmc_put_card(card, NULL);
 }
 
 static inline int mmc_blk_readonly(struct mmc_card *card)
@@ -2156,6 +2320,18 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
 
 	md->queue.blkdata = md;
 
+	/*
+	 * Keep an extra reference to the queue so that we can shutdown the
+	 * queue (i.e. call blk_cleanup_queue()) while there are still
+	 * references to the 'md'. The corresponding blk_put_queue() is in
+	 * mmc_blk_put().
+	 */
+	if (!blk_get_queue(md->queue.queue)) {
+		mmc_cleanup_queue(&md->queue);
+		ret = -ENODEV;
+		goto err_putdisk;
+	}
+
 	md->disk->major	= MMC_BLOCK_MAJOR;
 	md->disk->first_minor = devidx * perdev_minors;
 	md->disk->fops = &mmc_bdops;
@@ -2471,10 +2647,6 @@ static void mmc_blk_remove_req(struct mmc_blk_data *md)
 		 * from being accepted.
 		 */
 		card = md->queue.card;
-		spin_lock_irq(md->queue.queue->queue_lock);
-		queue_flag_set(QUEUE_FLAG_BYPASS, md->queue.queue);
-		spin_unlock_irq(md->queue.queue->queue_lock);
-		blk_set_queue_dying(md->queue.queue);
 		mmc_cleanup_queue(&md->queue);
 		if (md->disk->flags & GENHD_FL_UP) {
 			device_remove_file(disk_to_dev(md->disk), &md->force_ro);
@@ -2623,6 +2795,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp)
 
 	if (n != EXT_CSD_STR_LEN) {
 		err = -EINVAL;
+		kfree(ext_csd);
 		goto out_free;
 	}
 
diff --git a/drivers/mmc/core/block.h b/drivers/mmc/core/block.h
index 5946636101ef..31153f656f41 100644
--- a/drivers/mmc/core/block.h
+++ b/drivers/mmc/core/block.h
@@ -5,6 +5,16 @@
 struct mmc_queue;
 struct request;
 
-void mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req);
+void mmc_blk_cqe_recovery(struct mmc_queue *mq);
+
+enum mmc_issued;
+
+enum mmc_issued mmc_blk_mq_issue_rq(struct mmc_queue *mq, struct request *req);
+void mmc_blk_mq_complete(struct request *req);
+void mmc_blk_mq_recovery(struct mmc_queue *mq);
+
+struct work_struct;
+
+void mmc_blk_mq_complete_work(struct work_struct *work);
 
 #endif
diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c
index 7586ff2ad1f1..fc92c6c1c9a4 100644
--- a/drivers/mmc/core/bus.c
+++ b/drivers/mmc/core/bus.c
@@ -351,8 +351,6 @@ int mmc_add_card(struct mmc_card *card)
 #ifdef CONFIG_DEBUG_FS
 	mmc_add_card_debugfs(card);
 #endif
-	mmc_init_context_info(card->host);
-
 	card->dev.of_node = mmc_of_find_child_device(card->host, 0);
 
 	device_enable_async_suspend(&card->dev);
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 1f0f44f4dd5f..c0ba6d8823b7 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -341,6 +341,8 @@ int mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 {
 	int err;
 
+	init_completion(&mrq->cmd_completion);
+
 	mmc_retune_hold(host);
 
 	if (mmc_card_removed(host->card))
@@ -361,20 +363,6 @@ int mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 }
 EXPORT_SYMBOL(mmc_start_request);
 
-/*
- * mmc_wait_data_done() - done callback for data request
- * @mrq: done data request
- *
- * Wakes up mmc context, passed as a callback to host controller driver
- */
-static void mmc_wait_data_done(struct mmc_request *mrq)
-{
-	struct mmc_context_info *context_info = &mrq->host->context_info;
-
-	context_info->is_done_rcv = true;
-	wake_up_interruptible(&context_info->wait);
-}
-
 static void mmc_wait_done(struct mmc_request *mrq)
 {
 	complete(&mrq->completion);
@@ -392,37 +380,6 @@ static inline void mmc_wait_ongoing_tfr_cmd(struct mmc_host *host)
 		wait_for_completion(&ongoing_mrq->cmd_completion);
 }
 
-/*
- *__mmc_start_data_req() - starts data request
- * @host: MMC host to start the request
- * @mrq: data request to start
- *
- * Sets the done callback to be called when request is completed by the card.
- * Starts data mmc request execution
- * If an ongoing transfer is already in progress, wait for the command line
- * to become available before sending another command.
- */
-static int __mmc_start_data_req(struct mmc_host *host, struct mmc_request *mrq)
-{
-	int err;
-
-	mmc_wait_ongoing_tfr_cmd(host);
-
-	mrq->done = mmc_wait_data_done;
-	mrq->host = host;
-
-	init_completion(&mrq->cmd_completion);
-
-	err = mmc_start_request(host, mrq);
-	if (err) {
-		mrq->cmd->error = err;
-		mmc_complete_cmd(mrq);
-		mmc_wait_data_done(mrq);
-	}
-
-	return err;
-}
-
 static int __mmc_start_req(struct mmc_host *host, struct mmc_request *mrq)
 {
 	int err;
@@ -432,8 +389,6 @@ static int __mmc_start_req(struct mmc_host *host, struct mmc_request *mrq)
 	init_completion(&mrq->completion);
 	mrq->done = mmc_wait_done;
 
-	init_completion(&mrq->cmd_completion);
-
 	err = mmc_start_request(host, mrq);
 	if (err) {
 		mrq->cmd->error = err;
@@ -650,164 +605,11 @@ EXPORT_SYMBOL(mmc_cqe_recovery);
  */
 bool mmc_is_req_done(struct mmc_host *host, struct mmc_request *mrq)
 {
-	if (host->areq)
-		return host->context_info.is_done_rcv;
-	else
-		return completion_done(&mrq->completion);
+	return completion_done(&mrq->completion);
 }
 EXPORT_SYMBOL(mmc_is_req_done);
 
 /**
- *	mmc_pre_req - Prepare for a new request
- *	@host: MMC host to prepare command
- *	@mrq: MMC request to prepare for
- *
- *	mmc_pre_req() is called in prior to mmc_start_req() to let
- *	host prepare for the new request. Preparation of a request may be
- *	performed while another request is running on the host.
- */
-static void mmc_pre_req(struct mmc_host *host, struct mmc_request *mrq)
-{
-	if (host->ops->pre_req)
-		host->ops->pre_req(host, mrq);
-}
-
-/**
- *	mmc_post_req - Post process a completed request
- *	@host: MMC host to post process command
- *	@mrq: MMC request to post process for
- *	@err: Error, if non zero, clean up any resources made in pre_req
- *
- *	Let the host post process a completed request. Post processing of
- *	a request may be performed while another reuqest is running.
- */
-static void mmc_post_req(struct mmc_host *host, struct mmc_request *mrq,
-			 int err)
-{
-	if (host->ops->post_req)
-		host->ops->post_req(host, mrq, err);
-}
-
-/**
- * mmc_finalize_areq() - finalize an asynchronous request
- * @host: MMC host to finalize any ongoing request on
- *
- * Returns the status of the ongoing asynchronous request, but
- * MMC_BLK_SUCCESS if no request was going on.
- */
-static enum mmc_blk_status mmc_finalize_areq(struct mmc_host *host)
-{
-	struct mmc_context_info *context_info = &host->context_info;
-	enum mmc_blk_status status;
-
-	if (!host->areq)
-		return MMC_BLK_SUCCESS;
-
-	while (1) {
-		wait_event_interruptible(context_info->wait,
-				(context_info->is_done_rcv ||
-				 context_info->is_new_req));
-
-		if (context_info->is_done_rcv) {
-			struct mmc_command *cmd;
-
-			context_info->is_done_rcv = false;
-			cmd = host->areq->mrq->cmd;
-
-			if (!cmd->error || !cmd->retries ||
-			    mmc_card_removed(host->card)) {
-				status = host->areq->err_check(host->card,
-							       host->areq);
-				break; /* return status */
-			} else {
-				mmc_retune_recheck(host);
-				pr_info("%s: req failed (CMD%u): %d, retrying...\n",
-					mmc_hostname(host),
-					cmd->opcode, cmd->error);
-				cmd->retries--;
-				cmd->error = 0;
-				__mmc_start_request(host, host->areq->mrq);
-				continue; /* wait for done/new event again */
-			}
-		}
-
-		return MMC_BLK_NEW_REQUEST;
-	}
-
-	mmc_retune_release(host);
-
-	/*
-	 * Check BKOPS urgency for each R1 response
-	 */
-	if (host->card && mmc_card_mmc(host->card) &&
-	    ((mmc_resp_type(host->areq->mrq->cmd) == MMC_RSP_R1) ||
-	     (mmc_resp_type(host->areq->mrq->cmd) == MMC_RSP_R1B)) &&
-	    (host->areq->mrq->cmd->resp[0] & R1_EXCEPTION_EVENT)) {
-		mmc_start_bkops(host->card, true);
-	}
-
-	return status;
-}
-
-/**
- *	mmc_start_areq - start an asynchronous request
- *	@host: MMC host to start command
- *	@areq: asynchronous request to start
- *	@ret_stat: out parameter for status
- *
- *	Start a new MMC custom command request for a host.
- *	If there is on ongoing async request wait for completion
- *	of that request and start the new one and return.
- *	Does not wait for the new request to complete.
- *
- *      Returns the completed request, NULL in case of none completed.
- *	Wait for the an ongoing request (previoulsy started) to complete and
- *	return the completed request. If there is no ongoing request, NULL
- *	is returned without waiting. NULL is not an error condition.
- */
-struct mmc_async_req *mmc_start_areq(struct mmc_host *host,
-				     struct mmc_async_req *areq,
-				     enum mmc_blk_status *ret_stat)
-{
-	enum mmc_blk_status status;
-	int start_err = 0;
-	struct mmc_async_req *previous = host->areq;
-
-	/* Prepare a new request */
-	if (areq)
-		mmc_pre_req(host, areq->mrq);
-
-	/* Finalize previous request */
-	status = mmc_finalize_areq(host);
-	if (ret_stat)
-		*ret_stat = status;
-
-	/* The previous request is still going on... */
-	if (status == MMC_BLK_NEW_REQUEST)
-		return NULL;
-
-	/* Fine so far, start the new request! */
-	if (status == MMC_BLK_SUCCESS && areq)
-		start_err = __mmc_start_data_req(host, areq->mrq);
-
-	/* Postprocess the old request at this point */
-	if (host->areq)
-		mmc_post_req(host, host->areq->mrq, 0);
-
-	/* Cancel a prepared request if it was not started. */
-	if ((status != MMC_BLK_SUCCESS || start_err) && areq)
-		mmc_post_req(host, areq->mrq, -EINVAL);
-
-	if (status != MMC_BLK_SUCCESS)
-		host->areq = NULL;
-	else
-		host->areq = areq;
-
-	return previous;
-}
-EXPORT_SYMBOL(mmc_start_areq);
-
-/**
  *	mmc_wait_for_req - start a request and wait for completion
  *	@host: MMC host to start command
  *	@mrq: MMC request to start
@@ -2959,6 +2761,14 @@ static int mmc_pm_notify(struct notifier_block *notify_block,
 		if (!err)
 			break;
 
+		if (!mmc_card_is_removable(host)) {
+			dev_warn(mmc_dev(host),
+				 "pre_suspend failed for non-removable host: "
+				 "%d\n", err);
+			/* Avoid removing non-removable hosts */
+			break;
+		}
+
 		/* Calling bus_ops->remove() with a claimed host can deadlock */
 		host->bus_ops->remove(host);
 		mmc_claim_host(host);
@@ -2994,22 +2804,6 @@ void mmc_unregister_pm_notifier(struct mmc_host *host)
 }
 #endif
 
-/**
- * mmc_init_context_info() - init synchronization context
- * @host: mmc host
- *
- * Init struct context_info needed to implement asynchronous
- * request mechanism, used by mmc core, host driver and mmc requests
- * supplier.
- */
-void mmc_init_context_info(struct mmc_host *host)
-{
-	host->context_info.is_new_req = false;
-	host->context_info.is_done_rcv = false;
-	host->context_info.is_waiting_last_req = false;
-	init_waitqueue_head(&host->context_info.wait);
-}
-
 static int __init mmc_init(void)
 {
 	int ret;
diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
index 71e6c6d7ceb7..d6303d69071b 100644
--- a/drivers/mmc/core/core.h
+++ b/drivers/mmc/core/core.h
@@ -62,12 +62,10 @@ void mmc_set_initial_state(struct mmc_host *host);
 
 static inline void mmc_delay(unsigned int ms)
 {
-	if (ms < 1000 / HZ) {
-		cond_resched();
-		mdelay(ms);
-	} else {
+	if (ms <= 20)
+		usleep_range(ms * 1000, ms * 1250);
+	else
 		msleep(ms);
-	}
 }
 
 void mmc_rescan(struct work_struct *work);
@@ -91,8 +89,6 @@ void mmc_remove_host_debugfs(struct mmc_host *host);
 void mmc_add_card_debugfs(struct mmc_card *card);
 void mmc_remove_card_debugfs(struct mmc_card *card);
 
-void mmc_init_context_info(struct mmc_host *host);
-
 int mmc_execute_tuning(struct mmc_card *card);
 int mmc_hs200_to_hs400(struct mmc_card *card);
 int mmc_hs400_to_hs200(struct mmc_card *card);
@@ -110,12 +106,6 @@ bool mmc_is_req_done(struct mmc_host *host, struct mmc_request *mrq);
 
 int mmc_start_request(struct mmc_host *host, struct mmc_request *mrq);
 
-struct mmc_async_req;
-
-struct mmc_async_req *mmc_start_areq(struct mmc_host *host,
-				     struct mmc_async_req *areq,
-				     enum mmc_blk_status *ret_stat);
-
 int mmc_erase(struct mmc_card *card, unsigned int from, unsigned int nr,
 		unsigned int arg);
 int mmc_can_erase(struct mmc_card *card);
@@ -152,4 +142,35 @@ int mmc_cqe_start_req(struct mmc_host *host, struct mmc_request *mrq);
 void mmc_cqe_post_req(struct mmc_host *host, struct mmc_request *mrq);
 int mmc_cqe_recovery(struct mmc_host *host);
 
+/**
+ *	mmc_pre_req - Prepare for a new request
+ *	@host: MMC host to prepare command
+ *	@mrq: MMC request to prepare for
+ *
+ *	mmc_pre_req() is called in prior to mmc_start_req() to let
+ *	host prepare for the new request. Preparation of a request may be
+ *	performed while another request is running on the host.
+ */
+static inline void mmc_pre_req(struct mmc_host *host, struct mmc_request *mrq)
+{
+	if (host->ops->pre_req)
+		host->ops->pre_req(host, mrq);
+}
+
+/**
+ *	mmc_post_req - Post process a completed request
+ *	@host: MMC host to post process command
+ *	@mrq: MMC request to post process for
+ *	@err: Error, if non zero, clean up any resources made in pre_req
+ *
+ *	Let the host post process a completed request. Post processing of
+ *	a request may be performed while another request is running.
+ */
+static inline void mmc_post_req(struct mmc_host *host, struct mmc_request *mrq,
+				int err)
+{
+	if (host->ops->post_req)
+		host->ops->post_req(host, mrq, err);
+}
+
 #endif
diff --git a/drivers/mmc/core/host.h b/drivers/mmc/core/host.h
index fb689a1065ed..06ec19b5bf9f 100644
--- a/drivers/mmc/core/host.h
+++ b/drivers/mmc/core/host.h
@@ -41,6 +41,11 @@ static inline int mmc_host_cmd23(struct mmc_host *host)
 	return host->caps & MMC_CAP_CMD23;
 }
 
+static inline bool mmc_host_done_complete(struct mmc_host *host)
+{
+	return host->caps & MMC_CAP_DONE_COMPLETE;
+}
+
 static inline int mmc_boot_partition_access(struct mmc_host *host)
 {
 	return !(host->caps2 & MMC_CAP2_BOOTPART_NOACC);
@@ -74,6 +79,5 @@ static inline bool mmc_card_hs400es(struct mmc_card *card)
 	return card->host->ios.enhanced_strobe;
 }
 
-
 #endif
 
diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c
index 478869805b96..ef18daeaa4cc 100644
--- a/drivers/mmc/core/mmc_test.c
+++ b/drivers/mmc/core/mmc_test.c
@@ -101,7 +101,7 @@ struct mmc_test_transfer_result {
 	struct list_head link;
 	unsigned int count;
 	unsigned int sectors;
-	struct timespec ts;
+	struct timespec64 ts;
 	unsigned int rate;
 	unsigned int iops;
 };
@@ -171,11 +171,6 @@ struct mmc_test_multiple_rw {
 	enum mmc_test_prep_media prepare;
 };
 
-struct mmc_test_async_req {
-	struct mmc_async_req areq;
-	struct mmc_test_card *test;
-};
-
 /*******************************************************************/
 /*  General helper functions                                       */
 /*******************************************************************/
@@ -515,14 +510,11 @@ static int mmc_test_map_sg_max_scatter(struct mmc_test_mem *mem,
 /*
  * Calculate transfer rate in bytes per second.
  */
-static unsigned int mmc_test_rate(uint64_t bytes, struct timespec *ts)
+static unsigned int mmc_test_rate(uint64_t bytes, struct timespec64 *ts)
 {
 	uint64_t ns;
 
-	ns = ts->tv_sec;
-	ns *= 1000000000;
-	ns += ts->tv_nsec;
-
+	ns = timespec64_to_ns(ts);
 	bytes *= 1000000000;
 
 	while (ns > UINT_MAX) {
@@ -542,7 +534,7 @@ static unsigned int mmc_test_rate(uint64_t bytes, struct timespec *ts)
  * Save transfer results for future usage
  */
 static void mmc_test_save_transfer_result(struct mmc_test_card *test,
-	unsigned int count, unsigned int sectors, struct timespec ts,
+	unsigned int count, unsigned int sectors, struct timespec64 ts,
 	unsigned int rate, unsigned int iops)
 {
 	struct mmc_test_transfer_result *tr;
@@ -567,21 +559,21 @@ static void mmc_test_save_transfer_result(struct mmc_test_card *test,
  * Print the transfer rate.
  */
 static void mmc_test_print_rate(struct mmc_test_card *test, uint64_t bytes,
-				struct timespec *ts1, struct timespec *ts2)
+				struct timespec64 *ts1, struct timespec64 *ts2)
 {
 	unsigned int rate, iops, sectors = bytes >> 9;
-	struct timespec ts;
+	struct timespec64 ts;
 
-	ts = timespec_sub(*ts2, *ts1);
+	ts = timespec64_sub(*ts2, *ts1);
 
 	rate = mmc_test_rate(bytes, &ts);
 	iops = mmc_test_rate(100, &ts); /* I/O ops per sec x 100 */
 
-	pr_info("%s: Transfer of %u sectors (%u%s KiB) took %lu.%09lu "
+	pr_info("%s: Transfer of %u sectors (%u%s KiB) took %llu.%09u "
 			 "seconds (%u kB/s, %u KiB/s, %u.%02u IOPS)\n",
 			 mmc_hostname(test->card->host), sectors, sectors >> 1,
-			 (sectors & 1 ? ".5" : ""), (unsigned long)ts.tv_sec,
-			 (unsigned long)ts.tv_nsec, rate / 1000, rate / 1024,
+			 (sectors & 1 ? ".5" : ""), (u64)ts.tv_sec,
+			 (u32)ts.tv_nsec, rate / 1000, rate / 1024,
 			 iops / 100, iops % 100);
 
 	mmc_test_save_transfer_result(test, 1, sectors, ts, rate, iops);
@@ -591,24 +583,24 @@ static void mmc_test_print_rate(struct mmc_test_card *test, uint64_t bytes,
  * Print the average transfer rate.
  */
 static void mmc_test_print_avg_rate(struct mmc_test_card *test, uint64_t bytes,
-				    unsigned int count, struct timespec *ts1,
-				    struct timespec *ts2)
+				    unsigned int count, struct timespec64 *ts1,
+				    struct timespec64 *ts2)
 {
 	unsigned int rate, iops, sectors = bytes >> 9;
 	uint64_t tot = bytes * count;
-	struct timespec ts;
+	struct timespec64 ts;
 
-	ts = timespec_sub(*ts2, *ts1);
+	ts = timespec64_sub(*ts2, *ts1);
 
 	rate = mmc_test_rate(tot, &ts);
 	iops = mmc_test_rate(count * 100, &ts); /* I/O ops per sec x 100 */
 
 	pr_info("%s: Transfer of %u x %u sectors (%u x %u%s KiB) took "
-			 "%lu.%09lu seconds (%u kB/s, %u KiB/s, "
+			 "%llu.%09u seconds (%u kB/s, %u KiB/s, "
 			 "%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,
+			 (u64)ts.tv_sec, (u32)ts.tv_nsec,
 			 rate / 1000, rate / 1024, iops / 100, iops % 100,
 			 test->area.sg_len);
 
@@ -741,30 +733,6 @@ static int mmc_test_check_result(struct mmc_test_card *test,
 	return ret;
 }
 
-static enum mmc_blk_status 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);
-	int ret;
-
-	mmc_test_wait_busy(test_async->test);
-
-	/*
-	 * FIXME: this would earlier just casts a regular error code,
-	 * either of the kernel type -ERRORCODE or the local test framework
-	 * RESULT_* errorcode, into an enum mmc_blk_status and return as
-	 * result check. Instead, convert it to some reasonable type by just
-	 * returning either MMC_BLK_SUCCESS or MMC_BLK_CMD_ERR.
-	 * If possible, a reasonable error code should be returned.
-	 */
-	ret = mmc_test_check_result(test_async->test, areq->mrq);
-	if (ret)
-		return MMC_BLK_CMD_ERR;
-
-	return MMC_BLK_SUCCESS;
-}
-
 /*
  * Checks that a "short transfer" behaved as expected
  */
@@ -831,6 +799,45 @@ static struct mmc_test_req *mmc_test_req_alloc(void)
 	return rq;
 }
 
+static void mmc_test_wait_done(struct mmc_request *mrq)
+{
+	complete(&mrq->completion);
+}
+
+static int mmc_test_start_areq(struct mmc_test_card *test,
+			       struct mmc_request *mrq,
+			       struct mmc_request *prev_mrq)
+{
+	struct mmc_host *host = test->card->host;
+	int err = 0;
+
+	if (mrq) {
+		init_completion(&mrq->completion);
+		mrq->done = mmc_test_wait_done;
+		mmc_pre_req(host, mrq);
+	}
+
+	if (prev_mrq) {
+		wait_for_completion(&prev_mrq->completion);
+		err = mmc_test_wait_busy(test);
+		if (!err)
+			err = mmc_test_check_result(test, prev_mrq);
+	}
+
+	if (!err && mrq) {
+		err = mmc_start_request(host, mrq);
+		if (err)
+			mmc_retune_release(host);
+	}
+
+	if (prev_mrq)
+		mmc_post_req(host, prev_mrq, 0);
+
+	if (err && mrq)
+		mmc_post_req(host, mrq, err);
+
+	return err;
+}
 
 static int mmc_test_nonblock_transfer(struct mmc_test_card *test,
 				      struct scatterlist *sg, unsigned sg_len,
@@ -838,17 +845,10 @@ static int mmc_test_nonblock_transfer(struct mmc_test_card *test,
 				      unsigned blksz, int write, int count)
 {
 	struct mmc_test_req *rq1, *rq2;
-	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;
-	enum mmc_blk_status status;
+	struct mmc_request *mrq, *prev_mrq;
 	int i;
 	int ret = RESULT_OK;
 
-	test_areq[0].test = test;
-	test_areq[1].test = test;
-
 	rq1 = mmc_test_req_alloc();
 	rq2 = mmc_test_req_alloc();
 	if (!rq1 || !rq2) {
@@ -856,33 +856,25 @@ static int mmc_test_nonblock_transfer(struct mmc_test_card *test,
 		goto err;
 	}
 
-	cur_areq->mrq = &rq1->mrq;
-	cur_areq->err_check = mmc_test_check_result_async;
-	other_areq->mrq = &rq2->mrq;
-	other_areq->err_check = mmc_test_check_result_async;
+	mrq = &rq1->mrq;
+	prev_mrq = NULL;
 
 	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_areq(test->card->host, cur_areq, &status);
-
-		if (status != MMC_BLK_SUCCESS || (!done_areq && i > 0)) {
-			ret = RESULT_FAIL;
+		mmc_test_req_reset(container_of(mrq, struct mmc_test_req, mrq));
+		mmc_test_prepare_mrq(test, mrq, sg, sg_len, dev_addr, blocks,
+				     blksz, write);
+		ret = mmc_test_start_areq(test, mrq, prev_mrq);
+		if (ret)
 			goto err;
-		}
 
-		if (done_areq)
-			mmc_test_req_reset(container_of(done_areq->mrq,
-						struct mmc_test_req, mrq));
+		if (!prev_mrq)
+			prev_mrq = &rq2->mrq;
 
-		swap(cur_areq, other_areq);
+		swap(mrq, prev_mrq);
 		dev_addr += blocks;
 	}
 
-	done_areq = mmc_start_areq(test->card->host, NULL, &status);
-	if (status != MMC_BLK_SUCCESS)
-		ret = RESULT_FAIL;
-
+	ret = mmc_test_start_areq(test, NULL, prev_mrq);
 err:
 	kfree(rq1);
 	kfree(rq2);
@@ -1449,7 +1441,7 @@ static int mmc_test_area_io_seq(struct mmc_test_card *test, unsigned long sz,
 				int max_scatter, int timed, int count,
 				bool nonblock, int min_sg_len)
 {
-	struct timespec ts1, ts2;
+	struct timespec64 ts1, ts2;
 	int ret = 0;
 	int i;
 	struct mmc_test_area *t = &test->area;
@@ -1475,7 +1467,7 @@ static int mmc_test_area_io_seq(struct mmc_test_card *test, unsigned long sz,
 		return ret;
 
 	if (timed)
-		getnstimeofday(&ts1);
+		ktime_get_ts64(&ts1);
 	if (nonblock)
 		ret = mmc_test_nonblock_transfer(test, t->sg, t->sg_len,
 				 dev_addr, t->blocks, 512, write, count);
@@ -1489,7 +1481,7 @@ static int mmc_test_area_io_seq(struct mmc_test_card *test, unsigned long sz,
 		return ret;
 
 	if (timed)
-		getnstimeofday(&ts2);
+		ktime_get_ts64(&ts2);
 
 	if (timed)
 		mmc_test_print_avg_rate(test, sz, count, &ts1, &ts2);
@@ -1747,7 +1739,7 @@ static int mmc_test_profile_trim_perf(struct mmc_test_card *test)
 	struct mmc_test_area *t = &test->area;
 	unsigned long sz;
 	unsigned int dev_addr;
-	struct timespec ts1, ts2;
+	struct timespec64 ts1, ts2;
 	int ret;
 
 	if (!mmc_can_trim(test->card))
@@ -1758,19 +1750,19 @@ static int mmc_test_profile_trim_perf(struct mmc_test_card *test)
 
 	for (sz = 512; sz < t->max_sz; sz <<= 1) {
 		dev_addr = t->dev_addr + (sz >> 9);
-		getnstimeofday(&ts1);
+		ktime_get_ts64(&ts1);
 		ret = mmc_erase(test->card, dev_addr, sz >> 9, MMC_TRIM_ARG);
 		if (ret)
 			return ret;
-		getnstimeofday(&ts2);
+		ktime_get_ts64(&ts2);
 		mmc_test_print_rate(test, sz, &ts1, &ts2);
 	}
 	dev_addr = t->dev_addr;
-	getnstimeofday(&ts1);
+	ktime_get_ts64(&ts1);
 	ret = mmc_erase(test->card, dev_addr, sz >> 9, MMC_TRIM_ARG);
 	if (ret)
 		return ret;
-	getnstimeofday(&ts2);
+	ktime_get_ts64(&ts2);
 	mmc_test_print_rate(test, sz, &ts1, &ts2);
 	return 0;
 }
@@ -1779,19 +1771,19 @@ static int mmc_test_seq_read_perf(struct mmc_test_card *test, unsigned long sz)
 {
 	struct mmc_test_area *t = &test->area;
 	unsigned int dev_addr, i, cnt;
-	struct timespec ts1, ts2;
+	struct timespec64 ts1, ts2;
 	int ret;
 
 	cnt = t->max_sz / sz;
 	dev_addr = t->dev_addr;
-	getnstimeofday(&ts1);
+	ktime_get_ts64(&ts1);
 	for (i = 0; i < cnt; i++) {
 		ret = mmc_test_area_io(test, sz, dev_addr, 0, 0, 0);
 		if (ret)
 			return ret;
 		dev_addr += (sz >> 9);
 	}
-	getnstimeofday(&ts2);
+	ktime_get_ts64(&ts2);
 	mmc_test_print_avg_rate(test, sz, cnt, &ts1, &ts2);
 	return 0;
 }
@@ -1818,7 +1810,7 @@ static int mmc_test_seq_write_perf(struct mmc_test_card *test, unsigned long sz)
 {
 	struct mmc_test_area *t = &test->area;
 	unsigned int dev_addr, i, cnt;
-	struct timespec ts1, ts2;
+	struct timespec64 ts1, ts2;
 	int ret;
 
 	ret = mmc_test_area_erase(test);
@@ -1826,14 +1818,14 @@ static int mmc_test_seq_write_perf(struct mmc_test_card *test, unsigned long sz)
 		return ret;
 	cnt = t->max_sz / sz;
 	dev_addr = t->dev_addr;
-	getnstimeofday(&ts1);
+	ktime_get_ts64(&ts1);
 	for (i = 0; i < cnt; i++) {
 		ret = mmc_test_area_io(test, sz, dev_addr, 1, 0, 0);
 		if (ret)
 			return ret;
 		dev_addr += (sz >> 9);
 	}
-	getnstimeofday(&ts2);
+	ktime_get_ts64(&ts2);
 	mmc_test_print_avg_rate(test, sz, cnt, &ts1, &ts2);
 	return 0;
 }
@@ -1864,7 +1856,7 @@ static int mmc_test_profile_seq_trim_perf(struct mmc_test_card *test)
 	struct mmc_test_area *t = &test->area;
 	unsigned long sz;
 	unsigned int dev_addr, i, cnt;
-	struct timespec ts1, ts2;
+	struct timespec64 ts1, ts2;
 	int ret;
 
 	if (!mmc_can_trim(test->card))
@@ -1882,7 +1874,7 @@ static int mmc_test_profile_seq_trim_perf(struct mmc_test_card *test)
 			return ret;
 		cnt = t->max_sz / sz;
 		dev_addr = t->dev_addr;
-		getnstimeofday(&ts1);
+		ktime_get_ts64(&ts1);
 		for (i = 0; i < cnt; i++) {
 			ret = mmc_erase(test->card, dev_addr, sz >> 9,
 					MMC_TRIM_ARG);
@@ -1890,7 +1882,7 @@ static int mmc_test_profile_seq_trim_perf(struct mmc_test_card *test)
 				return ret;
 			dev_addr += (sz >> 9);
 		}
-		getnstimeofday(&ts2);
+		ktime_get_ts64(&ts2);
 		mmc_test_print_avg_rate(test, sz, cnt, &ts1, &ts2);
 	}
 	return 0;
@@ -1912,7 +1904,7 @@ static int mmc_test_rnd_perf(struct mmc_test_card *test, int write, int print,
 {
 	unsigned int dev_addr, cnt, rnd_addr, range1, range2, last_ea = 0, ea;
 	unsigned int ssz;
-	struct timespec ts1, ts2, ts;
+	struct timespec64 ts1, ts2, ts;
 	int ret;
 
 	ssz = sz >> 9;
@@ -1921,10 +1913,10 @@ static int mmc_test_rnd_perf(struct mmc_test_card *test, int write, int print,
 	range1 = rnd_addr / test->card->pref_erase;
 	range2 = range1 / ssz;
 
