Merge tag 'mmc-v5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc

Pull MMC updates from Ulf Hansson:
 "MMC core:
   - Fix a few memoryleaks
   - Minor improvements to the card initialization sequence
   - Partially support sleepy GPIO controllers for pwrseq eMMC

  MMC host:
   - alcor: Work with multiple-entry sglists
   - alcor: Enable DMA for writes
   - meson-gx: Improve tuning support
   - meson-gx: Avoid clock glitch when switching to DDR modes
   - meson-gx: Disable unreliable HS400 mode
   - mmci: Minor updates for support of HW busy detection
   - mmci: Support data transfers for the stm32_sdmmc variant
   - mmci: Restructure code to better support different variants
   - mtk-sd: Add support for version found on MT7620 family SOCs
   - mtk-sd: Add support for the MT8516 version
   - mtk-sd: Add Chaotian Jing as the maintainer
   - sdhci: Reorganize request-code to convert from tasklet to workqueue
   - sdhci_am654: Stabilize support for lower speed modes
   - sdhci-esdhc-imx: Add HS400 support for iMX7ULP
   - sdhci-esdhc-imx: Add support for iMX7ULP version
   - sdhci-of-arasan: Allow to disable DCMDs via DT for CQE
   - sdhci-of-esdhc: Add support for the ls1028a version
   - sdhci-of-esdhc: Several fixups for errata
   - sdhci-pci: Fix BYT OCP setting
   - sdhci-pci: Add support for Intel CML
   - sdhci-tegra: Add support for system suspend/resume
   - sdhci-tegra: Add CQE support for Tegra186 WAR
   - sdhci-tegra: Add support for Tegra194
   - sdhci-tegra: Update HW tuning process

  MEMSTICK:
   - I volunteered to help as a maintainer for the memstick subsystem,
     which is reflected by an update to the MAINTAINERS file. Changes
     are funneled through my MMC git and we will use the linux-mmc
     mailing list.

  MEMSTICK host:
   - A few minor cleanups"

* tag 'mmc-v5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc: (87 commits)
  mmc: sdhci-pci: Fix BYT OCP setting
  dt-bindings: mmc: add DT bindings for ls1028a eSDHC host controller
  mmc: alcor: Drop pointer to mmc_host from alcor_sdmmc_host
  mmc: mtk-sd: select REGULATOR
  mmc: mtk-sd: enable internal card-detect logic.
  mmc: mtk-sd: add support for config found in mt7620 family SOCs.
  mmc: mtk-sd: don't hard-code interrupt trigger type
  mmc: core: Fix tag set memory leak
  dt-bindings: mmc: Add support for MT8516 to mtk-sd
  mmc: mmci: Prevent polling for busy detection in IRQ context
  mmc: mmci: Cleanup mmci_cmd_irq() for busy detect
  mmc: usdhi6rol0: mark expected switch fall-throughs
  mmc: core: Verify SD bus width
  mmc: sdhci-esdhc-imx: Add HS400 support for iMX7ULP
  mmc: sdhci-esdhc-imx: add pm_qos to interact with cpuidle
  dt-bindings: mmc: fsl-imx-esdhc: add imx7ulp compatible string
  mmc: meson-gx: add signal resampling tuning
  mmc: meson-gx: remove Rx phase tuning
  mmc: meson-gx: avoid clock glitch when switching to DDR modes
  mmc: meson-gx: disable HS400
  ...

37 files changed, 1146 insertions, 650 deletions

diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 3a4402a79904..6a51f7a06ce7 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -363,11 +363,11 @@ int mmc_of_parse_voltage(struct device_node *np, u32 *mask)
 	int num_ranges, i;
 
 	voltage_ranges = of_get_property(np, "voltage-ranges", &num_ranges);
-	num_ranges = num_ranges / sizeof(*voltage_ranges) / 2;
 	if (!voltage_ranges) {
 		pr_debug("%pOF: voltage-ranges unspecified\n", np);
 		return 0;
 	}
+	num_ranges = num_ranges / sizeof(*voltage_ranges) / 2;
 	if (!num_ranges) {
 		pr_err("%pOF: voltage-ranges empty\n", np);
 		return -EINVAL;
@@ -429,8 +429,6 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
 
 	if (mmc_gpio_alloc(host)) {
 		put_device(&host->class_dev);
-		ida_simple_remove(&mmc_host_ida, host->index);
-		kfree(host);
 		return NULL;
 	}
 
