Merge tag 'mmc-v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc

Pull MMC updates from Ulf Hansson:
 "MMC core:
   - Don't force a retune before eMMC RPMB switch
   - Add optional HS400 tuning in HS400es initialization
   - Add a sysfs node to for write-protect-group-size
   - Add re-tuning test to the mmc-test module
   - Use mrq.sbc to support close-ended ioctl requests

  MMC host:
   - mmci: Add support for SDIO in-band irqs for the stm32 variant
   - mmc_spi: Remove broken support custom DMA mapped buffers
   - mtk-sd: Improve and extend the support for tunings
   - renesas_sdhi: Document support for the RZ/Five variant
   - sdhci_am654: Drop support for the ti,otap-del-sel DT property
   - sdhci-brcmstb: Add support for the brcm 74165b0 variant
   - sdhci-msm: Add compatibles for IPQ4019 and IPQ8074
   - sdhci-of-dwcmshc: Add support for the T-Head TH1520 variant
   - sdhci-xenon: Add support for the Marvell ac5 variant"

* tag 'mmc-v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc: (27 commits)
  mmc: xenon: Add ac5 support via bounce buffer
  dt-bindings: mmc: add Marvell ac5
  mmc: sdhci-brcmstb: add new sdhci reset sequence for brcm 74165b0
  dt-bindings: mmc: brcm,sdhci-brcmstb: Add support for 74165b0
  mmc: core: Do not force a retune before RPMB switch
  mmc: core: Add HS400 tuning in HS400es initialization
  mmc: sdhci_omap: Fix TI SoC dependencies
  mmc: sdhci_am654: Fix TI SoC dependencies
  mmc: core: Add wp_grp_size sysfs node
  mmc: mmc_test: Add re-tuning test
  mmc: mmc_spi: remove custom DMA mapped buffers
  dt-bindings: mmc: sdhci-msm: document dedicated IPQ4019 and IPQ8074
  dt-bindings: mmc: synopsys-dw-mshc: add iommus for Intel SocFPGA
  mmc: mtk-sd: Extend number of tuning steps
  dt-bindings: mmc: mtk-sd: add tuning steps related property
  mmc: sdhci-omap: don't misuse kernel-doc marker
  mmc: mtk-sd: Increase the verbosity of msdc_track_cmd_data
  mmc: core: Use mrq.sbc in close-ended ffu
  mmc: sdhci_am654: Drop lookup for deprecated ti,otap-del-sel
  mmc: sdhci-of-dwcmshc: Use logical OR instead of bitwise OR in dwcmshc_probe()
  ...

17 files changed, 744 insertions, 296 deletions

diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 134c36edb6cf..32d49100dff5 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -400,6 +400,10 @@ struct mmc_blk_ioc_data {
 	struct mmc_ioc_cmd ic;
 	unsigned char *buf;
 	u64 buf_bytes;
+	unsigned int flags;
+#define MMC_BLK_IOC_DROP	BIT(0)	/* drop this mrq */
+#define MMC_BLK_IOC_SBC	BIT(1)	/* use mrq.sbc */
+
 	struct mmc_rpmb_data *rpmb;
 };
 
@@ -465,7 +469,7 @@ static int mmc_blk_ioctl_copy_to_user(struct mmc_ioc_cmd __user *ic_ptr,
 }
 
 static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
-			       struct mmc_blk_ioc_data *idata)
+			       struct mmc_blk_ioc_data **idatas, int i)
 {
 	struct mmc_command cmd = {}, sbc = {};
 	struct mmc_data data = {};
@@ -475,10 +479,18 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 	unsigned int busy_timeout_ms;
 	int err;
 	unsigned int target_part;
+	struct mmc_blk_ioc_data *idata = idatas[i];
+	struct mmc_blk_ioc_data *prev_idata = NULL;
 
 	if (!card || !md || !idata)
 		return -EINVAL;
 
+	if (idata->flags & MMC_BLK_IOC_DROP)
+		return 0;
+
+	if (idata->flags & MMC_BLK_IOC_SBC)
+		prev_idata = idatas[i - 1];
+
 	/*
 	 * The RPMB accesses comes in from the character device, so we
 	 * need to target these explicitly. Else we just target the
@@ -532,7 +544,7 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 			return err;
 	}
 
-	if (idata->rpmb) {
+	if (idata->rpmb || prev_idata) {
 		sbc.opcode = MMC_SET_BLOCK_COUNT;
 		/*
 		 * We don't do any blockcount validation because the max size
@@ -540,6 +552,8 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 		 * 'Reliable Write' bit here.
 		 */
 		sbc.arg = data.blocks | (idata->ic.write_flag & BIT(31));
+		if (prev_idata)
+			sbc.arg = prev_idata->ic.arg;
 		sbc.flags = MMC_RSP_R1 | MMC_CMD_AC;
 		mrq.sbc = &sbc;
 	}
@@ -557,6 +571,15 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 	mmc_wait_for_req(card->host, &mrq);
 	memcpy(&idata->ic.response, cmd.resp, sizeof(cmd.resp));
 
+	if (prev_idata) {
+		memcpy(&prev_idata->ic.response, sbc.resp, sizeof(sbc.resp));
+		if (sbc.error) {
+			dev_err(mmc_dev(card->host), "%s: sbc error %d\n",
+							__func__, sbc.error);
+			return sbc.error;
+		}
+	}
+
 	if (cmd.error) {
 		dev_err(mmc_dev(card->host), "%s: cmd error %d\n",
 						__func__, cmd.error);
@@ -1034,6 +1057,20 @@ static inline void mmc_blk_reset_success(struct mmc_blk_data *md, int type)
 	md->reset_done &= ~type;
 }
 
+static void mmc_blk_check_sbc(struct mmc_queue_req *mq_rq)
+{
+	struct mmc_blk_ioc_data **idata = mq_rq->drv_op_data;
+	int i;
+
+	for (i = 1; i < mq_rq->ioc_count; i++) {
+		if (idata[i - 1]->ic.opcode == MMC_SET_BLOCK_COUNT &&
+		    mmc_op_multi(idata[i]->ic.opcode)) {
+			idata[i - 1]->flags |= MMC_BLK_IOC_DROP;
+			idata[i]->flags |= MMC_BLK_IOC_SBC;
+		}
+	}
+}
+
 /*
  * The non-block commands come back from the block layer after it queued it and
  * processed it with all other requests and then they get issued in this
@@ -1061,11 +1098,14 @@ static void mmc_blk_issue_drv_op(struct mmc_queue *mq, struct request *req)
 			if (ret)
 				break;
 		}
+
+		mmc_blk_check_sbc(mq_rq);
+
 		fallthrough;
 	case MMC_DRV_OP_IOCTL_RPMB:
 		idata = mq_rq->drv_op_data;
 		for (i = 0, ret = 0; i < mq_rq->ioc_count; i++) {
-			ret = __mmc_blk_ioctl_cmd(card, md, idata[i]);
+			ret = __mmc_blk_ioctl_cmd(card, md, idata, i);
 			if (ret)
 				break;
 		}
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 2f51db4df1a8..cf396e8f34e9 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -119,13 +119,12 @@ void mmc_retune_enable(struct mmc_host *host)
 
 /*
  * Pause re-tuning for a small set of operations.  The pause begins after the
- * next command and after first doing re-tuning.
+ * next command.
  */
 void mmc_retune_pause(struct mmc_host *host)
 {
 	if (!host->retune_paused) {
 		host->retune_paused = 1;
-		mmc_retune_needed(host);
 		mmc_retune_hold(host);
 	}
 }
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 705942edacc6..f410bee50132 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -136,6 +136,17 @@ static void mmc_set_erase_size(struct mmc_card *card)
 	mmc_init_erase(card);
 }
 
+
+static void mmc_set_wp_grp_size(struct mmc_card *card)
+{
+	if (card->ext_csd.erase_group_def & 1)
+		card->wp_grp_size = card->ext_csd.hc_erase_size *
+			card->ext_csd.raw_hc_erase_gap_size;
+	else
+		card->wp_grp_size = card->csd.erase_size *
+			(card->csd.wp_grp_size + 1);
+}
+
 /*
  * Given a 128-bit response, decode to our card CSD structure.
  */
@@ -186,6 +197,7 @@ static int mmc_decode_csd(struct mmc_card *card)
 		b = UNSTUFF_BITS(resp, 37, 5);
 		csd->erase_size = (a + 1) * (b + 1);
 		csd->erase_size <<= csd->write_blkbits - 9;
+		csd->wp_grp_size = UNSTUFF_BITS(resp, 32, 5);
 	}
 
 	return 0;
@@ -613,11 +625,6 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 		} else {
 			card->ext_csd.data_tag_unit_size = 0;
 		}
-
-		card->ext_csd.max_packed_writes =
-			ext_csd[EXT_CSD_MAX_PACKED_WRITES];
-		card->ext_csd.max_packed_reads =
-			ext_csd[EXT_CSD_MAX_PACKED_READS];
 	} else {
 		card->ext_csd.data_sector_size = 512;
 	}
@@ -790,6 +797,7 @@ MMC_DEV_ATTR(csd, "%08x%08x%08x%08x\n", card->raw_csd[0], card->raw_csd[1],
 MMC_DEV_ATTR(date, "%02d/%04d\n", card->cid.month, card->cid.year);
 MMC_DEV_ATTR(erase_size, "%u\n", card->erase_size << 9);
 MMC_DEV_ATTR(preferred_erase_size, "%u\n", card->pref_erase << 9);
+MMC_DEV_ATTR(wp_grp_size, "%u\n", card->wp_grp_size << 9);
 MMC_DEV_ATTR(ffu_capable, "%d\n", card->ext_csd.ffu_capable);
 MMC_DEV_ATTR(hwrev, "0x%x\n", card->cid.hwrev);
 MMC_DEV_ATTR(manfid, "0x%06x\n", card->cid.manfid);
@@ -850,6 +858,7 @@ static struct attribute *mmc_std_attrs[] = {
 	&dev_attr_date.attr,
 	&dev_attr_erase_size.attr,
 	&dev_attr_preferred_erase_size.attr,
+	&dev_attr_wp_grp_size.attr,
 	&dev_attr_fwrev.attr,
 	&dev_attr_ffu_capable.attr,
 	&dev_attr_hwrev.attr,
@@ -1764,7 +1773,7 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 			mmc_set_erase_size(card);
 		}
 	}
-
+	mmc_set_wp_grp_size(card);
 	/*
 	 * Ensure eMMC user default partition is enabled
 	 */
@@ -1822,8 +1831,13 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 
 		if (err)
 			goto free_card;
-
-	} else if (!mmc_card_hs400es(card)) {
+	} else if (mmc_card_hs400es(card)) {
+		if (host->ops->execute_hs400_tuning) {
+			err = host->ops->execute_hs400_tuning(host, card);
+			if (err)
+				goto free_card;
+		}
+	} else {
 		/* Select the desired bus width optionally */
 		err = mmc_select_bus_width(card);
 		if (err > 0 && mmc_card_hs(card)) {
diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c
index 0f6a563103fd..8f7f587a0025 100644
--- a/drivers/mmc/core/mmc_test.c
+++ b/drivers/mmc/core/mmc_test.c
@@ -1904,7 +1904,7 @@ static unsigned int mmc_test_rnd_num(unsigned int rnd_cnt)
 }
 