-	getnstimeofday(&ts1);
+	ktime_get_ts64(&ts1);
 	for (cnt = 0; cnt < UINT_MAX; cnt++) {
-		getnstimeofday(&ts2);
-		ts = timespec_sub(ts2, ts1);
+		ktime_get_ts64(&ts2);
+		ts = timespec64_sub(ts2, ts1);
 		if (ts.tv_sec >= 10)
 			break;
 		ea = mmc_test_rnd_num(range1);
@@ -1998,7 +1990,7 @@ static int mmc_test_seq_perf(struct mmc_test_card *test, int write,
 {
 	struct mmc_test_area *t = &test->area;
 	unsigned int dev_addr, i, cnt, sz, ssz;
-	struct timespec ts1, ts2;
+	struct timespec64 ts1, ts2;
 	int ret;
 
 	sz = t->max_tfr;
@@ -2025,7 +2017,7 @@ static int mmc_test_seq_perf(struct mmc_test_card *test, int write,
 	cnt = tot_sz / sz;
 	dev_addr &= 0xffff0000; /* Round to 64MiB boundary */
 
-	getnstimeofday(&ts1);
+	ktime_get_ts64(&ts1);
 	for (i = 0; i < cnt; i++) {
 		ret = mmc_test_area_io(test, sz, dev_addr, write,
 				       max_scatter, 0);
@@ -2033,7 +2025,7 @@ static int mmc_test_seq_perf(struct mmc_test_card *test, int write,
 			return ret;
 		dev_addr += ssz;
 	}
-	getnstimeofday(&ts2);
+	ktime_get_ts64(&ts2);
 
 	mmc_test_print_avg_rate(test, sz, cnt, &ts1, &ts2);
 
@@ -2328,10 +2320,17 @@ static int mmc_test_reset(struct mmc_test_card *test)
 	int err;
 
 	err = mmc_hw_reset(host);
-	if (!err)
+	if (!err) {
+		/*
+		 * Reset will re-enable the card's command queue, but tests
+		 * expect it to be disabled.
+		 */
+		if (card->ext_csd.cmdq_en)
+			mmc_cmdq_disable(card);
 		return RESULT_OK;
-	else if (err == -EOPNOTSUPP)
+	} else if (err == -EOPNOTSUPP) {
 		return RESULT_UNSUP_HOST;
+	}
 
 	return RESULT_FAIL;
 }
@@ -2356,11 +2355,9 @@ static int mmc_test_ongoing_transfer(struct mmc_test_card *test,
 	struct mmc_test_req *rq = mmc_test_req_alloc();
 	struct mmc_host *host = test->card->host;
 	struct mmc_test_area *t = &test->area;
-	struct mmc_test_async_req test_areq = { .test = test };
 	struct mmc_request *mrq;
 	unsigned long timeout;
 	bool expired = false;
-	enum mmc_blk_status blkstat = MMC_BLK_SUCCESS;
 	int ret = 0, cmd_ret;
 	u32 status = 0;
 	int count = 0;
@@ -2373,9 +2370,6 @@ static int mmc_test_ongoing_transfer(struct mmc_test_card *test,
 		mrq->sbc = &rq->sbc;
 	mrq->cap_cmd_during_tfr = true;
 
-	test_areq.areq.mrq = mrq;
-	test_areq.areq.err_check = mmc_test_check_result_async;
-
 	mmc_test_prepare_mrq(test, mrq, t->sg, t->sg_len, dev_addr, t->blocks,
 			     512, write);
 
@@ -2388,11 +2382,9 @@ static int mmc_test_ongoing_transfer(struct mmc_test_card *test,
 
 	/* Start ongoing data request */
 	if (use_areq) {
-		mmc_start_areq(host, &test_areq.areq, &blkstat);
-		if (blkstat != MMC_BLK_SUCCESS) {
-			ret = RESULT_FAIL;
+		ret = mmc_test_start_areq(test, mrq, NULL);
+		if (ret)
 			goto out_free;
-		}
 	} else {
 		mmc_wait_for_req(host, mrq);
 	}
@@ -2426,9 +2418,7 @@ static int mmc_test_ongoing_transfer(struct mmc_test_card *test,
 
 	/* Wait for data request to complete */
 	if (use_areq) {
-		mmc_start_areq(host, NULL, &blkstat);
-		if (blkstat != MMC_BLK_SUCCESS)
-			ret = RESULT_FAIL;
+		ret = mmc_test_start_areq(test, NULL, mrq);
 	} else {
 		mmc_wait_for_req_done(test->card->host, mrq);
 	}
@@ -3066,10 +3056,9 @@ static int mtf_test_show(struct seq_file *sf, void *data)
 		seq_printf(sf, "Test %d: %d\n", gr->testcase + 1, gr->result);
 
 		list_for_each_entry(tr, &gr->tr_lst, link) {
-			seq_printf(sf, "%u %d %lu.%09lu %u %u.%02u\n",
+			seq_printf(sf, "%u %d %llu.%09u %u %u.%02u\n",
 				tr->count, tr->sectors,
-				(unsigned long)tr->ts.tv_sec,
-				(unsigned long)tr->ts.tv_nsec,
+				(u64)tr->ts.tv_sec, (u32)tr->ts.tv_nsec,
 				tr->rate, tr->iops / 100, tr->iops % 100);
 		}
 	}
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 4f33d277b125..421fab7250ac 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -22,100 +22,147 @@
 #include "block.h"
 #include "core.h"
 #include "card.h"
+#include "host.h"
 
-/*
- * Prepare a MMC request. This just filters out odd stuff.
- */
-static int mmc_prep_request(struct request_queue *q, struct request *req)
+static inline bool mmc_cqe_dcmd_busy(struct mmc_queue *mq)
 {
-	struct mmc_queue *mq = q->queuedata;
+	/* Allow only 1 DCMD at a time */
+	return mq->in_flight[MMC_ISSUE_DCMD];
+}
 
-	if (mq && mmc_card_removed(mq->card))
-		return BLKPREP_KILL;
+void mmc_cqe_check_busy(struct mmc_queue *mq)
+{
+	if ((mq->cqe_busy & MMC_CQE_DCMD_BUSY) && !mmc_cqe_dcmd_busy(mq))
+		mq->cqe_busy &= ~MMC_CQE_DCMD_BUSY;
 
-	req->rq_flags |= RQF_DONTPREP;
+	mq->cqe_busy &= ~MMC_CQE_QUEUE_FULL;
+}
 
-	return BLKPREP_OK;
+static inline bool mmc_cqe_can_dcmd(struct mmc_host *host)
+{
+	return host->caps2 & MMC_CAP2_CQE_DCMD;
 }
 
-static int mmc_queue_thread(void *d)
+static enum mmc_issue_type mmc_cqe_issue_type(struct mmc_host *host,
+					      struct request *req)
 {
-	struct mmc_queue *mq = d;
-	struct request_queue *q = mq->queue;
-	struct mmc_context_info *cntx = &mq->card->host->context_info;
+	switch (req_op(req)) {
+	case REQ_OP_DRV_IN:
+	case REQ_OP_DRV_OUT:
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
+		return MMC_ISSUE_SYNC;
+	case REQ_OP_FLUSH:
+		return mmc_cqe_can_dcmd(host) ? MMC_ISSUE_DCMD : MMC_ISSUE_SYNC;
+	default:
+		return MMC_ISSUE_ASYNC;
+	}
+}
 
-	current->flags |= PF_MEMALLOC;
+enum mmc_issue_type mmc_issue_type(struct mmc_queue *mq, struct request *req)
+{
+	struct mmc_host *host = mq->card->host;
 
-	down(&mq->thread_sem);
-	do {
-		struct request *req;
+	if (mq->use_cqe)
+		return mmc_cqe_issue_type(host, req);
 
-		spin_lock_irq(q->queue_lock);
-		set_current_state(TASK_INTERRUPTIBLE);
-		req = blk_fetch_request(q);
-		mq->asleep = false;
-		cntx->is_waiting_last_req = false;
-		cntx->is_new_req = false;
-		if (!req) {
-			/*
-			 * Dispatch queue is empty so set flags for
-			 * mmc_request_fn() to wake us up.
-			 */
-			if (mq->qcnt)
-				cntx->is_waiting_last_req = true;
-			else
-				mq->asleep = true;
-		}
-		spin_unlock_irq(q->queue_lock);
+	if (req_op(req) == REQ_OP_READ || req_op(req) == REQ_OP_WRITE)
+		return MMC_ISSUE_ASYNC;
 
-		if (req || mq->qcnt) {
-			set_current_state(TASK_RUNNING);
-			mmc_blk_issue_rq(mq, req);
-			cond_resched();
-		} else {
-			if (kthread_should_stop()) {
-				set_current_state(TASK_RUNNING);
-				break;
-			}
-			up(&mq->thread_sem);
-			schedule();
-			down(&mq->thread_sem);
-		}
-	} while (1);
-	up(&mq->thread_sem);
+	return MMC_ISSUE_SYNC;
+}
 
-	return 0;
+static void __mmc_cqe_recovery_notifier(struct mmc_queue *mq)
+{
+	if (!mq->recovery_needed) {
+		mq->recovery_needed = true;
+		schedule_work(&mq->recovery_work);
+	}
 }
 
-/*
- * Generic MMC request handler.  This is called for any queue on a
- * particular host.  When the host is not busy, we look for a request
- * on any queue on this host, and attempt to issue it.  This may
- * not be the queue we were asked to process.
- */
-static void mmc_request_fn(struct request_queue *q)
+void mmc_cqe_recovery_notifier(struct mmc_request *mrq)
 {
+	struct mmc_queue_req *mqrq = container_of(mrq, struct mmc_queue_req,
+						  brq.mrq);
+	struct request *req = mmc_queue_req_to_req(mqrq);
+	struct request_queue *q = req->q;
 	struct mmc_queue *mq = q->queuedata;
-	struct request *req;
-	struct mmc_context_info *cntx;
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	__mmc_cqe_recovery_notifier(mq);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
 
-	if (!mq) {
-		while ((req = blk_fetch_request(q)) != NULL) {
-			req->rq_flags |= RQF_QUIET;
-			__blk_end_request_all(req, BLK_STS_IOERR);
+static enum blk_eh_timer_return mmc_cqe_timed_out(struct request *req)
+{
+	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+	struct mmc_request *mrq = &mqrq->brq.mrq;
+	struct mmc_queue *mq = req->q->queuedata;
+	struct mmc_host *host = mq->card->host;
+	enum mmc_issue_type issue_type = mmc_issue_type(mq, req);
+	bool recovery_needed = false;
+
+	switch (issue_type) {
+	case MMC_ISSUE_ASYNC:
+	case MMC_ISSUE_DCMD:
+		if (host->cqe_ops->cqe_timeout(host, mrq, &recovery_needed)) {
+			if (recovery_needed)
+				__mmc_cqe_recovery_notifier(mq);
+			return BLK_EH_RESET_TIMER;
 		}
-		return;
+		/* No timeout */
+		return BLK_EH_HANDLED;
+	default:
+		/* Timeout is handled by mmc core */
+		return BLK_EH_RESET_TIMER;
 	}
+}
+
+static enum blk_eh_timer_return mmc_mq_timed_out(struct request *req,
+						 bool reserved)
+{
+	struct request_queue *q = req->q;
+	struct mmc_queue *mq = q->queuedata;
+	unsigned long flags;
+	int ret;
 
-	cntx = &mq->card->host->context_info;
+	spin_lock_irqsave(q->queue_lock, flags);
 
-	if (cntx->is_waiting_last_req) {
-		cntx->is_new_req = true;
-		wake_up_interruptible(&cntx->wait);
-	}
+	if (mq->recovery_needed || !mq->use_cqe)
+		ret = BLK_EH_RESET_TIMER;
+	else
+		ret = mmc_cqe_timed_out(req);
 
-	if (mq->asleep)
-		wake_up_process(mq->thread);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	return ret;
+}
+
+static void mmc_mq_recovery_handler(struct work_struct *work)
+{
+	struct mmc_queue *mq = container_of(work, struct mmc_queue,
+					    recovery_work);
+	struct request_queue *q = mq->queue;
+
+	mmc_get_card(mq->card, &mq->ctx);
+
+	mq->in_recovery = true;
+
+	if (mq->use_cqe)
+		mmc_blk_cqe_recovery(mq);
+	else
+		mmc_blk_mq_recovery(mq);
+
+	mq->in_recovery = false;
+
+	spin_lock_irq(q->queue_lock);
+	mq->recovery_needed = false;
+	spin_unlock_irq(q->queue_lock);
+
+	mmc_put_card(mq->card, &mq->ctx);
+
+	blk_mq_run_hw_queues(q, true);
 }
 
 static struct scatterlist *mmc_alloc_sg(int sg_len, gfp_t gfp)
@@ -154,11 +201,10 @@ static void mmc_queue_setup_discard(struct request_queue *q,
  * @req: the request
  * @gfp: memory allocation policy
  */
-static int mmc_init_request(struct request_queue *q, struct request *req,
-			    gfp_t gfp)
+static int __mmc_init_request(struct mmc_queue *mq, struct request *req,
+			      gfp_t gfp)
 {
 	struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req);
-	struct mmc_queue *mq = q->queuedata;
 	struct mmc_card *card = mq->card;
 	struct mmc_host *host = card->host;
 
@@ -177,6 +223,131 @@ static void mmc_exit_request(struct request_queue *q, struct request *req)
 	mq_rq->sg = NULL;
 }
 
+static int mmc_mq_init_request(struct blk_mq_tag_set *set, struct request *req,
+			       unsigned int hctx_idx, unsigned int numa_node)
+{
+	return __mmc_init_request(set->driver_data, req, GFP_KERNEL);
+}
+
+static void mmc_mq_exit_request(struct blk_mq_tag_set *set, struct request *req,
+				unsigned int hctx_idx)
+{
+	struct mmc_queue *mq = set->driver_data;
+
+	mmc_exit_request(mq->queue, req);
+}
+
+/*
+ * We use BLK_MQ_F_BLOCKING and have only 1 hardware queue, which means requests
+ * will not be dispatched in parallel.
+ */
+static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
+				    const struct blk_mq_queue_data *bd)
+{
+	struct request *req = bd->rq;
+	struct request_queue *q = req->q;
+	struct mmc_queue *mq = q->queuedata;
+	struct mmc_card *card = mq->card;
+	struct mmc_host *host = card->host;
+	enum mmc_issue_type issue_type;
+	enum mmc_issued issued;
+	bool get_card, cqe_retune_ok;
+	int ret;
+
+	if (mmc_card_removed(mq->card)) {
+		req->rq_flags |= RQF_QUIET;
+		return BLK_STS_IOERR;
+	}
+
+	issue_type = mmc_issue_type(mq, req);
+
+	spin_lock_irq(q->queue_lock);
+
+	if (mq->recovery_needed) {
+		spin_unlock_irq(q->queue_lock);
+		return BLK_STS_RESOURCE;
+	}
+
+	switch (issue_type) {
+	case MMC_ISSUE_DCMD:
+		if (mmc_cqe_dcmd_busy(mq)) {
+			mq->cqe_busy |= MMC_CQE_DCMD_BUSY;
+			spin_unlock_irq(q->queue_lock);
+			return BLK_STS_RESOURCE;
+		}
+		break;
+	case MMC_ISSUE_ASYNC:
+		break;
+	default:
+		/*
+		 * Timeouts are handled by mmc core, and we don't have a host
+		 * API to abort requests, so we can't handle the timeout anyway.
+		 * However, when the timeout happens, blk_mq_complete_request()
+		 * no longer works (to stop the request disappearing under us).
+		 * To avoid racing with that, set a large timeout.
+		 */
+		req->timeout = 600 * HZ;
+		break;
+	}
+
+	mq->in_flight[issue_type] += 1;
+	get_card = (mmc_tot_in_flight(mq) == 1);
+	cqe_retune_ok = (mmc_cqe_qcnt(mq) == 1);
+
+	spin_unlock_irq(q->queue_lock);
+
+	if (!(req->rq_flags & RQF_DONTPREP)) {
+		req_to_mmc_queue_req(req)->retries = 0;
+		req->rq_flags |= RQF_DONTPREP;
+	}
+
+	if (get_card)
+		mmc_get_card(card, &mq->ctx);
+
+	if (mq->use_cqe) {
+		host->retune_now = host->need_retune && cqe_retune_ok &&
+				   !host->hold_retune;
+	}
+
+	blk_mq_start_request(req);
+
+	issued = mmc_blk_mq_issue_rq(mq, req);
+
+	switch (issued) {
+	case MMC_REQ_BUSY:
+		ret = BLK_STS_RESOURCE;
+		break;
+	case MMC_REQ_FAILED_TO_START:
+		ret = BLK_STS_IOERR;
+		break;
+	default:
+		ret = BLK_STS_OK;
+		break;
+	}
+
+	if (issued != MMC_REQ_STARTED) {
+		bool put_card = false;
+
+		spin_lock_irq(q->queue_lock);
+		mq->in_flight[issue_type] -= 1;
+		if (mmc_tot_in_flight(mq) == 0)
+			put_card = true;
+		spin_unlock_irq(q->queue_lock);
+		if (put_card)
+			mmc_put_card(card, &mq->ctx);
+	}
+
+	return ret;
+}
+
+static const struct blk_mq_ops mmc_mq_ops = {
+	.queue_rq	= mmc_mq_queue_rq,
+	.init_request	= mmc_mq_init_request,
+	.exit_request	= mmc_mq_exit_request,
+	.complete	= mmc_blk_mq_complete,
+	.timeout	= mmc_mq_timed_out,
+};
+
 static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
@@ -196,124 +367,139 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
 	blk_queue_max_segments(mq->queue, host->max_segs);
 	blk_queue_max_segment_size(mq->queue, host->max_seg_size);
 
-	/* Initialize thread_sem even if it is not used */
-	sema_init(&mq->thread_sem, 1);
+	INIT_WORK(&mq->recovery_work, mmc_mq_recovery_handler);
+	INIT_WORK(&mq->complete_work, mmc_blk_mq_complete_work);
+
+	mutex_init(&mq->complete_lock);
+
+	init_waitqueue_head(&mq->wait);
 }
 
-/**
- * mmc_init_queue - initialise a queue structure.
- * @mq: mmc queue
- * @card: mmc card to attach this queue
- * @lock: queue lock
- * @subname: partition subname
- *
- * Initialise a MMC card request queue.
- */
-int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
-		   spinlock_t *lock, const char *subname)
+static int mmc_mq_init_queue(struct mmc_queue *mq, int q_depth,
+			     const struct blk_mq_ops *mq_ops, spinlock_t *lock)
 {
-	struct mmc_host *host = card->host;
-	int ret = -ENOMEM;
-
-	mq->card = card;
-	mq->queue = blk_alloc_queue(GFP_KERNEL);
-	if (!mq->queue)
-		return -ENOMEM;
-	mq->queue->queue_lock = lock;
-	mq->queue->request_fn = mmc_request_fn;
-	mq->queue->init_rq_fn = mmc_init_request;
-	mq->queue->exit_rq_fn = mmc_exit_request;
-	mq->queue->cmd_size = sizeof(struct mmc_queue_req);
-	mq->queue->queuedata = mq;
-	mq->qcnt = 0;
-	ret = blk_init_allocated_queue(mq->queue);
-	if (ret) {
-		blk_cleanup_queue(mq->queue);
+	int ret;
+
+	memset(&mq->tag_set, 0, sizeof(mq->tag_set));
+	mq->tag_set.ops = mq_ops;
+	mq->tag_set.queue_depth = q_depth;
+	mq->tag_set.numa_node = NUMA_NO_NODE;
+	mq->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE |
+			    BLK_MQ_F_BLOCKING;
+	mq->tag_set.nr_hw_queues = 1;
+	mq->tag_set.cmd_size = sizeof(struct mmc_queue_req);
+	mq->tag_set.driver_data = mq;
+
+	ret = blk_mq_alloc_tag_set(&mq->tag_set);
+	if (ret)
 		return ret;
-	}
-
-	blk_queue_prep_rq(mq->queue, mmc_prep_request);
-
-	mmc_setup_queue(mq, card);
 
-	mq->thread = kthread_run(mmc_queue_thread, mq, "mmcqd/%d%s",
-		host->index, subname ? subname : "");
-
-	if (IS_ERR(mq->thread)) {
-		ret = PTR_ERR(mq->thread);
-		goto cleanup_queue;
+	mq->queue = blk_mq_init_queue(&mq->tag_set);
+	if (IS_ERR(mq->queue)) {
+		ret = PTR_ERR(mq->queue);
+		goto free_tag_set;
 	}
 
+	mq->queue->queue_lock = lock;
+	mq->queue->queuedata = mq;
+
 	return 0;
 
-cleanup_queue:
-	blk_cleanup_queue(mq->queue);
+free_tag_set:
+	blk_mq_free_tag_set(&mq->tag_set);
+
 	return ret;
 }
 
-void mmc_cleanup_queue(struct mmc_queue *mq)
-{
-	struct request_queue *q = mq->queue;
-	unsigned long flags;
+/* Set queue depth to get a reasonable value for q->nr_requests */
+#define MMC_QUEUE_DEPTH 64
 
-	/* Make sure the queue isn't suspended, as that will deadlock */
-	mmc_queue_resume(mq);
+static int mmc_mq_init(struct mmc_queue *mq, struct mmc_card *card,
+			 spinlock_t *lock)
+{
+	struct mmc_host *host = card->host;
+	int q_depth;
+	int ret;
+
+	/*
+	 * The queue depth for CQE must match the hardware because the request
+	 * tag is used to index the hardware queue.
+	 */
+	if (mq->use_cqe)
+		q_depth = min_t(int, card->ext_csd.cmdq_depth, host->cqe_qdepth);
+	else
+		q_depth = MMC_QUEUE_DEPTH;
+
+	ret = mmc_mq_init_queue(mq, q_depth, &mmc_mq_ops, lock);
+	if (ret)
+		return ret;
 
-	/* Then terminate our worker thread */
-	kthread_stop(mq->thread);
+	blk_queue_rq_timeout(mq->queue, 60 * HZ);
 
-	/* Empty the queue */
-	spin_lock_irqsave(q->queue_lock, flags);
-	q->queuedata = NULL;
-	blk_start_queue(q);
-	spin_unlock_irqrestore(q->queue_lock, flags);
+	mmc_setup_queue(mq, card);
 
-	mq->card = NULL;
+	return 0;
 }
-EXPORT_SYMBOL(mmc_cleanup_queue);
 
 /**
- * mmc_queue_suspend - suspend a MMC request queue
- * @mq: MMC queue to suspend
+ * mmc_init_queue - initialise a queue structure.
+ * @mq: mmc queue
+ * @card: mmc card to attach this queue
+ * @lock: queue lock
+ * @subname: partition subname
  *
- * Stop the block request queue, and wait for our thread to
- * complete any outstanding requests.  This ensures that we
- * won't suspend while a request is being processed.
+ * Initialise a MMC card request queue.
  */
-void mmc_queue_suspend(struct mmc_queue *mq)
+int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
+		   spinlock_t *lock, const char *subname)
 {
-	struct request_queue *q = mq->queue;
-	unsigned long flags;
+	struct mmc_host *host = card->host;
 
-	if (!mq->suspended) {
-		mq->suspended |= true;
+	mq->card = card;
 
-		spin_lock_irqsave(q->queue_lock, flags);
-		blk_stop_queue(q);
-		spin_unlock_irqrestore(q->queue_lock, flags);
+	mq->use_cqe = host->cqe_enabled;
 
-		down(&mq->thread_sem);
-	}
+	return mmc_mq_init(mq, card, lock);
+}
+
+void mmc_queue_suspend(struct mmc_queue *mq)
+{
+	blk_mq_quiesce_queue(mq->queue);
+
+	/*
+	 * The host remains claimed while there are outstanding requests, so
+	 * simply claiming and releasing here ensures there are none.
+	 */
+	mmc_claim_host(mq->card->host);
+	mmc_release_host(mq->card->host);
 }
 
-/**
- * mmc_queue_resume - resume a previously suspended MMC request queue
- * @mq: MMC queue to resume
- */
 void mmc_queue_resume(struct mmc_queue *mq)
 {
+	blk_mq_unquiesce_queue(mq->queue);
+}
+
+void mmc_cleanup_queue(struct mmc_queue *mq)
+{
 	struct request_queue *q = mq->queue;
-	unsigned long flags;
 
-	if (mq->suspended) {
-		mq->suspended = false;
+	/*
+	 * The legacy code handled the possibility of being suspended,
+	 * so do that here too.
+	 */
+	if (blk_queue_quiesced(q))
+		blk_mq_unquiesce_queue(q);
 
-		up(&mq->thread_sem);
+	blk_cleanup_queue(q);
 
-		spin_lock_irqsave(q->queue_lock, flags);
-		blk_start_queue(q);
-		spin_unlock_irqrestore(q->queue_lock, flags);
-	}
+	/*
+	 * A request can be completed before the next request, potentially
+	 * leaving a complete_work with nothing to do. Such a work item might
+	 * still be queued at this point. Flush it.
+	 */
+	flush_work(&mq->complete_work);
+
+	mq->card = NULL;
 }
 
 /*
diff --git a/drivers/mmc/core/queue.h b/drivers/mmc/core/queue.h
index 547b457c4251..17e59d50b496 100644
--- a/drivers/mmc/core/queue.h
+++ b/drivers/mmc/core/queue.h
@@ -8,6 +8,20 @@
 #include <linux/mmc/core.h>
 #include <linux/mmc/host.h>
 
+enum mmc_issued {
+	MMC_REQ_STARTED,
+	MMC_REQ_BUSY,
+	MMC_REQ_FAILED_TO_START,
+	MMC_REQ_FINISHED,
+};
+
+enum mmc_issue_type {
+	MMC_ISSUE_SYNC,
+	MMC_ISSUE_DCMD,
+	MMC_ISSUE_ASYNC,
+	MMC_ISSUE_MAX,
+};
+
 static inline struct mmc_queue_req *req_to_mmc_queue_req(struct request *rq)
 {
 	return blk_mq_rq_to_pdu(rq);
@@ -20,7 +34,6 @@ static inline struct request *mmc_queue_req_to_req(struct mmc_queue_req *mqr)
 	return blk_mq_rq_from_pdu(mqr);
 }
 
-struct task_struct;
 struct mmc_blk_data;
 struct mmc_blk_ioc_data;
 
@@ -30,7 +43,6 @@ struct mmc_blk_request {
 	struct mmc_command	cmd;
 	struct mmc_command	stop;
 	struct mmc_data		data;
-	int			retune_retry_done;
 };
 