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index c5208fb312ae..a533cab8fccc 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -184,11 +184,7 @@ int mmc_send_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr)
 		if (err)
 			break;
 
-		/* if we're just probing, do a single pass */
-		if (ocr == 0)
-			break;
-
-		/* otherwise wait until reset completes */
+		/* wait until reset completes */
 		if (mmc_host_is_spi(host)) {
 			if (!(cmd.resp[0] & R1_SPI_IDLE))
 				break;
@@ -200,6 +196,16 @@ int mmc_send_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr)
 		err = -ETIMEDOUT;
 
 		mmc_delay(10);
+
+		/*
+		 * According to eMMC specification v5.1 section 6.4.3, we
+		 * should issue CMD1 repeatedly in the idle state until
+		 * the eMMC is ready. Otherwise some eMMC devices seem to enter
+		 * the inactive mode after mmc_init_card() issued CMD0 when
+		 * the eMMC device is busy.
+		 */
+		if (!ocr && !mmc_host_is_spi(host))
+			cmd.arg = cmd.resp[0] | BIT(30);
 	}
 
 	if (rocr && !mmc_host_is_spi(host))
diff --git a/drivers/mmc/core/pwrseq_emmc.c b/drivers/mmc/core/pwrseq_emmc.c
index efb8a7965dd4..154f4204d58c 100644
--- a/drivers/mmc/core/pwrseq_emmc.c
+++ b/drivers/mmc/core/pwrseq_emmc.c
@@ -30,19 +30,14 @@ struct mmc_pwrseq_emmc {
 
 #define to_pwrseq_emmc(p) container_of(p, struct mmc_pwrseq_emmc, pwrseq)
 
-static void __mmc_pwrseq_emmc_reset(struct mmc_pwrseq_emmc *pwrseq)
-{
-	gpiod_set_value(pwrseq->reset_gpio, 1);
-	udelay(1);
-	gpiod_set_value(pwrseq->reset_gpio, 0);
-	udelay(200);
-}
-
 static void mmc_pwrseq_emmc_reset(struct mmc_host *host)
 {
 	struct mmc_pwrseq_emmc *pwrseq =  to_pwrseq_emmc(host->pwrseq);
 
-	__mmc_pwrseq_emmc_reset(pwrseq);
+	gpiod_set_value_cansleep(pwrseq->reset_gpio, 1);
+	udelay(1);
+	gpiod_set_value_cansleep(pwrseq->reset_gpio, 0);
+	udelay(200);
 }
 
 static int mmc_pwrseq_emmc_reset_nb(struct notifier_block *this,
@@ -50,8 +45,11 @@ static int mmc_pwrseq_emmc_reset_nb(struct notifier_block *this,
 {
 	struct mmc_pwrseq_emmc *pwrseq = container_of(this,
 					struct mmc_pwrseq_emmc, reset_nb);
+	gpiod_set_value(pwrseq->reset_gpio, 1);
+	udelay(1);
+	gpiod_set_value(pwrseq->reset_gpio, 0);
+	udelay(200);
 
-	__mmc_pwrseq_emmc_reset(pwrseq);
 	return NOTIFY_DONE;
 }
 
@@ -72,14 +70,18 @@ static int mmc_pwrseq_emmc_probe(struct platform_device *pdev)
 	if (IS_ERR(pwrseq->reset_gpio))
 		return PTR_ERR(pwrseq->reset_gpio);
 
