Merge tag 'mmc-v4.9' of git://git.linaro.org/people/ulf.hansson/mmc

Pull MMC updates from Ulf Hansson:

  MMC core:
   - Add support for sending commands during data transfer
   - Erase/discard/trim improvements
   - Improved error handling
   - Extend sysfs with SD status register
   - Document info about the vmmc/vmmcq regulators
   - Extend pwrseq-simple to manage an optional post-power-on-delay
   - Some various minor improvements and cleanups

  MMC host:
   - dw_mmc: Add reset support
   - dw_mmc: Return -EILSEQ for EBE and SBE error
   - dw_mmc: Some cleanups
   - dw_mmc-k3: Add UHS-I support Hisilicon Hikey
   - tmio: Add eMMC support
   - sh_mobile_sdhi: Add r8a7796 support
   - sunxi: Don't use sample clocks for sun4i/sun5i
   - sunxi: Add support for A64 mmc controller
   - sunxi: Some cleanups and improvements
   - sdhci: Support for sending commands during data transfer
   - sdhci: Do not allow tuning procedure to be interrupted
   - sdhci-pci: Enable SD/SDIO on Merrifield
   - sdhci-pci|acpi: Enable MMC_CAP_CMD_DURING_TFR
   - sdhci-pci: Some cleanups
   - sdhci-of-arasan: Set controller to test mode when no CD bit
   - sdhci-of-arasan: Some fixes for clocks and phys
   - sdhci-brcmstb: Don't use ADMA 64-bit when not supported
   - sdhci-tegra: Mark 64-bit DMA broken on Tegra124
   - sdhci-esdhc-imx: Fixups related to data timeouts

* tag 'mmc-v4.9' of git://git.linaro.org/people/ulf.hansson/mmc: (68 commits)
  mmc: dw_mmc: remove the deprecated "supports-highspeed" property
  mmc: dw_mmc: minor cleanup for dw_mci_adjust_fifoth
  mmc: dw_mmc: use macro to define ring buffer size
  mmc: dw_mmc: fix misleading error print if failing to do DMA transfer
  mmc: dw_mmc: avoid race condition of cpu and IDMAC
  mmc: dw_mmc: split out preparation of desc for IDMAC32 and IDMAC64
  mmc: core: don't try to switch block size for dual rate mode
  mmc: sdhci-of-arasan: Set controller to test mode when no CD bit
  dt: sdhci-of-arasan: Add device tree option xlnx, fails-without-test-cd
  mmc: tmio: add eMMC support
  mmc: rtsx_usb: use new macro for R1 without CRC
  mmc: rtsx_pci: use new macro for R1 without CRC
  mmc: add define for R1 response without CRC
  mmc: card: do away with indirection pointer
  mmc: sdhci-acpi: Set MMC_CAP_CMD_DURING_TFR for Intel eMMC controllers
  mmc: sdhci-pci: Set MMC_CAP_CMD_DURING_TFR for Intel eMMC controllers
  mmc: sdhci: Support cap_cmd_during_tfr requests
  mmc: mmc_test: Add tests for sending commands during transfer
  mmc: core: Add support for sending commands during data transfer
  mmc: sdhci-brcmstb: Fix incorrect capability
  ...

34 files changed, 1240 insertions, 464 deletions

diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 2206d4477dbb..c3335112e68c 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -142,8 +142,6 @@ static inline void mmc_blk_clear_packed(struct mmc_queue_req *mqrq)
 {
 	struct mmc_packed *packed = mqrq->packed;
 
-	BUG_ON(!packed);
-
 	mqrq->cmd_type = MMC_PACKED_NONE;
 	packed->nr_entries = MMC_PACKED_NR_ZERO;
 	packed->idx_failure = MMC_PACKED_NR_IDX;
@@ -1443,8 +1441,6 @@ static int mmc_blk_packed_err_check(struct mmc_card *card,
 	int err, check, status;
 	u8 *ext_csd;
 