 /**
@@ -52,28 +64,34 @@ enum mmc_drv_op {
 struct mmc_queue_req {
 	struct mmc_blk_request	brq;
 	struct scatterlist	*sg;
-	struct mmc_async_req	areq;
 	enum mmc_drv_op		drv_op;
 	int			drv_op_result;
 	void			*drv_op_data;
 	unsigned int		ioc_count;
+	int			retries;
 };
 
 struct mmc_queue {
 	struct mmc_card		*card;
-	struct task_struct	*thread;
-	struct semaphore	thread_sem;
-	bool			suspended;
-	bool			asleep;
+	struct mmc_ctx		ctx;
+	struct blk_mq_tag_set	tag_set;
 	struct mmc_blk_data	*blkdata;
 	struct request_queue	*queue;
-	/*
-	 * FIXME: this counter is not a very reliable way of keeping
-	 * track of how many requests that are ongoing. Switch to just
-	 * letting the block core keep track of requests and per-request
-	 * associated mmc_queue_req data.
-	 */
-	int			qcnt;
+	int			in_flight[MMC_ISSUE_MAX];
+	unsigned int		cqe_busy;
+#define MMC_CQE_DCMD_BUSY	BIT(0)
+#define MMC_CQE_QUEUE_FULL	BIT(1)
+	bool			use_cqe;
+	bool			recovery_needed;
+	bool			in_recovery;
+	bool			rw_wait;
+	bool			waiting;
+	struct work_struct	recovery_work;
+	wait_queue_head_t	wait;
+	struct request		*recovery_req;
+	struct request		*complete_req;
+	struct mutex		complete_lock;
+	struct work_struct	complete_work;
 };
 
 extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *,
@@ -84,4 +102,22 @@ extern void mmc_queue_resume(struct mmc_queue *);
 extern unsigned int mmc_queue_map_sg(struct mmc_queue *,
 				     struct mmc_queue_req *);
 
+void mmc_cqe_check_busy(struct mmc_queue *mq);
+void mmc_cqe_recovery_notifier(struct mmc_request *mrq);
+
+enum mmc_issue_type mmc_issue_type(struct mmc_queue *mq, struct request *req);
+
+static inline int mmc_tot_in_flight(struct mmc_queue *mq)
+{
+	return mq->in_flight[MMC_ISSUE_SYNC] +
+	       mq->in_flight[MMC_ISSUE_DCMD] +
+	       mq->in_flight[MMC_ISSUE_ASYNC];
+}
+
+static inline int mmc_cqe_qcnt(struct mmc_queue *mq)
+{
+	return mq->in_flight[MMC_ISSUE_DCMD] +
+	       mq->in_flight[MMC_ISSUE_ASYNC];
+}
+
 #endif
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index 863f1dbbfc1b..3698b0576009 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -121,20 +121,18 @@ EXPORT_SYMBOL(mmc_gpio_request_ro);
 void mmc_gpiod_request_cd_irq(struct mmc_host *host)
 {
 	struct mmc_gpio *ctx = host->slot.handler_priv;
-	int ret, irq;
+	int irq = -EINVAL;
+	int ret;
 
 	if (host->slot.cd_irq >= 0 || !ctx || !ctx->cd_gpio)
 		return;
 
-	irq = gpiod_to_irq(ctx->cd_gpio);
-
 	/*
-	 * Even if gpiod_to_irq() returns a valid IRQ number, the platform might
-	 * still prefer to poll, e.g., because that IRQ number is already used
-	 * by another unit and cannot be shared.
+	 * Do not use IRQ if the platform prefers to poll, e.g., because that
+	 * IRQ number is already used by another unit and cannot be shared.
 	 */
-	if (irq >= 0 && host->caps & MMC_CAP_NEEDS_POLL)
-		irq = -EINVAL;
+	if (!(host->caps & MMC_CAP_NEEDS_POLL))
+		irq = gpiod_to_irq(ctx->cd_gpio);
 
 	if (irq >= 0) {
 		if (!ctx->cd_gpio_isr)
@@ -307,3 +305,11 @@ int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
 	return 0;
 }
 EXPORT_SYMBOL(mmc_gpiod_request_ro);
+
+bool mmc_can_gpio_ro(struct mmc_host *host)
+{
+	struct mmc_gpio *ctx = host->slot.handler_priv;
+
+	return ctx->ro_gpio ? true : false;
+}
+EXPORT_SYMBOL(mmc_can_gpio_ro);
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index cec8152b5ede..67bd3344dd03 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -81,6 +81,7 @@ config MMC_SDHCI_BIG_ENDIAN_32BIT_BYTE_SWAPPER
 config MMC_SDHCI_PCI
 	tristate "SDHCI support on PCI bus"
 	depends on MMC_SDHCI && PCI
+	select MMC_CQHCI
 	help
 	  This selects the PCI Secure Digital Host Controller Interface.
 	  Most controllers found today are PCI devices.
@@ -132,6 +133,7 @@ config MMC_SDHCI_OF_ARASAN
 	depends on MMC_SDHCI_PLTFM
 	depends on OF
 	depends on COMMON_CLK
+	select MMC_CQHCI
 	help
 	  This selects the Arasan Secure Digital Host Controller Interface
 	  (SDHCI). This hardware is found e.g. in Xilinx' Zynq SoC.
@@ -320,7 +322,7 @@ config MMC_SDHCI_BCM_KONA
 config MMC_SDHCI_F_SDH30
 	tristate "SDHCI support for Fujitsu Semiconductor F_SDH30"
 	depends on MMC_SDHCI_PLTFM
-	depends on OF
+	depends on OF || ACPI
 	help
 	  This selects the Secure Digital Host Controller Interface (SDHCI)
 	  Needed by some Fujitsu SoC for MMC / SD / SDIO support.
@@ -595,11 +597,8 @@ config MMC_TMIO
 
 config MMC_SDHI
 	tristate "Renesas SDHI SD/SDIO controller support"
-	depends on SUPERH || ARM || ARM64
 	depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
 	select MMC_TMIO_CORE
-	select MMC_SDHI_SYS_DMAC if (SUPERH || ARM)
-	select MMC_SDHI_INTERNAL_DMAC if ARM64
 	help
 	  This provides support for the SDHI SD/SDIO controller found in
 	  Renesas SuperH, ARM and ARM64 based SoCs
@@ -607,6 +606,7 @@ config MMC_SDHI
 config MMC_SDHI_SYS_DMAC
 	tristate "DMA for SDHI SD/SDIO controllers using SYS-DMAC"
 	depends on MMC_SDHI
+	default MMC_SDHI if (SUPERH || ARM)
 	help
 	  This provides DMA support for SDHI SD/SDIO controllers
 	  using SYS-DMAC via DMA Engine. This supports the controllers
@@ -616,6 +616,7 @@ config MMC_SDHI_INTERNAL_DMAC
 	tristate "DMA for SDHI SD/SDIO controllers using on-chip bus mastering"
 	depends on ARM64 || COMPILE_TEST
 	depends on MMC_SDHI
+	default MMC_SDHI if ARM64
 	help
 	  This provides DMA support for SDHI SD/SDIO controllers
 	  using on-chip bus mastering. This supports the controllers
@@ -857,6 +858,19 @@ config MMC_SUNXI
 	  This selects support for the SD/MMC Host Controller on
 	  Allwinner sunxi SoCs.
 
+config MMC_CQHCI
+	tristate "Command Queue Host Controller Interface support"
+	depends on HAS_DMA
+	help
+	  This selects the Command Queue Host Controller Interface (CQHCI)
+	  support present in host controllers of Qualcomm Technologies, Inc
+	  amongst others.
+	  This controller supports eMMC devices with command queue support.
+
+	  If you have a controller with this interface, say Y or M here.
+
+	  If unsure, say N.
+
 config MMC_TOSHIBA_PCI
 	tristate "Toshiba Type A SD/MMC Card Interface Driver"
 	depends on PCI
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index a43cf0d5a5d3..84cd1388abc3 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -11,7 +11,7 @@ obj-$(CONFIG_MMC_MXC)		+= mxcmmc.o
 obj-$(CONFIG_MMC_MXS)		+= mxs-mmc.o
 obj-$(CONFIG_MMC_SDHCI)		+= sdhci.o
 obj-$(CONFIG_MMC_SDHCI_PCI)	+= sdhci-pci.o
-sdhci-pci-y			+= sdhci-pci-core.o sdhci-pci-o2micro.o
+sdhci-pci-y			+= sdhci-pci-core.o sdhci-pci-o2micro.o sdhci-pci-arasan.o
 obj-$(subst m,y,$(CONFIG_MMC_SDHCI_PCI))	+= sdhci-pci-data.o
 obj-$(CONFIG_MMC_SDHCI_ACPI)	+= sdhci-acpi.o
 obj-$(CONFIG_MMC_SDHCI_PXAV3)	+= sdhci-pxav3.o
@@ -39,12 +39,8 @@ obj-$(CONFIG_MMC_SDRICOH_CS)	+= sdricoh_cs.o
 obj-$(CONFIG_MMC_TMIO)		+= tmio_mmc.o
 obj-$(CONFIG_MMC_TMIO_CORE)	+= tmio_mmc_core.o
 obj-$(CONFIG_MMC_SDHI)		+= renesas_sdhi_core.o
-ifeq ($(subst m,y,$(CONFIG_MMC_SDHI_SYS_DMAC)),y)
-obj-$(CONFIG_MMC_SDHI)		+= renesas_sdhi_sys_dmac.o
-endif
-ifeq ($(subst m,y,$(CONFIG_MMC_SDHI_INTERNAL_DMAC)),y)
-obj-$(CONFIG_MMC_SDHI)		+= renesas_sdhi_internal_dmac.o
-endif
+obj-$(CONFIG_MMC_SDHI_SYS_DMAC)		+= renesas_sdhi_sys_dmac.o
+obj-$(CONFIG_MMC_SDHI_INTERNAL_DMAC)	+= renesas_sdhi_internal_dmac.o
 obj-$(CONFIG_MMC_CB710)		+= cb710-mmc.o
 obj-$(CONFIG_MMC_VIA_SDMMC)	+= via-sdmmc.o
 obj-$(CONFIG_SDH_BFIN)		+= bfin_sdh.o
@@ -92,6 +88,7 @@ obj-$(CONFIG_MMC_SDHCI_ST)		+= sdhci-st.o
 obj-$(CONFIG_MMC_SDHCI_MICROCHIP_PIC32)	+= sdhci-pic32.o
 obj-$(CONFIG_MMC_SDHCI_BRCMSTB)		+= sdhci-brcmstb.o
 obj-$(CONFIG_MMC_SDHCI_OMAP)		+= sdhci-omap.o
+obj-$(CONFIG_MMC_CQHCI)			+= cqhci.o
 
 ifeq ($(CONFIG_CB710_DEBUG),y)
 	CFLAGS-cb710-mmc	+= -DDEBUG
diff --git a/drivers/mmc/host/android-goldfish.c b/drivers/mmc/host/android-goldfish.c
index 63fe5091ca59..63d27589cd89 100644
--- a/drivers/mmc/host/android-goldfish.c
+++ b/drivers/mmc/host/android-goldfish.c
@@ -42,13 +42,11 @@
 #include <linux/spinlock.h>
 #include <linux/timer.h>
 #include <linux/clk.h>
-#include <linux/scatterlist.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>
 