-	/*
-	 * register reset handler to ensure emmc reset also from
-	 * emergency_reboot(), priority 255 is the highest priority
-	 * so it will be executed before any system reboot handler.
-	 */
-	pwrseq->reset_nb.notifier_call = mmc_pwrseq_emmc_reset_nb;
-	pwrseq->reset_nb.priority = 255;
-	register_restart_handler(&pwrseq->reset_nb);
+	if (!gpiod_cansleep(pwrseq->reset_gpio)) {
+		/*
+		 * register reset handler to ensure emmc reset also from
+		 * emergency_reboot(), priority 255 is the highest priority
+		 * so it will be executed before any system reboot handler.
+		 */
+		pwrseq->reset_nb.notifier_call = mmc_pwrseq_emmc_reset_nb;
+		pwrseq->reset_nb.priority = 255;
+		register_restart_handler(&pwrseq->reset_nb);
+	} else {
+		dev_notice(dev, "EMMC reset pin tied to a sleepy GPIO driver; reset on emergency-reboot disabled\n");
+	}
 
 	pwrseq->pwrseq.ops = &mmc_pwrseq_emmc_ops;
 	pwrseq->pwrseq.dev = dev;
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 7c364a9c4eeb..b5b9c6142f08 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -472,6 +472,7 @@ void mmc_cleanup_queue(struct mmc_queue *mq)
 		blk_mq_unquiesce_queue(q);
 
 	blk_cleanup_queue(q);
+	blk_mq_free_tag_set(&mq->tag_set);
 
 	/*
 	 * A request can be completed before the next request, potentially
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 265e1aeeb9d8..d3d32f9a2cb1 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -221,6 +221,14 @@ static int mmc_decode_scr(struct mmc_card *card)
 
 	if (scr->sda_spec3)
 		scr->cmds = UNSTUFF_BITS(resp, 32, 2);
+
+	/* SD Spec says: any SD Card shall set at least bits 0 and 2 */
+	if (!(scr->bus_widths & SD_SCR_BUS_WIDTH_1) ||
+	    !(scr->bus_widths & SD_SCR_BUS_WIDTH_4)) {
+		pr_err("%s: invalid bus width\n", mmc_hostname(card->host));
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 28fcd8f580a1..0e86340536b6 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -92,6 +92,7 @@ config MMC_SDHCI_PCI
 	tristate "SDHCI support on PCI bus"
 	depends on MMC_SDHCI && PCI
 	select MMC_CQHCI
+	select IOSF_MBI if X86
 	help
 	  This selects the PCI Secure Digital Host Controller Interface.
 	  Most controllers found today are PCI devices.
@@ -437,7 +438,7 @@ config MMC_WBSD
 	depends on ISA_DMA_API
 	help
 	  This selects the Winbond(R) W83L51xD Secure digital and
-          Multimedia card Interface.
+	  Multimedia card Interface.
 	  If you have a machine with a integrated W83L518D or W83L519D
 	  SD/MMC card reader, say Y or M here.
 
@@ -515,7 +516,7 @@ config MMC_TIFM_SD
 	  'Misc devices: TI Flash Media PCI74xx/PCI76xx host adapter support
 	  (TIFM_7XX1)'.
 
-          To compile this driver as a module, choose M here: the
+	  To compile this driver as a module, choose M here: the
 	  module will be called tifm_sd.
 
 config MMC_MVSDIO
@@ -531,12 +532,12 @@ config MMC_MVSDIO
 	  module will be called mvsdio.
 
 config MMC_DAVINCI
-        tristate "TI DAVINCI Multimedia Card Interface support"
-        depends on ARCH_DAVINCI
-        help
-          This selects the TI DAVINCI Multimedia card Interface.
-          If you have an DAVINCI board with a Multimedia Card slot,
-          say Y or M here.  If unsure, say N.
+	tristate "TI DAVINCI Multimedia Card Interface support"
+	depends on ARCH_DAVINCI
+	help
+	  This selects the TI DAVINCI Multimedia card Interface.
+	  If you have an DAVINCI board with a Multimedia Card slot,
+	  say Y or M here.  If unsure, say N.
 
 config MMC_GOLDFISH
 	tristate "goldfish qemu Multimedia Card Interface support"
@@ -565,18 +566,18 @@ config MMC_S3C
 	depends on S3C24XX_DMAC
 	help
 	  This selects a driver for the MCI interface found in
-          Samsung's S3C2410, S3C2412, S3C2440, S3C2442 CPUs.
+	  Samsung's S3C2410, S3C2412, S3C2440, S3C2442 CPUs.
 	  If you have a board based on one of those and a MMC/SD
 	  slot, say Y or M here.
 