 static int mmc_test_rnd_perf(struct mmc_test_card *test, int write, int print,
-			     unsigned long sz)
+			     unsigned long sz, int secs, int force_retuning)
 {
 	unsigned int dev_addr, cnt, rnd_addr, range1, range2, last_ea = 0, ea;
 	unsigned int ssz;
@@ -1921,7 +1921,7 @@ static int mmc_test_rnd_perf(struct mmc_test_card *test, int write, int print,
 	for (cnt = 0; cnt < UINT_MAX; cnt++) {
 		ktime_get_ts64(&ts2);
 		ts = timespec64_sub(ts2, ts1);
-		if (ts.tv_sec >= 10)
+		if (ts.tv_sec >= secs)
 			break;
 		ea = mmc_test_rnd_num(range1);
 		if (ea == last_ea)
@@ -1929,6 +1929,8 @@ static int mmc_test_rnd_perf(struct mmc_test_card *test, int write, int print,
 		last_ea = ea;
 		dev_addr = rnd_addr + test->card->pref_erase * ea +
 			   ssz * mmc_test_rnd_num(range2);
+		if (force_retuning)
+			mmc_retune_needed(test->card->host);
 		ret = mmc_test_area_io(test, sz, dev_addr, write, 0, 0);
 		if (ret)
 			return ret;
@@ -1953,24 +1955,35 @@ static int mmc_test_random_perf(struct mmc_test_card *test, int write)
 		 */
 		if (write) {
 			next = rnd_next;
-			ret = mmc_test_rnd_perf(test, write, 0, sz);
+			ret = mmc_test_rnd_perf(test, write, 0, sz, 10, 0);
 			if (ret)
 				return ret;
 			rnd_next = next;
 		}
-		ret = mmc_test_rnd_perf(test, write, 1, sz);
+		ret = mmc_test_rnd_perf(test, write, 1, sz, 10, 0);
 		if (ret)
 			return ret;
 	}
 	sz = t->max_tfr;
 	if (write) {
 		next = rnd_next;
-		ret = mmc_test_rnd_perf(test, write, 0, sz);
+		ret = mmc_test_rnd_perf(test, write, 0, sz, 10, 0);
 		if (ret)
 			return ret;
 		rnd_next = next;
 	}
-	return mmc_test_rnd_perf(test, write, 1, sz);
+	return mmc_test_rnd_perf(test, write, 1, sz, 10, 0);
+}
+
+static int mmc_test_retuning(struct mmc_test_card *test)
+{
+	if (!mmc_can_retune(test->card->host)) {
+		pr_info("%s: No retuning - test skipped\n",
+			mmc_hostname(test->card->host));
+		return RESULT_UNSUP_HOST;
+	}
+
+	return mmc_test_rnd_perf(test, 0, 0, 8192, 30, 1);
 }
 
 /*
@@ -2921,6 +2934,14 @@ static const struct mmc_test_case mmc_test_cases[] = {
 		.run = mmc_test_cmds_during_write_cmd23_nonblock,
 		.cleanup = mmc_test_area_cleanup,
 	},
+
+	{
+		.name = "Re-tuning reliability",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_retuning,
+		.cleanup = mmc_test_area_cleanup,
+	},
+
 };
 
 static DEFINE_MUTEX(mmc_test_lock);
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 58bd5fe4cd25..81f2c4e05287 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -1026,14 +1026,15 @@ config MMC_SDHCI_XENON
 
 config MMC_SDHCI_OMAP
 	tristate "TI SDHCI Controller Support"
+	depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST
 	depends on MMC_SDHCI_PLTFM && OF
 	select THERMAL
 	imply TI_SOC_THERMAL
 	select MMC_SDHCI_EXTERNAL_DMA if DMA_ENGINE
 	help
 	  This selects the Secure Digital Host Controller Interface (SDHCI)
-	  support present in TI's DRA7 SOCs. The controller supports
-	  SD/MMC/SDIO devices.
+	  support present in TI's Keystone/OMAP2+/DRA7 SOCs. The controller
+	  supports SD/MMC/SDIO devices.
 
 	  If you have a controller with this interface, say Y or M here.
 
@@ -1041,14 +1042,15 @@ config MMC_SDHCI_OMAP
 
 config MMC_SDHCI_AM654
 	tristate "Support for the SDHCI Controller in TI's AM654 SOCs"
+	depends on ARCH_K3 || COMPILE_TEST
 	depends on MMC_SDHCI_PLTFM && OF
 	select MMC_SDHCI_IO_ACCESSORS
 	select MMC_CQHCI
 	select REGMAP_MMIO
 	help
 	  This selects the Secure Digital Host Controller Interface (SDHCI)
-	  support present in TI's AM654 SOCs. The controller supports
-	  SD/MMC/SDIO devices.
+	  support present in TI's AM65x/AM64x/AM62x/J721E SOCs. The controller
+	  supports SD/MMC/SDIO devices.
 
 	  If you have a controller with this interface, say Y or M here.
 
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index b0cccef4cfbf..b8dda8160c4e 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -15,7 +15,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/bio.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direction.h>
 #include <linux/crc7.h>
 #include <linux/crc-itu-t.h>
 #include <linux/scatterlist.h>
@@ -119,19 +119,14 @@ struct mmc_spi_host {
 	struct spi_transfer	status;
 	struct spi_message	readback;
 
-	/* underlying DMA-aware controller, or null */
-	struct device		*dma_dev;
-
 	/* buffer used for commands and for message "overhead" */
 	struct scratch		*data;
-	dma_addr_t		data_dma;
 
 	/* Specs say to write ones most of the time, even when the card
 	 * has no need to read its input data; and many cards won't care.
 	 * This is our source of those ones.
 	 */
 	void			*ones;
-	dma_addr_t		ones_dma;
 };
 
 
@@ -147,11 +142,8 @@ static inline int mmc_cs_off(struct mmc_spi_host *host)
 	return spi_setup(host->spi);
 }
 
-static int
-mmc_spi_readbytes(struct mmc_spi_host *host, unsigned len)
+static int mmc_spi_readbytes(struct mmc_spi_host *host, unsigned int len)
 {
-	int status;
-
 	if (len > sizeof(*host->data)) {
 		WARN_ON(1);
 		return -EIO;
@@ -159,19 +151,7 @@ mmc_spi_readbytes(struct mmc_spi_host *host, unsigned len)
 
 	host->status.len = len;
 
-	if (host->dma_dev)
-		dma_sync_single_for_device(host->dma_dev,
-				host->data_dma, sizeof(*host->data),
-				DMA_FROM_DEVICE);
-
-	status = spi_sync_locked(host->spi, &host->readback);
-
-	if (host->dma_dev)
-		dma_sync_single_for_cpu(host->dma_dev,
-				host->data_dma, sizeof(*host->data),
-				DMA_FROM_DEVICE);
-
-	return status;
+	return spi_sync_locked(host->spi, &host->readback);
 }
 
 static int mmc_spi_skip(struct mmc_spi_host *host, unsigned long timeout,
@@ -506,23 +486,11 @@ mmc_spi_command_send(struct mmc_spi_host *host,
 	t = &host->t;
 	memset(t, 0, sizeof(*t));
 	t->tx_buf = t->rx_buf = data->status;
-	t->tx_dma = t->rx_dma = host->data_dma;
 	t->len = cp - data->status;
 	t->cs_change = 1;
 	spi_message_add_tail(t, &host->m);
 
-	if (host->dma_dev) {
-		host->m.is_dma_mapped = 1;
-		dma_sync_single_for_device(host->dma_dev,
-				host->data_dma, sizeof(*host->data),
-				DMA_BIDIRECTIONAL);
-	}
 	status = spi_sync_locked(host->spi, &host->m);
-
-	if (host->dma_dev)
-		dma_sync_single_for_cpu(host->dma_dev,
-				host->data_dma, sizeof(*host->data),
-				DMA_BIDIRECTIONAL);
 	if (status < 0) {
 		dev_dbg(&host->spi->dev, "  ... write returned %d\n", status);
 		cmd->error = status;
@@ -540,9 +508,6 @@ mmc_spi_command_send(struct mmc_spi_host *host,
  * We always provide TX data for data and CRC.  The MMC/SD protocol
  * requires us to write ones; but Linux defaults to writing zeroes;
  * so we explicitly initialize it to all ones on RX paths.
- *
- * We also handle DMA mapping, so the underlying SPI controller does
- * not need to (re)do it for each message.
  */
 static void
 mmc_spi_setup_data_message(
@@ -552,11 +517,8 @@ mmc_spi_setup_data_message(
 {
 	struct spi_transfer	*t;
 	struct scratch		*scratch = host->data;
-	dma_addr_t		dma = host->data_dma;
 
 	spi_message_init(&host->m);
-	if (dma)
-		host->m.is_dma_mapped = 1;
 
 	/* for reads, readblock() skips 0xff bytes before finding
 	 * the token; for writes, this transfer issues that token.
@@ -570,8 +532,6 @@ mmc_spi_setup_data_message(
 		else
 			scratch->data_token = SPI_TOKEN_SINGLE;
 		t->tx_buf = &scratch->data_token;
-		if (dma)
-			t->tx_dma = dma + offsetof(struct scratch, data_token);
 		spi_message_add_tail(t, &host->m);
 	}
 
@@ -581,7 +541,6 @@ mmc_spi_setup_data_message(
 	t = &host->t;
 	memset(t, 0, sizeof(*t));
 	t->tx_buf = host->ones;
-	t->tx_dma = host->ones_dma;
 	/* length and actual buffer info are written later */
 	spi_message_add_tail(t, &host->m);
 
@@ -591,14 +550,9 @@ mmc_spi_setup_data_message(
 	if (direction == DMA_TO_DEVICE) {
 		/* the actual CRC may get written later */
 		t->tx_buf = &scratch->crc_val;
-		if (dma)
-			t->tx_dma = dma + offsetof(struct scratch, crc_val);
 	} else {
 		t->tx_buf = host->ones;
-		t->tx_dma = host->ones_dma;
 		t->rx_buf = &scratch->crc_val;
-		if (dma)
-			t->rx_dma = dma + offsetof(struct scratch, crc_val);
 	}
 	spi_message_add_tail(t, &host->m);
 
@@ -621,10 +575,7 @@ mmc_spi_setup_data_message(
 		memset(t, 0, sizeof(*t));
 		t->len = (direction == DMA_TO_DEVICE) ? sizeof(scratch->status) : 1;
 		t->tx_buf = host->ones;
-		t->tx_dma = host->ones_dma;
 		t->rx_buf = scratch->status;
-		if (dma)
-			t->rx_dma = dma + offsetof(struct scratch, status);
 		t->cs_change = 1;
 		spi_message_add_tail(t, &host->m);
 	}
@@ -653,23 +604,13 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t,
 
 	if (host->mmc->use_spi_crc)
 		scratch->crc_val = cpu_to_be16(crc_itu_t(0, t->tx_buf, t->len));
-	if (host->dma_dev)
-		dma_sync_single_for_device(host->dma_dev,
-				host->data_dma, sizeof(*scratch),
-				DMA_BIDIRECTIONAL);
 
 	status = spi_sync_locked(spi, &host->m);
-
 	if (status != 0) {
 		dev_dbg(&spi->dev, "write error (%d)\n", status);
 		return status;
 	}
 
-	if (host->dma_dev)
-		dma_sync_single_for_cpu(host->dma_dev,
-				host->data_dma, sizeof(*scratch),
-				DMA_BIDIRECTIONAL);
-
 	/*
 	 * Get the transmission data-response reply.  It must follow
 	 * immediately after the data block we transferred.  This reply
@@ -718,8 +659,6 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t,
 	}
 
 	t->tx_buf += t->len;
-	if (host->dma_dev)
-		t->tx_dma += t->len;
 
 	/* Return when not busy.  If we didn't collect that status yet,
 	 * we'll need some more I/O.
@@ -783,30 +722,12 @@ mmc_spi_readblock(struct mmc_spi_host *host, struct spi_transfer *t,
 	}
 	leftover = status << 1;
 
-	if (host->dma_dev) {
-		dma_sync_single_for_device(host->dma_dev,
-				host->data_dma, sizeof(*scratch),
-				DMA_BIDIRECTIONAL);
-		dma_sync_single_for_device(host->dma_dev,
-				t->rx_dma, t->len,
-				DMA_FROM_DEVICE);
-	}
-
 	status = spi_sync_locked(spi, &host->m);
 	if (status < 0) {
 		dev_dbg(&spi->dev, "read error %d\n", status);
 		return status;
 	}
 