 #include <asm/types.h>
-#include <asm/io.h>
 #include <linux/uaccess.h>
 
 #define DRIVER_NAME "goldfish_mmc"
diff --git a/drivers/mmc/host/cqhci.c b/drivers/mmc/host/cqhci.c
new file mode 100644
index 000000000000..159270e947cf
--- /dev/null
+++ b/drivers/mmc/host/cqhci.c
@@ -0,0 +1,1150 @@
+/* Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/delay.h>
+#include <linux/highmem.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/dma-mapping.h>
+#include <linux/slab.h>
+#include <linux/scatterlist.h>
+#include <linux/platform_device.h>
+#include <linux/ktime.h>
+
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/card.h>
+
+#include "cqhci.h"
+
+#define DCMD_SLOT 31
+#define NUM_SLOTS 32
+
+struct cqhci_slot {
+	struct mmc_request *mrq;
+	unsigned int flags;
+#define CQHCI_EXTERNAL_TIMEOUT	BIT(0)
+#define CQHCI_COMPLETED		BIT(1)
+#define CQHCI_HOST_CRC		BIT(2)
+#define CQHCI_HOST_TIMEOUT	BIT(3)
+#define CQHCI_HOST_OTHER	BIT(4)
+};
+
+static inline u8 *get_desc(struct cqhci_host *cq_host, u8 tag)
+{
+	return cq_host->desc_base + (tag * cq_host->slot_sz);
+}
+
+static inline u8 *get_link_desc(struct cqhci_host *cq_host, u8 tag)
+{
+	u8 *desc = get_desc(cq_host, tag);
+
+	return desc + cq_host->task_desc_len;
+}
+
+static inline dma_addr_t get_trans_desc_dma(struct cqhci_host *cq_host, u8 tag)
+{
+	return cq_host->trans_desc_dma_base +
+		(cq_host->mmc->max_segs * tag *
+		 cq_host->trans_desc_len);
+}
+
+static inline u8 *get_trans_desc(struct cqhci_host *cq_host, u8 tag)
+{
+	return cq_host->trans_desc_base +
+		(cq_host->trans_desc_len * cq_host->mmc->max_segs * tag);
+}
+
+static void setup_trans_desc(struct cqhci_host *cq_host, u8 tag)
+{
+	u8 *link_temp;
+	dma_addr_t trans_temp;
+
+	link_temp = get_link_desc(cq_host, tag);
+	trans_temp = get_trans_desc_dma(cq_host, tag);
+
+	memset(link_temp, 0, cq_host->link_desc_len);
+	if (cq_host->link_desc_len > 8)
+		*(link_temp + 8) = 0;
+
+	if (tag == DCMD_SLOT && (cq_host->mmc->caps2 & MMC_CAP2_CQE_DCMD)) {
+		*link_temp = CQHCI_VALID(0) | CQHCI_ACT(0) | CQHCI_END(1);
+		return;
+	}
+
+	*link_temp = CQHCI_VALID(1) | CQHCI_ACT(0x6) | CQHCI_END(0);
+
+	if (cq_host->dma64) {
+		__le64 *data_addr = (__le64 __force *)(link_temp + 4);
+
+		data_addr[0] = cpu_to_le64(trans_temp);
+	} else {
+		__le32 *data_addr = (__le32 __force *)(link_temp + 4);
+
+		data_addr[0] = cpu_to_le32(trans_temp);
+	}
+}
+
+static void cqhci_set_irqs(struct cqhci_host *cq_host, u32 set)
+{
+	cqhci_writel(cq_host, set, CQHCI_ISTE);
+	cqhci_writel(cq_host, set, CQHCI_ISGE);
+}
+
+#define DRV_NAME "cqhci"
+
+#define CQHCI_DUMP(f, x...) \
+	pr_err("%s: " DRV_NAME ": " f, mmc_hostname(mmc), ## x)
+
+static void cqhci_dumpregs(struct cqhci_host *cq_host)
+{
+	struct mmc_host *mmc = cq_host->mmc;
+
+	CQHCI_DUMP("============ CQHCI REGISTER DUMP ===========\n");
+
+	CQHCI_DUMP("Caps:      0x%08x | Version:  0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_CAP),
+		   cqhci_readl(cq_host, CQHCI_VER));
+	CQHCI_DUMP("Config:    0x%08x | Control:  0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_CFG),
+		   cqhci_readl(cq_host, CQHCI_CTL));
+	CQHCI_DUMP("Int stat:  0x%08x | Int enab: 0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_IS),
+		   cqhci_readl(cq_host, CQHCI_ISTE));
+	CQHCI_DUMP("Int sig:   0x%08x | Int Coal: 0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_ISGE),
+		   cqhci_readl(cq_host, CQHCI_IC));
+	CQHCI_DUMP("TDL base:  0x%08x | TDL up32: 0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_TDLBA),
+		   cqhci_readl(cq_host, CQHCI_TDLBAU));
+	CQHCI_DUMP("Doorbell:  0x%08x | TCN:      0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_TDBR),
+		   cqhci_readl(cq_host, CQHCI_TCN));
+	CQHCI_DUMP("Dev queue: 0x%08x | Dev Pend: 0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_DQS),
+		   cqhci_readl(cq_host, CQHCI_DPT));
+	CQHCI_DUMP("Task clr:  0x%08x | SSC1:     0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_TCLR),
+		   cqhci_readl(cq_host, CQHCI_SSC1));
+	CQHCI_DUMP("SSC2:      0x%08x | DCMD rsp: 0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_SSC2),
+		   cqhci_readl(cq_host, CQHCI_CRDCT));
+	CQHCI_DUMP("RED mask:  0x%08x | TERRI:    0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_RMEM),
+		   cqhci_readl(cq_host, CQHCI_TERRI));
+	CQHCI_DUMP("Resp idx:  0x%08x | Resp arg: 0x%08x\n",
+		   cqhci_readl(cq_host, CQHCI_CRI),
+		   cqhci_readl(cq_host, CQHCI_CRA));
+
+	if (cq_host->ops->dumpregs)
+		cq_host->ops->dumpregs(mmc);
+	else
+		CQHCI_DUMP(": ===========================================\n");
+}
+
+/**
+ * The allocated descriptor table for task, link & transfer descritors
+ * looks like:
+ * |----------|
+ * |task desc |  |->|----------|
+ * |----------|  |  |trans desc|
+ * |link desc-|->|  |----------|
+ * |----------|          .
+ *      .                .
+ *  no. of slots      max-segs
+ *      .           |----------|
+ * |----------|
+ * The idea here is to create the [task+trans] table and mark & point the
+ * link desc to the transfer desc table on a per slot basis.
+ */
+static int cqhci_host_alloc_tdl(struct cqhci_host *cq_host)
+{
+	int i = 0;
+
+	/* task descriptor can be 64/128 bit irrespective of arch */
+	if (cq_host->caps & CQHCI_TASK_DESC_SZ_128) {
+		cqhci_writel(cq_host, cqhci_readl(cq_host, CQHCI_CFG) |
+			       CQHCI_TASK_DESC_SZ, CQHCI_CFG);
+		cq_host->task_desc_len = 16;
+	} else {
+		cq_host->task_desc_len = 8;
+	}
+
+	/*
+	 * 96 bits length of transfer desc instead of 128 bits which means
+	 * ADMA would expect next valid descriptor at the 96th bit
+	 * or 128th bit
+	 */
+	if (cq_host->dma64) {
+		if (cq_host->quirks & CQHCI_QUIRK_SHORT_TXFR_DESC_SZ)
+			cq_host->trans_desc_len = 12;
+		else
+			cq_host->trans_desc_len = 16;
+		cq_host->link_desc_len = 16;
+	} else {
+		cq_host->trans_desc_len = 8;
+		cq_host->link_desc_len = 8;
+	}
+
+	/* total size of a slot: 1 task & 1 transfer (link) */
+	cq_host->slot_sz = cq_host->task_desc_len + cq_host->link_desc_len;
+
+	cq_host->desc_size = cq_host->slot_sz * cq_host->num_slots;
+
+	cq_host->data_size = cq_host->trans_desc_len * cq_host->mmc->max_segs *
+		(cq_host->num_slots - 1);
+
+	pr_debug("%s: cqhci: desc_size: %zu data_sz: %zu slot-sz: %d\n",
+		 mmc_hostname(cq_host->mmc), cq_host->desc_size, cq_host->data_size,
+		 cq_host->slot_sz);
+
+	/*
+	 * allocate a dma-mapped chunk of memory for the descriptors
+	 * allocate a dma-mapped chunk of memory for link descriptors
+	 * setup each link-desc memory offset per slot-number to
+	 * the descriptor table.
+	 */
+	cq_host->desc_base = dmam_alloc_coherent(mmc_dev(cq_host->mmc),
+						 cq_host->desc_size,
+						 &cq_host->desc_dma_base,
+						 GFP_KERNEL);
+	cq_host->trans_desc_base = dmam_alloc_coherent(mmc_dev(cq_host->mmc),
+					      cq_host->data_size,
+					      &cq_host->trans_desc_dma_base,
+					      GFP_KERNEL);
+	if (!cq_host->desc_base || !cq_host->trans_desc_base)
+		return -ENOMEM;
+
+	pr_debug("%s: cqhci: desc-base: 0x%p trans-base: 0x%p\n desc_dma 0x%llx trans_dma: 0x%llx\n",
+		 mmc_hostname(cq_host->mmc), cq_host->desc_base, cq_host->trans_desc_base,
+		(unsigned long long)cq_host->desc_dma_base,
+		(unsigned long long)cq_host->trans_desc_dma_base);
+
+	for (; i < (cq_host->num_slots); i++)
+		setup_trans_desc(cq_host, i);
+
+	return 0;
+}
+
+static void __cqhci_enable(struct cqhci_host *cq_host)
+{
+	struct mmc_host *mmc = cq_host->mmc;
+	u32 cqcfg;
+
+	cqcfg = cqhci_readl(cq_host, CQHCI_CFG);
+
+	/* Configuration must not be changed while enabled */
+	if (cqcfg & CQHCI_ENABLE) {
+		cqcfg &= ~CQHCI_ENABLE;
+		cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+	}
+
+	cqcfg &= ~(CQHCI_DCMD | CQHCI_TASK_DESC_SZ);
+
+	if (mmc->caps2 & MMC_CAP2_CQE_DCMD)
+		cqcfg |= CQHCI_DCMD;
+
+	if (cq_host->caps & CQHCI_TASK_DESC_SZ_128)
+		cqcfg |= CQHCI_TASK_DESC_SZ;
+
+	cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+
+	cqhci_writel(cq_host, lower_32_bits(cq_host->desc_dma_base),
+		     CQHCI_TDLBA);
+	cqhci_writel(cq_host, upper_32_bits(cq_host->desc_dma_base),
+		     CQHCI_TDLBAU);
+
+	cqhci_writel(cq_host, cq_host->rca, CQHCI_SSC2);
+
+	cqhci_set_irqs(cq_host, 0);
+
+	cqcfg |= CQHCI_ENABLE;
+
+	cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+
+	mmc->cqe_on = true;
+
+	if (cq_host->ops->enable)
+		cq_host->ops->enable(mmc);
+
+	/* Ensure all writes are done before interrupts are enabled */
+	wmb();
+
+	cqhci_set_irqs(cq_host, CQHCI_IS_MASK);
+
+	cq_host->activated = true;
+}
+
+static void __cqhci_disable(struct cqhci_host *cq_host)
+{
+	u32 cqcfg;
+
+	cqcfg = cqhci_readl(cq_host, CQHCI_CFG);
+	cqcfg &= ~CQHCI_ENABLE;
+	cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+
+	cq_host->mmc->cqe_on = false;
+
+	cq_host->activated = false;
+}
+
+int cqhci_suspend(struct mmc_host *mmc)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+
+	if (cq_host->enabled)
+		__cqhci_disable(cq_host);
+
+	return 0;
+}
+EXPORT_SYMBOL(cqhci_suspend);
+
+int cqhci_resume(struct mmc_host *mmc)
+{
+	/* Re-enable is done upon first request */
+	return 0;
+}
+EXPORT_SYMBOL(cqhci_resume);
+
+static int cqhci_enable(struct mmc_host *mmc, struct mmc_card *card)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	int err;
+
+	if (cq_host->enabled)
+		return 0;
+
+	cq_host->rca = card->rca;
+
+	err = cqhci_host_alloc_tdl(cq_host);
+	if (err)
+		return err;
+
+	__cqhci_enable(cq_host);
+
+	cq_host->enabled = true;
+
+#ifdef DEBUG
+	cqhci_dumpregs(cq_host);
+#endif
+	return 0;
+}
+
+/* CQHCI is idle and should halt immediately, so set a small timeout */
+#define CQHCI_OFF_TIMEOUT 100
+
+static void cqhci_off(struct mmc_host *mmc)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	ktime_t timeout;
+	bool timed_out;
+	u32 reg;
+
+	if (!cq_host->enabled || !mmc->cqe_on || cq_host->recovery_halt)
+		return;
+
+	if (cq_host->ops->disable)
+		cq_host->ops->disable(mmc, false);
+
+	cqhci_writel(cq_host, CQHCI_HALT, CQHCI_CTL);
+
+	timeout = ktime_add_us(ktime_get(), CQHCI_OFF_TIMEOUT);
+	while (1) {
+		timed_out = ktime_compare(ktime_get(), timeout) > 0;
+		reg = cqhci_readl(cq_host, CQHCI_CTL);
+		if ((reg & CQHCI_HALT) || timed_out)
+			break;
+	}
+
+	if (timed_out)
+		pr_err("%s: cqhci: CQE stuck on\n", mmc_hostname(mmc));
+	else
+		pr_debug("%s: cqhci: CQE off\n", mmc_hostname(mmc));
+
+	mmc->cqe_on = false;
+}
+
+static void cqhci_disable(struct mmc_host *mmc)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+
+	if (!cq_host->enabled)
+		return;
+
+	cqhci_off(mmc);
+
+	__cqhci_disable(cq_host);
+
+	dmam_free_coherent(mmc_dev(mmc), cq_host->data_size,
+			   cq_host->trans_desc_base,
+			   cq_host->trans_desc_dma_base);
+
+	dmam_free_coherent(mmc_dev(mmc), cq_host->desc_size,
+			   cq_host->desc_base,
+			   cq_host->desc_dma_base);
+
+	cq_host->trans_desc_base = NULL;
+	cq_host->desc_base = NULL;
+
+	cq_host->enabled = false;
+}
+
+static void cqhci_prep_task_desc(struct mmc_request *mrq,
+					u64 *data, bool intr)
+{
+	u32 req_flags = mrq->data->flags;
+
+	*data = CQHCI_VALID(1) |
+		CQHCI_END(1) |
+		CQHCI_INT(intr) |
+		CQHCI_ACT(0x5) |
+		CQHCI_FORCED_PROG(!!(req_flags & MMC_DATA_FORCED_PRG)) |
+		CQHCI_DATA_TAG(!!(req_flags & MMC_DATA_DAT_TAG)) |
+		CQHCI_DATA_DIR(!!(req_flags & MMC_DATA_READ)) |
+		CQHCI_PRIORITY(!!(req_flags & MMC_DATA_PRIO)) |
+		CQHCI_QBAR(!!(req_flags & MMC_DATA_QBR)) |
+		CQHCI_REL_WRITE(!!(req_flags & MMC_DATA_REL_WR)) |
+		CQHCI_BLK_COUNT(mrq->data->blocks) |
+		CQHCI_BLK_ADDR((u64)mrq->data->blk_addr);
+
+	pr_debug("%s: cqhci: tag %d task descriptor 0x016%llx\n",
+		 mmc_hostname(mrq->host), mrq->tag, (unsigned long long)*data);
+}
+
+static int cqhci_dma_map(struct mmc_host *host, struct mmc_request *mrq)
+{
+	int sg_count;
+	struct mmc_data *data = mrq->data;
+
+	if (!data)
+		return -EINVAL;
+
+	sg_count = dma_map_sg(mmc_dev(host), data->sg,
+			      data->sg_len,
+			      (data->flags & MMC_DATA_WRITE) ?
+			      DMA_TO_DEVICE : DMA_FROM_DEVICE);
+	if (!sg_count) {
+		pr_err("%s: sg-len: %d\n", __func__, data->sg_len);
+		return -ENOMEM;
+	}
+
+	return sg_count;
+}
+
+static void cqhci_set_tran_desc(u8 *desc, dma_addr_t addr, int len, bool end,
+				bool dma64)
+{
+	__le32 *attr = (__le32 __force *)desc;
+
+	*attr = (CQHCI_VALID(1) |
+		 CQHCI_END(end ? 1 : 0) |
+		 CQHCI_INT(0) |
+		 CQHCI_ACT(0x4) |
+		 CQHCI_DAT_LENGTH(len));
+
+	if (dma64) {
+		__le64 *dataddr = (__le64 __force *)(desc + 4);
+
+		dataddr[0] = cpu_to_le64(addr);
+	} else {
+		__le32 *dataddr = (__le32 __force *)(desc + 4);
+
+		dataddr[0] = cpu_to_le32(addr);
+	}
+}
+
+static int cqhci_prep_tran_desc(struct mmc_request *mrq,
+			       struct cqhci_host *cq_host, int tag)
+{
+	struct mmc_data *data = mrq->data;
+	int i, sg_count, len;
+	bool end = false;
+	bool dma64 = cq_host->dma64;
+	dma_addr_t addr;
+	u8 *desc;
+	struct scatterlist *sg;
+
+	sg_count = cqhci_dma_map(mrq->host, mrq);
+	if (sg_count < 0) {
+		pr_err("%s: %s: unable to map sg lists, %d\n",
+				mmc_hostname(mrq->host), __func__, sg_count);
+		return sg_count;
+	}
+
+	desc = get_trans_desc(cq_host, tag);
+
+	for_each_sg(data->sg, sg, sg_count, i) {
+		addr = sg_dma_address(sg);
+		len = sg_dma_len(sg);
+
+		if ((i+1) == sg_count)
+			end = true;
+		cqhci_set_tran_desc(desc, addr, len, end, dma64);
+		desc += cq_host->trans_desc_len;
+	}
+
+	return 0;
+}
+
+static void cqhci_prep_dcmd_desc(struct mmc_host *mmc,
+				   struct mmc_request *mrq)
+{
+	u64 *task_desc = NULL;
+	u64 data = 0;
+	u8 resp_type;
+	u8 *desc;
+	__le64 *dataddr;
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	u8 timing;
+
+	if (!(mrq->cmd->flags & MMC_RSP_PRESENT)) {
+		resp_type = 0x0;
+		timing = 0x1;
+	} else {
+		if (mrq->cmd->flags & MMC_RSP_R1B) {
+			resp_type = 0x3;
+			timing = 0x0;
+		} else {
+			resp_type = 0x2;
+			timing = 0x1;
+		}
+	}
+
+	task_desc = (__le64 __force *)get_desc(cq_host, cq_host->dcmd_slot);
+	memset(task_desc, 0, cq_host->task_desc_len);
+	data |= (CQHCI_VALID(1) |
+		 CQHCI_END(1) |
+		 CQHCI_INT(1) |
+		 CQHCI_QBAR(1) |
+		 CQHCI_ACT(0x5) |
+		 CQHCI_CMD_INDEX(mrq->cmd->opcode) |
+		 CQHCI_CMD_TIMING(timing) | CQHCI_RESP_TYPE(resp_type));
+	*task_desc |= data;
+	desc = (u8 *)task_desc;
+	pr_debug("%s: cqhci: dcmd: cmd: %d timing: %d resp: %d\n",
+		 mmc_hostname(mmc), mrq->cmd->opcode, timing, resp_type);
+	dataddr = (__le64 __force *)(desc + 4);
+	dataddr[0] = cpu_to_le64((u64)mrq->cmd->arg);
+
+}
+
+static void cqhci_post_req(struct mmc_host *host, struct mmc_request *mrq)
+{
+	struct mmc_data *data = mrq->data;
+
+	if (data) {
+		dma_unmap_sg(mmc_dev(host), data->sg, data->sg_len,
+			     (data->flags & MMC_DATA_READ) ?
+			     DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	}
+}
+
+static inline int cqhci_tag(struct mmc_request *mrq)
+{
+	return mrq->cmd ? DCMD_SLOT : mrq->tag;
+}
+
+static int cqhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	int err = 0;
+	u64 data = 0;
+	u64 *task_desc = NULL;
+	int tag = cqhci_tag(mrq);
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	unsigned long flags;
+
+	if (!cq_host->enabled) {
+		pr_err("%s: cqhci: not enabled\n", mmc_hostname(mmc));
+		return -EINVAL;
+	}
+
+	/* First request after resume has to re-enable */
+	if (!cq_host->activated)
+		__cqhci_enable(cq_host);
+
+	if (!mmc->cqe_on) {
+		cqhci_writel(cq_host, 0, CQHCI_CTL);
+		mmc->cqe_on = true;
+		pr_debug("%s: cqhci: CQE on\n", mmc_hostname(mmc));
+		if (cqhci_readl(cq_host, CQHCI_CTL) && CQHCI_HALT) {
+			pr_err("%s: cqhci: CQE failed to exit halt state\n",
+			       mmc_hostname(mmc));
+		}
+		if (cq_host->ops->enable)
+			cq_host->ops->enable(mmc);
+	}
+
+	if (mrq->data) {
+		task_desc = (__le64 __force *)get_desc(cq_host, tag);
+		cqhci_prep_task_desc(mrq, &data, 1);
+		*task_desc = cpu_to_le64(data);
+		err = cqhci_prep_tran_desc(mrq, cq_host, tag);
+		if (err) {
+			pr_err("%s: cqhci: failed to setup tx desc: %d\n",
+			       mmc_hostname(mmc), err);
+			return err;
+		}
+	} else {
+		cqhci_prep_dcmd_desc(mmc, mrq);
+	}
+
+	spin_lock_irqsave(&cq_host->lock, flags);
+
+	if (cq_host->recovery_halt) {
+		err = -EBUSY;
+		goto out_unlock;
+	}
+
+	cq_host->slot[tag].mrq = mrq;
+	cq_host->slot[tag].flags = 0;
+
+	cq_host->qcnt += 1;
+
+	cqhci_writel(cq_host, 1 << tag, CQHCI_TDBR);
+	if (!(cqhci_readl(cq_host, CQHCI_TDBR) & (1 << tag)))
+		pr_debug("%s: cqhci: doorbell not set for tag %d\n",
+			 mmc_hostname(mmc), tag);
+out_unlock:
+	spin_unlock_irqrestore(&cq_host->lock, flags);
+
+	if (err)
+		cqhci_post_req(mmc, mrq);
+
+	return err;
+}
+
+static void cqhci_recovery_needed(struct mmc_host *mmc, struct mmc_request *mrq,
+				  bool notify)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+
+	if (!cq_host->recovery_halt) {
+		cq_host->recovery_halt = true;
+		pr_debug("%s: cqhci: recovery needed\n", mmc_hostname(mmc));
+		wake_up(&cq_host->wait_queue);
+		if (notify && mrq->recovery_notifier)
+			mrq->recovery_notifier(mrq);
+	}
+}
+
+static unsigned int cqhci_error_flags(int error1, int error2)
+{
+	int error = error1 ? error1 : error2;
+
+	switch (error) {
+	case -EILSEQ:
+		return CQHCI_HOST_CRC;
+	case -ETIMEDOUT:
+		return CQHCI_HOST_TIMEOUT;
+	default:
+		return CQHCI_HOST_OTHER;
+	}
+}
+
+static void cqhci_error_irq(struct mmc_host *mmc, u32 status, int cmd_error,
+			    int data_error)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	struct cqhci_slot *slot;
+	u32 terri;
+	int tag;
+
+	spin_lock(&cq_host->lock);
+
+	terri = cqhci_readl(cq_host, CQHCI_TERRI);
+
+	pr_debug("%s: cqhci: error IRQ status: 0x%08x cmd error %d data error %d TERRI: 0x%08x\n",
+		 mmc_hostname(mmc), status, cmd_error, data_error, terri);
+
+	/* Forget about errors when recovery has already been triggered */
+	if (cq_host->recovery_halt)
+		goto out_unlock;
+
+	if (!cq_host->qcnt) {
+		WARN_ONCE(1, "%s: cqhci: error when idle. IRQ status: 0x%08x cmd error %d data error %d TERRI: 0x%08x\n",
+			  mmc_hostname(mmc), status, cmd_error, data_error,
+			  terri);
+		goto out_unlock;
+	}
+
+	if (CQHCI_TERRI_C_VALID(terri)) {
+		tag = CQHCI_TERRI_C_TASK(terri);
+		slot = &cq_host->slot[tag];
+		if (slot->mrq) {
+			slot->flags = cqhci_error_flags(cmd_error, data_error);
+			cqhci_recovery_needed(mmc, slot->mrq, true);
+		}
+	}
+
+	if (CQHCI_TERRI_D_VALID(terri)) {
+		tag = CQHCI_TERRI_D_TASK(terri);
+		slot = &cq_host->slot[tag];
+		if (slot->mrq) {
+			slot->flags = cqhci_error_flags(data_error, cmd_error);
+			cqhci_recovery_needed(mmc, slot->mrq, true);
+		}
+	}
+
+	if (!cq_host->recovery_halt) {
+		/*
+		 * The only way to guarantee forward progress is to mark at
+		 * least one task in error, so if none is indicated, pick one.
+		 */
+		for (tag = 0; tag < NUM_SLOTS; tag++) {
+			slot = &cq_host->slot[tag];
+			if (!slot->mrq)
+				continue;
+			slot->flags = cqhci_error_flags(data_error, cmd_error);
+			cqhci_recovery_needed(mmc, slot->mrq, true);
+			break;
+		}
+	}
+
+out_unlock:
+	spin_unlock(&cq_host->lock);
+}
+
+static void cqhci_finish_mrq(struct mmc_host *mmc, unsigned int tag)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	struct cqhci_slot *slot = &cq_host->slot[tag];
+	struct mmc_request *mrq = slot->mrq;
+	struct mmc_data *data;
+
+	if (!mrq) {
+		WARN_ONCE(1, "%s: cqhci: spurious TCN for tag %d\n",
+			  mmc_hostname(mmc), tag);
+		return;
+	}
+
+	/* No completions allowed during recovery */
+	if (cq_host->recovery_halt) {
+		slot->flags |= CQHCI_COMPLETED;
+		return;
+	}
+
+	slot->mrq = NULL;
+
+	cq_host->qcnt -= 1;
+
+	data = mrq->data;
+	if (data) {
+		if (data->error)
+			data->bytes_xfered = 0;
+		else
+			data->bytes_xfered = data->blksz * data->blocks;
+	}
+
+	mmc_cqe_request_done(mmc, mrq);
+}
+
+irqreturn_t cqhci_irq(struct mmc_host *mmc, u32 intmask, int cmd_error,
+		      int data_error)
+{
+	u32 status;
+	unsigned long tag = 0, comp_status;
+	struct cqhci_host *cq_host = mmc->cqe_private;
+
+	status = cqhci_readl(cq_host, CQHCI_IS);
+	cqhci_writel(cq_host, status, CQHCI_IS);
+
+	pr_debug("%s: cqhci: IRQ status: 0x%08x\n", mmc_hostname(mmc), status);
+
+	if ((status & CQHCI_IS_RED) || cmd_error || data_error)
+		cqhci_error_irq(mmc, status, cmd_error, data_error);
+
+	if (status & CQHCI_IS_TCC) {
+		/* read TCN and complete the request */
+		comp_status = cqhci_readl(cq_host, CQHCI_TCN);
+		cqhci_writel(cq_host, comp_status, CQHCI_TCN);
+		pr_debug("%s: cqhci: TCN: 0x%08lx\n",
+			 mmc_hostname(mmc), comp_status);
+
+		spin_lock(&cq_host->lock);
+
+		for_each_set_bit(tag, &comp_status, cq_host->num_slots) {
+			/* complete the corresponding mrq */
+			pr_debug("%s: cqhci: completing tag %lu\n",
+				 mmc_hostname(mmc), tag);
+			cqhci_finish_mrq(mmc, tag);
+		}
+
+		if (cq_host->waiting_for_idle && !cq_host->qcnt) {
+			cq_host->waiting_for_idle = false;
+			wake_up(&cq_host->wait_queue);
+		}
+
+		spin_unlock(&cq_host->lock);
+	}
+
+	if (status & CQHCI_IS_TCL)
+		wake_up(&cq_host->wait_queue);
+
+	if (status & CQHCI_IS_HAC)
+		wake_up(&cq_host->wait_queue);
+
+	return IRQ_HANDLED;
+}
+EXPORT_SYMBOL(cqhci_irq);
+
+static bool cqhci_is_idle(struct cqhci_host *cq_host, int *ret)
+{
+	unsigned long flags;
+	bool is_idle;
+
+	spin_lock_irqsave(&cq_host->lock, flags);
+	is_idle = !cq_host->qcnt || cq_host->recovery_halt;
+	*ret = cq_host->recovery_halt ? -EBUSY : 0;
+	cq_host->waiting_for_idle = !is_idle;
+	spin_unlock_irqrestore(&cq_host->lock, flags);
+
+	return is_idle;
+}
+
+static int cqhci_wait_for_idle(struct mmc_host *mmc)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	int ret;
+
+	wait_event(cq_host->wait_queue, cqhci_is_idle(cq_host, &ret));
+
+	return ret;
+}
+
+static bool cqhci_timeout(struct mmc_host *mmc, struct mmc_request *mrq,
+			  bool *recovery_needed)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	int tag = cqhci_tag(mrq);
+	struct cqhci_slot *slot = &cq_host->slot[tag];
+	unsigned long flags;
+	bool timed_out;
+
+	spin_lock_irqsave(&cq_host->lock, flags);
+	timed_out = slot->mrq == mrq;
+	if (timed_out) {
+		slot->flags |= CQHCI_EXTERNAL_TIMEOUT;
+		cqhci_recovery_needed(mmc, mrq, false);
+		*recovery_needed = cq_host->recovery_halt;
+	}
+	spin_unlock_irqrestore(&cq_host->lock, flags);
+
+	if (timed_out) {
+		pr_err("%s: cqhci: timeout for tag %d\n",
+		       mmc_hostname(mmc), tag);
+		cqhci_dumpregs(cq_host);
+	}
+
+	return timed_out;
+}
+
+static bool cqhci_tasks_cleared(struct cqhci_host *cq_host)
+{
+	return !(cqhci_readl(cq_host, CQHCI_CTL) & CQHCI_CLEAR_ALL_TASKS);
+}
+
+static bool cqhci_clear_all_tasks(struct mmc_host *mmc, unsigned int timeout)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	bool ret;
+	u32 ctl;
+
+	cqhci_set_irqs(cq_host, CQHCI_IS_TCL);
+
+	ctl = cqhci_readl(cq_host, CQHCI_CTL);
+	ctl |= CQHCI_CLEAR_ALL_TASKS;
+	cqhci_writel(cq_host, ctl, CQHCI_CTL);
+
+	wait_event_timeout(cq_host->wait_queue, cqhci_tasks_cleared(cq_host),
+			   msecs_to_jiffies(timeout) + 1);
+
+	cqhci_set_irqs(cq_host, 0);
+
+	ret = cqhci_tasks_cleared(cq_host);
+
+	if (!ret)
+		pr_debug("%s: cqhci: Failed to clear tasks\n",
+			 mmc_hostname(mmc));
+
+	return ret;
+}
+
+static bool cqhci_halted(struct cqhci_host *cq_host)
+{
+	return cqhci_readl(cq_host, CQHCI_CTL) & CQHCI_HALT;
+}
+
+static bool cqhci_halt(struct mmc_host *mmc, unsigned int timeout)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	bool ret;
+	u32 ctl;
+
+	if (cqhci_halted(cq_host))
+		return true;
+
+	cqhci_set_irqs(cq_host, CQHCI_IS_HAC);
+
+	ctl = cqhci_readl(cq_host, CQHCI_CTL);
+	ctl |= CQHCI_HALT;
+	cqhci_writel(cq_host, ctl, CQHCI_CTL);
+
+	wait_event_timeout(cq_host->wait_queue, cqhci_halted(cq_host),
+			   msecs_to_jiffies(timeout) + 1);
+
+	cqhci_set_irqs(cq_host, 0);
+
+	ret = cqhci_halted(cq_host);
+
+	if (!ret)
+		pr_debug("%s: cqhci: Failed to halt\n", mmc_hostname(mmc));
+
+	return ret;
+}
+
+/*
+ * After halting we expect to be able to use the command line. We interpret the
+ * failure to halt to mean the data lines might still be in use (and the upper
+ * layers will need to send a STOP command), so we set the timeout based on a
+ * generous command timeout.
+ */
+#define CQHCI_START_HALT_TIMEOUT	5
+
+static void cqhci_recovery_start(struct mmc_host *mmc)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+
+	pr_debug("%s: cqhci: %s\n", mmc_hostname(mmc), __func__);
+
+	WARN_ON(!cq_host->recovery_halt);
+
+	cqhci_halt(mmc, CQHCI_START_HALT_TIMEOUT);
+
+	if (cq_host->ops->disable)
+		cq_host->ops->disable(mmc, true);
+
+	mmc->cqe_on = false;
+}
+
+static int cqhci_error_from_flags(unsigned int flags)
+{
+	if (!flags)
+		return 0;
+
+	/* CRC errors might indicate re-tuning so prefer to report that */
+	if (flags & CQHCI_HOST_CRC)
+		return -EILSEQ;
+
+	if (flags & (CQHCI_EXTERNAL_TIMEOUT | CQHCI_HOST_TIMEOUT))
+		return -ETIMEDOUT;
+
+	return -EIO;
+}
+
+static void cqhci_recover_mrq(struct cqhci_host *cq_host, unsigned int tag)
+{
+	struct cqhci_slot *slot = &cq_host->slot[tag];
+	struct mmc_request *mrq = slot->mrq;
+	struct mmc_data *data;
+
+	if (!mrq)
+		return;
+
+	slot->mrq = NULL;
+
+	cq_host->qcnt -= 1;
+
+	data = mrq->data;
+	if (data) {
+		data->bytes_xfered = 0;
+		data->error = cqhci_error_from_flags(slot->flags);
+	} else {
+		mrq->cmd->error = cqhci_error_from_flags(slot->flags);
+	}
+
+	mmc_cqe_request_done(cq_host->mmc, mrq);
+}
+
+static void cqhci_recover_mrqs(struct cqhci_host *cq_host)
+{
+	int i;
+
+	for (i = 0; i < cq_host->num_slots; i++)
+		cqhci_recover_mrq(cq_host, i);
+}
+
+/*
+ * By now the command and data lines should be unused so there is no reason for
+ * CQHCI to take a long time to halt, but if it doesn't halt there could be
+ * problems clearing tasks, so be generous.
+ */
+#define CQHCI_FINISH_HALT_TIMEOUT	20
+
+/* CQHCI could be expected to clear it's internal state pretty quickly */
+#define CQHCI_CLEAR_TIMEOUT		20
+
+static void cqhci_recovery_finish(struct mmc_host *mmc)
+{
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	unsigned long flags;
+	u32 cqcfg;
+	bool ok;
+
+	pr_debug("%s: cqhci: %s\n", mmc_hostname(mmc), __func__);
+
+	WARN_ON(!cq_host->recovery_halt);
+
+	ok = cqhci_halt(mmc, CQHCI_FINISH_HALT_TIMEOUT);
+
+	if (!cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT))
+		ok = false;
+
+	/*
+	 * The specification contradicts itself, by saying that tasks cannot be
+	 * cleared if CQHCI does not halt, but if CQHCI does not halt, it should
+	 * be disabled/re-enabled, but not to disable before clearing tasks.
+	 * Have a go anyway.
+	 */
+	if (!ok) {
+		pr_debug("%s: cqhci: disable / re-enable\n", mmc_hostname(mmc));
+		cqcfg = cqhci_readl(cq_host, CQHCI_CFG);
+		cqcfg &= ~CQHCI_ENABLE;
+		cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+		cqcfg |= CQHCI_ENABLE;
+		cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+		/* Be sure that there are no tasks */
+		ok = cqhci_halt(mmc, CQHCI_FINISH_HALT_TIMEOUT);
+		if (!cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT))
+			ok = false;
+		WARN_ON(!ok);
+	}
+
+	cqhci_recover_mrqs(cq_host);
+
+	WARN_ON(cq_host->qcnt);
+
+	spin_lock_irqsave(&cq_host->lock, flags);
+	cq_host->qcnt = 0;
+	cq_host->recovery_halt = false;
+	mmc->cqe_on = false;
+	spin_unlock_irqrestore(&cq_host->lock, flags);
+
+	/* Ensure all writes are done before interrupts are re-enabled */
+	wmb();
+
+	cqhci_writel(cq_host, CQHCI_IS_HAC | CQHCI_IS_TCL, CQHCI_IS);
+
+	cqhci_set_irqs(cq_host, CQHCI_IS_MASK);
+
+	pr_debug("%s: cqhci: recovery done\n", mmc_hostname(mmc));
+}
+
+static const struct mmc_cqe_ops cqhci_cqe_ops = {
+	.cqe_enable = cqhci_enable,
+	.cqe_disable = cqhci_disable,
+	.cqe_request = cqhci_request,
+	.cqe_post_req = cqhci_post_req,
+	.cqe_off = cqhci_off,
+	.cqe_wait_for_idle = cqhci_wait_for_idle,
+	.cqe_timeout = cqhci_timeout,
+	.cqe_recovery_start = cqhci_recovery_start,
+	.cqe_recovery_finish = cqhci_recovery_finish,
+};
+
+struct cqhci_host *cqhci_pltfm_init(struct platform_device *pdev)
+{
+	struct cqhci_host *cq_host;
+	struct resource *cqhci_memres = NULL;
+
+	/* check and setup CMDQ interface */
+	cqhci_memres = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						   "cqhci_mem");
+	if (!cqhci_memres) {
+		dev_dbg(&pdev->dev, "CMDQ not supported\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	cq_host = devm_kzalloc(&pdev->dev, sizeof(*cq_host), GFP_KERNEL);
+	if (!cq_host)
+		return ERR_PTR(-ENOMEM);
+	cq_host->mmio = devm_ioremap(&pdev->dev,
+				     cqhci_memres->start,
+				     resource_size(cqhci_memres));
+	if (!cq_host->mmio) {
+		dev_err(&pdev->dev, "failed to remap cqhci regs\n");
+		return ERR_PTR(-EBUSY);
+	}
+	dev_dbg(&pdev->dev, "CMDQ ioremap: done\n");
+
+	return cq_host;
+}
+EXPORT_SYMBOL(cqhci_pltfm_init);
+
+static unsigned int cqhci_ver_major(struct cqhci_host *cq_host)
+{
+	return CQHCI_VER_MAJOR(cqhci_readl(cq_host, CQHCI_VER));
+}
+
+static unsigned int cqhci_ver_minor(struct cqhci_host *cq_host)
+{
+	u32 ver = cqhci_readl(cq_host, CQHCI_VER);
+
+	return CQHCI_VER_MINOR1(ver) * 10 + CQHCI_VER_MINOR2(ver);
+}
+
+int cqhci_init(struct cqhci_host *cq_host, struct mmc_host *mmc,
+	      bool dma64)
+{
+	int err;
+
+	cq_host->dma64 = dma64;
+	cq_host->mmc = mmc;
+	cq_host->mmc->cqe_private = cq_host;
+
+	cq_host->num_slots = NUM_SLOTS;
+	cq_host->dcmd_slot = DCMD_SLOT;
+
+	mmc->cqe_ops = &cqhci_cqe_ops;
+
+	mmc->cqe_qdepth = NUM_SLOTS;
+	if (mmc->caps2 & MMC_CAP2_CQE_DCMD)
+		mmc->cqe_qdepth -= 1;
+
+	cq_host->slot = devm_kcalloc(mmc_dev(mmc), cq_host->num_slots,
+				     sizeof(*cq_host->slot), GFP_KERNEL);
+	if (!cq_host->slot) {
+		err = -ENOMEM;
+		goto out_err;
+	}
+
+	spin_lock_init(&cq_host->lock);
+
+	init_completion(&cq_host->halt_comp);
+	init_waitqueue_head(&cq_host->wait_queue);
+
+	pr_info("%s: CQHCI version %u.%02u\n",
+		mmc_hostname(mmc), cqhci_ver_major(cq_host),
+		cqhci_ver_minor(cq_host));
+
+	return 0;
+
+out_err:
+	pr_err("%s: CQHCI version %u.%02u failed to initialize, error %d\n",
+	       mmc_hostname(mmc), cqhci_ver_major(cq_host),
+	       cqhci_ver_minor(cq_host), err);
+	return err;
+}
+EXPORT_SYMBOL(cqhci_init);
+
+MODULE_AUTHOR("Venkat Gopalakrishnan <venkatg@codeaurora.org>");
+MODULE_DESCRIPTION("Command Queue Host Controller Interface driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/cqhci.h b/drivers/mmc/host/cqhci.h
new file mode 100644
index 000000000000..9e68286a07b4
--- /dev/null
+++ b/drivers/mmc/host/cqhci.h
@@ -0,0 +1,240 @@
+/* Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef LINUX_MMC_CQHCI_H
+#define LINUX_MMC_CQHCI_H
+
+#include <linux/compiler.h>
+#include <linux/bitops.h>
+#include <linux/spinlock_types.h>
+#include <linux/types.h>
+#include <linux/completion.h>
+#include <linux/wait.h>
+#include <linux/irqreturn.h>
+#include <asm/io.h>
+
+/* registers */
+/* version */
+#define CQHCI_VER			0x00
+#define CQHCI_VER_MAJOR(x)		(((x) & GENMASK(11, 8)) >> 8)
+#define CQHCI_VER_MINOR1(x)		(((x) & GENMASK(7, 4)) >> 4)
+#define CQHCI_VER_MINOR2(x)		((x) & GENMASK(3, 0))
+
+/* capabilities */
+#define CQHCI_CAP			0x04
+/* configuration */
+#define CQHCI_CFG			0x08
+#define CQHCI_DCMD			0x00001000
+#define CQHCI_TASK_DESC_SZ		0x00000100
+#define CQHCI_ENABLE			0x00000001
+
+/* control */
+#define CQHCI_CTL			0x0C
+#define CQHCI_CLEAR_ALL_TASKS		0x00000100
+#define CQHCI_HALT			0x00000001
+
+/* interrupt status */
+#define CQHCI_IS			0x10
+#define CQHCI_IS_HAC			BIT(0)
+#define CQHCI_IS_TCC			BIT(1)
+#define CQHCI_IS_RED			BIT(2)
+#define CQHCI_IS_TCL			BIT(3)
+
+#define CQHCI_IS_MASK (CQHCI_IS_TCC | CQHCI_IS_RED)
+
+/* interrupt status enable */
+#define CQHCI_ISTE			0x14
+
+/* interrupt signal enable */
+#define CQHCI_ISGE			0x18
+
+/* interrupt coalescing */
+#define CQHCI_IC			0x1C
+#define CQHCI_IC_ENABLE			BIT(31)
+#define CQHCI_IC_RESET			BIT(16)
+#define CQHCI_IC_ICCTHWEN		BIT(15)
+#define CQHCI_IC_ICCTH(x)		(((x) & 0x1F) << 8)
+#define CQHCI_IC_ICTOVALWEN		BIT(7)
+#define CQHCI_IC_ICTOVAL(x)		((x) & 0x7F)
+
+/* task list base address */
+#define CQHCI_TDLBA			0x20
+
+/* task list base address upper */
+#define CQHCI_TDLBAU			0x24
+
+/* door-bell */
+#define CQHCI_TDBR			0x28
+
+/* task completion notification */
+#define CQHCI_TCN			0x2C
+
+/* device queue status */
+#define CQHCI_DQS			0x30
+
+/* device pending tasks */
+#define CQHCI_DPT			0x34
+
+/* task clear */
+#define CQHCI_TCLR			0x38
+
+/* send status config 1 */
+#define CQHCI_SSC1			0x40
+
+/* send status config 2 */
+#define CQHCI_SSC2			0x44
+
+/* response for dcmd */
+#define CQHCI_CRDCT			0x48
+
+/* response mode error mask */
+#define CQHCI_RMEM			0x50
+
+/* task error info */
+#define CQHCI_TERRI			0x54
+
+#define CQHCI_TERRI_C_INDEX(x)		((x) & GENMASK(5, 0))
+#define CQHCI_TERRI_C_TASK(x)		(((x) & GENMASK(12, 8)) >> 8)
+#define CQHCI_TERRI_C_VALID(x)		((x) & BIT(15))
+#define CQHCI_TERRI_D_INDEX(x)		(((x) & GENMASK(21, 16)) >> 16)
+#define CQHCI_TERRI_D_TASK(x)		(((x) & GENMASK(28, 24)) >> 24)
+#define CQHCI_TERRI_D_VALID(x)		((x) & BIT(31))
+
+/* command response index */
+#define CQHCI_CRI			0x58
+
+/* command response argument */
+#define CQHCI_CRA			0x5C
+
+#define CQHCI_INT_ALL			0xF
+#define CQHCI_IC_DEFAULT_ICCTH		31
+#define CQHCI_IC_DEFAULT_ICTOVAL	1
+
+/* attribute fields */
+#define CQHCI_VALID(x)			(((x) & 1) << 0)
+#define CQHCI_END(x)			(((x) & 1) << 1)
+#define CQHCI_INT(x)			(((x) & 1) << 2)
+#define CQHCI_ACT(x)			(((x) & 0x7) << 3)
+
+/* data command task descriptor fields */
+#define CQHCI_FORCED_PROG(x)		(((x) & 1) << 6)
+#define CQHCI_CONTEXT(x)		(((x) & 0xF) << 7)
+#define CQHCI_DATA_TAG(x)		(((x) & 1) << 11)
+#define CQHCI_DATA_DIR(x)		(((x) & 1) << 12)
+#define CQHCI_PRIORITY(x)		(((x) & 1) << 13)
+#define CQHCI_QBAR(x)			(((x) & 1) << 14)
+#define CQHCI_REL_WRITE(x)		(((x) & 1) << 15)
+#define CQHCI_BLK_COUNT(x)		(((x) & 0xFFFF) << 16)
+#define CQHCI_BLK_ADDR(x)		(((x) & 0xFFFFFFFF) << 32)
+
+/* direct command task descriptor fields */
+#define CQHCI_CMD_INDEX(x)		(((x) & 0x3F) << 16)
+#define CQHCI_CMD_TIMING(x)		(((x) & 1) << 22)
+#define CQHCI_RESP_TYPE(x)		(((x) & 0x3) << 23)
+
+/* transfer descriptor fields */
+#define CQHCI_DAT_LENGTH(x)		(((x) & 0xFFFF) << 16)
+#define CQHCI_DAT_ADDR_LO(x)		(((x) & 0xFFFFFFFF) << 32)
+#define CQHCI_DAT_ADDR_HI(x)		(((x) & 0xFFFFFFFF) << 0)
+
+struct cqhci_host_ops;
+struct mmc_host;
+struct cqhci_slot;
+
+struct cqhci_host {
+	const struct cqhci_host_ops *ops;
+	void __iomem *mmio;
+	struct mmc_host *mmc;
+
+	spinlock_t lock;
+
+	/* relative card address of device */
+	unsigned int rca;
+
+	/* 64 bit DMA */
+	bool dma64;
+	int num_slots;
+	int qcnt;
+
+	u32 dcmd_slot;
+	u32 caps;
+#define CQHCI_TASK_DESC_SZ_128		0x1
+
+	u32 quirks;
+#define CQHCI_QUIRK_SHORT_TXFR_DESC_SZ	0x1
+
+	bool enabled;
+	bool halted;
+	bool init_done;
+	bool activated;
+	bool waiting_for_idle;
+	bool recovery_halt;
+
+	size_t desc_size;
+	size_t data_size;
+
+	u8 *desc_base;
+
+	/* total descriptor size */
+	u8 slot_sz;
+
+	/* 64/128 bit depends on CQHCI_CFG */
+	u8 task_desc_len;
+
+	/* 64 bit on 32-bit arch, 128 bit on 64-bit */
+	u8 link_desc_len;
+
+	u8 *trans_desc_base;
+	/* same length as transfer descriptor */
+	u8 trans_desc_len;
+
+	dma_addr_t desc_dma_base;
+	dma_addr_t trans_desc_dma_base;
+
+	struct completion halt_comp;
+	wait_queue_head_t wait_queue;
+	struct cqhci_slot *slot;
+};
+
+struct cqhci_host_ops {
+	void (*dumpregs)(struct mmc_host *mmc);
+	void (*write_l)(struct cqhci_host *host, u32 val, int reg);
+	u32 (*read_l)(struct cqhci_host *host, int reg);
+	void (*enable)(struct mmc_host *mmc);
+	void (*disable)(struct mmc_host *mmc, bool recovery);
+};
+
+static inline void cqhci_writel(struct cqhci_host *host, u32 val, int reg)
+{
+	if (unlikely(host->ops->write_l))
+		host->ops->write_l(host, val, reg);
+	else
+		writel_relaxed(val, host->mmio + reg);
+}
+
+static inline u32 cqhci_readl(struct cqhci_host *host, int reg)
+{
+	if (unlikely(host->ops->read_l))
+		return host->ops->read_l(host, reg);
+	else
+		return readl_relaxed(host->mmio + reg);
+}
+
+struct platform_device;
+
+irqreturn_t cqhci_irq(struct mmc_host *mmc, u32 intmask, int cmd_error,
+		      int data_error);
+int cqhci_init(struct cqhci_host *cq_host, struct mmc_host *mmc, bool dma64);
+struct cqhci_host *cqhci_pltfm_init(struct platform_device *pdev);
+int cqhci_suspend(struct mmc_host *mmc);
+int cqhci_resume(struct mmc_host *mmc);
+
+#endif
diff --git a/drivers/mmc/host/davinci_mmc.c b/drivers/mmc/host/davinci_mmc.c
index 351330dfb954..8e363174f9d6 100644
--- a/drivers/mmc/host/davinci_mmc.c
+++ b/drivers/mmc/host/davinci_mmc.c
@@ -174,7 +174,7 @@ module_param(poll_loopcount, uint, S_IRUGO);
 MODULE_PARM_DESC(poll_loopcount,
 		 "Maximum polling loop count. Default = 32");
 