-	BUG_ON(!packed);
-
 	packed->retries--;
 	check = mmc_blk_err_check(card, areq);
 	err = get_card_status(card, &status, 0);
@@ -1673,6 +1669,18 @@ static u8 mmc_blk_prep_packed_list(struct mmc_queue *mq, struct request *req)
 	u8 max_packed_rw = 0;
 	u8 reqs = 0;
 
+	/*
+	 * We don't need to check packed for any further
+	 * operation of packed stuff as we set MMC_PACKED_NONE
+	 * and return zero for reqs if geting null packed. Also
+	 * we clean the flag of MMC_BLK_PACKED_CMD to avoid doing
+	 * it again when removing blk req.
+	 */
+	if (!mqrq->packed) {
+		md->flags &= (~MMC_BLK_PACKED_CMD);
+		goto no_packed;
+	}
+
 	if (!(md->flags & MMC_BLK_PACKED_CMD))
 		goto no_packed;
 
@@ -1782,8 +1790,6 @@ static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq,
 	u8 hdr_blocks;
 	u8 i = 1;
 
-	BUG_ON(!packed);
-
 	mqrq->cmd_type = MMC_PACKED_WRITE;
 	packed->blocks = 0;
 	packed->idx_failure = MMC_PACKED_NR_IDX;
@@ -1887,8 +1893,6 @@ static int mmc_blk_end_packed_req(struct mmc_queue_req *mq_rq)
 	int idx = packed->idx_failure, i = 0;
 	int ret = 0;
 
-	BUG_ON(!packed);
-
 	while (!list_empty(&packed->list)) {
 		prq = list_entry_rq(packed->list.next);
 		if (idx == i) {
@@ -1917,8 +1921,6 @@ static void mmc_blk_abort_packed_req(struct mmc_queue_req *mq_rq)
 	struct request *prq;
 	struct mmc_packed *packed = mq_rq->packed;
 
-	BUG_ON(!packed);
-
 	while (!list_empty(&packed->list)) {
 		prq = list_entry_rq(packed->list.next);
 		list_del_init(&prq->queuelist);
@@ -1935,8 +1937,6 @@ static void mmc_blk_revert_packed_req(struct mmc_queue *mq,
 	struct request_queue *q = mq->queue;
 	struct mmc_packed *packed = mq_rq->packed;
 
-	BUG_ON(!packed);
-
 	while (!list_empty(&packed->list)) {
 		prq = list_entry_rq(packed->list.prev);
 		if (prq->queuelist.prev != &packed->list) {
@@ -2144,7 +2144,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 	return 0;
 }
 
-static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
+int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 {
 	int ret;
 	struct mmc_blk_data *md = mq->data;
@@ -2265,7 +2265,6 @@ again:
 	if (ret)
 		goto err_putdisk;
 
-	md->queue.issue_fn = mmc_blk_issue_rq;
 	md->queue.data = md;
 
 	md->disk->major	= MMC_BLOCK_MAJOR;
@@ -2303,7 +2302,8 @@ again:
 	set_capacity(md->disk, size);
 
 	if (mmc_host_cmd23(card->host)) {
-		if (mmc_card_mmc(card) ||
+		if ((mmc_card_mmc(card) &&
+		     card->csd.mmca_vsn >= CSD_SPEC_VER_3) ||
 		    (mmc_card_sd(card) &&
 		     card->scr.cmds & SD_SCR_CMD23_SUPPORT))
 			md->flags |= MMC_BLK_CMD23;
diff --git a/drivers/mmc/card/block.h b/drivers/mmc/card/block.h
new file mode 100644
index 000000000000..cdabb2ee74be
--- /dev/null
+++ b/drivers/mmc/card/block.h
@@ -0,0 +1 @@
+int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req);
diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c
index c032eef45762..5a8dc5a76e0d 100644
--- a/drivers/mmc/card/mmc_test.c
+++ b/drivers/mmc/card/mmc_test.c
@@ -184,6 +184,29 @@ static int mmc_test_set_blksize(struct mmc_test_card *test, unsigned size)
 	return mmc_set_blocklen(test->card, size);
 }
 