-	if (host->dma_dev) {
-		dma_sync_single_for_cpu(host->dma_dev,
-				host->data_dma, sizeof(*scratch),
-				DMA_BIDIRECTIONAL);
-		dma_sync_single_for_cpu(host->dma_dev,
-				t->rx_dma, t->len,
-				DMA_FROM_DEVICE);
-	}
-
 	if (bitshift) {
 		/* Walk through the data and the crc and do
 		 * all the magic to get byte-aligned data.
@@ -841,8 +762,6 @@ mmc_spi_readblock(struct mmc_spi_host *host, struct spi_transfer *t,
 	}
 
 	t->rx_buf += t->len;
-	if (host->dma_dev)
-		t->rx_dma += t->len;
 
 	return 0;
 }
@@ -857,7 +776,6 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd,
 		struct mmc_data *data, u32 blk_size)
 {
 	struct spi_device	*spi = host->spi;
-	struct device		*dma_dev = host->dma_dev;
 	struct spi_transfer	*t;
 	enum dma_data_direction	direction = mmc_get_dma_dir(data);
 	struct scatterlist	*sg;
@@ -884,31 +802,8 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd,
 	 */
 	for_each_sg(data->sg, sg, data->sg_len, n_sg) {
 		int			status = 0;
-		dma_addr_t		dma_addr = 0;
 		void			*kmap_addr;
 		unsigned		length = sg->length;
-		enum dma_data_direction	dir = direction;
-
-		/* set up dma mapping for controller drivers that might
-		 * use DMA ... though they may fall back to PIO
-		 */
-		if (dma_dev) {
-			/* never invalidate whole *shared* pages ... */
-			if ((sg->offset != 0 || length != PAGE_SIZE)
-					&& dir == DMA_FROM_DEVICE)
-				dir = DMA_BIDIRECTIONAL;
-
-			dma_addr = dma_map_page(dma_dev, sg_page(sg), 0,
-						PAGE_SIZE, dir);
-			if (dma_mapping_error(dma_dev, dma_addr)) {
-				data->error = -EFAULT;
-				break;
-			}
-			if (direction == DMA_TO_DEVICE)
-				t->tx_dma = dma_addr + sg->offset;
-			else
-				t->rx_dma = dma_addr + sg->offset;
-		}
 
 		/* allow pio too; we don't allow highmem */
 		kmap_addr = kmap(sg_page(sg));
@@ -941,8 +836,6 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd,
 		if (direction == DMA_FROM_DEVICE)
 			flush_dcache_page(sg_page(sg));
 		kunmap(sg_page(sg));
-		if (dma_dev)
-			dma_unmap_page(dma_dev, dma_addr, PAGE_SIZE, dir);
 
 		if (status < 0) {
 			data->error = status;
@@ -977,21 +870,9 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd,
 		scratch->status[0] = SPI_TOKEN_STOP_TRAN;
 
 		host->early_status.tx_buf = host->early_status.rx_buf;
-		host->early_status.tx_dma = host->early_status.rx_dma;
 		host->early_status.len = statlen;
 
-		if (host->dma_dev)
-			dma_sync_single_for_device(host->dma_dev,
-					host->data_dma, sizeof(*scratch),
-					DMA_BIDIRECTIONAL);
-
 		tmp = spi_sync_locked(spi, &host->m);
-
-		if (host->dma_dev)
-			dma_sync_single_for_cpu(host->dma_dev,
-					host->data_dma, sizeof(*scratch),
-					DMA_BIDIRECTIONAL);
-
 		if (tmp < 0) {
 			if (!data->error)
 				data->error = tmp;
@@ -1265,52 +1146,6 @@ mmc_spi_detect_irq(int irq, void *mmc)
 	return IRQ_HANDLED;
 }
 
-#ifdef CONFIG_HAS_DMA
-static int mmc_spi_dma_alloc(struct mmc_spi_host *host)
-{
-	struct spi_device *spi = host->spi;
-	struct device *dev;
-
-	if (!spi->master->dev.parent->dma_mask)
-		return 0;
-
-	dev = spi->master->dev.parent;
-
-	host->ones_dma = dma_map_single(dev, host->ones, MMC_SPI_BLOCKSIZE,
-					DMA_TO_DEVICE);
-	if (dma_mapping_error(dev, host->ones_dma))
-		return -ENOMEM;
-
-	host->data_dma = dma_map_single(dev, host->data, sizeof(*host->data),
-					DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(dev, host->data_dma)) {
-		dma_unmap_single(dev, host->ones_dma, MMC_SPI_BLOCKSIZE,
-				 DMA_TO_DEVICE);
-		return -ENOMEM;
-	}
-
-	dma_sync_single_for_cpu(dev, host->data_dma, sizeof(*host->data),
-				DMA_BIDIRECTIONAL);
-
-	host->dma_dev = dev;
-	return 0;
-}
-
-static void mmc_spi_dma_free(struct mmc_spi_host *host)
-{
-	if (!host->dma_dev)
-		return;
-
-	dma_unmap_single(host->dma_dev, host->ones_dma, MMC_SPI_BLOCKSIZE,
-			 DMA_TO_DEVICE);
-	dma_unmap_single(host->dma_dev, host->data_dma,	sizeof(*host->data),
-			 DMA_BIDIRECTIONAL);
-}
-#else
-static inline int mmc_spi_dma_alloc(struct mmc_spi_host *host) { return 0; }
-static inline void mmc_spi_dma_free(struct mmc_spi_host *host) {}
-#endif
-
 static int mmc_spi_probe(struct spi_device *spi)
 {
 	void			*ones;
@@ -1402,24 +1237,17 @@ static int mmc_spi_probe(struct spi_device *spi)
 			host->powerup_msecs = 250;
 	}
 
-	/* preallocate dma buffers */
+	/* Preallocate buffers */
 	host->data = kmalloc(sizeof(*host->data), GFP_KERNEL);
 	if (!host->data)
 		goto fail_nobuf1;
 
-	status = mmc_spi_dma_alloc(host);
-	if (status)
-		goto fail_dma;
-
 	/* setup message for status/busy readback */
 	spi_message_init(&host->readback);
-	host->readback.is_dma_mapped = (host->dma_dev != NULL);
 
 	spi_message_add_tail(&host->status, &host->readback);
 	host->status.tx_buf = host->ones;
-	host->status.tx_dma = host->ones_dma;
 	host->status.rx_buf = &host->data->status;
-	host->status.rx_dma = host->data_dma + offsetof(struct scratch, status);
 	host->status.cs_change = 1;
 
 	/* register card detect irq */
@@ -1464,9 +1292,8 @@ static int mmc_spi_probe(struct spi_device *spi)
 	if (!status)
 		has_ro = true;
 
-	dev_info(&spi->dev, "SD/MMC host %s%s%s%s%s\n",
+	dev_info(&spi->dev, "SD/MMC host %s%s%s%s\n",
 			dev_name(&mmc->class_dev),
-			host->dma_dev ? "" : ", no DMA",
 			has_ro ? "" : ", no WP",
 			(host->pdata && host->pdata->setpower)
 				? "" : ", no poweroff",
@@ -1477,8 +1304,6 @@ static int mmc_spi_probe(struct spi_device *spi)
 fail_gpiod_request:
 	mmc_remove_host(mmc);
 fail_glue_init:
-	mmc_spi_dma_free(host);
-fail_dma:
 	kfree(host->data);
 fail_nobuf1:
 	mmc_spi_put_pdata(spi);
@@ -1500,7 +1325,6 @@ static void mmc_spi_remove(struct spi_device *spi)
 
 	mmc_remove_host(mmc);
 
-	mmc_spi_dma_free(host);
 	kfree(host->data);
 	kfree(host->ones);
 
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index e967cca7a16f..b790c3c3c8f9 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -273,6 +273,7 @@ static struct variant_data variant_stm32_sdmmc = {
 	.datactrl_mask_sdio	= MCI_DPSM_ST_SDIOEN,
 	.stm32_idmabsize_mask	= GENMASK(12, 5),
 	.stm32_idmabsize_align	= BIT(5),
+	.supports_sdio_irq	= true,
 	.busy_timeout		= true,
 	.busy_detect		= true,
 	.busy_detect_flag	= MCI_STM32_BUSYD0,
@@ -300,6 +301,7 @@ static struct variant_data variant_stm32_sdmmcv2 = {
 	.datactrl_mask_sdio	= MCI_DPSM_ST_SDIOEN,
 	.stm32_idmabsize_mask	= GENMASK(16, 5),
 	.stm32_idmabsize_align	= BIT(5),
+	.supports_sdio_irq	= true,
 	.dma_lli		= true,
 	.busy_timeout		= true,
 	.busy_detect		= true,
@@ -328,6 +330,7 @@ static struct variant_data variant_stm32_sdmmcv3 = {
 	.datactrl_mask_sdio	= MCI_DPSM_ST_SDIOEN,
 	.stm32_idmabsize_mask	= GENMASK(16, 6),
 	.stm32_idmabsize_align	= BIT(6),
+	.supports_sdio_irq	= true,
 	.dma_lli		= true,
 	.busy_timeout		= true,
 	.busy_detect		= true,
@@ -421,8 +424,9 @@ void mmci_write_pwrreg(struct mmci_host *host, u32 pwr)
  */
 static void mmci_write_datactrlreg(struct mmci_host *host, u32 datactrl)
 {
-	/* Keep busy mode in DPSM if enabled */
-	datactrl |= host->datactrl_reg & host->variant->busy_dpsm_flag;
+	/* Keep busy mode in DPSM and SDIO mask if enabled */
+	datactrl |= host->datactrl_reg & (host->variant->busy_dpsm_flag |
+					  host->variant->datactrl_mask_sdio);
 
 	if (host->datactrl_reg != datactrl) {
 		host->datactrl_reg = datactrl;
@@ -1762,6 +1766,25 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static void mmci_write_sdio_irq_bit(struct mmci_host *host, int enable)
+{
+	void __iomem *base = host->base;
+	u32 mask = readl_relaxed(base + MMCIMASK0);
+
+	if (enable)
+		writel_relaxed(mask | MCI_ST_SDIOITMASK, base + MMCIMASK0);
+	else
+		writel_relaxed(mask & ~MCI_ST_SDIOITMASK, base + MMCIMASK0);
+}
+
+static void mmci_signal_sdio_irq(struct mmci_host *host, u32 status)
+{
+	if (status & MCI_ST_SDIOIT) {
+		mmci_write_sdio_irq_bit(host, 0);
+		sdio_signal_irq(host->mmc);
+	}
+}
+
 /*
  * Handle completion of command and data transfers.
  */
@@ -1806,6 +1829,9 @@ static irqreturn_t mmci_irq(int irq, void *dev_id)
 			mmci_data_irq(host, host->data, status);
 		}
 
+		if (host->variant->supports_sdio_irq)
+			mmci_signal_sdio_irq(host, status);
+
 		/*
 		 * Busy detection has been handled by mmci_cmd_irq() above.
 		 * Clear the status bit to prevent polling in IRQ context.
@@ -2042,6 +2068,35 @@ static int mmci_sig_volt_switch(struct mmc_host *mmc, struct mmc_ios *ios)
 	return ret;
 }
 
+static void mmci_enable_sdio_irq(struct mmc_host *mmc, int enable)
+{
+	struct mmci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+
+	if (enable)
+		/* Keep the SDIO mode bit if SDIO irqs are enabled */
+		pm_runtime_get_sync(mmc_dev(mmc));
+
+	spin_lock_irqsave(&host->lock, flags);
+	mmci_write_sdio_irq_bit(host, enable);
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	if (!enable) {
+		pm_runtime_mark_last_busy(mmc_dev(mmc));
+		pm_runtime_put_autosuspend(mmc_dev(mmc));
+	}
+}
+
+static void mmci_ack_sdio_irq(struct mmc_host *mmc)
+{
+	struct mmci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&host->lock, flags);
+	mmci_write_sdio_irq_bit(host, 1);
+	spin_unlock_irqrestore(&host->lock, flags);
+}
+
 static struct mmc_host_ops mmci_ops = {
 	.request	= mmci_request,
 	.pre_req	= mmci_pre_request,
@@ -2317,6 +2372,16 @@ static int mmci_probe(struct amba_device *dev,
 		mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY;
 	}
 