-static unsigned __initdata use_dma = 1;
+static unsigned use_dma = 1;
 module_param(use_dma, uint, 0);
 MODULE_PARM_DESC(use_dma, "Whether to use DMA or not. Default = 1");
 
@@ -496,8 +496,7 @@ static int mmc_davinci_start_dma_transfer(struct mmc_davinci_host *host,
 	return ret;
 }
 
-static void __init_or_module
-davinci_release_dma_channels(struct mmc_davinci_host *host)
+static void davinci_release_dma_channels(struct mmc_davinci_host *host)
 {
 	if (!host->use_dma)
 		return;
@@ -506,7 +505,7 @@ davinci_release_dma_channels(struct mmc_davinci_host *host)
 	dma_release_channel(host->dma_rx);
 }
 
-static int __init davinci_acquire_dma_channels(struct mmc_davinci_host *host)
+static int davinci_acquire_dma_channels(struct mmc_davinci_host *host)
 {
 	host->dma_tx = dma_request_chan(mmc_dev(host->mmc), "tx");
 	if (IS_ERR(host->dma_tx)) {
@@ -1201,7 +1200,7 @@ static int mmc_davinci_parse_pdata(struct mmc_host *mmc)
 	return 0;
 }
 
-static int __init davinci_mmcsd_probe(struct platform_device *pdev)
+static int davinci_mmcsd_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *match;
 	struct mmc_davinci_host *host = NULL;
@@ -1254,8 +1253,9 @@ static int __init davinci_mmcsd_probe(struct platform_device *pdev)
 		pdev->id_entry = match->data;
 		ret = mmc_of_parse(mmc);
 		if (ret) {
-			dev_err(&pdev->dev,
-				"could not parse of data: %d\n", ret);
+			if (ret != -EPROBE_DEFER)
+				dev_err(&pdev->dev,
+					"could not parse of data: %d\n", ret);
 			goto parse_fail;
 		}
 	} else {
@@ -1414,11 +1414,12 @@ static struct platform_driver davinci_mmcsd_driver = {
 		.pm	= davinci_mmcsd_pm_ops,
 		.of_match_table = davinci_mmc_dt_ids,
 	},
+	.probe		= davinci_mmcsd_probe,
 	.remove		= __exit_p(davinci_mmcsd_remove),
 	.id_table	= davinci_mmc_devtype,
 };
 
-module_platform_driver_probe(davinci_mmcsd_driver, davinci_mmcsd_probe);
+module_platform_driver(davinci_mmcsd_driver);
 
 MODULE_AUTHOR("Texas Instruments India");
 MODULE_LICENSE("GPL");
diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c
index e0862d3f65b3..32a6a228cd12 100644
--- a/drivers/mmc/host/meson-gx-mmc.c
+++ b/drivers/mmc/host/meson-gx-mmc.c
@@ -1208,7 +1208,7 @@ static int meson_mmc_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (!irq) {
+	if (irq <= 0) {
 		dev_err(&pdev->dev, "failed to get interrupt resource.\n");
 		ret = -EINVAL;
 		goto free_host;
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index e8a1bb1ae694..70b0df8b9c78 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -82,6 +82,10 @@ static unsigned int fmax = 515633;
  * @qcom_fifo: enables qcom specific fifo pio read logic.
  * @qcom_dml: enables qcom specific dma glue for dma transfers.
  * @reversed_irq_handling: handle data irq before cmd irq.
+ * @mmcimask1: true if variant have a MMCIMASK1 register.
+ * @start_err: bitmask identifying the STARTBITERR bit inside MMCISTATUS
+ *	       register.
+ * @opendrain: bitmask identifying the OPENDRAIN bit inside MMCIPOWER register
  */
 struct variant_data {
 	unsigned int		clkreg;
@@ -111,6 +115,9 @@ struct variant_data {
 	bool			qcom_fifo;
 	bool			qcom_dml;
 	bool			reversed_irq_handling;
+	bool			mmcimask1;
+	u32			start_err;
+	u32			opendrain;
 };
 
 static struct variant_data variant_arm = {
@@ -120,6 +127,9 @@ static struct variant_data variant_arm = {
 	.pwrreg_powerup		= MCI_PWR_UP,
 	.f_max			= 100000000,
 	.reversed_irq_handling	= true,
+	.mmcimask1		= true,
+	.start_err		= MCI_STARTBITERR,
+	.opendrain		= MCI_ROD,
 };
 
 static struct variant_data variant_arm_extended_fifo = {
@@ -128,6 +138,9 @@ static struct variant_data variant_arm_extended_fifo = {
 	.datalength_bits	= 16,
 	.pwrreg_powerup		= MCI_PWR_UP,
 	.f_max			= 100000000,
+	.mmcimask1		= true,
+	.start_err		= MCI_STARTBITERR,
+	.opendrain		= MCI_ROD,
 };
 
 static struct variant_data variant_arm_extended_fifo_hwfc = {
@@ -137,6 +150,9 @@ static struct variant_data variant_arm_extended_fifo_hwfc = {
 	.datalength_bits	= 16,
 	.pwrreg_powerup		= MCI_PWR_UP,
 	.f_max			= 100000000,
+	.mmcimask1		= true,
+	.start_err		= MCI_STARTBITERR,
+	.opendrain		= MCI_ROD,
 };
 
 static struct variant_data variant_u300 = {
@@ -152,6 +168,9 @@ static struct variant_data variant_u300 = {
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
 	.pwrreg_nopower		= true,
+	.mmcimask1		= true,
+	.start_err		= MCI_STARTBITERR,
+	.opendrain		= MCI_OD,
 };
 
 static struct variant_data variant_nomadik = {
@@ -168,6 +187,9 @@ static struct variant_data variant_nomadik = {
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
 	.pwrreg_nopower		= true,
+	.mmcimask1		= true,
+	.start_err		= MCI_STARTBITERR,
+	.opendrain		= MCI_OD,
 };
 
 static struct variant_data variant_ux500 = {
@@ -190,6 +212,9 @@ static struct variant_data variant_ux500 = {
 	.busy_detect_flag	= MCI_ST_CARDBUSY,
 	.busy_detect_mask	= MCI_ST_BUSYENDMASK,
 	.pwrreg_nopower		= true,
+	.mmcimask1		= true,
+	.start_err		= MCI_STARTBITERR,
+	.opendrain		= MCI_OD,
 };
 
 static struct variant_data variant_ux500v2 = {
@@ -214,6 +239,26 @@ static struct variant_data variant_ux500v2 = {
 	.busy_detect_flag	= MCI_ST_CARDBUSY,
 	.busy_detect_mask	= MCI_ST_BUSYENDMASK,
 	.pwrreg_nopower		= true,
+	.mmcimask1		= true,
+	.start_err		= MCI_STARTBITERR,
+	.opendrain		= MCI_OD,
+};
+
+static struct variant_data variant_stm32 = {
+	.fifosize		= 32 * 4,
+	.fifohalfsize		= 8 * 4,
+	.clkreg			= MCI_CLK_ENABLE,
+	.clkreg_enable		= MCI_ST_UX500_HWFCEN,
+	.clkreg_8bit_bus_enable = MCI_ST_8BIT_BUS,
+	.clkreg_neg_edge_enable	= MCI_ST_UX500_NEG_EDGE,
+	.datalength_bits	= 24,
+	.datactrl_mask_sdio	= MCI_DPSM_ST_SDIOEN,
+	.st_sdio		= true,
+	.st_clkdiv		= true,
+	.pwrreg_powerup		= MCI_PWR_ON,
+	.f_max			= 48000000,
+	.pwrreg_clkgate		= true,
+	.pwrreg_nopower		= true,
 };
 
 static struct variant_data variant_qcom = {
@@ -232,6 +277,9 @@ static struct variant_data variant_qcom = {
 	.explicit_mclk_control	= true,
 	.qcom_fifo		= true,
 	.qcom_dml		= true,
+	.mmcimask1		= true,
+	.start_err		= MCI_STARTBITERR,
+	.opendrain		= MCI_ROD,
 };
 
 /* Busy detection for the ST Micro variant */
@@ -396,6 +444,7 @@ mmci_request_end(struct mmci_host *host, struct mmc_request *mrq)
 static void mmci_set_mask1(struct mmci_host *host, unsigned int mask)
 {
 	void __iomem *base = host->base;
+	struct variant_data *variant = host->variant;
 
 	if (host->singleirq) {
 		unsigned int mask0 = readl(base + MMCIMASK0);
@@ -406,7 +455,10 @@ static void mmci_set_mask1(struct mmci_host *host, unsigned int mask)
 		writel(mask0, base + MMCIMASK0);
 	}
 
-	writel(mask, base + MMCIMASK1);
+	if (variant->mmcimask1)
+		writel(mask, base + MMCIMASK1);
+
+	host->mask1_reg = mask;
 }
 
 static void mmci_stop_data(struct mmci_host *host)
@@ -921,8 +973,9 @@ mmci_data_irq(struct mmci_host *host, struct mmc_data *data,
 		return;
 
 	/* First check for errors */
-	if (status & (MCI_DATACRCFAIL|MCI_DATATIMEOUT|MCI_STARTBITERR|
-		      MCI_TXUNDERRUN|MCI_RXOVERRUN)) {
+	if (status & (MCI_DATACRCFAIL | MCI_DATATIMEOUT |
+		      host->variant->start_err |
+		      MCI_TXUNDERRUN | MCI_RXOVERRUN)) {
 		u32 remain, success;
 
 		/* Terminate the DMA transfer */
@@ -1286,7 +1339,7 @@ static irqreturn_t mmci_irq(int irq, void *dev_id)
 		status = readl(host->base + MMCISTATUS);
 
 		if (host->singleirq) {
-			if (status & readl(host->base + MMCIMASK1))
+			if (status & host->mask1_reg)
 				mmci_pio_irq(irq, dev_id);
 
 			status &= ~MCI_IRQ1MASK;
@@ -1429,16 +1482,18 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 				~MCI_ST_DATA2DIREN);
 	}
 
-	if (ios->bus_mode == MMC_BUSMODE_OPENDRAIN) {
-		if (host->hw_designer != AMBA_VENDOR_ST)
-			pwr |= MCI_ROD;
-		else {
-			/*
-			 * The ST Micro variant use the ROD bit for something
-			 * else and only has OD (Open Drain).
-			 */
-			pwr |= MCI_OD;
-		}
+	if (variant->opendrain) {
+		if (ios->bus_mode == MMC_BUSMODE_OPENDRAIN)
+			pwr |= variant->opendrain;
+	} else {
+		/*
+		 * If the variant cannot configure the pads by its own, then we
+		 * expect the pinctrl to be able to do that for us
+		 */
+		if (ios->bus_mode == MMC_BUSMODE_OPENDRAIN)
+			pinctrl_select_state(host->pinctrl, host->pins_opendrain);
+		else
+			pinctrl_select_state(host->pinctrl, host->pins_default);
 	}
 
 	/*
@@ -1583,6 +1638,35 @@ static int mmci_probe(struct amba_device *dev,
 	host = mmc_priv(mmc);
 	host->mmc = mmc;
 
+	/*
+	 * Some variant (STM32) doesn't have opendrain bit, nevertheless
+	 * pins can be set accordingly using pinctrl
+	 */
+	if (!variant->opendrain) {
+		host->pinctrl = devm_pinctrl_get(&dev->dev);
+		if (IS_ERR(host->pinctrl)) {
+			dev_err(&dev->dev, "failed to get pinctrl");
+			ret = PTR_ERR(host->pinctrl);
+			goto host_free;
+		}
+
+		host->pins_default = pinctrl_lookup_state(host->pinctrl,
+							  PINCTRL_STATE_DEFAULT);
+		if (IS_ERR(host->pins_default)) {
+			dev_err(mmc_dev(mmc), "Can't select default pins\n");
+			ret = PTR_ERR(host->pins_default);
+			goto host_free;
+		}
+
+		host->pins_opendrain = pinctrl_lookup_state(host->pinctrl,
+							    MMCI_PINCTRL_STATE_OPENDRAIN);
+		if (IS_ERR(host->pins_opendrain)) {
+			dev_err(mmc_dev(mmc), "Can't select opendrain pins\n");
+			ret = PTR_ERR(host->pins_opendrain);
+			goto host_free;
+		}
+	}
+
 	host->hw_designer = amba_manf(dev);
 	host->hw_revision = amba_rev(dev);
 	dev_dbg(mmc_dev(mmc), "designer ID = 0x%02x\n", host->hw_designer);
@@ -1729,7 +1813,10 @@ static int mmci_probe(struct amba_device *dev,
 	spin_lock_init(&host->lock);
 
 	writel(0, host->base + MMCIMASK0);
-	writel(0, host->base + MMCIMASK1);
+
+	if (variant->mmcimask1)
+		writel(0, host->base + MMCIMASK1);
+
 	writel(0xfff, host->base + MMCICLEAR);
 
 	/*
@@ -1809,6 +1896,7 @@ static int mmci_remove(struct amba_device *dev)
 
 	if (mmc) {
 		struct mmci_host *host = mmc_priv(mmc);
+		struct variant_data *variant = host->variant;
 
 		/*
 		 * Undo pm_runtime_put() in probe.  We use the _sync
@@ -1819,7 +1907,9 @@ static int mmci_remove(struct amba_device *dev)
 		mmc_remove_host(mmc);
 
 		writel(0, host->base + MMCIMASK0);
-		writel(0, host->base + MMCIMASK1);
+
+		if (variant->mmcimask1)
+			writel(0, host->base + MMCIMASK1);
 
 		writel(0, host->base + MMCICOMMAND);
 		writel(0, host->base + MMCIDATACTRL);
@@ -1951,6 +2041,11 @@ static const struct amba_id mmci_ids[] = {
 		.mask   = 0xf0ffffff,
 		.data	= &variant_ux500v2,
 	},
+	{
+		.id     = 0x00880180,
+		.mask   = 0x00ffffff,
+		.data	= &variant_stm32,
+	},
 	/* Qualcomm variants */
 	{
 		.id     = 0x00051180,
diff --git a/drivers/mmc/host/mmci.h b/drivers/mmc/host/mmci.h
index 4a8bef1aac8f..f91cdf7f6dae 100644
--- a/drivers/mmc/host/mmci.h
+++ b/drivers/mmc/host/mmci.h
@@ -192,6 +192,8 @@
 
 #define NR_SG		128
 
+#define MMCI_PINCTRL_STATE_OPENDRAIN "opendrain"
+
 struct clk;
 struct variant_data;
 struct dma_chan;
@@ -223,9 +225,13 @@ struct mmci_host {
 	u32			clk_reg;
 	u32			datactrl_reg;
 	u32			busy_status;
+	u32			mask1_reg;
 	bool			vqmmc_enabled;
 	struct mmci_platform_data *plat;
 	struct variant_data	*variant;
+	struct pinctrl		*pinctrl;
+	struct pinctrl_state	*pins_default;
+	struct pinctrl_state	*pins_opendrain;
 
 	u8			hw_designer;
 	u8			hw_revision:4;
diff --git a/drivers/mmc/host/renesas_sdhi.h b/drivers/mmc/host/renesas_sdhi.h
index b9dfea5d8193..f13f798d8506 100644
--- a/drivers/mmc/host/renesas_sdhi.h
+++ b/drivers/mmc/host/renesas_sdhi.h
@@ -35,6 +35,28 @@ struct renesas_sdhi_of_data {
 	unsigned short max_segs;
 };
 
+struct tmio_mmc_dma {
+	enum dma_slave_buswidth dma_buswidth;
+	bool (*filter)(struct dma_chan *chan, void *arg);
+	void (*enable)(struct tmio_mmc_host *host, bool enable);
+	struct completion	dma_dataend;
+	struct tasklet_struct	dma_complete;
+};
+
+struct renesas_sdhi {
+	struct clk *clk;
+	struct clk *clk_cd;
+	struct tmio_mmc_data mmc_data;
+	struct tmio_mmc_dma dma_priv;
+	struct pinctrl *pinctrl;
+	struct pinctrl_state *pins_default, *pins_uhs;
+	void __iomem *scc_ctl;
+	u32 scc_tappos;
+};
+
+#define host_to_priv(host) \
+	container_of((host)->pdata, struct renesas_sdhi, mmc_data)
+
 int renesas_sdhi_probe(struct platform_device *pdev,
 		       const struct tmio_mmc_dma_ops *dma_ops);
 int renesas_sdhi_remove(struct platform_device *pdev);
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index 157e1d9e7725..80943fa07db6 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -47,19 +47,6 @@
 #define SDHI_VER_GEN3_SD	0xcc10
 #define SDHI_VER_GEN3_SDMMC	0xcd10
 
-#define host_to_priv(host) \
-	container_of((host)->pdata, struct renesas_sdhi, mmc_data)
-
-struct renesas_sdhi {
-	struct clk *clk;
-	struct clk *clk_cd;
-	struct tmio_mmc_data mmc_data;
-	struct tmio_mmc_dma dma_priv;
-	struct pinctrl *pinctrl;
-	struct pinctrl_state *pins_default, *pins_uhs;
-	void __iomem *scc_ctl;
-};
-
 static void renesas_sdhi_sdbuf_width(struct tmio_mmc_host *host, int width)
 {
 	u32 val;
@@ -281,7 +268,7 @@ static unsigned int renesas_sdhi_init_tuning(struct tmio_mmc_host *host)
 		       ~SH_MOBILE_SDHI_SCC_RVSCNTL_RVSEN &
 		       sd_scc_read32(host, priv, SH_MOBILE_SDHI_SCC_RVSCNTL));
 
-	sd_scc_write32(host, priv, SH_MOBILE_SDHI_SCC_DT2FF, host->scc_tappos);
+	sd_scc_write32(host, priv, SH_MOBILE_SDHI_SCC_DT2FF, priv->scc_tappos);
 
 	/* Read TAPNUM */
 	return (sd_scc_read32(host, priv, SH_MOBILE_SDHI_SCC_DTCNTL) >>
@@ -498,7 +485,7 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 	if (IS_ERR(priv->clk)) {
 		ret = PTR_ERR(priv->clk);
 		dev_err(&pdev->dev, "cannot get clock: %d\n", ret);
-		goto eprobe;
+		return ret;
 	}
 
 	/*
@@ -524,11 +511,9 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 						"state_uhs");
 	}
 
-	host = tmio_mmc_host_alloc(pdev);
-	if (!host) {
-		ret = -ENOMEM;
-		goto eprobe;
-	}
+	host = tmio_mmc_host_alloc(pdev, mmc_data);
+	if (IS_ERR(host))
+		return PTR_ERR(host);
 
 	if (of_data) {
 		mmc_data->flags |= of_data->tmio_flags;
@@ -542,18 +527,18 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 		host->bus_shift = of_data->bus_shift;
 	}
 
-	host->dma		= dma_priv;
 	host->write16_hook	= renesas_sdhi_write16_hook;
 	host->clk_enable	= renesas_sdhi_clk_enable;
 	host->clk_update	= renesas_sdhi_clk_update;
 	host->clk_disable	= renesas_sdhi_clk_disable;
 	host->multi_io_quirk	= renesas_sdhi_multi_io_quirk;
+	host->dma_ops		= dma_ops;
 
 	/* SDR speeds are only available on Gen2+ */
 	if (mmc_data->flags & TMIO_MMC_MIN_RCAR2) {
 		/* card_busy caused issues on r8a73a4 (pre-Gen2) CD-less SDHI */
-		host->card_busy	= renesas_sdhi_card_busy;
-		host->start_signal_voltage_switch =
+		host->ops.card_busy = renesas_sdhi_card_busy;
+		host->ops.start_signal_voltage_switch =
 			renesas_sdhi_start_signal_voltage_switch;
 	}
 
@@ -587,10 +572,14 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 	/* All SDHI have SDIO status bits which must be 1 */
 	mmc_data->flags |= TMIO_MMC_SDIO_STATUS_SETBITS;
 
-	ret = tmio_mmc_host_probe(host, mmc_data, dma_ops);
-	if (ret < 0)
+	ret = renesas_sdhi_clk_enable(host);
+	if (ret)
 		goto efree;
 
+	ret = tmio_mmc_host_probe(host);
+	if (ret < 0)
+		goto edisclk;
+
 	/* One Gen2 SDHI incarnation does NOT have a CBSY bit */
 	if (sd_ctrl_read16(host, CTL_VERSION) == SDHI_VER_GEN2_SDR50)
 		mmc_data->flags &= ~TMIO_MMC_HAVE_CBSY;
@@ -607,7 +596,7 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 		for (i = 0; i < of_data->taps_num; i++) {
 			if (taps[i].clk_rate == 0 ||
 			    taps[i].clk_rate == host->mmc->f_max) {
-				host->scc_tappos = taps->tap;
+				priv->scc_tappos = taps->tap;
 				hit = true;
 				break;
 			}
@@ -651,19 +640,21 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 
 eirq:
 	tmio_mmc_host_remove(host);
+edisclk:
+	renesas_sdhi_clk_disable(host);
 efree:
 	tmio_mmc_host_free(host);
-eprobe:
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(renesas_sdhi_probe);
 
 int renesas_sdhi_remove(struct platform_device *pdev)
 {
-	struct mmc_host *mmc = platform_get_drvdata(pdev);
-	struct tmio_mmc_host *host = mmc_priv(mmc);
+	struct tmio_mmc_host *host = platform_get_drvdata(pdev);
 
 	tmio_mmc_host_remove(host);
+	renesas_sdhi_clk_disable(host);
 
 	return 0;
 }
diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
index 41cbe84c1d18..7c03cfead6f9 100644
--- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c
+++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
@@ -103,6 +103,8 @@ renesas_sdhi_internal_dmac_dm_write(struct tmio_mmc_host *host,
 static void
 renesas_sdhi_internal_dmac_enable_dma(struct tmio_mmc_host *host, bool enable)
 {
+	struct renesas_sdhi *priv = host_to_priv(host);
+
 	if (!host->chan_tx || !host->chan_rx)
 		return;
 
@@ -110,8 +112,8 @@ renesas_sdhi_internal_dmac_enable_dma(struct tmio_mmc_host *host, bool enable)
 		renesas_sdhi_internal_dmac_dm_write(host, DM_CM_INFO1,
 						    INFO1_CLEAR);
 
-	if (host->dma->enable)
-		host->dma->enable(host, enable);
+	if (priv->dma_priv.enable)
+		priv->dma_priv.enable(host, enable);
 }
 
 static void
@@ -130,7 +132,9 @@ renesas_sdhi_internal_dmac_abort_dma(struct tmio_mmc_host *host) {
 
 static void
 renesas_sdhi_internal_dmac_dataend_dma(struct tmio_mmc_host *host) {
-	tasklet_schedule(&host->dma_complete);
+	struct renesas_sdhi *priv = host_to_priv(host);
+
+	tasklet_schedule(&priv->dma_priv.dma_complete);
 }
 
 static void
@@ -220,10 +224,12 @@ static void
 renesas_sdhi_internal_dmac_request_dma(struct tmio_mmc_host *host,
 				       struct tmio_mmc_data *pdata)
 {
+	struct renesas_sdhi *priv = host_to_priv(host);
+
 	/* Each value is set to non-zero to assume "enabling" each DMA */
 	host->chan_rx = host->chan_tx = (void *)0xdeadbeaf;
 
-	tasklet_init(&host->dma_complete,
+	tasklet_init(&priv->dma_priv.dma_complete,
 		     renesas_sdhi_internal_dmac_complete_tasklet_fn,
 		     (unsigned long)host);
 	tasklet_init(&host->dma_issue,
@@ -255,6 +261,7 @@ static const struct soc_device_attribute gen3_soc_whitelist[] = {
         { .soc_id = "r8a7795", .revision = "ES1.*" },
         { .soc_id = "r8a7795", .revision = "ES2.0" },
         { .soc_id = "r8a7796", .revision = "ES1.0" },
+        { .soc_id = "r8a77995", .revision = "ES1.0" },
         { /* sentinel */ }
 };
 
diff --git a/drivers/mmc/host/renesas_sdhi_sys_dmac.c b/drivers/mmc/host/renesas_sdhi_sys_dmac.c
index 9ab10436e4b8..82d757c480b2 100644
--- a/drivers/mmc/host/renesas_sdhi_sys_dmac.c
+++ b/drivers/mmc/host/renesas_sdhi_sys_dmac.c
@@ -117,11 +117,13 @@ MODULE_DEVICE_TABLE(of, renesas_sdhi_sys_dmac_of_match);
 static void renesas_sdhi_sys_dmac_enable_dma(struct tmio_mmc_host *host,
 					     bool enable)
 {
+	struct renesas_sdhi *priv = host_to_priv(host);
+
 	if (!host->chan_tx || !host->chan_rx)
 		return;
 
-	if (host->dma->enable)
-		host->dma->enable(host, enable);
+	if (priv->dma_priv.enable)
+		priv->dma_priv.enable(host, enable);
 }
 
 static void renesas_sdhi_sys_dmac_abort_dma(struct tmio_mmc_host *host)
@@ -138,12 +140,15 @@ static void renesas_sdhi_sys_dmac_abort_dma(struct tmio_mmc_host *host)
 
 static void renesas_sdhi_sys_dmac_dataend_dma(struct tmio_mmc_host *host)
 {
-	complete(&host->dma_dataend);
+	struct renesas_sdhi *priv = host_to_priv(host);
+
+	complete(&priv->dma_priv.dma_dataend);
 }
 
 static void renesas_sdhi_sys_dmac_dma_callback(void *arg)
 {
 	struct tmio_mmc_host *host = arg;
+	struct renesas_sdhi *priv = host_to_priv(host);
 
 	spin_lock_irq(&host->lock);
 
@@ -161,7 +166,7 @@ static void renesas_sdhi_sys_dmac_dma_callback(void *arg)
 
 	spin_unlock_irq(&host->lock);
 
-	wait_for_completion(&host->dma_dataend);
+	wait_for_completion(&priv->dma_priv.dma_dataend);
 
 	spin_lock_irq(&host->lock);
 	tmio_mmc_do_data_irq(host);
@@ -171,6 +176,7 @@ out:
 
 static void renesas_sdhi_sys_dmac_start_dma_rx(struct tmio_mmc_host *host)
 {
+	struct renesas_sdhi *priv = host_to_priv(host);
 	struct scatterlist *sg = host->sg_ptr, *sg_tmp;
 	struct dma_async_tx_descriptor *desc = NULL;
 	struct dma_chan *chan = host->chan_rx;
@@ -214,7 +220,7 @@ static void renesas_sdhi_sys_dmac_start_dma_rx(struct tmio_mmc_host *host)
 					       DMA_CTRL_ACK);
 
 	if (desc) {
-		reinit_completion(&host->dma_dataend);
+		reinit_completion(&priv->dma_priv.dma_dataend);
 		desc->callback = renesas_sdhi_sys_dmac_dma_callback;
 		desc->callback_param = host;
 