 	  If unsure, say N.
 
 config MMC_S3C_HW_SDIO_IRQ
-       bool "Hardware support for SDIO IRQ"
-       depends on MMC_S3C
-       help
-         Enable the hardware support for SDIO interrupts instead of using
-	 the generic polling code.
+	bool "Hardware support for SDIO IRQ"
+	depends on MMC_S3C
+	help
+	  Enable the hardware support for SDIO interrupts instead of using
+	  the generic polling code.
 
 choice
 	prompt "Samsung S3C SD/MMC transfer code"
@@ -941,6 +942,7 @@ config MMC_BCM2835
 config MMC_MTK
 	tristate "MediaTek SD/MMC Card Interface support"
 	depends on HAS_DMA
+	select REGULATOR
 	help
 	  This selects the MediaTek(R) Secure digital and Multimedia card Interface.
 	  If you have a machine with a integrated SD/MMC card reader, say Y or M here.
@@ -948,15 +950,16 @@ config MMC_MTK
 	  If unsure, say N.
 
 config MMC_SDHCI_MICROCHIP_PIC32
-        tristate "Microchip PIC32MZDA SDHCI support"
-        depends on MMC_SDHCI && PIC32MZDA && MMC_SDHCI_PLTFM
-        help
-          This selects the Secure Digital Host Controller Interface (SDHCI)
-          for PIC32MZDA platform.
+	tristate "Microchip PIC32MZDA SDHCI support"
+	depends on MMC_SDHCI && PIC32MZDA && MMC_SDHCI_PLTFM
+	help
+	  This selects the Secure Digital Host Controller Interface (SDHCI)
+	  for PIC32MZDA platform.
 
-          If you have a controller with this interface, say Y or M here.
+	  If you have a controller with this interface, say Y or M here.
+
+	  If unsure, say N.
 
-          If unsure, say N.
 config MMC_SDHCI_BRCMSTB
 	tristate "Broadcom SDIO/SD/MMC support"
 	depends on ARCH_BRCMSTB || BMIPS_GENERIC
@@ -993,6 +996,7 @@ config MMC_SDHCI_OMAP
 config MMC_SDHCI_AM654
 	tristate "Support for the SDHCI Controller in TI's AM654 SOCs"
 	depends on MMC_SDHCI_PLTFM && OF
+	select MMC_SDHCI_IO_ACCESSORS
 	help
 	  This selects the Secure Digital Host Controller Interface (SDHCI)
 	  support present in TI's AM654 SOCs. The controller supports
diff --git a/drivers/mmc/host/alcor.c b/drivers/mmc/host/alcor.c
index 6e6b7ade4b60..e481535cba2b 100644
--- a/drivers/mmc/host/alcor.c
+++ b/drivers/mmc/host/alcor.c
@@ -43,7 +43,6 @@ struct alcor_sdmmc_host {
 	struct  device *dev;
 	struct alcor_pci_priv *alcor_pci;
 
-	struct mmc_host *mmc;
 	struct mmc_request *mrq;
 	struct mmc_command *cmd;
 	struct mmc_data *data;
@@ -117,6 +116,9 @@ static void alcor_reset(struct alcor_sdmmc_host *host, u8 val)
 	dev_err(host->dev, "%s: timeout\n", __func__);
 }
 