+	if (variant->supports_sdio_irq && host->mmc->caps & MMC_CAP_SDIO_IRQ) {
+		mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD;
+
+		mmci_ops.enable_sdio_irq = mmci_enable_sdio_irq;
+		mmci_ops.ack_sdio_irq	= mmci_ack_sdio_irq;
+
+		mmci_write_datactrlreg(host,
+				       host->variant->datactrl_mask_sdio);
+	}
+
 	/* Variants with mandatory busy timeout in HW needs R1B responses. */
 	if (variant->busy_timeout)
 		mmc->caps |= MMC_CAP_NEED_RSP_BUSY;
diff --git a/drivers/mmc/host/mmci.h b/drivers/mmc/host/mmci.h
index 34d9897c289b..a5eb4ced4d5d 100644
--- a/drivers/mmc/host/mmci.h
+++ b/drivers/mmc/host/mmci.h
@@ -331,6 +331,7 @@ enum mmci_busy_state {
  *	       register.
  * @opendrain: bitmask identifying the OPENDRAIN bit inside MMCIPOWER register
  * @dma_lli: true if variant has dma link list feature.
+ * @supports_sdio_irq: allow SD I/O card to interrupt the host
  * @stm32_idmabsize_mask: stm32 sdmmc idma buffer size.
  * @dma_flow_controller: use peripheral as flow controller for DMA.
  */
@@ -377,6 +378,7 @@ struct variant_data {
 	u32			start_err;
 	u32			opendrain;
 	u8			dma_lli:1;
+	bool			supports_sdio_irq;
 	u32			stm32_idmabsize_mask;
 	u32			stm32_idmabsize_align;
 	bool			dma_flow_controller;
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 97f7c3d4be6e..1634b1f5d201 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -252,12 +252,16 @@
 
 #define MSDC_PAD_TUNE_DATWRDLY	  GENMASK(4, 0)		/* RW */
 #define MSDC_PAD_TUNE_DATRRDLY	  GENMASK(12, 8)	/* RW */
+#define MSDC_PAD_TUNE_DATRRDLY2	  GENMASK(12, 8)	/* RW */
 #define MSDC_PAD_TUNE_CMDRDLY	  GENMASK(20, 16)	/* RW */
+#define MSDC_PAD_TUNE_CMDRDLY2	  GENMASK(20, 16)	/* RW */
 #define MSDC_PAD_TUNE_CMDRRDLY	  GENMASK(26, 22)	/* RW */
 #define MSDC_PAD_TUNE_CLKTDLY	  GENMASK(31, 27)	/* RW */
 #define MSDC_PAD_TUNE_RXDLYSEL	  BIT(15)   /* RW */
 #define MSDC_PAD_TUNE_RD_SEL	  BIT(13)   /* RW */
 #define MSDC_PAD_TUNE_CMD_SEL	  BIT(21)   /* RW */
+#define MSDC_PAD_TUNE_RD2_SEL	  BIT(13)   /* RW */
+#define MSDC_PAD_TUNE_CMD2_SEL	  BIT(21)   /* RW */
 
 #define PAD_DS_TUNE_DLY_SEL       BIT(0)	  /* RW */
 #define PAD_DS_TUNE_DLY1	  GENMASK(6, 2)   /* RW */
@@ -325,7 +329,9 @@
 
 #define DEFAULT_DEBOUNCE	(8)	/* 8 cycles CD debounce */
 
-#define PAD_DELAY_MAX	32 /* PAD delay cells */
+#define TUNING_REG2_FIXED_OFFEST	4
+#define PAD_DELAY_HALF	32 /* PAD delay cells */
+#define PAD_DELAY_FULL	64
 /*--------------------------------------------------------------------------*/
 /* Descriptor Structure                                                     */
 /*--------------------------------------------------------------------------*/
@@ -461,6 +467,7 @@ struct msdc_host {
 	u32 hs400_ds_dly3;
 	u32 hs200_cmd_int_delay; /* cmd internal delay for HS200/SDR104 */
 	u32 hs400_cmd_int_delay; /* cmd internal delay for HS400 */
+	u32 tuning_step;
 	bool hs400_cmd_resp_sel_rising;
 				 /* cmd response sample selection for HS400 */
 	bool hs400_mode;	/* current eMMC will run at hs400 mode */
@@ -1149,9 +1156,11 @@ static void msdc_recheck_sdio_irq(struct msdc_host *host)
 
 static void msdc_track_cmd_data(struct msdc_host *host, struct mmc_command *cmd)
 {
-	if (host->error)
-		dev_dbg(host->dev, "%s: cmd=%d arg=%08X; host->error=0x%08X\n",
-			__func__, cmd->opcode, cmd->arg, host->error);
+	if (host->error &&
+	    ((!mmc_op_tuning(cmd->opcode) && !host->hs400_tuning) ||
+	     cmd->error == -ETIMEDOUT))
+		dev_warn(host->dev, "%s: cmd=%d arg=%08X; host->error=0x%08X\n",
+			 __func__, cmd->opcode, cmd->arg, host->error);
 }
 
 static void msdc_request_done(struct msdc_host *host, struct mmc_request *mrq)
@@ -1615,7 +1624,7 @@ static irqreturn_t msdc_cmdq_irq(struct msdc_host *host, u32 intsts)
 	}
 
 	if (cmd_err || dat_err) {
-		dev_err(host->dev, "cmd_err = %d, dat_err =%d, intsts = 0x%x",
+		dev_err(host->dev, "cmd_err = %d, dat_err = %d, intsts = 0x%x",
 			cmd_err, dat_err, intsts);
 	}
 
@@ -1780,10 +1789,20 @@ static void msdc_init_hw(struct msdc_host *host)
 				     DATA_K_VALUE_SEL);
 			sdr_set_bits(host->top_base + EMMC_TOP_CMD,
 				     PAD_CMD_RD_RXDLY_SEL);
+			if (host->tuning_step > PAD_DELAY_HALF) {
+				sdr_set_bits(host->top_base + EMMC_TOP_CONTROL,
+					     PAD_DAT_RD_RXDLY2_SEL);
+				sdr_set_bits(host->top_base + EMMC_TOP_CMD,
+					     PAD_CMD_RD_RXDLY2_SEL);
+			}
 		} else {
 			sdr_set_bits(host->base + tune_reg,
 				     MSDC_PAD_TUNE_RD_SEL |
 				     MSDC_PAD_TUNE_CMD_SEL);
+			if (host->tuning_step > PAD_DELAY_HALF)
+				sdr_set_bits(host->base + tune_reg + TUNING_REG2_FIXED_OFFEST,
+					     MSDC_PAD_TUNE_RD2_SEL |
+					     MSDC_PAD_TUNE_CMD2_SEL);
 		}
 	} else {
 		/* choose clock tune */
@@ -1925,24 +1944,24 @@ static void msdc_ops_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		msdc_set_mclk(host, ios->timing, ios->clock);
 }
 
-static u32 test_delay_bit(u32 delay, u32 bit)
+static u64 test_delay_bit(u64 delay, u32 bit)
 {
-	bit %= PAD_DELAY_MAX;
-	return delay & BIT(bit);
+	bit %= PAD_DELAY_FULL;
+	return delay & BIT_ULL(bit);
 }
 
-static int get_delay_len(u32 delay, u32 start_bit)
+static int get_delay_len(u64 delay, u32 start_bit)
 {
 	int i;
 
-	for (i = 0; i < (PAD_DELAY_MAX - start_bit); i++) {
+	for (i = 0; i < (PAD_DELAY_FULL - start_bit); i++) {
 		if (test_delay_bit(delay, start_bit + i) == 0)
 			return i;
 	}
-	return PAD_DELAY_MAX - start_bit;
+	return PAD_DELAY_FULL - start_bit;
 }
 
-static struct msdc_delay_phase get_best_delay(struct msdc_host *host, u32 delay)
+static struct msdc_delay_phase get_best_delay(struct msdc_host *host, u64 delay)
 {
 	int start = 0, len = 0;
 	int start_final = 0, len_final = 0;
@@ -1950,28 +1969,28 @@ static struct msdc_delay_phase get_best_delay(struct msdc_host *host, u32 delay)
 	struct msdc_delay_phase delay_phase = { 0, };
 
 	if (delay == 0) {
-		dev_err(host->dev, "phase error: [map:%x]\n", delay);
+		dev_err(host->dev, "phase error: [map:%016llx]\n", delay);
 		delay_phase.final_phase = final_phase;
 		return delay_phase;
 	}
 
-	while (start < PAD_DELAY_MAX) {
+	while (start < PAD_DELAY_FULL) {
 		len = get_delay_len(delay, start);
 		if (len_final < len) {
 			start_final = start;
 			len_final = len;
 		}
 		start += len ? len : 1;
-		if (len >= 12 && start_final < 4)
+		if (!upper_32_bits(delay) && len >= 12 && start_final < 4)
 			break;
 	}
 
 	/* The rule is that to find the smallest delay cell */
 	if (start_final == 0)
-		final_phase = (start_final + len_final / 3) % PAD_DELAY_MAX;
+		final_phase = (start_final + len_final / 3) % PAD_DELAY_FULL;
 	else
-		final_phase = (start_final + len_final / 2) % PAD_DELAY_MAX;
-	dev_dbg(host->dev, "phase: [map:%x] [maxlen:%d] [final:%d]\n",
+		final_phase = (start_final + len_final / 2) % PAD_DELAY_FULL;
+	dev_dbg(host->dev, "phase: [map:%016llx] [maxlen:%d] [final:%d]\n",
 		delay, len_final, final_phase);
 
 	delay_phase.maxlen = len_final;
@@ -1984,30 +2003,64 @@ static inline void msdc_set_cmd_delay(struct msdc_host *host, u32 value)
 {
 	u32 tune_reg = host->dev_comp->pad_tune_reg;
 
-	if (host->top_base)
-		sdr_set_field(host->top_base + EMMC_TOP_CMD, PAD_CMD_RXDLY,
-			      value);
-	else
-		sdr_set_field(host->base + tune_reg, MSDC_PAD_TUNE_CMDRDLY,
-			      value);
+	if (host->top_base) {
+		if (value < PAD_DELAY_HALF) {
+			sdr_set_field(host->top_base + EMMC_TOP_CMD, PAD_CMD_RXDLY, value);
+			sdr_set_field(host->top_base + EMMC_TOP_CMD, PAD_CMD_RXDLY2, 0);
+		} else {
+			sdr_set_field(host->top_base + EMMC_TOP_CMD, PAD_CMD_RXDLY,
+				      PAD_DELAY_HALF - 1);
+			sdr_set_field(host->top_base + EMMC_TOP_CMD, PAD_CMD_RXDLY2,
+				      value - PAD_DELAY_HALF);
+		}
+	} else {
+		if (value < PAD_DELAY_HALF) {
+			sdr_set_field(host->base + tune_reg, MSDC_PAD_TUNE_CMDRDLY, value);
+			sdr_set_field(host->base + tune_reg + TUNING_REG2_FIXED_OFFEST,
+				      MSDC_PAD_TUNE_CMDRDLY2, 0);
+		} else {
+			sdr_set_field(host->base + tune_reg, MSDC_PAD_TUNE_CMDRDLY,
+				      PAD_DELAY_HALF - 1);
+			sdr_set_field(host->base + tune_reg + TUNING_REG2_FIXED_OFFEST,
+				      MSDC_PAD_TUNE_CMDRDLY2, value - PAD_DELAY_HALF);
+		}
+	}
 }
 
 static inline void msdc_set_data_delay(struct msdc_host *host, u32 value)
 {
 	u32 tune_reg = host->dev_comp->pad_tune_reg;
 