@@ -245,6 +251,7 @@ pio:
 
 static void renesas_sdhi_sys_dmac_start_dma_tx(struct tmio_mmc_host *host)
 {
+	struct renesas_sdhi *priv = host_to_priv(host);
 	struct scatterlist *sg = host->sg_ptr, *sg_tmp;
 	struct dma_async_tx_descriptor *desc = NULL;
 	struct dma_chan *chan = host->chan_tx;
@@ -293,7 +300,7 @@ static void renesas_sdhi_sys_dmac_start_dma_tx(struct tmio_mmc_host *host)
 					       DMA_CTRL_ACK);
 
 	if (desc) {
-		reinit_completion(&host->dma_dataend);
+		reinit_completion(&priv->dma_priv.dma_dataend);
 		desc->callback = renesas_sdhi_sys_dmac_dma_callback;
 		desc->callback_param = host;
 
@@ -341,7 +348,7 @@ static void renesas_sdhi_sys_dmac_issue_tasklet_fn(unsigned long priv)
 
 	spin_lock_irq(&host->lock);
 
-	if (host && host->data) {
+	if (host->data) {
 		if (host->data->flags & MMC_DATA_READ)
 			chan = host->chan_rx;
 		else
@@ -359,9 +366,11 @@ static void renesas_sdhi_sys_dmac_issue_tasklet_fn(unsigned long priv)
 static void renesas_sdhi_sys_dmac_request_dma(struct tmio_mmc_host *host,
 					      struct tmio_mmc_data *pdata)
 {
+	struct renesas_sdhi *priv = host_to_priv(host);
+
 	/* We can only either use DMA for both Tx and Rx or not use it at all */
-	if (!host->dma || (!host->pdev->dev.of_node &&
-			   (!pdata->chan_priv_tx || !pdata->chan_priv_rx)))
+	if (!host->pdev->dev.of_node &&
+	    (!pdata->chan_priv_tx || !pdata->chan_priv_rx))
 		return;
 
 	if (!host->chan_tx && !host->chan_rx) {
@@ -378,7 +387,7 @@ static void renesas_sdhi_sys_dmac_request_dma(struct tmio_mmc_host *host,
 		dma_cap_set(DMA_SLAVE, mask);
 
 		host->chan_tx = dma_request_slave_channel_compat(mask,
-					host->dma->filter, pdata->chan_priv_tx,
+					priv->dma_priv.filter, pdata->chan_priv_tx,
 					&host->pdev->dev, "tx");
 		dev_dbg(&host->pdev->dev, "%s: TX: got channel %p\n", __func__,
 			host->chan_tx);
@@ -389,7 +398,7 @@ static void renesas_sdhi_sys_dmac_request_dma(struct tmio_mmc_host *host,
 		cfg.direction = DMA_MEM_TO_DEV;
 		cfg.dst_addr = res->start +
 			(CTL_SD_DATA_PORT << host->bus_shift);
-		cfg.dst_addr_width = host->dma->dma_buswidth;
+		cfg.dst_addr_width = priv->dma_priv.dma_buswidth;
 		if (!cfg.dst_addr_width)
 			cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
 		cfg.src_addr = 0;
@@ -398,7 +407,7 @@ static void renesas_sdhi_sys_dmac_request_dma(struct tmio_mmc_host *host,
 			goto ecfgtx;
 
 		host->chan_rx = dma_request_slave_channel_compat(mask,
-					host->dma->filter, pdata->chan_priv_rx,
+					priv->dma_priv.filter, pdata->chan_priv_rx,
 					&host->pdev->dev, "rx");
 		dev_dbg(&host->pdev->dev, "%s: RX: got channel %p\n", __func__,
 			host->chan_rx);
@@ -408,7 +417,7 @@ static void renesas_sdhi_sys_dmac_request_dma(struct tmio_mmc_host *host,
 
 		cfg.direction = DMA_DEV_TO_MEM;
 		cfg.src_addr = cfg.dst_addr + host->pdata->dma_rx_offset;
-		cfg.src_addr_width = host->dma->dma_buswidth;
+		cfg.src_addr_width = priv->dma_priv.dma_buswidth;
 		if (!cfg.src_addr_width)
 			cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
 		cfg.dst_addr = 0;
@@ -420,7 +429,7 @@ static void renesas_sdhi_sys_dmac_request_dma(struct tmio_mmc_host *host,
 		if (!host->bounce_buf)
 			goto ebouncebuf;
 
-		init_completion(&host->dma_dataend);
+		init_completion(&priv->dma_priv.dma_dataend);
 		tasklet_init(&host->dma_issue,
 			     renesas_sdhi_sys_dmac_issue_tasklet_fn,
 			     (unsigned long)host);
diff --git a/drivers/mmc/host/s3cmci.c b/drivers/mmc/host/s3cmci.c
index 555c7f133eb8..f77493604312 100644
--- a/drivers/mmc/host/s3cmci.c
+++ b/drivers/mmc/host/s3cmci.c
@@ -1660,7 +1660,7 @@ static int s3cmci_probe(struct platform_device *pdev)
 	}
 
 	host->irq = platform_get_irq(pdev, 0);
-	if (host->irq == 0) {
+	if (host->irq <= 0) {
 		dev_err(&pdev->dev, "failed to get interrupt resource.\n");
 		ret = -EINVAL;
 		goto probe_iounmap;
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index b988997a1e80..4065da58789d 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -76,6 +76,7 @@ struct sdhci_acpi_slot {
 	size_t		priv_size;
 	int (*probe_slot)(struct platform_device *, const char *, const char *);
 	int (*remove_slot)(struct platform_device *);
+	int (*setup_host)(struct platform_device *pdev);
 };
 
 struct sdhci_acpi_host {
@@ -96,14 +97,21 @@ static inline bool sdhci_acpi_flag(struct sdhci_acpi_host *c, unsigned int flag)
 	return c->slot && (c->slot->flags & flag);
 }
 
+#define INTEL_DSM_HS_CAPS_SDR25		BIT(0)
+#define INTEL_DSM_HS_CAPS_DDR50		BIT(1)
+#define INTEL_DSM_HS_CAPS_SDR50		BIT(2)
+#define INTEL_DSM_HS_CAPS_SDR104	BIT(3)
+
 enum {
 	INTEL_DSM_FNS		=  0,
 	INTEL_DSM_V18_SWITCH	=  3,
 	INTEL_DSM_V33_SWITCH	=  4,
+	INTEL_DSM_HS_CAPS	=  8,
 };
 
 struct intel_host {
 	u32	dsm_fns;
+	u32	hs_caps;
 };
 
 static const guid_t intel_dsm_guid =
@@ -152,6 +160,8 @@ static void intel_dsm_init(struct intel_host *intel_host, struct device *dev,
 {
 	int err;
 
+	intel_host->hs_caps = ~0;
+
 	err = __intel_dsm(intel_host, dev, INTEL_DSM_FNS, &intel_host->dsm_fns);
 	if (err) {
 		pr_debug("%s: DSM not supported, error %d\n",
@@ -161,6 +171,8 @@ static void intel_dsm_init(struct intel_host *intel_host, struct device *dev,
 
 	pr_debug("%s: DSM function mask %#x\n",
 		 mmc_hostname(mmc), intel_host->dsm_fns);
+
+	intel_dsm(intel_host, dev, INTEL_DSM_HS_CAPS, &intel_host->hs_caps);
 }
 
 static int intel_start_signal_voltage_switch(struct mmc_host *mmc,
@@ -398,6 +410,26 @@ static int intel_probe_slot(struct platform_device *pdev, const char *hid,
 	return 0;
 }
 
+static int intel_setup_host(struct platform_device *pdev)
+{
+	struct sdhci_acpi_host *c = platform_get_drvdata(pdev);
+	struct intel_host *intel_host = sdhci_acpi_priv(c);
+
+	if (!(intel_host->hs_caps & INTEL_DSM_HS_CAPS_SDR25))
+		c->host->mmc->caps &= ~MMC_CAP_UHS_SDR25;
+
+	if (!(intel_host->hs_caps & INTEL_DSM_HS_CAPS_SDR50))
+		c->host->mmc->caps &= ~MMC_CAP_UHS_SDR50;
+
+	if (!(intel_host->hs_caps & INTEL_DSM_HS_CAPS_DDR50))
+		c->host->mmc->caps &= ~MMC_CAP_UHS_DDR50;
+
+	if (!(intel_host->hs_caps & INTEL_DSM_HS_CAPS_SDR104))
+		c->host->mmc->caps &= ~MMC_CAP_UHS_SDR104;
+
+	return 0;
+}
+
 static const struct sdhci_acpi_slot sdhci_acpi_slot_int_emmc = {
 	.chip    = &sdhci_acpi_chip_int,
 	.caps    = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
@@ -409,6 +441,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_emmc = {
 		   SDHCI_QUIRK2_STOP_WITH_TC |
 		   SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400,
 	.probe_slot	= intel_probe_slot,
+	.setup_host	= intel_setup_host,
 	.priv_size	= sizeof(struct intel_host),
 };
 
@@ -421,6 +454,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_sdio = {
 	.flags   = SDHCI_ACPI_RUNTIME_PM,
 	.pm_caps = MMC_PM_KEEP_POWER,
 	.probe_slot	= intel_probe_slot,
+	.setup_host	= intel_setup_host,
 	.priv_size	= sizeof(struct intel_host),
 };
 
@@ -432,6 +466,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_sd = {
 		   SDHCI_QUIRK2_STOP_WITH_TC,
 	.caps    = MMC_CAP_WAIT_WHILE_BUSY | MMC_CAP_AGGRESSIVE_PM,
 	.probe_slot	= intel_probe_slot,
+	.setup_host	= intel_setup_host,
 	.priv_size	= sizeof(struct intel_host),
 };
 
@@ -446,6 +481,83 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_qcom_sd = {
 	.caps    = MMC_CAP_NONREMOVABLE,
 };
 
+/* AMD sdhci reset dll register. */
+#define SDHCI_AMD_RESET_DLL_REGISTER    0x908
+
+static int amd_select_drive_strength(struct mmc_card *card,
+				     unsigned int max_dtr, int host_drv,
+				     int card_drv, int *drv_type)
+{
+	return MMC_SET_DRIVER_TYPE_A;
+}
+
+static void sdhci_acpi_amd_hs400_dll(struct sdhci_host *host)
+{
+	/* AMD Platform requires dll setting */
+	sdhci_writel(host, 0x40003210, SDHCI_AMD_RESET_DLL_REGISTER);
+	usleep_range(10, 20);
+	sdhci_writel(host, 0x40033210, SDHCI_AMD_RESET_DLL_REGISTER);
+}
+
+/*
+ * For AMD Platform it is required to disable the tuning
+ * bit first controller to bring to HS Mode from HS200
+ * mode, later enable to tune to HS400 mode.
+ */
+static void amd_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	unsigned int old_timing = host->timing;
+
+	sdhci_set_ios(mmc, ios);
+	if (old_timing == MMC_TIMING_MMC_HS200 &&
+	    ios->timing == MMC_TIMING_MMC_HS)
+		sdhci_writew(host, 0x9, SDHCI_HOST_CONTROL2);
+	if (old_timing != MMC_TIMING_MMC_HS400 &&
+	    ios->timing == MMC_TIMING_MMC_HS400) {
+		sdhci_writew(host, 0x80, SDHCI_HOST_CONTROL2);
+		sdhci_acpi_amd_hs400_dll(host);
+	}
+}
+
+static const struct sdhci_ops sdhci_acpi_ops_amd = {
+	.set_clock	= sdhci_set_clock,
+	.set_bus_width	= sdhci_set_bus_width,
+	.reset		= sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
+};
+
+static const struct sdhci_acpi_chip sdhci_acpi_chip_amd = {
+	.ops = &sdhci_acpi_ops_amd,
+};
+
+static int sdhci_acpi_emmc_amd_probe_slot(struct platform_device *pdev,
+					  const char *hid, const char *uid)
+{
+	struct sdhci_acpi_host *c = platform_get_drvdata(pdev);
+	struct sdhci_host *host   = c->host;
+
+	sdhci_read_caps(host);
+	if (host->caps1 & SDHCI_SUPPORT_DDR50)
+		host->mmc->caps = MMC_CAP_1_8V_DDR;
+
+	if ((host->caps1 & SDHCI_SUPPORT_SDR104) &&
+	    (host->mmc->caps & MMC_CAP_1_8V_DDR))
+		host->mmc->caps2 = MMC_CAP2_HS400_1_8V;
+
+	host->mmc_host_ops.select_drive_strength = amd_select_drive_strength;
+	host->mmc_host_ops.set_ios = amd_set_ios;
+	return 0;
+}
+
+static const struct sdhci_acpi_slot sdhci_acpi_slot_amd_emmc = {
+	.chip   = &sdhci_acpi_chip_amd,
+	.caps   = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE,
+	.quirks = SDHCI_QUIRK_32BIT_DMA_ADDR | SDHCI_QUIRK_32BIT_DMA_SIZE |
+			SDHCI_QUIRK_32BIT_ADMA_SIZE,
+	.probe_slot     = sdhci_acpi_emmc_amd_probe_slot,
+};
+
 struct sdhci_acpi_uid_slot {
 	const char *hid;
 	const char *uid;
@@ -469,6 +581,7 @@ static const struct sdhci_acpi_uid_slot sdhci_acpi_uids[] = {
 	{ "PNP0D40"  },
 	{ "QCOM8051", NULL, &sdhci_acpi_slot_qcom_sd_3v },
 	{ "QCOM8052", NULL, &sdhci_acpi_slot_qcom_sd },
+	{ "AMDI0040", NULL, &sdhci_acpi_slot_amd_emmc },
 	{ },
 };
 
@@ -485,6 +598,7 @@ static const struct acpi_device_id sdhci_acpi_ids[] = {
 	{ "PNP0D40"  },
 	{ "QCOM8051" },
 	{ "QCOM8052" },
+	{ "AMDI0040" },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, sdhci_acpi_ids);
@@ -566,6 +680,10 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 	host->hw_name	= "ACPI";
 	host->ops	= &sdhci_acpi_ops_dflt;
 	host->irq	= platform_get_irq(pdev, 0);
+	if (host->irq <= 0) {
+		err = -EINVAL;
+		goto err_free;
+	}
 
 	host->ioaddr = devm_ioremap_nocache(dev, iomem->start,
 					    resource_size(iomem));
@@ -609,10 +727,20 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 		}
 	}
 
-	err = sdhci_add_host(host);
+	err = sdhci_setup_host(host);
 	if (err)
 		goto err_free;
 
+	if (c->slot && c->slot->setup_host) {
+		err = c->slot->setup_host(pdev);
+		if (err)
+			goto err_cleanup;
+	}
+
+	err = __sdhci_add_host(host);
+	if (err)
+		goto err_cleanup;
+
 	if (c->use_runtime_pm) {
 		pm_runtime_set_active(dev);
 		pm_suspend_ignore_children(dev, 1);
@@ -625,6 +753,8 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_cleanup:
+	sdhci_cleanup_host(c->host);
 err_free:
 	sdhci_free_host(c->host);
 	return err;
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 8b941f814472..cd2b5f643a15 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -193,6 +193,7 @@ struct pltfm_imx_data {
 	struct clk *clk_ipg;
 	struct clk *clk_ahb;
 	struct clk *clk_per;
+	unsigned int actual_clock;
 	enum {
 		NO_CMD_PENDING,      /* no multiblock command pending */
 		MULTIBLK_IN_PROCESS, /* exact multiblock cmd in process */
@@ -1403,11 +1404,15 @@ static int sdhci_esdhc_runtime_suspend(struct device *dev)
 	int ret;
 
 	ret = sdhci_runtime_suspend_host(host);
+	if (ret)
+		return ret;
 
 	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
 		mmc_retune_needed(host->mmc);
 
 	if (!sdhci_sdio_irq_enabled(host)) {
+		imx_data->actual_clock = host->mmc->actual_clock;
+		esdhc_pltfm_set_clock(host, 0);
 		clk_disable_unprepare(imx_data->clk_per);
 		clk_disable_unprepare(imx_data->clk_ipg);
 	}
@@ -1423,31 +1428,34 @@ static int sdhci_esdhc_runtime_resume(struct device *dev)
 	struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host);
 	int err;
 
+	err = clk_prepare_enable(imx_data->clk_ahb);
+	if (err)
+		return err;
+
 	if (!sdhci_sdio_irq_enabled(host)) {
 		err = clk_prepare_enable(imx_data->clk_per);
 		if (err)
-			return err;
+			goto disable_ahb_clk;
 		err = clk_prepare_enable(imx_data->clk_ipg);
 		if (err)
 			goto disable_per_clk;
+		esdhc_pltfm_set_clock(host, imx_data->actual_clock);
 	}
-	err = clk_prepare_enable(imx_data->clk_ahb);
-	if (err)
-		goto disable_ipg_clk;
+
 	err = sdhci_runtime_resume_host(host);
 	if (err)
-		goto disable_ahb_clk;
+		goto disable_ipg_clk;
 
 	return 0;
 
-disable_ahb_clk:
-	clk_disable_unprepare(imx_data->clk_ahb);
 disable_ipg_clk:
 	if (!sdhci_sdio_irq_enabled(host))
 		clk_disable_unprepare(imx_data->clk_ipg);
 disable_per_clk:
 	if (!sdhci_sdio_irq_enabled(host))
 		clk_disable_unprepare(imx_data->clk_per);
+disable_ahb_clk:
+	clk_disable_unprepare(imx_data->clk_ahb);
 	return err;
 }
 #endif
diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index 0720ea717011..c33a5f7393bd 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -25,11 +25,13 @@
 #include <linux/of_device.h>
 #include <linux/phy/phy.h>
 #include <linux/regmap.h>
-#include "sdhci-pltfm.h"
 #include <linux/of.h>
 
-#define SDHCI_ARASAN_VENDOR_REGISTER	0x78
+#include "cqhci.h"
+#include "sdhci-pltfm.h"
 
+#define SDHCI_ARASAN_VENDOR_REGISTER	0x78
+#define SDHCI_ARASAN_CQE_BASE_ADDR	0x200
 #define VENDOR_ENHANCED_STROBE		BIT(0)
 
 #define PHY_CLK_TOO_SLOW_HZ		400000
@@ -90,6 +92,7 @@ struct sdhci_arasan_data {
 	struct phy	*phy;
 	bool		is_phy_on;
 
+	bool		has_cqe;
 	struct clk_hw	sdcardclk_hw;
 	struct clk      *sdcardclk;
 
@@ -262,6 +265,17 @@ static int sdhci_arasan_voltage_switch(struct mmc_host *mmc,
 	return -EINVAL;
 }
 
+static void sdhci_arasan_set_power(struct sdhci_host *host, unsigned char mode,
+		     unsigned short vdd)
+{
+	if (!IS_ERR(host->mmc->supply.vmmc)) {
+		struct mmc_host *mmc = host->mmc;
+
+		mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
+	}
+	sdhci_set_power_noreg(host, mode, vdd);
+}
+
 static const struct sdhci_ops sdhci_arasan_ops = {
 	.set_clock = sdhci_arasan_set_clock,
 	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
@@ -269,6 +283,7 @@ static const struct sdhci_ops sdhci_arasan_ops = {
 	.set_bus_width = sdhci_set_bus_width,
 	.reset = sdhci_arasan_reset,
 	.set_uhs_signaling = sdhci_set_uhs_signaling,
+	.set_power = sdhci_arasan_set_power,
 };
 
 static const struct sdhci_pltfm_data sdhci_arasan_pdata = {
@@ -278,6 +293,62 @@ static const struct sdhci_pltfm_data sdhci_arasan_pdata = {
 			SDHCI_QUIRK2_CLOCK_DIV_ZERO_BROKEN,
 };
 
+static u32 sdhci_arasan_cqhci_irq(struct sdhci_host *host, u32 intmask)
+{
+	int cmd_error = 0;
+	int data_error = 0;
+
+	if (!sdhci_cqe_irq(host, intmask, &cmd_error, &data_error))
+		return intmask;
+
+	cqhci_irq(host->mmc, intmask, cmd_error, data_error);
+
+	return 0;
+}
+
+static void sdhci_arasan_dumpregs(struct mmc_host *mmc)
+{
+	sdhci_dumpregs(mmc_priv(mmc));
+}
+
+static void sdhci_arasan_cqe_enable(struct mmc_host *mmc)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	u32 reg;
+
+	reg = sdhci_readl(host, SDHCI_PRESENT_STATE);
+	while (reg & SDHCI_DATA_AVAILABLE) {
+		sdhci_readl(host, SDHCI_BUFFER);
+		reg = sdhci_readl(host, SDHCI_PRESENT_STATE);
+	}
+
+	sdhci_cqe_enable(mmc);
+}
+
+static const struct cqhci_host_ops sdhci_arasan_cqhci_ops = {
+	.enable         = sdhci_arasan_cqe_enable,
+	.disable        = sdhci_cqe_disable,
+	.dumpregs       = sdhci_arasan_dumpregs,
+};
+
+static const struct sdhci_ops sdhci_arasan_cqe_ops = {
+	.set_clock = sdhci_arasan_set_clock,
+	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
+	.get_timeout_clock = sdhci_pltfm_clk_get_max_clock,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = sdhci_arasan_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
+	.set_power = sdhci_arasan_set_power,
+	.irq = sdhci_arasan_cqhci_irq,
+};
+
+static const struct sdhci_pltfm_data sdhci_arasan_cqe_pdata = {
+	.ops = &sdhci_arasan_cqe_ops,
+	.quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+			SDHCI_QUIRK2_CLOCK_DIV_ZERO_BROKEN,
+};
+
 #ifdef CONFIG_PM_SLEEP
 /**
  * sdhci_arasan_suspend - Suspend method for the driver
@@ -297,6 +368,12 @@ static int sdhci_arasan_suspend(struct device *dev)
 	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
 		mmc_retune_needed(host->mmc);
 
+	if (sdhci_arasan->has_cqe) {
+		ret = cqhci_suspend(host->mmc);
+		if (ret)
+			return ret;
+	}
+
 	ret = sdhci_suspend_host(host);
 	if (ret)
 		return ret;
@@ -353,7 +430,16 @@ static int sdhci_arasan_resume(struct device *dev)
 		sdhci_arasan->is_phy_on = true;
 	}
 
-	return sdhci_resume_host(host);
+	ret = sdhci_resume_host(host);
+	if (ret) {
+		dev_err(dev, "Cannot resume host.\n");
+		return ret;
+	}
+
+	if (sdhci_arasan->has_cqe)
+		return cqhci_resume(host->mmc);
+
+	return 0;
 }
 #endif /* ! CONFIG_PM_SLEEP */
 
@@ -556,6 +642,49 @@ static void sdhci_arasan_unregister_sdclk(struct device *dev)
 	of_clk_del_provider(dev->of_node);
 }
 
+static int sdhci_arasan_add_host(struct sdhci_arasan_data *sdhci_arasan)
+{
+	struct sdhci_host *host = sdhci_arasan->host;
+	struct cqhci_host *cq_host;
+	bool dma64;
+	int ret;
+
+	if (!sdhci_arasan->has_cqe)
+		return sdhci_add_host(host);
+
+	ret = sdhci_setup_host(host);
+	if (ret)
+		return ret;
+
+	cq_host = devm_kzalloc(host->mmc->parent,
+			       sizeof(*cq_host), GFP_KERNEL);
+	if (!cq_host) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	cq_host->mmio = host->ioaddr + SDHCI_ARASAN_CQE_BASE_ADDR;
+	cq_host->ops = &sdhci_arasan_cqhci_ops;
+
+	dma64 = host->flags & SDHCI_USE_64_BIT_DMA;
+	if (dma64)
+		cq_host->caps |= CQHCI_TASK_DESC_SZ_128;
+
+	ret = cqhci_init(cq_host, host->mmc, dma64);
+	if (ret)
+		goto cleanup;
+
+	ret = __sdhci_add_host(host);
+	if (ret)
+		goto cleanup;
+
+	return 0;
+
+cleanup:
+	sdhci_cleanup_host(host);
+	return ret;
+}
+
 static int sdhci_arasan_probe(struct platform_device *pdev)
 {
 	int ret;
@@ -566,9 +695,15 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 	struct sdhci_pltfm_host *pltfm_host;
 	struct sdhci_arasan_data *sdhci_arasan;
 	struct device_node *np = pdev->dev.of_node;
+	const struct sdhci_pltfm_data *pdata;
+
+	if (of_device_is_compatible(pdev->dev.of_node, "arasan,sdhci-5.1"))
+		pdata = &sdhci_arasan_cqe_pdata;
+	else
+		pdata = &sdhci_arasan_pdata;
+
+	host = sdhci_pltfm_init(pdev, pdata, sizeof(*sdhci_arasan));
 
-	host = sdhci_pltfm_init(pdev, &sdhci_arasan_pdata,
-				sizeof(*sdhci_arasan));
 	if (IS_ERR(host))
 		return PTR_ERR(host);
 
@@ -663,9 +798,11 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 					sdhci_arasan_hs400_enhanced_strobe;
 		host->mmc_host_ops.start_signal_voltage_switch =
 					sdhci_arasan_voltage_switch;
+		sdhci_arasan->has_cqe = true;
+		host->mmc->caps2 |= MMC_CAP2_CQE | MMC_CAP2_CQE_DCMD;
 	}
 
-	ret = sdhci_add_host(host);
+	ret = sdhci_arasan_add_host(sdhci_arasan);
 	if (ret)
 		goto err_add_host;
 
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 1f424374bbbb..4ffa6b173a21 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -589,10 +589,18 @@ static void esdhc_pltfm_set_bus_width(struct sdhci_host *host, int width)
 
 static void esdhc_reset(struct sdhci_host *host, u8 mask)
 {
+	u32 val;
+
 	sdhci_reset(host, mask);
 
 	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
 	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
+
+	if (mask & SDHCI_RESET_ALL) {
+		val = sdhci_readl(host, ESDHC_TBCTL);
+		val &= ~ESDHC_TB_EN;
+		sdhci_writel(host, val, ESDHC_TBCTL);
+	}
 }
 