+/*
+ * Perform DMA I/O of a single page.
+ */
 static void alcor_data_set_dma(struct alcor_sdmmc_host *host)
 {
 	struct alcor_pci_priv *priv = host->alcor_pci;
@@ -153,12 +155,26 @@ static void alcor_trigger_data_transfer(struct alcor_sdmmc_host *host)
 		ctrl |= AU6601_DATA_WRITE;
 
 	if (data->host_cookie == COOKIE_MAPPED) {
+		/*
+		 * For DMA transfers, this function is called just once,
+		 * at the start of the operation. The hardware can only
+		 * perform DMA I/O on a single page at a time, so here
+		 * we kick off the transfer with the first page, and expect
+		 * subsequent pages to be transferred upon IRQ events
+		 * indicating that the single-page DMA was completed.
+		 */
 		alcor_data_set_dma(host);
 		ctrl |= AU6601_DATA_DMA_MODE;
 		host->dma_on = 1;
 		alcor_write32(priv, data->sg_count * 0x1000,
 			       AU6601_REG_BLOCK_SIZE);
 	} else {
+		/*
+		 * For PIO transfers, we break down each operation
+		 * into several sector-sized transfers. When one sector has
+		 * complete, the IRQ handler will call this function again
+		 * to kick off the transfer of the next sector.
+		 */
 		alcor_write32(priv, data->blksz, AU6601_REG_BLOCK_SIZE);
 	}
 
@@ -276,7 +292,7 @@ static void alcor_send_cmd(struct alcor_sdmmc_host *host,
 		break;
 	default:
 		dev_err(host->dev, "%s: cmd->flag (0x%02x) is not valid\n",
-			mmc_hostname(host->mmc), mmc_resp_type(cmd));
+			mmc_hostname(mmc_from_priv(host)), mmc_resp_type(cmd));
 		break;
 	}
 
@@ -317,7 +333,7 @@ static void alcor_request_complete(struct alcor_sdmmc_host *host,
 	host->data = NULL;
 	host->dma_on = 0;
 
-	mmc_request_done(host->mmc, mrq);
+	mmc_request_done(mmc_from_priv(host), mrq);
 }
 
 static void alcor_finish_data(struct alcor_sdmmc_host *host)
@@ -547,7 +563,7 @@ static void alcor_cd_irq(struct alcor_sdmmc_host *host, u32 intmask)
 		alcor_request_complete(host, 1);
 	}
 
-	mmc_detect_change(host->mmc, msecs_to_jiffies(1));
+	mmc_detect_change(mmc_from_priv(host), msecs_to_jiffies(1));
 }
 
 static irqreturn_t alcor_irq_thread(int irq, void *d)
@@ -771,12 +787,17 @@ static void alcor_pre_req(struct mmc_host *mmc,
 	data->host_cookie = COOKIE_UNMAPPED;
 
 	/* FIXME: looks like the DMA engine works only with CMD18 */
-	if (cmd->opcode != 18)
+	if (cmd->opcode != MMC_READ_MULTIPLE_BLOCK
+			&& cmd->opcode != MMC_WRITE_MULTIPLE_BLOCK)
 		return;
 	/*
 	 * We don't do DMA on "complex" transfers, i.e. with
-	 * non-word-aligned buffers or lengths. Also, we don't bother
-	 * with all the DMA setup overhead for short transfers.
+	 * non-word-aligned buffers or lengths. A future improvement
+	 * could be made to use temporary DMA bounce-buffers when these
+	 * requirements are not met.
+	 *
+	 * Also, we don't bother with all the DMA setup overhead for
+	 * short transfers.
 	 */
 	if (data->blocks * data->blksz < AU6601_MAX_DMA_BLOCK_SIZE)
 		return;
@@ -787,6 +808,8 @@ static void alcor_pre_req(struct mmc_host *mmc,
 	for_each_sg(data->sg, sg, data->sg_len, i) {
 		if (sg->length != AU6601_MAX_DMA_BLOCK_SIZE)
 			return;
+		if (sg->offset != 0)
+			return;
 	}
 
 	/* This data might be unmapped at this time */
@@ -1024,7 +1047,7 @@ static void alcor_hw_uninit(struct alcor_sdmmc_host *host)
 
 static void alcor_init_mmc(struct alcor_sdmmc_host *host)
 {
-	struct mmc_host *mmc = host->mmc;
+	struct mmc_host *mmc = mmc_from_priv(host);
 
 	mmc->f_min = AU6601_MIN_CLOCK;
 	mmc->f_max = AU6601_MAX_CLOCK;
@@ -1036,26 +1059,21 @@ static void alcor_init_mmc(struct alcor_sdmmc_host *host)
 	mmc->ops = &alcor_sdc_ops;
 