-	if (host->top_base)
-		sdr_set_field(host->top_base + EMMC_TOP_CONTROL,
-			      PAD_DAT_RD_RXDLY, value);
-	else
-		sdr_set_field(host->base + tune_reg, MSDC_PAD_TUNE_DATRRDLY,
-			      value);
+	if (host->top_base) {
+		if (value < PAD_DELAY_HALF) {
+			sdr_set_field(host->top_base + EMMC_TOP_CONTROL,
+				      PAD_DAT_RD_RXDLY, value);
+			sdr_set_field(host->top_base + EMMC_TOP_CONTROL,
+				      PAD_DAT_RD_RXDLY2, 0);
+		} else {
+			sdr_set_field(host->top_base + EMMC_TOP_CONTROL,
+				      PAD_DAT_RD_RXDLY, PAD_DELAY_HALF - 1);
+			sdr_set_field(host->top_base + EMMC_TOP_CONTROL,
+				      PAD_DAT_RD_RXDLY2, value - PAD_DELAY_HALF);
+		}
+	} else {
+		if (value < PAD_DELAY_HALF) {
+			sdr_set_field(host->base + tune_reg, MSDC_PAD_TUNE_DATRRDLY, value);
+			sdr_set_field(host->base + tune_reg + TUNING_REG2_FIXED_OFFEST,
+				      MSDC_PAD_TUNE_DATRRDLY2, 0);
+		} else {
+			sdr_set_field(host->base + tune_reg, MSDC_PAD_TUNE_DATRRDLY,
+				      PAD_DELAY_HALF - 1);
+			sdr_set_field(host->base + tune_reg + TUNING_REG2_FIXED_OFFEST,
+				      MSDC_PAD_TUNE_DATRRDLY2, value - PAD_DELAY_HALF);
+		}
+	}
 }
 
 static int msdc_tune_response(struct mmc_host *mmc, u32 opcode)
 {
 	struct msdc_host *host = mmc_priv(mmc);
-	u32 rise_delay = 0, fall_delay = 0;
+	u64 rise_delay = 0, fall_delay = 0;
 	struct msdc_delay_phase final_rise_delay, final_fall_delay = { 0,};
 	struct msdc_delay_phase internal_delay_phase;
 	u8 final_delay, final_maxlen;
@@ -2023,7 +2076,7 @@ static int msdc_tune_response(struct mmc_host *mmc, u32 opcode)
 			      host->hs200_cmd_int_delay);
 
 	sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
-	for (i = 0 ; i < PAD_DELAY_MAX; i++) {
+	for (i = 0; i < host->tuning_step; i++) {
 		msdc_set_cmd_delay(host, i);
 		/*
 		 * Using the same parameters, it may sometimes pass the test,
@@ -2033,9 +2086,9 @@ static int msdc_tune_response(struct mmc_host *mmc, u32 opcode)
 		for (j = 0; j < 3; j++) {
 			mmc_send_tuning(mmc, opcode, &cmd_err);
 			if (!cmd_err) {
-				rise_delay |= BIT(i);
+				rise_delay |= BIT_ULL(i);
 			} else {
-				rise_delay &= ~BIT(i);
+				rise_delay &= ~BIT_ULL(i);
 				break;
 			}
 		}
@@ -2047,7 +2100,7 @@ static int msdc_tune_response(struct mmc_host *mmc, u32 opcode)
 		goto skip_fall;
 
 	sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
-	for (i = 0; i < PAD_DELAY_MAX; i++) {
+	for (i = 0; i < host->tuning_step; i++) {
 		msdc_set_cmd_delay(host, i);
 		/*
 		 * Using the same parameters, it may sometimes pass the test,
@@ -2057,9 +2110,9 @@ static int msdc_tune_response(struct mmc_host *mmc, u32 opcode)
 		for (j = 0; j < 3; j++) {
 			mmc_send_tuning(mmc, opcode, &cmd_err);
 			if (!cmd_err) {
-				fall_delay |= BIT(i);
+				fall_delay |= BIT_ULL(i);
 			} else {
-				fall_delay &= ~BIT(i);
+				fall_delay &= ~BIT_ULL(i);
 				break;
 			}
 		}
@@ -2082,12 +2135,12 @@ skip_fall:
 	if (host->dev_comp->async_fifo || host->hs200_cmd_int_delay)
 		goto skip_internal;
 
-	for (i = 0; i < PAD_DELAY_MAX; i++) {
+	for (i = 0; i < host->tuning_step; i++) {
 		sdr_set_field(host->base + tune_reg,
 			      MSDC_PAD_TUNE_CMDRRDLY, i);
 		mmc_send_tuning(mmc, opcode, &cmd_err);
 		if (!cmd_err)
-			internal_delay |= BIT(i);
+			internal_delay |= BIT_ULL(i);
 	}
 	dev_dbg(host->dev, "Final internal delay: 0x%x\n", internal_delay);
 	internal_delay_phase = get_best_delay(host, internal_delay);
@@ -2121,7 +2174,8 @@ static int hs400_tune_response(struct mmc_host *mmc, u32 opcode)
 		sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
 	else
 		sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
-	for (i = 0 ; i < PAD_DELAY_MAX; i++) {
+
+	for (i = 0; i < PAD_DELAY_HALF; i++) {
 		sdr_set_field(host->base + PAD_CMD_TUNE,
 			      PAD_CMD_TUNE_RX_DLY3, i);
 		/*
@@ -2151,7 +2205,7 @@ static int hs400_tune_response(struct mmc_host *mmc, u32 opcode)
 static int msdc_tune_data(struct mmc_host *mmc, u32 opcode)
 {
 	struct msdc_host *host = mmc_priv(mmc);
-	u32 rise_delay = 0, fall_delay = 0;
+	u64 rise_delay = 0, fall_delay = 0;
 	struct msdc_delay_phase final_rise_delay, final_fall_delay = { 0,};
 	u8 final_delay, final_maxlen;
 	int i, ret;
@@ -2160,11 +2214,11 @@ static int msdc_tune_data(struct mmc_host *mmc, u32 opcode)
 		      host->latch_ck);
 	sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_DSPL);
 	sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_W_DSPL);
-	for (i = 0 ; i < PAD_DELAY_MAX; i++) {
+	for (i = 0; i < host->tuning_step; i++) {
 		msdc_set_data_delay(host, i);
 		ret = mmc_send_tuning(mmc, opcode, NULL);
 		if (!ret)
-			rise_delay |= BIT(i);
+			rise_delay |= BIT_ULL(i);
 	}
 	final_rise_delay = get_best_delay(host, rise_delay);
 	/* if rising edge has enough margin, then do not scan falling edge */
@@ -2174,11 +2228,11 @@ static int msdc_tune_data(struct mmc_host *mmc, u32 opcode)
 
 	sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_DSPL);
 	sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_W_DSPL);
-	for (i = 0; i < PAD_DELAY_MAX; i++) {
+	for (i = 0; i < host->tuning_step; i++) {
 		msdc_set_data_delay(host, i);
 		ret = mmc_send_tuning(mmc, opcode, NULL);
 		if (!ret)
-			fall_delay |= BIT(i);
+			fall_delay |= BIT_ULL(i);
 	}
 	final_fall_delay = get_best_delay(host, fall_delay);
 
@@ -2206,7 +2260,7 @@ skip_fall:
 static int msdc_tune_together(struct mmc_host *mmc, u32 opcode)
 {
 	struct msdc_host *host = mmc_priv(mmc);
-	u32 rise_delay = 0, fall_delay = 0;
+	u64 rise_delay = 0, fall_delay = 0;
 	struct msdc_delay_phase final_rise_delay, final_fall_delay = { 0,};
 	u8 final_delay, final_maxlen;
 	int i, ret;
@@ -2217,12 +2271,12 @@ static int msdc_tune_together(struct mmc_host *mmc, u32 opcode)
 	sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
 	sdr_clr_bits(host->base + MSDC_IOCON,
 		     MSDC_IOCON_DSPL | MSDC_IOCON_W_DSPL);
-	for (i = 0 ; i < PAD_DELAY_MAX; i++) {
+	for (i = 0; i < host->tuning_step; i++) {
 		msdc_set_cmd_delay(host, i);
 		msdc_set_data_delay(host, i);
 		ret = mmc_send_tuning(mmc, opcode, NULL);
 		if (!ret)
-			rise_delay |= BIT(i);
+			rise_delay |= BIT_ULL(i);
 	}
 	final_rise_delay = get_best_delay(host, rise_delay);
 	/* if rising edge has enough margin, then do not scan falling edge */
@@ -2233,12 +2287,12 @@ static int msdc_tune_together(struct mmc_host *mmc, u32 opcode)
 	sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
 	sdr_set_bits(host->base + MSDC_IOCON,
 		     MSDC_IOCON_DSPL | MSDC_IOCON_W_DSPL);
-	for (i = 0; i < PAD_DELAY_MAX; i++) {
+	for (i = 0; i < host->tuning_step; i++) {
 		msdc_set_cmd_delay(host, i);
 		msdc_set_data_delay(host, i);
 		ret = mmc_send_tuning(mmc, opcode, NULL);
 		if (!ret)
-			fall_delay |= BIT(i);
+			fall_delay |= BIT_ULL(i);
 	}
 	final_fall_delay = get_best_delay(host, fall_delay);
 
@@ -2346,7 +2400,7 @@ static int msdc_execute_hs400_tuning(struct mmc_host *mmc, struct mmc_card *card
 	}
 
 	host->hs400_tuning = true;
-	for (i = 0; i < PAD_DELAY_MAX; i++) {
+	for (i = 0; i < PAD_DELAY_HALF; i++) {
 		if (host->top_base)
 			sdr_set_field(host->top_base + EMMC50_PAD_DS_TUNE,
 				      PAD_DS_DLY1, i);
@@ -2580,6 +2634,8 @@ static const struct cqhci_host_ops msdc_cmdq_ops = {
 static void msdc_of_property_parse(struct platform_device *pdev,
 				   struct msdc_host *host)
 {
+	struct mmc_host *mmc = mmc_from_priv(host);
+
 	of_property_read_u32(pdev->dev.of_node, "mediatek,latch-ck",
 			     &host->latch_ck);
 
@@ -2601,6 +2657,14 @@ static void msdc_of_property_parse(struct platform_device *pdev,
 	else
 		host->hs400_cmd_resp_sel_rising = false;
 
+	if (of_property_read_u32(pdev->dev.of_node, "mediatek,tuning-step",
+				 &host->tuning_step)) {
+		if (mmc->caps2 & MMC_CAP2_NO_MMC)
+			host->tuning_step = PAD_DELAY_FULL;
+		else
+			host->tuning_step = PAD_DELAY_HALF;
+	}
+
 	if (of_property_read_bool(pdev->dev.of_node,
 				  "supports-cqe"))
 		host->cqhci = true;
diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c
index c23251bb95f3..9053526fa212 100644
--- a/drivers/mmc/host/sdhci-brcmstb.c
+++ b/drivers/mmc/host/sdhci-brcmstb.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/mmc/host.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -44,8 +45,13 @@ struct brcmstb_match_priv {
 
 static inline void enable_clock_gating(struct sdhci_host *host)
 {
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_brcmstb_priv *priv = sdhci_pltfm_priv(pltfm_host);
 	u32 reg;
 
+	if (!(priv->flags & BRCMSTB_PRIV_FLAGS_GATE_CLOCK))
+		return;
+
 	reg = sdhci_readl(host, SDHCI_VENDOR);
 	reg |= SDHCI_VENDOR_GATE_SDCLK_EN;
 	sdhci_writel(host, reg, SDHCI_VENDOR);
@@ -53,14 +59,53 @@ static inline void enable_clock_gating(struct sdhci_host *host)
 
 static void brcmstb_reset(struct sdhci_host *host, u8 mask)
 {
-	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
-	struct sdhci_brcmstb_priv *priv = sdhci_pltfm_priv(pltfm_host);
-
 	sdhci_and_cqhci_reset(host, mask);
 