+static bool mmc_test_card_cmd23(struct mmc_card *card)
+{
+	return mmc_card_mmc(card) ||
+	       (mmc_card_sd(card) && card->scr.cmds & SD_SCR_CMD23_SUPPORT);
+}
+
+static void mmc_test_prepare_sbc(struct mmc_test_card *test,
+				 struct mmc_request *mrq, unsigned int blocks)
+{
+	struct mmc_card *card = test->card;
+
+	if (!mrq->sbc || !mmc_host_cmd23(card->host) ||
+	    !mmc_test_card_cmd23(card) || !mmc_op_multi(mrq->cmd->opcode) ||
+	    (card->quirks & MMC_QUIRK_BLK_NO_CMD23)) {
+		mrq->sbc = NULL;
+		return;
+	}
+
+	mrq->sbc->opcode = MMC_SET_BLOCK_COUNT;
+	mrq->sbc->arg = blocks;
+	mrq->sbc->flags = MMC_RSP_R1 | MMC_CMD_AC;
+}
+
 /*
  * Fill in the mmc_request structure given a set of transfer parameters.
  */
@@ -221,6 +244,8 @@ static void mmc_test_prepare_mrq(struct mmc_test_card *test,
 	mrq->data->sg = sg;
 	mrq->data->sg_len = sg_len;
 
+	mmc_test_prepare_sbc(test, mrq, blocks);
+
 	mmc_set_data_timeout(mrq->data, test->card);
 }
 
@@ -693,6 +718,8 @@ static int mmc_test_check_result(struct mmc_test_card *test,
 
 	ret = 0;
 
+	if (mrq->sbc && mrq->sbc->error)
+		ret = mrq->sbc->error;
 	if (!ret && mrq->cmd->error)
 		ret = mrq->cmd->error;
 	if (!ret && mrq->data->error)
@@ -2278,6 +2305,245 @@ static int mmc_test_reset(struct mmc_test_card *test)
 	return RESULT_FAIL;
 }
 