 	/* The hardware does DMA data transfer of 4096 bytes to/from a single
-	 * buffer address. Scatterlists are not supported, but upon DMA
-	 * completion (signalled via IRQ), the original vendor driver does
-	 * then immediately set up another DMA transfer of the next 4096
-	 * bytes.
-	 *
-	 * This means that we need to handle the I/O in 4096 byte chunks.
-	 * Lacking a way to limit the sglist entries to 4096 bytes, we instead
-	 * impose that only one segment is provided, with maximum size 4096,
-	 * which also happens to be the minimum size. This means that the
-	 * single-entry sglist handled by this driver can be handed directly
-	 * to the hardware, nice and simple.
+	 * buffer address. Scatterlists are not supported at the hardware
+	 * level, however we can work with them at the driver level,
+	 * provided that each segment is exactly 4096 bytes in size.
+	 * Upon DMA completion of a single segment (signalled via IRQ), we
+	 * immediately proceed to transfer the next segment from the
+	 * scatterlist.
 	 *
-	 * Unfortunately though, that means we only do 4096 bytes I/O per
-	 * MMC command. A future improvement would be to make the driver
-	 * accept sg lists and entries of any size, and simply iterate
-	 * through them 4096 bytes at a time.
+	 * The overall request is limited to 240 sectors, matching the
+	 * original vendor driver.
 	 */
 	mmc->max_segs = AU6601_MAX_DMA_SEGMENTS;
 	mmc->max_seg_size = AU6601_MAX_DMA_BLOCK_SIZE;
-	mmc->max_req_size = mmc->max_seg_size;
+	mmc->max_blk_count = 240;
+	mmc->max_req_size = mmc->max_blk_count * mmc->max_blk_size;
+	dma_set_max_seg_size(host->dev, mmc->max_seg_size);
 }
 
 static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev)
@@ -1072,7 +1090,6 @@ static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev)
 	}
 
 	host = mmc_priv(mmc);
-	host->mmc = mmc;
 	host->dev = &pdev->dev;
 	host->cur_power_mode = MMC_POWER_UNDEFINED;
 	host->alcor_pci = priv;
@@ -1104,13 +1121,14 @@ static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev)
 static int alcor_pci_sdmmc_drv_remove(struct platform_device *pdev)
 {
 	struct alcor_sdmmc_host *host = dev_get_drvdata(&pdev->dev);
+	struct mmc_host *mmc = mmc_from_priv(host);
 
 	if (cancel_delayed_work_sync(&host->timeout_work))
 		alcor_request_complete(host, 0);
 
 	alcor_hw_uninit(host);
-	mmc_remove_host(host->mmc);
-	mmc_free_host(host->mmc);
+	mmc_remove_host(mmc);
+	mmc_free_host(mmc);
 
 	return 0;
 }
diff --git a/drivers/mmc/host/cqhci.c b/drivers/mmc/host/cqhci.c
index a8af682a9182..d59cb0a51964 100644
--- a/drivers/mmc/host/cqhci.c
+++ b/drivers/mmc/host/cqhci.c
@@ -537,6 +537,8 @@ static void cqhci_prep_dcmd_desc(struct mmc_host *mmc,
 		 CQHCI_ACT(0x5) |
 		 CQHCI_CMD_INDEX(mrq->cmd->opcode) |
 		 CQHCI_CMD_TIMING(timing) | CQHCI_RESP_TYPE(resp_type));
+	if (cq_host->ops->update_dcmd_desc)
+		cq_host->ops->update_dcmd_desc(mmc, mrq, &data);
 	*task_desc |= data;
 	desc = (u8 *)task_desc;
 	pr_debug("%s: cqhci: dcmd: cmd: %d timing: %d resp: %d\n",
diff --git a/drivers/mmc/host/cqhci.h b/drivers/mmc/host/cqhci.h
index 9e68286a07b4..1e8e01d81015 100644
--- a/drivers/mmc/host/cqhci.h
+++ b/drivers/mmc/host/cqhci.h
@@ -88,6 +88,7 @@
 