 	/* Reset will clear this, so re-enable it */
-	if (priv->flags & BRCMSTB_PRIV_FLAGS_GATE_CLOCK)
-		enable_clock_gating(host);
+	enable_clock_gating(host);
+}
+
+static void brcmstb_sdhci_reset_cmd_data(struct sdhci_host *host, u8 mask)
+{
+	u32 new_mask = (mask &  (SDHCI_RESET_CMD | SDHCI_RESET_DATA)) << 24;
+	int ret;
+	u32 reg;
+
+	/*
+	 * SDHCI_CLOCK_CONTROL register CARD_EN and CLOCK_INT_EN bits shall
+	 * be set along with SOFTWARE_RESET register RESET_CMD or RESET_DATA
+	 * bits, hence access SDHCI_CLOCK_CONTROL register as 32-bit register
+	 */
+	new_mask |= SDHCI_CLOCK_CARD_EN | SDHCI_CLOCK_INT_EN;
+	reg = sdhci_readl(host, SDHCI_CLOCK_CONTROL);
+	sdhci_writel(host, reg | new_mask, SDHCI_CLOCK_CONTROL);
+
+	reg = sdhci_readb(host, SDHCI_SOFTWARE_RESET);
+
+	ret = read_poll_timeout_atomic(sdhci_readb, reg, !(reg & mask),
+				       10, 10000, false,
+				       host, SDHCI_SOFTWARE_RESET);
+
+	if (ret) {
+		pr_err("%s: Reset 0x%x never completed.\n",
+		       mmc_hostname(host->mmc), (int)mask);
+		sdhci_err_stats_inc(host, CTRL_TIMEOUT);
+		sdhci_dumpregs(host);
+	}
+}
+
+static void brcmstb_reset_74165b0(struct sdhci_host *host, u8 mask)
+{
+	/* take care of RESET_ALL as usual */
+	if (mask & SDHCI_RESET_ALL)
+		sdhci_and_cqhci_reset(host, SDHCI_RESET_ALL);
+
+	/* cmd and/or data treated differently on this core */
+	if (mask & (SDHCI_RESET_CMD | SDHCI_RESET_DATA))
+		brcmstb_sdhci_reset_cmd_data(host, mask);
+
+	/* Reset will clear this, so re-enable it */
+	enable_clock_gating(host);
 }
 
 static void sdhci_brcmstb_hs400es(struct mmc_host *mmc, struct mmc_ios *ios)
@@ -162,6 +207,13 @@ static struct sdhci_ops sdhci_brcmstb_ops_7216 = {
 	.set_uhs_signaling = sdhci_brcmstb_set_uhs_signaling,
 };
 
+static struct sdhci_ops sdhci_brcmstb_ops_74165b0 = {
+	.set_clock = sdhci_brcmstb_set_clock,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = brcmstb_reset_74165b0,
+	.set_uhs_signaling = sdhci_brcmstb_set_uhs_signaling,
+};
+
 static struct brcmstb_match_priv match_priv_7425 = {
 	.flags = BRCMSTB_MATCH_FLAGS_NO_64BIT |
 	BRCMSTB_MATCH_FLAGS_BROKEN_TIMEOUT,
@@ -179,10 +231,17 @@ static const struct brcmstb_match_priv match_priv_7216 = {
 	.ops = &sdhci_brcmstb_ops_7216,
 };
 
+static struct brcmstb_match_priv match_priv_74165b0 = {
+	.flags = BRCMSTB_MATCH_FLAGS_HAS_CLOCK_GATE,
+	.hs400es = sdhci_brcmstb_hs400es,
+	.ops = &sdhci_brcmstb_ops_74165b0,
+};
+
 static const struct of_device_id __maybe_unused sdhci_brcm_of_match[] = {
 	{ .compatible = "brcm,bcm7425-sdhci", .data = &match_priv_7425 },
 	{ .compatible = "brcm,bcm7445-sdhci", .data = &match_priv_7445 },
 	{ .compatible = "brcm,bcm7216-sdhci", .data = &match_priv_7216 },
+	{ .compatible = "brcm,bcm74165b0-sdhci", .data = &match_priv_74165b0 },
 	{},
 };
 
diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c
index 3a3bae6948a8..a1f57af6acfb 100644
--- a/drivers/mmc/host/sdhci-of-dwcmshc.c
+++ b/drivers/mmc/host/sdhci-of-dwcmshc.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/dma-mapping.h>
 #include <linux/iopoll.h>
@@ -35,6 +36,21 @@
 #define DWCMSHC_CARD_IS_EMMC		BIT(0)
 #define DWCMSHC_ENHANCED_STROBE		BIT(8)
 #define DWCMSHC_EMMC_ATCTRL		0x40
+/* Tuning and auto-tuning fields in AT_CTRL_R control register */
+#define AT_CTRL_AT_EN			BIT(0) /* autotuning is enabled */
+#define AT_CTRL_CI_SEL			BIT(1) /* interval to drive center phase select */
+#define AT_CTRL_SWIN_TH_EN		BIT(2) /* sampling window threshold enable */
+#define AT_CTRL_RPT_TUNE_ERR		BIT(3) /* enable reporting framing errors */
+#define AT_CTRL_SW_TUNE_EN		BIT(4) /* enable software managed tuning */
+#define AT_CTRL_WIN_EDGE_SEL_MASK	GENMASK(11, 8) /* bits [11:8] */
+#define AT_CTRL_WIN_EDGE_SEL		0xf /* sampling window edge select */
+#define AT_CTRL_TUNE_CLK_STOP_EN	BIT(16) /* clocks stopped during phase code change */
+#define AT_CTRL_PRE_CHANGE_DLY_MASK	GENMASK(18, 17) /* bits [18:17] */
+#define AT_CTRL_PRE_CHANGE_DLY		0x1  /* 2-cycle latency */
+#define AT_CTRL_POST_CHANGE_DLY_MASK	GENMASK(20, 19) /* bits [20:19] */
+#define AT_CTRL_POST_CHANGE_DLY		0x3  /* 4-cycle latency */
+#define AT_CTRL_SWIN_TH_VAL_MASK	GENMASK(31, 24) /* bits [31:24] */
+#define AT_CTRL_SWIN_TH_VAL		0x9  /* sampling window threshold */
 
 /* Rockchip specific Registers */
 #define DWCMSHC_EMMC_DLL_CTRL		0x800
@@ -72,6 +88,82 @@
 	(((x) & DWCMSHC_EMMC_DLL_TIMEOUT) == 0))
 #define RK35xx_MAX_CLKS 3
 
+/* PHY register area pointer */
+#define DWC_MSHC_PTR_PHY_R	0x300
+
+/* PHY general configuration */
+#define PHY_CNFG_R		(DWC_MSHC_PTR_PHY_R + 0x00)
+#define PHY_CNFG_RSTN_DEASSERT	0x1  /* Deassert PHY reset */
+#define PHY_CNFG_PAD_SP_MASK	GENMASK(19, 16) /* bits [19:16] */
+#define PHY_CNFG_PAD_SP		0x0c /* PMOS TX drive strength */
+#define PHY_CNFG_PAD_SN_MASK	GENMASK(23, 20) /* bits [23:20] */
+#define PHY_CNFG_PAD_SN		0x0c /* NMOS TX drive strength */
+
+/* PHY command/response pad settings */
+#define PHY_CMDPAD_CNFG_R	(DWC_MSHC_PTR_PHY_R + 0x04)
+
+/* PHY data pad settings */
+#define PHY_DATAPAD_CNFG_R	(DWC_MSHC_PTR_PHY_R + 0x06)
+
+/* PHY clock pad settings */
+#define PHY_CLKPAD_CNFG_R	(DWC_MSHC_PTR_PHY_R + 0x08)
+
+/* PHY strobe pad settings */
+#define PHY_STBPAD_CNFG_R	(DWC_MSHC_PTR_PHY_R + 0x0a)
+
+/* PHY reset pad settings */
+#define PHY_RSTNPAD_CNFG_R	(DWC_MSHC_PTR_PHY_R + 0x0c)
+
+/* Bitfields are common for all pad settings */
+#define PHY_PAD_RXSEL_1V8		0x1 /* Receiver type select for 1.8V */
+#define PHY_PAD_RXSEL_3V3		0x2 /* Receiver type select for 3.3V */
+
+#define PHY_PAD_WEAKPULL_MASK		GENMASK(4, 3) /* bits [4:3] */
+#define PHY_PAD_WEAKPULL_PULLUP		0x1 /* Weak pull up enabled */
+#define PHY_PAD_WEAKPULL_PULLDOWN	0x2 /* Weak pull down enabled */
+
+#define PHY_PAD_TXSLEW_CTRL_P_MASK	GENMASK(8, 5) /* bits [8:5] */
+#define PHY_PAD_TXSLEW_CTRL_P		0x3 /* Slew control for P-Type pad TX */
+#define PHY_PAD_TXSLEW_CTRL_N_MASK	GENMASK(12, 9) /* bits [12:9] */
+#define PHY_PAD_TXSLEW_CTRL_N		0x3 /* Slew control for N-Type pad TX */
+
+/* PHY CLK delay line settings */
+#define PHY_SDCLKDL_CNFG_R		(DWC_MSHC_PTR_PHY_R + 0x1d)
+#define PHY_SDCLKDL_CNFG_UPDATE	BIT(4) /* set before writing to SDCLKDL_DC */
+
+/* PHY CLK delay line delay code */
+#define PHY_SDCLKDL_DC_R		(DWC_MSHC_PTR_PHY_R + 0x1e)
+#define PHY_SDCLKDL_DC_INITIAL		0x40 /* initial delay code */
+#define PHY_SDCLKDL_DC_DEFAULT		0x32 /* default delay code */
+#define PHY_SDCLKDL_DC_HS400		0x18 /* delay code for HS400 mode */
+
+/* PHY drift_cclk_rx delay line configuration setting */
+#define PHY_ATDL_CNFG_R			(DWC_MSHC_PTR_PHY_R + 0x21)
+#define PHY_ATDL_CNFG_INPSEL_MASK	GENMASK(3, 2) /* bits [3:2] */
+#define PHY_ATDL_CNFG_INPSEL		0x3 /* delay line input source */
+
+/* PHY DLL control settings */
+#define PHY_DLL_CTRL_R			(DWC_MSHC_PTR_PHY_R + 0x24)
+#define PHY_DLL_CTRL_DISABLE		0x0 /* PHY DLL is enabled */
+#define PHY_DLL_CTRL_ENABLE		0x1 /* PHY DLL is disabled */
+
+/* PHY DLL  configuration register 1 */
+#define PHY_DLL_CNFG1_R			(DWC_MSHC_PTR_PHY_R + 0x25)
+#define PHY_DLL_CNFG1_SLVDLY_MASK	GENMASK(5, 4) /* bits [5:4] */
+#define PHY_DLL_CNFG1_SLVDLY		0x2 /* DLL slave update delay input */
+#define PHY_DLL_CNFG1_WAITCYCLE		0x5 /* DLL wait cycle input */
+
+/* PHY DLL configuration register 2 */
+#define PHY_DLL_CNFG2_R			(DWC_MSHC_PTR_PHY_R + 0x26)
+#define PHY_DLL_CNFG2_JUMPSTEP		0xa /* DLL jump step input */
+
+/* PHY DLL master and slave delay line configuration settings */
+#define PHY_DLLDL_CNFG_R		(DWC_MSHC_PTR_PHY_R + 0x28)
+#define PHY_DLLDL_CNFG_SLV_INPSEL_MASK	GENMASK(6, 5) /* bits [6:5] */
+#define PHY_DLLDL_CNFG_SLV_INPSEL	0x3 /* clock source select for slave DL */
+
+#define FLAG_IO_FIXED_1V8	BIT(0)
+
 #define BOUNDARY_OK(addr, len) \
 	((addr | (SZ_128M - 1)) == ((addr + len - 1) | (SZ_128M - 1)))
 
@@ -92,6 +184,8 @@ struct dwcmshc_priv {
 	struct clk	*bus_clk;
 	int vendor_specific_area1; /* P_VENDOR_SPECIFIC_AREA reg */
 	void *priv; /* pointer to SoC private stuff */
+	u16 delay_line;
+	u16 flags;
 };
 
 /*
@@ -157,6 +251,127 @@ static void dwcmshc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	sdhci_request(mmc, mrq);
 }
 