+struct mmc_test_req {
+	struct mmc_request mrq;
+	struct mmc_command sbc;
+	struct mmc_command cmd;
+	struct mmc_command stop;
+	struct mmc_command status;
+	struct mmc_data data;
+};
+
+static struct mmc_test_req *mmc_test_req_alloc(void)
+{
+	struct mmc_test_req *rq = kzalloc(sizeof(*rq), GFP_KERNEL);
+
+	if (rq) {
+		rq->mrq.cmd = &rq->cmd;
+		rq->mrq.data = &rq->data;
+		rq->mrq.stop = &rq->stop;
+	}
+
+	return rq;
+}
+
+static int mmc_test_send_status(struct mmc_test_card *test,
+				struct mmc_command *cmd)
+{
+	memset(cmd, 0, sizeof(*cmd));
+
+	cmd->opcode = MMC_SEND_STATUS;
+	if (!mmc_host_is_spi(test->card->host))
+		cmd->arg = test->card->rca << 16;
+	cmd->flags = MMC_RSP_SPI_R2 | MMC_RSP_R1 | MMC_CMD_AC;
+
+	return mmc_wait_for_cmd(test->card->host, cmd, 0);
+}
+
+static int mmc_test_ongoing_transfer(struct mmc_test_card *test,
+				     unsigned int dev_addr, int use_sbc,
+				     int repeat_cmd, int write, int use_areq)
+{
+	struct mmc_test_req *rq = mmc_test_req_alloc();
+	struct mmc_host *host = test->card->host;
+	struct mmc_test_area *t = &test->area;
+	struct mmc_async_req areq;
+	struct mmc_request *mrq;
+	unsigned long timeout;
+	bool expired = false;
+	int ret = 0, cmd_ret;
+	u32 status = 0;
+	int count = 0;
+
+	if (!rq)
+		return -ENOMEM;
+
+	mrq = &rq->mrq;
+	if (use_sbc)
+		mrq->sbc = &rq->sbc;
+	mrq->cap_cmd_during_tfr = true;
+
+	areq.mrq = mrq;
+	areq.err_check = mmc_test_check_result_async;
+
+	mmc_test_prepare_mrq(test, mrq, t->sg, t->sg_len, dev_addr, t->blocks,
+			     512, write);
+
+	if (use_sbc && t->blocks > 1 && !mrq->sbc) {
+		ret =  mmc_host_cmd23(host) ?
+		       RESULT_UNSUP_CARD :
+		       RESULT_UNSUP_HOST;
+		goto out_free;
+	}
+
+	/* Start ongoing data request */
+	if (use_areq) {
+		mmc_start_req(host, &areq, &ret);
+		if (ret)
+			goto out_free;
+	} else {
+		mmc_wait_for_req(host, mrq);
+	}
+
+	timeout = jiffies + msecs_to_jiffies(3000);
+	do {
+		count += 1;
+
+		/* Send status command while data transfer in progress */
+		cmd_ret = mmc_test_send_status(test, &rq->status);
+		if (cmd_ret)
+			break;
+
+		status = rq->status.resp[0];
+		if (status & R1_ERROR) {
+			cmd_ret = -EIO;
+			break;
+		}
+
+		if (mmc_is_req_done(host, mrq))
+			break;
+
+		expired = time_after(jiffies, timeout);
+		if (expired) {
+			pr_info("%s: timeout waiting for Tran state status %#x\n",
+				mmc_hostname(host), status);
+			cmd_ret = -ETIMEDOUT;
+			break;
+		}
+	} while (repeat_cmd && R1_CURRENT_STATE(status) != R1_STATE_TRAN);
+
+	/* Wait for data request to complete */
+	if (use_areq)
+		mmc_start_req(host, NULL, &ret);
+	else
+		mmc_wait_for_req_done(test->card->host, mrq);
+
+	/*
+	 * For cap_cmd_during_tfr request, upper layer must send stop if
+	 * required.
+	 */
+	if (mrq->data->stop && (mrq->data->error || !mrq->sbc)) {
+		if (ret)
+			mmc_wait_for_cmd(host, mrq->data->stop, 0);
+		else
+			ret = mmc_wait_for_cmd(host, mrq->data->stop, 0);
+	}
+
+	if (ret)
+		goto out_free;
+
+	if (cmd_ret) {
+		pr_info("%s: Send Status failed: status %#x, error %d\n",
+			mmc_hostname(test->card->host), status, cmd_ret);
+	}
+
+	ret = mmc_test_check_result(test, mrq);
+	if (ret)
+		goto out_free;
+
+	ret = mmc_test_wait_busy(test);
+	if (ret)
+		goto out_free;
+
+	if (repeat_cmd && (t->blocks + 1) << 9 > t->max_tfr)
+		pr_info("%s: %d commands completed during transfer of %u blocks\n",
+			mmc_hostname(test->card->host), count, t->blocks);
+
+	if (cmd_ret)
+		ret = cmd_ret;
+out_free:
+	kfree(rq);
+
+	return ret;
+}
+
+static int __mmc_test_cmds_during_tfr(struct mmc_test_card *test,
+				      unsigned long sz, int use_sbc, int write,
+				      int use_areq)
+{
+	struct mmc_test_area *t = &test->area;
+	int ret;
+