 /* send status config 1 */
 #define CQHCI_SSC1			0x40
+#define CQHCI_SSC1_CBC_MASK		GENMASK(19, 16)
 
 /* send status config 2 */
 #define CQHCI_SSC2			0x44
@@ -147,6 +148,7 @@
 
 struct cqhci_host_ops;
 struct mmc_host;
+struct mmc_request;
 struct cqhci_slot;
 
 struct cqhci_host {
@@ -210,6 +212,8 @@ struct cqhci_host_ops {
 	u32 (*read_l)(struct cqhci_host *host, int reg);
 	void (*enable)(struct mmc_host *mmc);
 	void (*disable)(struct mmc_host *mmc, bool recovery);
+	void (*update_dcmd_desc)(struct mmc_host *mmc, struct mmc_request *mrq,
+				 u64 *data);
 };
 
 static inline void cqhci_writel(struct cqhci_host *host, u32 val, int reg)
diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c
index 2eba507790e4..c5a8af4ca76b 100644
--- a/drivers/mmc/host/meson-gx-mmc.c
+++ b/drivers/mmc/host/meson-gx-mmc.c
@@ -23,6 +23,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/device.h>
+#include <linux/iopoll.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/ioport.h>
@@ -48,6 +49,8 @@
 #define   CLK_CORE_PHASE_MASK GENMASK(9, 8)
 #define   CLK_TX_PHASE_MASK GENMASK(11, 10)
 #define   CLK_RX_PHASE_MASK GENMASK(13, 12)
+#define   CLK_PHASE_0 0
+#define   CLK_PHASE_180 2
 #define   CLK_V2_TX_DELAY_MASK GENMASK(19, 16)
 #define   CLK_V2_RX_DELAY_MASK GENMASK(23, 20)
 #define   CLK_V2_ALWAYS_ON BIT(24)
@@ -56,10 +59,6 @@
 #define   CLK_V3_RX_DELAY_MASK GENMASK(27, 22)
 #define   CLK_V3_ALWAYS_ON BIT(28)
 
-#define   CLK_DELAY_STEP_PS 200
-#define   CLK_PHASE_STEP 30
-#define   CLK_PHASE_POINT_NUM (360 / CLK_PHASE_STEP)
-
 #define   CLK_TX_DELAY_MASK(h)		(h->data->tx_delay_mask)
 #define   CLK_RX_DELAY_MASK(h)		(h->data->rx_delay_mask)
 #define   CLK_ALWAYS_ON(h)		(h->data->always_on)
@@ -164,10 +163,10 @@ struct meson_host {
 
 	void __iomem *regs;
 	struct clk *core_clk;
+	struct clk *mux_clk;
 	struct clk *mmc_clk;
-	struct clk *rx_clk;
-	struct clk *tx_clk;
 	unsigned long req_rate;
+	bool ddr;
 
 	struct pinctrl *pinctrl;
 	struct pinctrl_state *pins_default;
@@ -207,90 +206,6 @@ struct meson_host {
 #define CMD_RESP_MASK GENMASK(31, 1)
 #define CMD_RESP_SRAM BIT(0)
 