+static void dwcmshc_phy_1_8v_init(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct dwcmshc_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	u32 val;
+
+	/* deassert phy reset & set tx drive strength */
+	val = PHY_CNFG_RSTN_DEASSERT;
+	val |= FIELD_PREP(PHY_CNFG_PAD_SP_MASK, PHY_CNFG_PAD_SP);
+	val |= FIELD_PREP(PHY_CNFG_PAD_SN_MASK, PHY_CNFG_PAD_SN);
+	sdhci_writel(host, val, PHY_CNFG_R);
+
+	/* disable delay line */
+	sdhci_writeb(host, PHY_SDCLKDL_CNFG_UPDATE, PHY_SDCLKDL_CNFG_R);
+
+	/* set delay line */
+	sdhci_writeb(host, priv->delay_line, PHY_SDCLKDL_DC_R);
+	sdhci_writeb(host, PHY_DLL_CNFG2_JUMPSTEP, PHY_DLL_CNFG2_R);
+
+	/* enable delay lane */
+	val = sdhci_readb(host, PHY_SDCLKDL_CNFG_R);
+	val &= ~(PHY_SDCLKDL_CNFG_UPDATE);
+	sdhci_writeb(host, val, PHY_SDCLKDL_CNFG_R);
+
+	/* configure phy pads */
+	val = PHY_PAD_RXSEL_1V8;
+	val |= FIELD_PREP(PHY_PAD_WEAKPULL_MASK, PHY_PAD_WEAKPULL_PULLUP);
+	val |= FIELD_PREP(PHY_PAD_TXSLEW_CTRL_P_MASK, PHY_PAD_TXSLEW_CTRL_P);
+	val |= FIELD_PREP(PHY_PAD_TXSLEW_CTRL_N_MASK, PHY_PAD_TXSLEW_CTRL_N);
+	sdhci_writew(host, val, PHY_CMDPAD_CNFG_R);
+	sdhci_writew(host, val, PHY_DATAPAD_CNFG_R);
+	sdhci_writew(host, val, PHY_RSTNPAD_CNFG_R);
+
+	val = FIELD_PREP(PHY_PAD_TXSLEW_CTRL_P_MASK, PHY_PAD_TXSLEW_CTRL_P);
+	val |= FIELD_PREP(PHY_PAD_TXSLEW_CTRL_N_MASK, PHY_PAD_TXSLEW_CTRL_N);
+	sdhci_writew(host, val, PHY_CLKPAD_CNFG_R);
+
+	val = PHY_PAD_RXSEL_1V8;
+	val |= FIELD_PREP(PHY_PAD_WEAKPULL_MASK, PHY_PAD_WEAKPULL_PULLDOWN);
+	val |= FIELD_PREP(PHY_PAD_TXSLEW_CTRL_P_MASK, PHY_PAD_TXSLEW_CTRL_P);
+	val |= FIELD_PREP(PHY_PAD_TXSLEW_CTRL_N_MASK, PHY_PAD_TXSLEW_CTRL_N);
+	sdhci_writew(host, val, PHY_STBPAD_CNFG_R);
+
+	/* enable data strobe mode */
+	sdhci_writeb(host, FIELD_PREP(PHY_DLLDL_CNFG_SLV_INPSEL_MASK, PHY_DLLDL_CNFG_SLV_INPSEL),
+		     PHY_DLLDL_CNFG_R);
+
+	/* enable phy dll */
+	sdhci_writeb(host, PHY_DLL_CTRL_ENABLE, PHY_DLL_CTRL_R);
+}
+
+static void dwcmshc_phy_3_3v_init(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct dwcmshc_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	u32 val;
+
+	/* deassert phy reset & set tx drive strength */
+	val = PHY_CNFG_RSTN_DEASSERT;
+	val |= FIELD_PREP(PHY_CNFG_PAD_SP_MASK, PHY_CNFG_PAD_SP);
+	val |= FIELD_PREP(PHY_CNFG_PAD_SN_MASK, PHY_CNFG_PAD_SN);
+	sdhci_writel(host, val, PHY_CNFG_R);
+
+	/* disable delay line */
+	sdhci_writeb(host, PHY_SDCLKDL_CNFG_UPDATE, PHY_SDCLKDL_CNFG_R);
+
+	/* set delay line */
+	sdhci_writeb(host, priv->delay_line, PHY_SDCLKDL_DC_R);
+	sdhci_writeb(host, PHY_DLL_CNFG2_JUMPSTEP, PHY_DLL_CNFG2_R);
+
+	/* enable delay lane */
+	val = sdhci_readb(host, PHY_SDCLKDL_CNFG_R);
+	val &= ~(PHY_SDCLKDL_CNFG_UPDATE);
+	sdhci_writeb(host, val, PHY_SDCLKDL_CNFG_R);
+
+	/* configure phy pads */
+	val = PHY_PAD_RXSEL_3V3;
+	val |= FIELD_PREP(PHY_PAD_WEAKPULL_MASK, PHY_PAD_WEAKPULL_PULLUP);
+	val |= FIELD_PREP(PHY_PAD_TXSLEW_CTRL_P_MASK, PHY_PAD_TXSLEW_CTRL_P);
+	val |= FIELD_PREP(PHY_PAD_TXSLEW_CTRL_N_MASK, PHY_PAD_TXSLEW_CTRL_N);
+	sdhci_writew(host, val, PHY_CMDPAD_CNFG_R);
+	sdhci_writew(host, val, PHY_DATAPAD_CNFG_R);
+	sdhci_writew(host, val, PHY_RSTNPAD_CNFG_R);
+
+	val = FIELD_PREP(PHY_PAD_TXSLEW_CTRL_P_MASK, PHY_PAD_TXSLEW_CTRL_P);
+	val |= FIELD_PREP(PHY_PAD_TXSLEW_CTRL_N_MASK, PHY_PAD_TXSLEW_CTRL_N);
+	sdhci_writew(host, val, PHY_CLKPAD_CNFG_R);
+
+	val = PHY_PAD_RXSEL_3V3;
+	val |= FIELD_PREP(PHY_PAD_WEAKPULL_MASK, PHY_PAD_WEAKPULL_PULLDOWN);
+	val |= FIELD_PREP(PHY_PAD_TXSLEW_CTRL_P_MASK, PHY_PAD_TXSLEW_CTRL_P);
+	val |= FIELD_PREP(PHY_PAD_TXSLEW_CTRL_N_MASK, PHY_PAD_TXSLEW_CTRL_N);
+	sdhci_writew(host, val, PHY_STBPAD_CNFG_R);
+
+	/* enable phy dll */
+	sdhci_writeb(host, PHY_DLL_CTRL_ENABLE, PHY_DLL_CTRL_R);
+}
+
+static void th1520_sdhci_set_phy(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct dwcmshc_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	u32 emmc_caps = MMC_CAP2_NO_SD | MMC_CAP2_NO_SDIO;
+	u16 emmc_ctrl;
+
+	/* Before power on, set PHY configs */
+	if (priv->flags & FLAG_IO_FIXED_1V8)
+		dwcmshc_phy_1_8v_init(host);
+	else
+		dwcmshc_phy_3_3v_init(host);
+
+	if ((host->mmc->caps2 & emmc_caps) == emmc_caps) {
+		emmc_ctrl = sdhci_readw(host, priv->vendor_specific_area1 + DWCMSHC_EMMC_CONTROL);
+		emmc_ctrl |= DWCMSHC_CARD_IS_EMMC;
+		sdhci_writew(host, emmc_ctrl, priv->vendor_specific_area1 + DWCMSHC_EMMC_CONTROL);
+	}
+
+	sdhci_writeb(host, FIELD_PREP(PHY_DLL_CNFG1_SLVDLY_MASK, PHY_DLL_CNFG1_SLVDLY) |
+		     PHY_DLL_CNFG1_WAITCYCLE, PHY_DLL_CNFG1_R);
+}
+
 static void dwcmshc_set_uhs_signaling(struct sdhci_host *host,
 				      unsigned int timing)
 {
@@ -189,9 +404,25 @@ static void dwcmshc_set_uhs_signaling(struct sdhci_host *host,
 		ctrl_2 |= DWCMSHC_CTRL_HS400;
 	}
 
+	if (priv->flags & FLAG_IO_FIXED_1V8)
+		ctrl_2 |= SDHCI_CTRL_VDD_180;
 	sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2);
 }
 
+static void th1520_set_uhs_signaling(struct sdhci_host *host,
+				     unsigned int timing)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct dwcmshc_priv *priv = sdhci_pltfm_priv(pltfm_host);
+
+	dwcmshc_set_uhs_signaling(host, timing);
+	if (timing == MMC_TIMING_MMC_HS400)
+		priv->delay_line = PHY_SDCLKDL_DC_HS400;
+	else
+		sdhci_writeb(host, 0, PHY_DLLDL_CNFG_R);
+	th1520_sdhci_set_phy(host);
+}
+
 static void dwcmshc_hs400_enhanced_strobe(struct mmc_host *mmc,
 					  struct mmc_ios *ios)
 {
@@ -338,6 +569,79 @@ static void rk35xx_sdhci_reset(struct sdhci_host *host, u8 mask)
 	sdhci_reset(host, mask);
 }
 
+static int th1520_execute_tuning(struct sdhci_host *host, u32 opcode)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct dwcmshc_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	u32 val = 0;
+
+	if (host->flags & SDHCI_HS400_TUNING)
+		return 0;
+
+	sdhci_writeb(host, FIELD_PREP(PHY_ATDL_CNFG_INPSEL_MASK, PHY_ATDL_CNFG_INPSEL),
+		     PHY_ATDL_CNFG_R);
+	val = sdhci_readl(host, priv->vendor_specific_area1 + DWCMSHC_EMMC_ATCTRL);
+
+	/*
+	 * configure tuning settings:
+	 *  - center phase select code driven in block gap interval
+	 *  - disable reporting of framing errors
+	 *  - disable software managed tuning
+	 *  - disable user selection of sampling window edges,
+	 *    instead tuning calculated edges are used
+	 */
+	val &= ~(AT_CTRL_CI_SEL | AT_CTRL_RPT_TUNE_ERR | AT_CTRL_SW_TUNE_EN |
+		 FIELD_PREP(AT_CTRL_WIN_EDGE_SEL_MASK, AT_CTRL_WIN_EDGE_SEL));
+
+	/*
+	 * configure tuning settings:
+	 *  - enable auto-tuning
+	 *  - enable sampling window threshold
+	 *  - stop clocks during phase code change
+	 *  - set max latency in cycles between tx and rx clocks
+	 *  - set max latency in cycles to switch output phase
+	 *  - set max sampling window threshold value
+	 */
+	val |= AT_CTRL_AT_EN | AT_CTRL_SWIN_TH_EN | AT_CTRL_TUNE_CLK_STOP_EN;
+	val |= FIELD_PREP(AT_CTRL_PRE_CHANGE_DLY_MASK, AT_CTRL_PRE_CHANGE_DLY);
+	val |= FIELD_PREP(AT_CTRL_POST_CHANGE_DLY_MASK, AT_CTRL_POST_CHANGE_DLY);
+	val |= FIELD_PREP(AT_CTRL_SWIN_TH_VAL_MASK, AT_CTRL_SWIN_TH_VAL);
+
+	sdhci_writel(host, val, priv->vendor_specific_area1 + DWCMSHC_EMMC_ATCTRL);
+	val = sdhci_readl(host, priv->vendor_specific_area1 + DWCMSHC_EMMC_ATCTRL);
+
+	/* perform tuning */
+	sdhci_start_tuning(host);
+	host->tuning_err = __sdhci_execute_tuning(host, opcode);
+	if (host->tuning_err) {
+		/* disable auto-tuning upon tuning error */
+		val &= ~AT_CTRL_AT_EN;
+		sdhci_writel(host, val, priv->vendor_specific_area1 + DWCMSHC_EMMC_ATCTRL);
+		dev_err(mmc_dev(host->mmc), "tuning failed: %d\n", host->tuning_err);
+		return -EIO;
+	}
+	sdhci_end_tuning(host);
+
+	return 0;
+}
+
+static void th1520_sdhci_reset(struct sdhci_host *host, u8 mask)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct dwcmshc_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	u16 ctrl_2;
+
+	sdhci_reset(host, mask);
+
+	if (priv->flags & FLAG_IO_FIXED_1V8) {
+		ctrl_2 = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+		if (!(ctrl_2 & SDHCI_CTRL_VDD_180)) {
+			ctrl_2 |= SDHCI_CTRL_VDD_180;
+			sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2);
+		}
+	}
+}
+
 static const struct sdhci_ops sdhci_dwcmshc_ops = {
 	.set_clock		= sdhci_set_clock,
 	.set_bus_width		= sdhci_set_bus_width,
@@ -356,6 +660,17 @@ static const struct sdhci_ops sdhci_dwcmshc_rk35xx_ops = {
 	.adma_write_desc	= dwcmshc_adma_write_desc,
 };
 