 /* The SCFG, Supplemental Configuration Unit, provides SoC specific
diff --git a/drivers/mmc/host/sdhci-pci-arasan.c b/drivers/mmc/host/sdhci-pci-arasan.c
new file mode 100644
index 000000000000..499f3205ec5c
--- /dev/null
+++ b/drivers/mmc/host/sdhci-pci-arasan.c
@@ -0,0 +1,331 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * sdhci-pci-arasan.c - Driver for Arasan PCI Controller with
+ * integrated phy.
+ *
+ * Copyright (C) 2017 Arasan Chip Systems Inc.
+ *
+ * Author: Atul Garg <agarg@arasan.com>
+ */
+
+#include <linux/pci.h>
+#include <linux/delay.h>
+
+#include "sdhci.h"
+#include "sdhci-pci.h"
+
+/* Extra registers for Arasan SD/SDIO/MMC Host Controller with PHY */
+#define PHY_ADDR_REG	0x300
+#define PHY_DAT_REG	0x304
+
+#define PHY_WRITE	BIT(8)
+#define PHY_BUSY	BIT(9)
+#define DATA_MASK	0xFF
+
+/* PHY Specific Registers */
+#define DLL_STATUS	0x00
+#define IPAD_CTRL1	0x01
+#define IPAD_CTRL2	0x02
+#define IPAD_STS	0x03
+#define IOREN_CTRL1	0x06
+#define IOREN_CTRL2	0x07
+#define IOPU_CTRL1	0x08
+#define IOPU_CTRL2	0x09
+#define ITAP_DELAY	0x0C
+#define OTAP_DELAY	0x0D
+#define STRB_SEL	0x0E
+#define CLKBUF_SEL	0x0F
+#define MODE_CTRL	0x11
+#define DLL_TRIM	0x12
+#define CMD_CTRL	0x20
+#define DATA_CTRL	0x21
+#define STRB_CTRL	0x22
+#define CLK_CTRL	0x23
+#define PHY_CTRL	0x24
+
+#define DLL_ENBL	BIT(3)
+#define RTRIM_EN	BIT(1)
+#define PDB_ENBL	BIT(1)
+#define RETB_ENBL	BIT(6)
+#define ODEN_CMD	BIT(1)
+#define ODEN_DAT	0xFF
+#define REN_STRB	BIT(0)
+#define REN_CMND	BIT(1)
+#define REN_DATA	0xFF
+#define PU_CMD		BIT(1)
+#define PU_DAT		0xFF
+#define ITAPDLY_EN	BIT(0)
+#define OTAPDLY_EN	BIT(0)
+#define OD_REL_CMD	BIT(1)
+#define OD_REL_DAT	0xFF
+#define DLLTRM_ICP	0x8
+#define PDB_CMND	BIT(0)
+#define PDB_DATA	0xFF
+#define PDB_STRB	BIT(0)
+#define PDB_CLOCK	BIT(0)
+#define CALDONE_MASK	0x10
+#define DLL_RDY_MASK	0x10
+#define MAX_CLK_BUF	0x7
+
+/* Mode Controls */
+#define ENHSTRB_MODE	BIT(0)
+#define HS400_MODE	BIT(1)
+#define LEGACY_MODE	BIT(2)
+#define DDR50_MODE	BIT(3)
+
+/*
+ * Controller has no specific bits for HS200/HS.
+ * Used BIT(4), BIT(5) for software programming.
+ */
+#define HS200_MODE	BIT(4)
+#define HISPD_MODE	BIT(5)
+
+#define OTAPDLY(x)	(((x) << 1) | OTAPDLY_EN)
+#define ITAPDLY(x)	(((x) << 1) | ITAPDLY_EN)
+#define FREQSEL(x)	(((x) << 5) | DLL_ENBL)
+#define IOPAD(x, y)	((x) | ((y) << 2))
+
+/* Arasan private data */
+struct arasan_host {
+	u32 chg_clk;
+};
+
+static int arasan_phy_addr_poll(struct sdhci_host *host, u32 offset, u32 mask)
+{
+	ktime_t timeout = ktime_add_us(ktime_get(), 100);
+	bool failed;
+	u8 val = 0;
+
+	while (1) {
+		failed = ktime_after(ktime_get(), timeout);
+		val = sdhci_readw(host, PHY_ADDR_REG);
+		if (!(val & mask))
+			return 0;
+		if (failed)
+			return -EBUSY;
+	}
+}
+
+static int arasan_phy_write(struct sdhci_host *host, u8 data, u8 offset)
+{
+	sdhci_writew(host, data, PHY_DAT_REG);
+	sdhci_writew(host, (PHY_WRITE | offset), PHY_ADDR_REG);
+	return arasan_phy_addr_poll(host, PHY_ADDR_REG, PHY_BUSY);
+}
+
+static int arasan_phy_read(struct sdhci_host *host, u8 offset, u8 *data)
+{
+	int ret;
+
+	sdhci_writew(host, 0, PHY_DAT_REG);
+	sdhci_writew(host, offset, PHY_ADDR_REG);
+	ret = arasan_phy_addr_poll(host, PHY_ADDR_REG, PHY_BUSY);
+
+	/* Masking valid data bits */
+	*data = sdhci_readw(host, PHY_DAT_REG) & DATA_MASK;
+	return ret;
+}
+
+static int arasan_phy_sts_poll(struct sdhci_host *host, u32 offset, u32 mask)
+{
+	int ret;
+	ktime_t timeout = ktime_add_us(ktime_get(), 100);
+	bool failed;
+	u8 val = 0;
+
+	while (1) {
+		failed = ktime_after(ktime_get(), timeout);
+		ret = arasan_phy_read(host, offset, &val);
+		if (ret)
+			return -EBUSY;
+		else if (val & mask)
+			return 0;
+		if (failed)
+			return -EBUSY;
+	}
+}
+
+/* Initialize the Arasan PHY */
+static int arasan_phy_init(struct sdhci_host *host)
+{
+	int ret;
+	u8 val;
+
+	/* Program IOPADs and wait for calibration to be done */
+	if (arasan_phy_read(host, IPAD_CTRL1, &val) ||
+	    arasan_phy_write(host, val | RETB_ENBL | PDB_ENBL, IPAD_CTRL1) ||
+	    arasan_phy_read(host, IPAD_CTRL2, &val) ||
+	    arasan_phy_write(host, val | RTRIM_EN, IPAD_CTRL2))
+		return -EBUSY;
+	ret = arasan_phy_sts_poll(host, IPAD_STS, CALDONE_MASK);
+	if (ret)
+		return -EBUSY;
+
+	/* Program CMD/Data lines */
+	if (arasan_phy_read(host, IOREN_CTRL1, &val) ||
+	    arasan_phy_write(host, val | REN_CMND | REN_STRB, IOREN_CTRL1) ||
+	    arasan_phy_read(host, IOPU_CTRL1, &val) ||
+	    arasan_phy_write(host, val | PU_CMD, IOPU_CTRL1) ||
+	    arasan_phy_read(host, CMD_CTRL, &val) ||
+	    arasan_phy_write(host, val | PDB_CMND, CMD_CTRL) ||
+	    arasan_phy_read(host, IOREN_CTRL2, &val) ||
+	    arasan_phy_write(host, val | REN_DATA, IOREN_CTRL2) ||
+	    arasan_phy_read(host, IOPU_CTRL2, &val) ||
+	    arasan_phy_write(host, val | PU_DAT, IOPU_CTRL2) ||
+	    arasan_phy_read(host, DATA_CTRL, &val) ||
+	    arasan_phy_write(host, val | PDB_DATA, DATA_CTRL) ||
+	    arasan_phy_read(host, STRB_CTRL, &val) ||
+	    arasan_phy_write(host, val | PDB_STRB, STRB_CTRL) ||
+	    arasan_phy_read(host, CLK_CTRL, &val) ||
+	    arasan_phy_write(host, val | PDB_CLOCK, CLK_CTRL) ||
+	    arasan_phy_read(host, CLKBUF_SEL, &val) ||
+	    arasan_phy_write(host, val | MAX_CLK_BUF, CLKBUF_SEL) ||
+	    arasan_phy_write(host, LEGACY_MODE, MODE_CTRL))
+		return -EBUSY;
+	return 0;
+}
+
+/* Set Arasan PHY for different modes */
+static int arasan_phy_set(struct sdhci_host *host, u8 mode, u8 otap,
+			  u8 drv_type, u8 itap, u8 trim, u8 clk)
+{
+	u8 val;
+	int ret;
+
+	if (mode == HISPD_MODE || mode == HS200_MODE)
+		ret = arasan_phy_write(host, 0x0, MODE_CTRL);
+	else
+		ret = arasan_phy_write(host, mode, MODE_CTRL);
+	if (ret)
+		return ret;
+	if (mode == HS400_MODE || mode == HS200_MODE) {
+		ret = arasan_phy_read(host, IPAD_CTRL1, &val);
+		if (ret)
+			return ret;
+		ret = arasan_phy_write(host, IOPAD(val, drv_type), IPAD_CTRL1);
+		if (ret)
+			return ret;
+	}
+	if (mode == LEGACY_MODE) {
+		ret = arasan_phy_write(host, 0x0, OTAP_DELAY);
+		if (ret)
+			return ret;
+		ret = arasan_phy_write(host, 0x0, ITAP_DELAY);
+	} else {
+		ret = arasan_phy_write(host, OTAPDLY(otap), OTAP_DELAY);
+		if (ret)
+			return ret;
+		if (mode != HS200_MODE)
+			ret = arasan_phy_write(host, ITAPDLY(itap), ITAP_DELAY);
+		else
+			ret = arasan_phy_write(host, 0x0, ITAP_DELAY);
+	}
+	if (ret)
+		return ret;
+	if (mode != LEGACY_MODE) {
+		ret = arasan_phy_write(host, trim, DLL_TRIM);
+		if (ret)
+			return ret;
+	}
+	ret = arasan_phy_write(host, 0, DLL_STATUS);
+	if (ret)
+		return ret;
+	if (mode != LEGACY_MODE) {
+		ret = arasan_phy_write(host, FREQSEL(clk), DLL_STATUS);
+		if (ret)
+			return ret;
+		ret = arasan_phy_sts_poll(host, DLL_STATUS, DLL_RDY_MASK);
+		if (ret)
+			return -EBUSY;
+	}
+	return 0;
+}
+
+static int arasan_select_phy_clock(struct sdhci_host *host)
+{
+	struct sdhci_pci_slot *slot = sdhci_priv(host);
+	struct arasan_host *arasan_host = sdhci_pci_priv(slot);
+	u8 clk;
+
+	if (arasan_host->chg_clk == host->mmc->ios.clock)
+		return 0;
+
+	arasan_host->chg_clk = host->mmc->ios.clock;
+	if (host->mmc->ios.clock == 200000000)
+		clk = 0x0;
+	else if (host->mmc->ios.clock == 100000000)
+		clk = 0x2;
+	else if (host->mmc->ios.clock == 50000000)
+		clk = 0x1;
+	else
+		clk = 0x0;
+
+	if (host->mmc_host_ops.hs400_enhanced_strobe) {
+		arasan_phy_set(host, ENHSTRB_MODE, 1, 0x0, 0x0,
+			       DLLTRM_ICP, clk);
+	} else {
+		switch (host->mmc->ios.timing) {
+		case MMC_TIMING_LEGACY:
+			arasan_phy_set(host, LEGACY_MODE, 0x0, 0x0, 0x0,
+				       0x0, 0x0);
+			break;
+		case MMC_TIMING_MMC_HS:
+		case MMC_TIMING_SD_HS:
+			arasan_phy_set(host, HISPD_MODE, 0x3, 0x0, 0x2,
+				       DLLTRM_ICP, clk);
+			break;
+		case MMC_TIMING_MMC_HS200:
+		case MMC_TIMING_UHS_SDR104:
+			arasan_phy_set(host, HS200_MODE, 0x2,
+				       host->mmc->ios.drv_type, 0x0,
+				       DLLTRM_ICP, clk);
+			break;
+		case MMC_TIMING_MMC_DDR52:
+		case MMC_TIMING_UHS_DDR50:
+			arasan_phy_set(host, DDR50_MODE, 0x1, 0x0,
+				       0x0, DLLTRM_ICP, clk);
+			break;
+		case MMC_TIMING_MMC_HS400:
+			arasan_phy_set(host, HS400_MODE, 0x1,
+				       host->mmc->ios.drv_type, 0xa,
+				       DLLTRM_ICP, clk);
+			break;
+		default:
+			break;
+		}
+	}
+	return 0;
+}
+
+static int arasan_pci_probe_slot(struct sdhci_pci_slot *slot)
+{
+	int err;
+
+	slot->host->mmc->caps |= MMC_CAP_NONREMOVABLE | MMC_CAP_8_BIT_DATA;
+	err = arasan_phy_init(slot->host);
+	if (err)
+		return -ENODEV;
+	return 0;
+}
+
+static void arasan_sdhci_set_clock(struct sdhci_host *host, unsigned int clock)
+{
+	sdhci_set_clock(host, clock);
+
+	/* Change phy settings for the new clock */
+	arasan_select_phy_clock(host);
+}
+
+static const struct sdhci_ops arasan_sdhci_pci_ops = {
+	.set_clock	= arasan_sdhci_set_clock,
+	.enable_dma	= sdhci_pci_enable_dma,
+	.set_bus_width	= sdhci_set_bus_width,
+	.reset		= sdhci_reset,
+	.set_uhs_signaling	= sdhci_set_uhs_signaling,
+};
+
+const struct sdhci_pci_fixes sdhci_arasan = {
+	.probe_slot = arasan_pci_probe_slot,
+	.ops        = &arasan_sdhci_pci_ops,
+	.priv_size  = sizeof(struct arasan_host),
+};
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 3e4f04fd5175..6d1a983e6227 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -30,17 +30,37 @@
 #include <linux/mmc/sdhci-pci-data.h>
 #include <linux/acpi.h>
 
+#include "cqhci.h"
+
 #include "sdhci.h"
 #include "sdhci-pci.h"
 
-static int sdhci_pci_enable_dma(struct sdhci_host *host);
 static void sdhci_pci_hw_reset(struct sdhci_host *host);
 
 #ifdef CONFIG_PM_SLEEP
-static int __sdhci_pci_suspend_host(struct sdhci_pci_chip *chip)
+static int sdhci_pci_init_wakeup(struct sdhci_pci_chip *chip)
+{
+	mmc_pm_flag_t pm_flags = 0;
+	int i;
+
+	for (i = 0; i < chip->num_slots; i++) {
+		struct sdhci_pci_slot *slot = chip->slots[i];
+
+		if (slot)
+			pm_flags |= slot->host->mmc->pm_flags;
+	}
+
+	return device_set_wakeup_enable(&chip->pdev->dev,
+					(pm_flags & MMC_PM_KEEP_POWER) &&
+					(pm_flags & MMC_PM_WAKE_SDIO_IRQ));
+}
+
+static int sdhci_pci_suspend_host(struct sdhci_pci_chip *chip)
 {
 	int i, ret;
 
+	sdhci_pci_init_wakeup(chip);
+
 	for (i = 0; i < chip->num_slots; i++) {
 		struct sdhci_pci_slot *slot = chip->slots[i];
 		struct sdhci_host *host;
@@ -56,9 +76,6 @@ static int __sdhci_pci_suspend_host(struct sdhci_pci_chip *chip)
 		ret = sdhci_suspend_host(host);
 		if (ret)
 			goto err_pci_suspend;
-
-		if (host->mmc->pm_flags & MMC_PM_WAKE_SDIO_IRQ)
-			sdhci_enable_irq_wakeups(host);
 	}
 
 	return 0;
@@ -69,52 +86,44 @@ err_pci_suspend:
 	return ret;
 }
 
-static int sdhci_pci_init_wakeup(struct sdhci_pci_chip *chip)
+int sdhci_pci_resume_host(struct sdhci_pci_chip *chip)
 {
-	mmc_pm_flag_t pm_flags = 0;
-	int i;
+	struct sdhci_pci_slot *slot;
+	int i, ret;
 
 	for (i = 0; i < chip->num_slots; i++) {
-		struct sdhci_pci_slot *slot = chip->slots[i];
+		slot = chip->slots[i];
+		if (!slot)
+			continue;
 
-		if (slot)
-			pm_flags |= slot->host->mmc->pm_flags;
+		ret = sdhci_resume_host(slot->host);
+		if (ret)
+			return ret;
 	}
 
-	return device_init_wakeup(&chip->pdev->dev,
-				  (pm_flags & MMC_PM_KEEP_POWER) &&
-				  (pm_flags & MMC_PM_WAKE_SDIO_IRQ));
+	return 0;
 }
 
-static int sdhci_pci_suspend_host(struct sdhci_pci_chip *chip)
+static int sdhci_cqhci_suspend(struct sdhci_pci_chip *chip)
 {
 	int ret;
 
-	ret = __sdhci_pci_suspend_host(chip);
+	ret = cqhci_suspend(chip->slots[0]->host->mmc);
 	if (ret)
 		return ret;
 
-	sdhci_pci_init_wakeup(chip);
-
-	return 0;
+	return sdhci_pci_suspend_host(chip);
 }
 
-int sdhci_pci_resume_host(struct sdhci_pci_chip *chip)
+static int sdhci_cqhci_resume(struct sdhci_pci_chip *chip)
 {
-	struct sdhci_pci_slot *slot;
-	int i, ret;
-
-	for (i = 0; i < chip->num_slots; i++) {
-		slot = chip->slots[i];
-		if (!slot)
-			continue;
+	int ret;
 
-		ret = sdhci_resume_host(slot->host);
-		if (ret)
-			return ret;
-	}
+	ret = sdhci_pci_resume_host(chip);
+	if (ret)
+		return ret;
 
-	return 0;
+	return cqhci_resume(chip->slots[0]->host->mmc);
 }
 #endif
 
@@ -166,8 +175,48 @@ static int sdhci_pci_runtime_resume_host(struct sdhci_pci_chip *chip)
 
 	return 0;
 }
+
+static int sdhci_cqhci_runtime_suspend(struct sdhci_pci_chip *chip)
+{
+	int ret;
+
+	ret = cqhci_suspend(chip->slots[0]->host->mmc);
+	if (ret)
+		return ret;
+
+	return sdhci_pci_runtime_suspend_host(chip);
+}
+
+static int sdhci_cqhci_runtime_resume(struct sdhci_pci_chip *chip)
+{
+	int ret;
+
+	ret = sdhci_pci_runtime_resume_host(chip);
+	if (ret)
+		return ret;
+
+	return cqhci_resume(chip->slots[0]->host->mmc);
+}
 #endif
 
+static u32 sdhci_cqhci_irq(struct sdhci_host *host, u32 intmask)
+{
+	int cmd_error = 0;
+	int data_error = 0;
+
+	if (!sdhci_cqe_irq(host, intmask, &cmd_error, &data_error))
+		return intmask;
+
+	cqhci_irq(host->mmc, intmask, cmd_error, data_error);
+
+	return 0;
+}
+
+static void sdhci_pci_dumpregs(struct mmc_host *mmc)
+{
+	sdhci_dumpregs(mmc_priv(mmc));
+}
+
 /*****************************************************************************\
  *                                                                           *
  * Hardware specific quirk handling                                          *
@@ -583,6 +632,18 @@ static const struct sdhci_ops sdhci_intel_byt_ops = {
 	.voltage_switch		= sdhci_intel_voltage_switch,
 };
 
+static const struct sdhci_ops sdhci_intel_glk_ops = {
+	.set_clock		= sdhci_set_clock,
+	.set_power		= sdhci_intel_set_power,
+	.enable_dma		= sdhci_pci_enable_dma,
+	.set_bus_width		= sdhci_set_bus_width,
+	.reset			= sdhci_reset,
+	.set_uhs_signaling	= sdhci_set_uhs_signaling,
+	.hw_reset		= sdhci_pci_hw_reset,
+	.voltage_switch		= sdhci_intel_voltage_switch,
+	.irq			= sdhci_cqhci_irq,
+};
+
 static void byt_read_dsm(struct sdhci_pci_slot *slot)
 {
 	struct intel_host *intel_host = sdhci_pci_priv(slot);
@@ -612,12 +673,80 @@ static int glk_emmc_probe_slot(struct sdhci_pci_slot *slot)
 {
 	int ret = byt_emmc_probe_slot(slot);
 
+	slot->host->mmc->caps2 |= MMC_CAP2_CQE;
+
 	if (slot->chip->pdev->device != PCI_DEVICE_ID_INTEL_GLK_EMMC) {
 		slot->host->mmc->caps2 |= MMC_CAP2_HS400_ES,
 		slot->host->mmc_host_ops.hs400_enhanced_strobe =
 						intel_hs400_enhanced_strobe;
+		slot->host->mmc->caps2 |= MMC_CAP2_CQE_DCMD;
+	}
+
+	return ret;
+}
+
+static void glk_cqe_enable(struct mmc_host *mmc)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	u32 reg;
+
+	/*
+	 * CQE gets stuck if it sees Buffer Read Enable bit set, which can be
+	 * the case after tuning, so ensure the buffer is drained.
+	 */
+	reg = sdhci_readl(host, SDHCI_PRESENT_STATE);
+	while (reg & SDHCI_DATA_AVAILABLE) {
+		sdhci_readl(host, SDHCI_BUFFER);
+		reg = sdhci_readl(host, SDHCI_PRESENT_STATE);
 	}
 
+	sdhci_cqe_enable(mmc);
+}
+
+static const struct cqhci_host_ops glk_cqhci_ops = {
+	.enable		= glk_cqe_enable,
+	.disable	= sdhci_cqe_disable,
+	.dumpregs	= sdhci_pci_dumpregs,
+};
+
+static int glk_emmc_add_host(struct sdhci_pci_slot *slot)
+{
+	struct device *dev = &slot->chip->pdev->dev;
+	struct sdhci_host *host = slot->host;
+	struct cqhci_host *cq_host;
+	bool dma64;
+	int ret;
+
+	ret = sdhci_setup_host(host);
+	if (ret)
+		return ret;
+
+	cq_host = devm_kzalloc(dev, sizeof(*cq_host), GFP_KERNEL);
+	if (!cq_host) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	cq_host->mmio = host->ioaddr + 0x200;
+	cq_host->quirks |= CQHCI_QUIRK_SHORT_TXFR_DESC_SZ;
+	cq_host->ops = &glk_cqhci_ops;
+
+	dma64 = host->flags & SDHCI_USE_64_BIT_DMA;
+	if (dma64)
+		cq_host->caps |= CQHCI_TASK_DESC_SZ_128;
+
+	ret = cqhci_init(cq_host, host->mmc, dma64);
+	if (ret)
+		goto cleanup;
+
+	ret = __sdhci_add_host(host);
+	if (ret)
+		goto cleanup;
+
+	return 0;
+
+cleanup:
+	sdhci_cleanup_host(host);
 	return ret;
 }
 
@@ -699,11 +828,20 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_emmc = {
 static const struct sdhci_pci_fixes sdhci_intel_glk_emmc = {
 	.allow_runtime_pm	= true,
 	.probe_slot		= glk_emmc_probe_slot,
+	.add_host		= glk_emmc_add_host,
+#ifdef CONFIG_PM_SLEEP
+	.suspend		= sdhci_cqhci_suspend,
+	.resume			= sdhci_cqhci_resume,
+#endif
+#ifdef CONFIG_PM
+	.runtime_suspend	= sdhci_cqhci_runtime_suspend,
+	.runtime_resume		= sdhci_cqhci_runtime_resume,
+#endif
 	.quirks			= SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
 	.quirks2		= SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
 				  SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400 |
 				  SDHCI_QUIRK2_STOP_WITH_TC,
-	.ops			= &sdhci_intel_byt_ops,
+	.ops			= &sdhci_intel_glk_ops,
 	.priv_size		= sizeof(struct intel_host),
 };
 
@@ -778,6 +916,8 @@ static int intel_mrfld_mmc_probe_slot(struct sdhci_pci_slot *slot)
 		slot->host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
 		break;
 	case INTEL_MRFLD_SDIO:
+		/* Advertise 2.0v for compatibility with the SDIO card's OCR */
+		slot->host->ocr_mask = MMC_VDD_20_21 | MMC_VDD_165_195;
 		slot->host->mmc->caps |= MMC_CAP_NONREMOVABLE |
 					 MMC_CAP_POWER_OFF_CARD;
 		break;
@@ -955,7 +1095,7 @@ static int jmicron_suspend(struct sdhci_pci_chip *chip)
 {
 	int i, ret;
 
-	ret = __sdhci_pci_suspend_host(chip);
+	ret = sdhci_pci_suspend_host(chip);
 	if (ret)
 		return ret;
 
@@ -965,8 +1105,6 @@ static int jmicron_suspend(struct sdhci_pci_chip *chip)
 			jmicron_enable_mmc(chip->slots[i]->host, 0);
 	}
 
-	sdhci_pci_init_wakeup(chip);
-
 	return 0;
 }
 
@@ -1306,6 +1444,7 @@ static const struct pci_device_id pci_ids[] = {
 	SDHCI_PCI_DEVICE(O2, SDS1,     o2),
 	SDHCI_PCI_DEVICE(O2, SEABIRD0, o2),
 	SDHCI_PCI_DEVICE(O2, SEABIRD1, o2),
+	SDHCI_PCI_DEVICE(ARASAN, PHY_EMMC, arasan),
 	SDHCI_PCI_DEVICE_CLASS(AMD, SYSTEM_SDHCI, PCI_CLASS_MASK, amd),
 	/* Generic SD host controller */
 	{PCI_DEVICE_CLASS(SYSTEM_SDHCI, PCI_CLASS_MASK)},
@@ -1320,7 +1459,7 @@ MODULE_DEVICE_TABLE(pci, pci_ids);
  *                                                                           *
 \*****************************************************************************/
 
-static int sdhci_pci_enable_dma(struct sdhci_host *host)
+int sdhci_pci_enable_dma(struct sdhci_host *host)
 {
 	struct sdhci_pci_slot *slot;
 	struct pci_dev *pdev;
@@ -1543,10 +1682,13 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
 		}
 	}
 
-	host->mmc->pm_caps = MMC_PM_KEEP_POWER | MMC_PM_WAKE_SDIO_IRQ;
+	host->mmc->pm_caps = MMC_PM_KEEP_POWER;
 	host->mmc->slotno = slotno;
 	host->mmc->caps2 |= MMC_CAP2_NO_PRESCAN_POWERUP;
 
+	if (device_can_wakeup(&pdev->dev))
+		host->mmc->pm_caps |= MMC_PM_WAKE_SDIO_IRQ;
+
 	if (slot->cd_idx >= 0) {
 		ret = mmc_gpiod_request_cd(host->mmc, NULL, slot->cd_idx,
 					   slot->cd_override_level, 0, NULL);
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index 0056f08a29cc..5cbcdc448f98 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -55,6 +55,9 @@
 
 #define PCI_SUBDEVICE_ID_NI_7884	0x7884
 
+#define PCI_VENDOR_ID_ARASAN		0x16e6
+#define PCI_DEVICE_ID_ARASAN_PHY_EMMC	0x0670
+
 /*
  * PCI device class and mask
  */
@@ -170,11 +173,13 @@ static inline void *sdhci_pci_priv(struct sdhci_pci_slot *slot)
 #ifdef CONFIG_PM_SLEEP
 int sdhci_pci_resume_host(struct sdhci_pci_chip *chip);
 #endif
-
+int sdhci_pci_enable_dma(struct sdhci_host *host);
 int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot);
 int sdhci_pci_o2_probe(struct sdhci_pci_chip *chip);
 #ifdef CONFIG_PM_SLEEP
 int sdhci_pci_o2_resume(struct sdhci_pci_chip *chip);
 #endif
 
+extern const struct sdhci_pci_fixes sdhci_arasan;
+
 #endif /* __SDHCI_PCI_H */
diff --git a/drivers/mmc/host/sdhci-spear.c b/drivers/mmc/host/sdhci-spear.c
index 8c0f88428556..14511526a3a8 100644
--- a/drivers/mmc/host/sdhci-spear.c
+++ b/drivers/mmc/host/sdhci-spear.c
@@ -82,6 +82,10 @@ static int sdhci_probe(struct platform_device *pdev)
 	host->hw_name = "sdhci";
 	host->ops = &sdhci_pltfm_ops;
 	host->irq = platform_get_irq(pdev, 0);
+	if (host->irq <= 0) {
+		ret = -EINVAL;
+		goto err_host;
+	}
 	host->quirks = SDHCI_QUIRK_BROKEN_ADMA;
 
 	sdhci = sdhci_priv(host);
diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c
index 0842bbc2d7ad..4d0791f6ec23 100644
--- a/drivers/mmc/host/sdhci-xenon.c
+++ b/drivers/mmc/host/sdhci-xenon.c
@@ -230,7 +230,14 @@ static void xenon_set_power(struct sdhci_host *host, unsigned char mode,
 		mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
 }
 
+static void xenon_voltage_switch(struct sdhci_host *host)
+{
+	/* Wait for 5ms after set 1.8V signal enable bit */
+	usleep_range(5000, 5500);
+}
+
 static const struct sdhci_ops sdhci_xenon_ops = {
+	.voltage_switch		= xenon_voltage_switch,
 	.set_clock		= sdhci_set_clock,
 	.set_power		= xenon_set_power,
 	.set_bus_width		= sdhci_set_bus_width,
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index e9290a3439d5..070aff9c108f 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1434,6 +1434,13 @@ void sdhci_set_power_noreg(struct sdhci_host *host, unsigned char mode,
 	if (mode != MMC_POWER_OFF) {
 		switch (1 << vdd) {
 		case MMC_VDD_165_195:
+		/*
+		 * Without a regulator, SDHCI does not support 2.0v
+		 * so we only get here if the driver deliberately
+		 * added the 2.0v range to ocr_avail. Map it to 1.8v
+		 * for the purpose of turning on the power.
+		 */
+		case MMC_VDD_20_21:
 			pwr = SDHCI_POWER_180;
 			break;
 		case MMC_VDD_29_30:
@@ -2821,25 +2828,33 @@ static irqreturn_t sdhci_thread_irq(int irq, void *dev_id)
  * sdhci_disable_irq_wakeups() since it will be set by
  * sdhci_enable_card_detection() or sdhci_init().
  */
-void sdhci_enable_irq_wakeups(struct sdhci_host *host)
+static bool sdhci_enable_irq_wakeups(struct sdhci_host *host)
 {
+	u8 mask = SDHCI_WAKE_ON_INSERT | SDHCI_WAKE_ON_REMOVE |
+		  SDHCI_WAKE_ON_INT;
+	u32 irq_val = 0;
+	u8 wake_val = 0;
 	u8 val;
-	u8 mask = SDHCI_WAKE_ON_INSERT | SDHCI_WAKE_ON_REMOVE
-			| SDHCI_WAKE_ON_INT;
-	u32 irq_val = SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE |
-		      SDHCI_INT_CARD_INT;
 
-	val = sdhci_readb(host, SDHCI_WAKE_UP_CONTROL);
-	val |= mask ;
-	/* Avoid fake wake up */
-	if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) {
-		val &= ~(SDHCI_WAKE_ON_INSERT | SDHCI_WAKE_ON_REMOVE);
-		irq_val &= ~(SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE);
+	if (!(host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION)) {
+		wake_val |= SDHCI_WAKE_ON_INSERT | SDHCI_WAKE_ON_REMOVE;
+		irq_val |= SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE;
 	}
+
+	wake_val |= SDHCI_WAKE_ON_INT;
+	irq_val |= SDHCI_INT_CARD_INT;
+
+	val = sdhci_readb(host, SDHCI_WAKE_UP_CONTROL);
+	val &= ~mask;
+	val |= wake_val;
 	sdhci_writeb(host, val, SDHCI_WAKE_UP_CONTROL);
+
 	sdhci_writel(host, irq_val, SDHCI_INT_ENABLE);
+
+	host->irq_wake_enabled = !enable_irq_wake(host->irq);
+
+	return host->irq_wake_enabled;
 }
-EXPORT_SYMBOL_GPL(sdhci_enable_irq_wakeups);
 
 static void sdhci_disable_irq_wakeups(struct sdhci_host *host)
 {
@@ -2850,6 +2865,10 @@ static void sdhci_disable_irq_wakeups(struct sdhci_host *host)
 	val = sdhci_readb(host, SDHCI_WAKE_UP_CONTROL);
 	val &= ~mask;
 	sdhci_writeb(host, val, SDHCI_WAKE_UP_CONTROL);
+
+	disable_irq_wake(host->irq);
+
+	host->irq_wake_enabled = false;
 }
 
 int sdhci_suspend_host(struct sdhci_host *host)
@@ -2858,15 +2877,14 @@ int sdhci_suspend_host(struct sdhci_host *host)
 
 	mmc_retune_timer_stop(host->mmc);
 