-struct meson_mmc_phase {
-	struct clk_hw hw;
-	void __iomem *reg;
-	unsigned long phase_mask;
-	unsigned long delay_mask;
-	unsigned int delay_step_ps;
-};
-
-#define to_meson_mmc_phase(_hw) container_of(_hw, struct meson_mmc_phase, hw)
-
-static int meson_mmc_clk_get_phase(struct clk_hw *hw)
-{
-	struct meson_mmc_phase *mmc = to_meson_mmc_phase(hw);
-	unsigned int phase_num = 1 <<  hweight_long(mmc->phase_mask);
-	unsigned long period_ps, p, d;
-		int degrees;
-	u32 val;
-
-	val = readl(mmc->reg);
-	p = (val & mmc->phase_mask) >> __ffs(mmc->phase_mask);
-	degrees = p * 360 / phase_num;
-
-	if (mmc->delay_mask) {
-		period_ps = DIV_ROUND_UP((unsigned long)NSEC_PER_SEC * 1000,
-					 clk_get_rate(hw->clk));
-		d = (val & mmc->delay_mask) >> __ffs(mmc->delay_mask);
-		degrees += d * mmc->delay_step_ps * 360 / period_ps;
-		degrees %= 360;
-	}
-
-	return degrees;
-}
-
-static void meson_mmc_apply_phase_delay(struct meson_mmc_phase *mmc,
-					unsigned int phase,
-					unsigned int delay)
-{
-	u32 val;
-
-	val = readl(mmc->reg);
-	val &= ~mmc->phase_mask;
-	val |= phase << __ffs(mmc->phase_mask);
-
-	if (mmc->delay_mask) {
-		val &= ~mmc->delay_mask;
-		val |= delay << __ffs(mmc->delay_mask);
-	}
-
-	writel(val, mmc->reg);
-}
-
-static int meson_mmc_clk_set_phase(struct clk_hw *hw, int degrees)
-{
-	struct meson_mmc_phase *mmc = to_meson_mmc_phase(hw);
-	unsigned int phase_num = 1 <<  hweight_long(mmc->phase_mask);
-	unsigned long period_ps, d = 0, r;
-	uint64_t p;
-
-	p = degrees % 360;
-
-	if (!mmc->delay_mask) {
-		p = DIV_ROUND_CLOSEST_ULL(p, 360 / phase_num);
-	} else {
-		period_ps = DIV_ROUND_UP((unsigned long)NSEC_PER_SEC * 1000,
-					 clk_get_rate(hw->clk));
-
-		/* First compute the phase index (p), the remainder (r) is the
-		 * part we'll try to acheive using the delays (d).
-		 */
-		r = do_div(p, 360 / phase_num);
-		d = DIV_ROUND_CLOSEST(r * period_ps,
-				      360 * mmc->delay_step_ps);
-		d = min(d, mmc->delay_mask >> __ffs(mmc->delay_mask));
-	}
-
-	meson_mmc_apply_phase_delay(mmc, p, d);
-	return 0;
-}
-
-static const struct clk_ops meson_mmc_clk_phase_ops = {
-	.get_phase = meson_mmc_clk_get_phase,
-	.set_phase = meson_mmc_clk_set_phase,
-};
-
 static unsigned int meson_mmc_get_timeout_msecs(struct mmc_data *data)
 {
 	unsigned int timeout = data->timeout_ns / NSEC_PER_MSEC;
@@ -383,16 +298,6 @@ static void meson_mmc_post_req(struct mmc_host *mmc, struct mmc_request *mrq,
 			     mmc_get_dma_dir(data));
 }
 
-static bool meson_mmc_timing_is_ddr(struct mmc_ios *ios)
-{
-	if (ios->timing == MMC_TIMING_MMC_DDR52 ||
-	    ios->timing == MMC_TIMING_UHS_DDR50 ||
-	    ios->timing == MMC_TIMING_MMC_HS400)
-		return true;
-
-	return false;
-}
-
 /*
  * Gating the clock on this controller is tricky.  It seems the mmc clock
  * is also used by the controller.  It may crash during some operation if the
@@ -429,36 +334,41 @@ static void meson_mmc_clk_ungate(struct meson_host *host)
 	writel(cfg, host->regs + SD_EMMC_CFG);
 }
 
-static int meson_mmc_clk_set(struct meson_host *host, struct mmc_ios *ios)
+static int meson_mmc_clk_set(struct meson_host *host, unsigned long rate,
+			     bool ddr)
 {
 	struct mmc_host *mmc = host->mmc;
-	unsigned long rate = ios->clock;
 	int ret;
 	u32 cfg;
 
-	/* DDR modes require higher module clock */
-	if (meson_mmc_timing_is_ddr(ios))
-		rate <<= 1;
-
 	/* Same request - bail-out */
-	if (host->req_rate == rate)
+	if (host->ddr == ddr && host->req_rate == rate)
 		return 0;
 
 	/* stop clock */
 	meson_mmc_clk_gate(host);