+static const struct sdhci_ops sdhci_dwcmshc_th1520_ops = {
+	.set_clock		= sdhci_set_clock,
+	.set_bus_width		= sdhci_set_bus_width,
+	.set_uhs_signaling	= th1520_set_uhs_signaling,
+	.get_max_clock		= dwcmshc_get_max_clock,
+	.reset			= th1520_sdhci_reset,
+	.adma_write_desc	= dwcmshc_adma_write_desc,
+	.voltage_switch		= dwcmshc_phy_1_8v_init,
+	.platform_execute_tuning = &th1520_execute_tuning,
+};
+
 static const struct sdhci_pltfm_data sdhci_dwcmshc_pdata = {
 	.ops = &sdhci_dwcmshc_ops,
 	.quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
@@ -379,6 +694,12 @@ static const struct sdhci_pltfm_data sdhci_dwcmshc_rk35xx_pdata = {
 		   SDHCI_QUIRK2_CLOCK_DIV_ZERO_BROKEN,
 };
 
+static const struct sdhci_pltfm_data sdhci_dwcmshc_th1520_pdata = {
+	.ops = &sdhci_dwcmshc_th1520_ops,
+	.quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
+};
+
 static int dwcmshc_rk35xx_init(struct sdhci_host *host, struct dwcmshc_priv *dwc_priv)
 {
 	int err;
@@ -447,6 +768,10 @@ static const struct of_device_id sdhci_dwcmshc_dt_ids[] = {
 		.compatible = "snps,dwcmshc-sdhci",
 		.data = &sdhci_dwcmshc_pdata,
 	},
+	{
+		.compatible = "thead,th1520-dwcmshc",
+		.data = &sdhci_dwcmshc_th1520_pdata,
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, sdhci_dwcmshc_dt_ids);
@@ -542,6 +867,30 @@ static int dwcmshc_probe(struct platform_device *pdev)
 			goto err_clk;
 	}
 
+	if (pltfm_data == &sdhci_dwcmshc_th1520_pdata) {
+		priv->delay_line = PHY_SDCLKDL_DC_DEFAULT;
+
+		if (device_property_read_bool(dev, "mmc-ddr-1_8v") ||
+		    device_property_read_bool(dev, "mmc-hs200-1_8v") ||
+		    device_property_read_bool(dev, "mmc-hs400-1_8v"))
+			priv->flags |= FLAG_IO_FIXED_1V8;
+		else
+			priv->flags &= ~FLAG_IO_FIXED_1V8;
+
+		/*
+		 * start_signal_voltage_switch() will try 3.3V first
+		 * then 1.8V. Use SDHCI_SIGNALING_180 rather than
+		 * SDHCI_SIGNALING_330 to avoid setting voltage to 3.3V
+		 * in sdhci_start_signal_voltage_switch().
+		 */
+		if (priv->flags & FLAG_IO_FIXED_1V8) {
+			host->flags &= ~SDHCI_SIGNALING_330;
+			host->flags |=  SDHCI_SIGNALING_180;
+		}
+
+		sdhci_enable_v4_mode(host);
+	}
+
 #ifdef CONFIG_ACPI
 	if (pltfm_data == &sdhci_dwcmshc_bf3_pdata)
 		sdhci_enable_v4_mode(host);
diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c
index 1e0bc7bace1b..e78faef67d7a 100644
--- a/drivers/mmc/host/sdhci-omap.c
+++ b/drivers/mmc/host/sdhci-omap.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  * SDHCI Controller driver for TI's OMAP SoCs
  *
  * Copyright (C) 2017 Texas Instruments
diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c
index 25ba7aecc3be..0e52867f6e91 100644
--- a/drivers/mmc/host/sdhci-xenon.c
+++ b/drivers/mmc/host/sdhci-xenon.c
@@ -18,6 +18,8 @@
 #include <linux/of.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
+#include <linux/mm.h>
+#include <linux/dma-mapping.h>
 
 #include "sdhci-pltfm.h"
 #include "sdhci-xenon.h"
@@ -422,6 +424,7 @@ static int xenon_probe_params(struct platform_device *pdev)
 	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
 	u32 sdhc_id, nr_sdhc;
 	u32 tuning_count;
+	struct sysinfo si;
 
 	/* Disable HS200 on Armada AP806 */
 	if (priv->hw_version == XENON_AP806)
@@ -450,6 +453,23 @@ static int xenon_probe_params(struct platform_device *pdev)
 	}
 	priv->tuning_count = tuning_count;
 
+	/*
+	 * AC5/X/IM HW has only 31-bits passed in the crossbar switch.
+	 * If we have more than 2GB of memory, this means we might pass
+	 * memory pointers which are above 2GB and which cannot be properly
+	 * represented. In this case, disable ADMA, 64-bit DMA and allow only SDMA.
+	 * This effectively will enable bounce buffer quirk in the
+	 * generic SDHCI driver, which will make sure DMA is only done
+	 * from supported memory regions:
+	 */
+	if (priv->hw_version == XENON_AC5) {
+		si_meminfo(&si);
+		if (si.totalram * si.mem_unit > SZ_2G) {
+			host->quirks |= SDHCI_QUIRK_BROKEN_ADMA;
+			host->quirks2 |= SDHCI_QUIRK2_BROKEN_64_BIT_DMA;
+		}
+	}
+
 	return xenon_phy_parse_params(dev, host);
 }
 
@@ -562,6 +582,16 @@ static int xenon_probe(struct platform_device *pdev)
 		goto remove_sdhc;
 
 	pm_runtime_put_autosuspend(&pdev->dev);
+	/*
+	 * If we previously detected AC5 with over 2GB of memory,
+	 * then we disable ADMA and 64-bit DMA.
+	 * This means generic SDHCI driver has set the DMA mask to
+	 * 32-bit. Since DDR starts at 0x2_0000_0000, we must use
+	 * 34-bit DMA mask to access this DDR memory:
+	 */
+	if (priv->hw_version == XENON_AC5 &&
+	    host->quirks2 & SDHCI_QUIRK2_BROKEN_64_BIT_DMA)
+		dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(34));
 
 	return 0;
 
@@ -680,6 +710,7 @@ static const struct of_device_id sdhci_xenon_dt_ids[] = {
 	{ .compatible = "marvell,armada-ap807-sdhci", .data = (void *)XENON_AP807},
 	{ .compatible = "marvell,armada-cp110-sdhci", .data =  (void *)XENON_CP110},
 	{ .compatible = "marvell,armada-3700-sdhci", .data =  (void *)XENON_A3700},
+	{ .compatible = "marvell,ac5-sdhci",	     .data =  (void *)XENON_AC5},
 	{}
 };
 MODULE_DEVICE_TABLE(of, sdhci_xenon_dt_ids);
diff --git a/drivers/mmc/host/sdhci-xenon.h b/drivers/mmc/host/sdhci-xenon.h
index 3e9c6c908a79..0460d97aad26 100644
--- a/drivers/mmc/host/sdhci-xenon.h
+++ b/drivers/mmc/host/sdhci-xenon.h
@@ -57,7 +57,8 @@ enum xenon_variant {
 	XENON_A3700,
 	XENON_AP806,
 	XENON_AP807,
-	XENON_CP110
+	XENON_CP110,
+	XENON_AC5
 };
 
 struct xenon_priv {
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index ff41aa56564e..c79f73459915 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -2841,7 +2841,7 @@ void sdhci_send_tuning(struct sdhci_host *host, u32 opcode)
 }
 EXPORT_SYMBOL_GPL(sdhci_send_tuning);
 
-static int __sdhci_execute_tuning(struct sdhci_host *host, u32 opcode)
+int __sdhci_execute_tuning(struct sdhci_host *host, u32 opcode)
 {
 	int i;
 
@@ -2879,6 +2879,7 @@ static int __sdhci_execute_tuning(struct sdhci_host *host, u32 opcode)
 	sdhci_reset_tuning(host);
 	return -EAGAIN;
 }
+EXPORT_SYMBOL_GPL(__sdhci_execute_tuning);
 
 int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 {
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index f219bdea8f28..a20864fc0641 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -793,6 +793,7 @@ void sdhci_set_bus_width(struct sdhci_host *host, int width);
 void sdhci_reset(struct sdhci_host *host, u8 mask);
 void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing);
 int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode);
+int __sdhci_execute_tuning(struct sdhci_host *host, u32 opcode);
 void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios);
 int sdhci_start_signal_voltage_switch(struct mmc_host *mmc,
 				      struct mmc_ios *ios);
diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c
index 967bd2dfcda1..d659c59422e1 100644
--- a/drivers/mmc/host/sdhci_am654.c
+++ b/drivers/mmc/host/sdhci_am654.c
@@ -141,7 +141,6 @@ static const struct timing_data td[] = {
 
 struct sdhci_am654_data {
 	struct regmap *base;
-	bool legacy_otapdly;
 	int otap_del_sel[ARRAY_SIZE(td)];
 	int itap_del_sel[ARRAY_SIZE(td)];
 	int clkbuf_sel;
@@ -272,11 +271,7 @@ static void sdhci_am654_set_clock(struct sdhci_host *host, unsigned int clock)
 	sdhci_set_clock(host, clock);
 
 	/* Setup DLL Output TAP delay */
-	if (sdhci_am654->legacy_otapdly)
-		otap_del_sel = sdhci_am654->otap_del_sel[0];
-	else
-		otap_del_sel = sdhci_am654->otap_del_sel[timing];
-
+	otap_del_sel = sdhci_am654->otap_del_sel[timing];
 	otap_del_ena = (timing > MMC_TIMING_UHS_SDR25) ? 1 : 0;
 
 	mask = OTAPDLYENA_MASK | OTAPDLYSEL_MASK;
@@ -314,10 +309,7 @@ static void sdhci_j721e_4bit_set_clock(struct sdhci_host *host,
 	u32 mask, val;
 
 	/* Setup DLL Output TAP delay */
-	if (sdhci_am654->legacy_otapdly)
-		otap_del_sel = sdhci_am654->otap_del_sel[0];
-	else
-		otap_del_sel = sdhci_am654->otap_del_sel[timing];
+	otap_del_sel = sdhci_am654->otap_del_sel[timing];
 
 	mask = OTAPDLYENA_MASK | OTAPDLYSEL_MASK;
 	val = (0x1 << OTAPDLYENA_SHIFT) |
@@ -577,32 +569,15 @@ static int sdhci_am654_get_otap_delay(struct sdhci_host *host,
 	int i;
 	int ret;
 
-	ret = device_property_read_u32(dev, td[MMC_TIMING_LEGACY].otap_binding,
-				 &sdhci_am654->otap_del_sel[MMC_TIMING_LEGACY]);
-	if (ret) {
-		/*
-		 * ti,otap-del-sel-legacy is mandatory, look for old binding
-		 * if not found.
-		 */
-		ret = device_property_read_u32(dev, "ti,otap-del-sel",
-					       &sdhci_am654->otap_del_sel[0]);
-		if (ret) {
-			dev_err(dev, "Couldn't find otap-del-sel\n");
-
-			return ret;
-		}
-
-		dev_info(dev, "Using legacy binding ti,otap-del-sel\n");
-		sdhci_am654->legacy_otapdly = true;
-
-		return 0;
-	}
-
 	for (i = MMC_TIMING_LEGACY; i <= MMC_TIMING_MMC_HS400; i++) {
 
 		ret = device_property_read_u32(dev, td[i].otap_binding,
 					       &sdhci_am654->otap_del_sel[i]);
 		if (ret) {
+			if (i == MMC_TIMING_LEGACY) {
+				dev_err(dev, "Couldn't find mandatory ti,otap-del-sel-legacy\n");
+				return ret;
+			}
 			dev_dbg(dev, "Couldn't find %s\n",
 				td[i].otap_binding);
 			/*