-	if (!device_may_wakeup(mmc_dev(host->mmc))) {
+	if (!device_may_wakeup(mmc_dev(host->mmc)) ||
+	    !sdhci_enable_irq_wakeups(host)) {
 		host->ier = 0;
 		sdhci_writel(host, 0, SDHCI_INT_ENABLE);
 		sdhci_writel(host, 0, SDHCI_SIGNAL_ENABLE);
 		free_irq(host->irq, host);
-	} else {
-		sdhci_enable_irq_wakeups(host);
-		enable_irq_wake(host->irq);
 	}
+
 	return 0;
 }
 
@@ -2894,15 +2912,14 @@ int sdhci_resume_host(struct sdhci_host *host)
 		mmiowb();
 	}
 
-	if (!device_may_wakeup(mmc_dev(host->mmc))) {
+	if (host->irq_wake_enabled) {
+		sdhci_disable_irq_wakeups(host);
+	} else {
 		ret = request_threaded_irq(host->irq, sdhci_irq,
 					   sdhci_thread_irq, IRQF_SHARED,
 					   mmc_hostname(host->mmc), host);
 		if (ret)
 			return ret;
-	} else {
-		sdhci_disable_irq_wakeups(host);
-		disable_irq_wake(host->irq);
 	}
 
 	sdhci_enable_card_detection(host);
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 54bc444c317f..afab26fd70e6 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -484,6 +484,7 @@ struct sdhci_host {
 	bool bus_on;		/* Bus power prevents runtime suspend */
 	bool preset_enabled;	/* Preset is enabled */
 	bool pending_reset;	/* Cmd/data reset is pending */
+	bool irq_wake_enabled;	/* IRQ wakeup is enabled */
 
 	struct mmc_request *mrqs_done[SDHCI_MAX_MRQS];	/* Requests done */
 	struct mmc_command *cmd;	/* Current command */
@@ -718,7 +719,6 @@ void sdhci_enable_sdio_irq(struct mmc_host *mmc, int enable);
 #ifdef CONFIG_PM
 int sdhci_suspend_host(struct sdhci_host *host);
 int sdhci_resume_host(struct sdhci_host *host);
-void sdhci_enable_irq_wakeups(struct sdhci_host *host);
 int sdhci_runtime_suspend_host(struct sdhci_host *host);
 int sdhci_runtime_resume_host(struct sdhci_host *host);
 #endif
diff --git a/drivers/mmc/host/sdhci_f_sdh30.c b/drivers/mmc/host/sdhci_f_sdh30.c
index 04ca0d33a521..485f7591fae4 100644
--- a/drivers/mmc/host/sdhci_f_sdh30.c
+++ b/drivers/mmc/host/sdhci_f_sdh30.c
@@ -10,9 +10,11 @@
  * the Free Software Foundation, version 2 of the License.
  */
 
+#include <linux/acpi.h>
 #include <linux/err.h>
 #include <linux/delay.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/property.h>
 #include <linux/clk.h>
 
@@ -146,7 +148,6 @@ static int sdhci_f_sdh30_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, host);
 
-	sdhci_get_of_property(pdev);
 	host->hw_name = "f_sdh30";
 	host->ops = &sdhci_f_sdh30_ops;
 	host->irq = irq;
@@ -158,25 +159,29 @@ static int sdhci_f_sdh30_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	priv->clk_iface = devm_clk_get(&pdev->dev, "iface");
-	if (IS_ERR(priv->clk_iface)) {
-		ret = PTR_ERR(priv->clk_iface);
-		goto err;
-	}
+	if (dev_of_node(dev)) {
+		sdhci_get_of_property(pdev);
 
-	ret = clk_prepare_enable(priv->clk_iface);
-	if (ret)
-		goto err;
+		priv->clk_iface = devm_clk_get(&pdev->dev, "iface");
+		if (IS_ERR(priv->clk_iface)) {
+			ret = PTR_ERR(priv->clk_iface);
+			goto err;
+		}
 
-	priv->clk = devm_clk_get(&pdev->dev, "core");
-	if (IS_ERR(priv->clk)) {
-		ret = PTR_ERR(priv->clk);
-		goto err_clk;
-	}
+		ret = clk_prepare_enable(priv->clk_iface);
+		if (ret)
+			goto err;
 
-	ret = clk_prepare_enable(priv->clk);
-	if (ret)
-		goto err_clk;
+		priv->clk = devm_clk_get(&pdev->dev, "core");
+		if (IS_ERR(priv->clk)) {
+			ret = PTR_ERR(priv->clk);
+			goto err_clk;
+		}
+
+		ret = clk_prepare_enable(priv->clk);
+		if (ret)
+			goto err_clk;
+	}
 
 	/* init vendor specific regs */
 	ctrl = sdhci_readw(host, F_SDH30_AHB_CONFIG);
@@ -226,16 +231,27 @@ static int sdhci_f_sdh30_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_OF
 static const struct of_device_id f_sdh30_dt_ids[] = {
 	{ .compatible = "fujitsu,mb86s70-sdhci-3.0" },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, f_sdh30_dt_ids);
+#endif
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id f_sdh30_acpi_ids[] = {
+	{ "SCX0002" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(acpi, f_sdh30_acpi_ids);
+#endif
 
 static struct platform_driver sdhci_f_sdh30_driver = {
 	.driver = {
 		.name = "f_sdh30",
-		.of_match_table = f_sdh30_dt_ids,
+		.of_match_table = of_match_ptr(f_sdh30_dt_ids),
+		.acpi_match_table = ACPI_PTR(f_sdh30_acpi_ids),
 		.pm	= &sdhci_pltfm_pmops,
 	},
 	.probe	= sdhci_f_sdh30_probe,
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 53fb18bb7bee..7bb00c68a756 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -916,7 +916,7 @@ static void sh_mmcif_start_cmd(struct sh_mmcif_host *host,
 			       struct mmc_request *mrq)
 {
 	struct mmc_command *cmd = mrq->cmd;
-	u32 opc = cmd->opcode;
+	u32 opc;
 	u32 mask = 0;
 	unsigned long flags;
 
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index cc98355dbdb9..bad612d6f879 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -3,7 +3,7 @@
  * (C) Copyright 2007-2011 Reuuimlla Technology Co., Ltd.
  * (C) Copyright 2007-2011 Aaron Maoye <leafy.myeh@reuuimllatech.com>
  * (C) Copyright 2013-2014 O2S GmbH <www.o2s.ch>
- * (C) Copyright 2013-2014 David Lanzend�rfer <david.lanzendoerfer@o2s.ch>
+ * (C) Copyright 2013-2014 David Lanzendörfer <david.lanzendoerfer@o2s.ch>
  * (C) Copyright 2013-2014 Hans de Goede <hdegoede@redhat.com>
  * (C) Copyright 2017 Sootech SA
  *
@@ -1255,6 +1255,11 @@ static int sunxi_mmc_resource_request(struct sunxi_mmc_host *host,
 		goto error_assert_reset;
 
 	host->irq = platform_get_irq(pdev, 0);
+	if (host->irq <= 0) {
+		ret = -EINVAL;
+		goto error_assert_reset;
+	}
+
 	return devm_request_threaded_irq(&pdev->dev, host->irq, sunxi_mmc_irq,
 			sunxi_mmc_handle_manual_stop, 0, "sunxi-mmc", host);
 
@@ -1393,5 +1398,5 @@ module_platform_driver(sunxi_mmc_driver);
 
 MODULE_DESCRIPTION("Allwinner's SD/MMC Card Controller Driver");
 MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("David Lanzend�rfer <david.lanzendoerfer@o2s.ch>");
+MODULE_AUTHOR("David Lanzendörfer <david.lanzendoerfer@o2s.ch>");
 MODULE_ALIAS("platform:sunxi-mmc");
diff --git a/drivers/mmc/host/tmio_mmc.c b/drivers/mmc/host/tmio_mmc.c
index 64b7e9f18361..43a2ea5cff24 100644
--- a/drivers/mmc/host/tmio_mmc.c
+++ b/drivers/mmc/host/tmio_mmc.c
@@ -92,14 +92,19 @@ static int tmio_mmc_probe(struct platform_device *pdev)
 
 	pdata->flags |= TMIO_MMC_HAVE_HIGH_REG;
 
-	host = tmio_mmc_host_alloc(pdev);
-	if (!host)
+	host = tmio_mmc_host_alloc(pdev, pdata);
+	if (IS_ERR(host)) {
+		ret = PTR_ERR(host);
 		goto cell_disable;
+	}
 
 	/* SD control register space size is 0x200, 0x400 for bus_shift=1 */
 	host->bus_shift = resource_size(res) >> 10;
 
-	ret = tmio_mmc_host_probe(host, pdata, NULL);
+	host->mmc->f_max = pdata->hclk;
+	host->mmc->f_min = pdata->hclk / 512;
+
+	ret = tmio_mmc_host_probe(host);
 	if (ret)
 		goto host_free;
 
@@ -128,15 +133,11 @@ out:
 static int tmio_mmc_remove(struct platform_device *pdev)
 {
 	const struct mfd_cell *cell = mfd_get_cell(pdev);
-	struct mmc_host *mmc = platform_get_drvdata(pdev);
+	struct tmio_mmc_host *host = platform_get_drvdata(pdev);
 
-	if (mmc) {
-		struct tmio_mmc_host *host = mmc_priv(mmc);
-
-		tmio_mmc_host_remove(host);
-		if (cell->disable)
-			cell->disable(pdev);
-	}
+	tmio_mmc_host_remove(host);
+	if (cell->disable)
+		cell->disable(pdev);
 
 	return 0;
 }
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 3e6ff8921440..e7d651352dc9 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -112,12 +112,6 @@
 struct tmio_mmc_data;
 struct tmio_mmc_host;
 
-struct tmio_mmc_dma {
-	enum dma_slave_buswidth dma_buswidth;
-	bool (*filter)(struct dma_chan *chan, void *arg);
-	void (*enable)(struct tmio_mmc_host *host, bool enable);
-};
-
 struct tmio_mmc_dma_ops {
 	void (*start)(struct tmio_mmc_host *host, struct mmc_data *data);
 	void (*enable)(struct tmio_mmc_host *host, bool enable);
@@ -134,6 +128,7 @@ struct tmio_mmc_host {
 	struct mmc_request      *mrq;
 	struct mmc_data         *data;
 	struct mmc_host         *mmc;
+	struct mmc_host_ops     ops;
 
 	/* Callbacks for clock / power control */
 	void (*set_pwr)(struct platform_device *host, int state);
@@ -144,18 +139,15 @@ struct tmio_mmc_host {
 	struct scatterlist      *sg_orig;
 	unsigned int            sg_len;
 	unsigned int            sg_off;
-	unsigned long		bus_shift;
+	unsigned int		bus_shift;
 
 	struct platform_device *pdev;
 	struct tmio_mmc_data *pdata;
-	struct tmio_mmc_dma	*dma;
 
 	/* DMA support */
 	bool			force_pio;
 	struct dma_chan		*chan_rx;
 	struct dma_chan		*chan_tx;
-	struct completion	dma_dataend;
-	struct tasklet_struct	dma_complete;
 	struct tasklet_struct	dma_issue;
 	struct scatterlist	bounce_sg;
 	u8			*bounce_buf;
@@ -174,7 +166,6 @@ struct tmio_mmc_host {
 	struct mutex		ios_lock;	/* protect set_ios() context */
 	bool			native_hotplug;
 	bool			sdio_irq_enabled;
-	u32			scc_tappos;
 
 	/* Mandatory callback */
 	int (*clk_enable)(struct tmio_mmc_host *host);
@@ -185,9 +176,6 @@ struct tmio_mmc_host {
 	void (*clk_disable)(struct tmio_mmc_host *host);
 	int (*multi_io_quirk)(struct mmc_card *card,
 			      unsigned int direction, int blk_size);
-	int (*card_busy)(struct mmc_host *mmc);
-	int (*start_signal_voltage_switch)(struct mmc_host *mmc,
-					   struct mmc_ios *ios);
 	int (*write16_hook)(struct tmio_mmc_host *host, int addr);
 	void (*hw_reset)(struct tmio_mmc_host *host);
 	void (*prepare_tuning)(struct tmio_mmc_host *host, unsigned long tap);
@@ -207,11 +195,10 @@ struct tmio_mmc_host {
 	const struct tmio_mmc_dma_ops *dma_ops;
 };
 
-struct tmio_mmc_host *tmio_mmc_host_alloc(struct platform_device *pdev);
+struct tmio_mmc_host *tmio_mmc_host_alloc(struct platform_device *pdev,
+					  struct tmio_mmc_data *pdata);
 void tmio_mmc_host_free(struct tmio_mmc_host *host);
-int tmio_mmc_host_probe(struct tmio_mmc_host *host,
-			struct tmio_mmc_data *pdata,
-			const struct tmio_mmc_dma_ops *dma_ops);
+int tmio_mmc_host_probe(struct tmio_mmc_host *host);
 void tmio_mmc_host_remove(struct tmio_mmc_host *host);
 void tmio_mmc_do_data_irq(struct tmio_mmc_host *host);
 
@@ -240,26 +227,26 @@ int tmio_mmc_host_runtime_resume(struct device *dev);
 
 static inline u16 sd_ctrl_read16(struct tmio_mmc_host *host, int addr)
 {
-	return readw(host->ctl + (addr << host->bus_shift));
+	return ioread16(host->ctl + (addr << host->bus_shift));
 }
 
 static inline void sd_ctrl_read16_rep(struct tmio_mmc_host *host, int addr,
 				      u16 *buf, int count)
 {
-	readsw(host->ctl + (addr << host->bus_shift), buf, count);
+	ioread16_rep(host->ctl + (addr << host->bus_shift), buf, count);
 }
 
 static inline u32 sd_ctrl_read16_and_16_as_32(struct tmio_mmc_host *host,
 					      int addr)
 {
-	return readw(host->ctl + (addr << host->bus_shift)) |
-	       readw(host->ctl + ((addr + 2) << host->bus_shift)) << 16;
+	return ioread16(host->ctl + (addr << host->bus_shift)) |
+	       ioread16(host->ctl + ((addr + 2) << host->bus_shift)) << 16;
 }
 
 static inline void sd_ctrl_read32_rep(struct tmio_mmc_host *host, int addr,
 				      u32 *buf, int count)
 {
-	readsl(host->ctl + (addr << host->bus_shift), buf, count);
+	ioread32_rep(host->ctl + (addr << host->bus_shift), buf, count);
 }
 
 static inline void sd_ctrl_write16(struct tmio_mmc_host *host, int addr,
@@ -270,26 +257,26 @@ static inline void sd_ctrl_write16(struct tmio_mmc_host *host, int addr,
 	 */
 	if (host->write16_hook && host->write16_hook(host, addr))
 		return;
-	writew(val, host->ctl + (addr << host->bus_shift));
+	iowrite16(val, host->ctl + (addr << host->bus_shift));
 }
 
 static inline void sd_ctrl_write16_rep(struct tmio_mmc_host *host, int addr,
 				       u16 *buf, int count)
 {
-	writesw(host->ctl + (addr << host->bus_shift), buf, count);
+	iowrite16_rep(host->ctl + (addr << host->bus_shift), buf, count);
 }
 
 static inline void sd_ctrl_write32_as_16_and_16(struct tmio_mmc_host *host,
 						int addr, u32 val)
 {
-	writew(val & 0xffff, host->ctl + (addr << host->bus_shift));
-	writew(val >> 16, host->ctl + ((addr + 2) << host->bus_shift));
+	iowrite16(val & 0xffff, host->ctl + (addr << host->bus_shift));
+	iowrite16(val >> 16, host->ctl + ((addr + 2) << host->bus_shift));
 }
 
 static inline void sd_ctrl_write32_rep(struct tmio_mmc_host *host, int addr,
 				       const u32 *buf, int count)
 {
-	writesl(host->ctl + (addr << host->bus_shift), buf, count);
+	iowrite32_rep(host->ctl + (addr << host->bus_shift), buf, count);
 }
 
 #endif
diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c
index 583bf3262df5..33494241245a 100644
--- a/drivers/mmc/host/tmio_mmc_core.c
+++ b/drivers/mmc/host/tmio_mmc_core.c
@@ -806,7 +806,7 @@ static int tmio_mmc_execute_tuning(struct mmc_host *mmc, u32 opcode)
 		if (ret == 0)
 			set_bit(i, host->taps);
 
-		mdelay(1);
+		usleep_range(1000, 1200);
 	}
 
 	ret = host->select_tuning(host);
@@ -926,20 +926,6 @@ static void tmio_mmc_done_work(struct work_struct *work)
 	tmio_mmc_finish_request(host);
 }
 
-static int tmio_mmc_clk_enable(struct tmio_mmc_host *host)
-{
-	if (!host->clk_enable)
-		return -ENOTSUPP;
-
-	return host->clk_enable(host);
-}
-
-static void tmio_mmc_clk_disable(struct tmio_mmc_host *host)
-{
-	if (host->clk_disable)
-		host->clk_disable(host);
-}
-
 static void tmio_mmc_power_on(struct tmio_mmc_host *host, unsigned short vdd)
 {
 	struct mmc_host *mmc = host->mmc;
@@ -958,7 +944,7 @@ static void tmio_mmc_power_on(struct tmio_mmc_host *host, unsigned short vdd)
 		 * 100us were not enough. Is this the same 140us delay, as in
 		 * tmio_mmc_set_ios()?
 		 */
-		udelay(200);
+		usleep_range(200, 300);
 	}
 	/*
 	 * It seems, VccQ should be switched on after Vcc, this is also what the
@@ -966,7 +952,7 @@ static void tmio_mmc_power_on(struct tmio_mmc_host *host, unsigned short vdd)
 	 */
 	if (!IS_ERR(mmc->supply.vqmmc) && !ret) {
 		ret = regulator_enable(mmc->supply.vqmmc);
-		udelay(200);
+		usleep_range(200, 300);
 	}
 
 	if (ret < 0)
@@ -1059,7 +1045,7 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	}
 
 	/* Let things settle. delay taken from winCE driver */
-	udelay(140);
+	usleep_range(140, 200);
 	if (PTR_ERR(host->mrq) == -EINTR)
 		dev_dbg(&host->pdev->dev,
 			"%s.%d: IOS interrupted: clk %u, mode %u",
@@ -1076,15 +1062,9 @@ static int tmio_mmc_get_ro(struct mmc_host *mmc)
 {
 	struct tmio_mmc_host *host = mmc_priv(mmc);
 	struct tmio_mmc_data *pdata = host->pdata;
-	int ret = mmc_gpio_get_ro(mmc);
-
-	if (ret >= 0)
-		return ret;
-
-	ret = !((pdata->flags & TMIO_MMC_WRPROTECT_DISABLE) ||
-		(sd_ctrl_read16_and_16_as_32(host, CTL_STATUS) & TMIO_STAT_WRPROTECT));
 
-	return ret;
+	return !((pdata->flags & TMIO_MMC_WRPROTECT_DISABLE) ||
+		 (sd_ctrl_read16_and_16_as_32(host, CTL_STATUS) & TMIO_STAT_WRPROTECT));
 }
 
 static int tmio_multi_io_quirk(struct mmc_card *card,
@@ -1098,7 +1078,7 @@ static int tmio_multi_io_quirk(struct mmc_card *card,
 	return blk_size;
 }
 
-static struct mmc_host_ops tmio_mmc_ops = {
+static const struct mmc_host_ops tmio_mmc_ops = {
 	.request	= tmio_mmc_request,
 	.set_ios	= tmio_mmc_set_ios,
 	.get_ro         = tmio_mmc_get_ro,
@@ -1145,19 +1125,45 @@ static void tmio_mmc_of_parse(struct platform_device *pdev,
 		pdata->flags |= TMIO_MMC_WRPROTECT_DISABLE;
 }
 
-struct tmio_mmc_host*
-tmio_mmc_host_alloc(struct platform_device *pdev)
+struct tmio_mmc_host *tmio_mmc_host_alloc(struct platform_device *pdev,
+					  struct tmio_mmc_data *pdata)
 {
 	struct tmio_mmc_host *host;
 	struct mmc_host *mmc;
+	struct resource *res;
+	void __iomem *ctl;
+	int ret;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ctl = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ctl))
+		return ERR_CAST(ctl);
 
 	mmc = mmc_alloc_host(sizeof(struct tmio_mmc_host), &pdev->dev);
 	if (!mmc)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	host = mmc_priv(mmc);
+	host->ctl = ctl;
 	host->mmc = mmc;
 	host->pdev = pdev;
+	host->pdata = pdata;
+	host->ops = tmio_mmc_ops;
+	mmc->ops = &host->ops;
+
+	ret = mmc_of_parse(host->mmc);
+	if (ret) {
+		host = ERR_PTR(ret);
+		goto free;
+	}
+
+	tmio_mmc_of_parse(pdev, pdata);
+
+	platform_set_drvdata(pdev, host);
+
+	return host;
+free:
+	mmc_free_host(mmc);
 
 	return host;
 }
@@ -1169,32 +1175,24 @@ void tmio_mmc_host_free(struct tmio_mmc_host *host)
 }
 EXPORT_SYMBOL_GPL(tmio_mmc_host_free);
 
-int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
-			struct tmio_mmc_data *pdata,
-			const struct tmio_mmc_dma_ops *dma_ops)
+int tmio_mmc_host_probe(struct tmio_mmc_host *_host)
 {
 	struct platform_device *pdev = _host->pdev;
+	struct tmio_mmc_data *pdata = _host->pdata;
 	struct mmc_host *mmc = _host->mmc;
-	struct resource *res_ctl;
 	int ret;
 	u32 irq_mask = TMIO_MASK_CMD;
 
-	tmio_mmc_of_parse(pdev, pdata);
+	/*
+	 * Check the sanity of mmc->f_min to prevent tmio_mmc_set_clock() from
+	 * looping forever...
+	 */
+	if (mmc->f_min == 0)
+		return -EINVAL;
 
 	if (!(pdata->flags & TMIO_MMC_HAS_IDLE_WAIT))
 		_host->write16_hook = NULL;
 
-	res_ctl = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res_ctl)
-		return -EINVAL;
-
-	ret = mmc_of_parse(mmc);
-	if (ret < 0)
-		return ret;
-
-	_host->pdata = pdata;
-	platform_set_drvdata(pdev, mmc);
-
 	_host->set_pwr = pdata->set_pwr;
 	_host->set_clk_div = pdata->set_clk_div;
 
@@ -1202,15 +1200,11 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 	if (ret < 0)
 		return ret;
 
-	_host->ctl = devm_ioremap(&pdev->dev,
-				  res_ctl->start, resource_size(res_ctl));
-	if (!_host->ctl)
-		return -ENOMEM;
-
-	tmio_mmc_ops.card_busy = _host->card_busy;
-	tmio_mmc_ops.start_signal_voltage_switch =
-		_host->start_signal_voltage_switch;
-	mmc->ops = &tmio_mmc_ops;
+	if (pdata->flags & TMIO_MMC_USE_GPIO_CD) {
+		ret = mmc_gpio_request_cd(mmc, pdata->cd_gpio, 0);
+		if (ret)
+			return ret;
+	}
 
 	mmc->caps |= MMC_CAP_4_BIT_DATA | pdata->capabilities;
 	mmc->caps2 |= pdata->capabilities2;
@@ -1233,7 +1227,10 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 	}
 	mmc->max_seg_size = mmc->max_req_size;
 
-	_host->native_hotplug = !(pdata->flags & TMIO_MMC_USE_GPIO_CD ||
+	if (mmc_can_gpio_ro(mmc))
+		_host->ops.get_ro = mmc_gpio_get_ro;
+
+	_host->native_hotplug = !(mmc_can_gpio_cd(mmc) ||
 				  mmc->caps & MMC_CAP_NEEDS_POLL ||
 				  !mmc_card_is_removable(mmc));
 
@@ -1246,18 +1243,6 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 	if (pdata->flags & TMIO_MMC_MIN_RCAR2)
 		_host->native_hotplug = true;
 
-	if (tmio_mmc_clk_enable(_host) < 0) {
-		mmc->f_max = pdata->hclk;
-		mmc->f_min = mmc->f_max / 512;
-	}
-
-	/*
-	 * Check the sanity of mmc->f_min to prevent tmio_mmc_set_clock() from
-	 * looping forever...
-	 */
-	if (mmc->f_min == 0)
-		return -EINVAL;
-
 	/*
 	 * While using internal tmio hardware logic for card detection, we need
 	 * to ensure it stays powered for it to work.
@@ -1293,7 +1278,6 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 	INIT_WORK(&_host->done, tmio_mmc_done_work);
 
 	/* See if we also get DMA */
-	_host->dma_ops = dma_ops;
 	tmio_mmc_request_dma(_host, pdata);
 
 	pm_runtime_set_active(&pdev->dev);
@@ -1307,14 +1291,6 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 
 	dev_pm_qos_expose_latency_limit(&pdev->dev, 100);
 
-	if (pdata->flags & TMIO_MMC_USE_GPIO_CD) {
-		ret = mmc_gpio_request_cd(mmc, pdata->cd_gpio, 0);
-		if (ret)
-			goto remove_host;
-
-		mmc_gpiod_request_cd_irq(mmc);
-	}
-
 	return 0;
 
 remove_host:
@@ -1343,16 +1319,27 @@ void tmio_mmc_host_remove(struct tmio_mmc_host *host)
 
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-
-	tmio_mmc_clk_disable(host);
 }
 EXPORT_SYMBOL_GPL(tmio_mmc_host_remove);
 
 #ifdef CONFIG_PM
+static int tmio_mmc_clk_enable(struct tmio_mmc_host *host)
+{
+	if (!host->clk_enable)
+		return -ENOTSUPP;
+
+	return host->clk_enable(host);
+}
+
+static void tmio_mmc_clk_disable(struct tmio_mmc_host *host)
+{
+	if (host->clk_disable)
+		host->clk_disable(host);
+}
+
 int tmio_mmc_host_runtime_suspend(struct device *dev)
 {
-	struct mmc_host *mmc = dev_get_drvdata(dev);
-	struct tmio_mmc_host *host = mmc_priv(mmc);
+	struct tmio_mmc_host *host = dev_get_drvdata(dev);
 
 	tmio_mmc_disable_mmc_irqs(host, TMIO_MASK_ALL);
 
@@ -1372,8 +1359,7 @@ static bool tmio_mmc_can_retune(struct tmio_mmc_host *host)
 
 int tmio_mmc_host_runtime_resume(struct device *dev)
 {
-	struct mmc_host *mmc = dev_get_drvdata(dev);
-	struct tmio_mmc_host *host = mmc_priv(mmc);
+	struct tmio_mmc_host *host = dev_get_drvdata(dev);
 
 	tmio_mmc_reset(host);
 	tmio_mmc_clk_enable(host);
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index e7743eca1021..85146235231e 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -324,6 +324,7 @@ struct mmc_host {
 #define MMC_CAP_DRIVER_TYPE_A	(1 << 23)	/* Host supports Driver Type A */
 #define MMC_CAP_DRIVER_TYPE_C	(1 << 24)	/* Host supports Driver Type C */
 #define MMC_CAP_DRIVER_TYPE_D	(1 << 25)	/* Host supports Driver Type D */
+#define MMC_CAP_DONE_COMPLETE	(1 << 27)	/* RW reqs can be completed within mmc_request_done() */
 #define MMC_CAP_CD_WAKE		(1 << 28)	/* Enable card detect wake */
 #define MMC_CAP_CMD_DURING_TFR	(1 << 29)	/* Commands during data transfer */
 #define MMC_CAP_CMD23		(1 << 30)	/* CMD23 supported. */
@@ -380,6 +381,7 @@ struct mmc_host {
 	unsigned int		doing_retune:1;	/* re-tuning in progress */
 	unsigned int		retune_now:1;	/* do re-tuning at next req */
 	unsigned int		retune_paused:1; /* re-tuning is temporarily disabled */
+	unsigned int		use_blk_mq:1;	/* use blk-mq */
 
 	int			rescan_disable;	/* disable card detection */
 	int			rescan_entered;	/* used with nonremovable devices */
@@ -422,9 +424,6 @@ struct mmc_host {
 
 	struct dentry		*debugfs_root;
 
-	struct mmc_async_req	*areq;		/* active async req */
-	struct mmc_context_info	context_info;	/* async synchronization info */
-
 	/* Ongoing data transfer that allows commands during transfer */
 	struct mmc_request	*ongoing_mrq;
 
diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h
index 82f0d289f110..91f1ba0663c8 100644
--- a/include/linux/mmc/slot-gpio.h
+++ b/include/linux/mmc/slot-gpio.h
@@ -33,5 +33,6 @@ void mmc_gpio_set_cd_isr(struct mmc_host *host,
 			 irqreturn_t (*isr)(int irq, void *dev_id));
 void mmc_gpiod_request_cd_irq(struct mmc_host *host);
 bool mmc_can_gpio_cd(struct mmc_host *host);
+bool mmc_can_gpio_ro(struct mmc_host *host);
 
 #endif