+	if (!(test->card->host->caps & MMC_CAP_CMD_DURING_TFR))
+		return RESULT_UNSUP_HOST;
+
+	ret = mmc_test_area_map(test, sz, 0, 0);
+	if (ret)
+		return ret;
+
+	ret = mmc_test_ongoing_transfer(test, t->dev_addr, use_sbc, 0, write,
+					use_areq);
+	if (ret)
+		return ret;
+
+	return mmc_test_ongoing_transfer(test, t->dev_addr, use_sbc, 1, write,
+					 use_areq);
+}
+
+static int mmc_test_cmds_during_tfr(struct mmc_test_card *test, int use_sbc,
+				    int write, int use_areq)
+{
+	struct mmc_test_area *t = &test->area;
+	unsigned long sz;
+	int ret;
+
+	for (sz = 512; sz <= t->max_tfr; sz += 512) {
+		ret = __mmc_test_cmds_during_tfr(test, sz, use_sbc, write,
+						 use_areq);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+/*
+ * Commands during read - no Set Block Count (CMD23).
+ */
+static int mmc_test_cmds_during_read(struct mmc_test_card *test)
+{
+	return mmc_test_cmds_during_tfr(test, 0, 0, 0);
+}
+
+/*
+ * Commands during write - no Set Block Count (CMD23).
+ */
+static int mmc_test_cmds_during_write(struct mmc_test_card *test)
+{
+	return mmc_test_cmds_during_tfr(test, 0, 1, 0);
+}
+
+/*
+ * Commands during read - use Set Block Count (CMD23).
+ */
+static int mmc_test_cmds_during_read_cmd23(struct mmc_test_card *test)
+{
+	return mmc_test_cmds_during_tfr(test, 1, 0, 0);
+}
+
+/*
+ * Commands during write - use Set Block Count (CMD23).
+ */
+static int mmc_test_cmds_during_write_cmd23(struct mmc_test_card *test)
+{
+	return mmc_test_cmds_during_tfr(test, 1, 1, 0);
+}
+
+/*
+ * Commands during non-blocking read - use Set Block Count (CMD23).
+ */
+static int mmc_test_cmds_during_read_cmd23_nonblock(struct mmc_test_card *test)
+{
+	return mmc_test_cmds_during_tfr(test, 1, 0, 1);
+}
+
+/*
+ * Commands during non-blocking write - use Set Block Count (CMD23).
+ */
+static int mmc_test_cmds_during_write_cmd23_nonblock(struct mmc_test_card *test)
+{
+	return mmc_test_cmds_during_tfr(test, 1, 1, 1);
+}
+
 static const struct mmc_test_case mmc_test_cases[] = {
 	{
 		.name = "Basic write (no data verification)",
@@ -2605,6 +2871,48 @@ static const struct mmc_test_case mmc_test_cases[] = {
 		.name = "Reset test",
 		.run = mmc_test_reset,
 	},
+
+	{
+		.name = "Commands during read - no Set Block Count (CMD23)",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_cmds_during_read,
+		.cleanup = mmc_test_area_cleanup,
+	},
+
+	{
+		.name = "Commands during write - no Set Block Count (CMD23)",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_cmds_during_write,
+		.cleanup = mmc_test_area_cleanup,
+	},
+
+	{
+		.name = "Commands during read - use Set Block Count (CMD23)",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_cmds_during_read_cmd23,
+		.cleanup = mmc_test_area_cleanup,
+	},
+
+	{
+		.name = "Commands during write - use Set Block Count (CMD23)",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_cmds_during_write_cmd23,
+		.cleanup = mmc_test_area_cleanup,
+	},
+
+	{
+		.name = "Commands during non-blocking read - use Set Block Count (CMD23)",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_cmds_during_read_cmd23_nonblock,
+		.cleanup = mmc_test_area_cleanup,
+	},
+
+	{
+		.name = "Commands during non-blocking write - use Set Block Count (CMD23)",
+		.prepare = mmc_test_area_prepare,
+		.run = mmc_test_cmds_during_write_cmd23_nonblock,
+		.cleanup = mmc_test_area_cleanup,
+	},
 };
 
 static DEFINE_MUTEX(mmc_test_lock);
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index 708057261b38..8037f73a109a 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -19,7 +19,9 @@
 
 #include <linux/mmc/card.h>
 #include <linux/mmc/host.h>
+
 #include "queue.h"
+#include "block.h"
 
 #define MMC_QUEUE_BOUNCESZ	65536
 
@@ -68,7 +70,7 @@ static int mmc_queue_thread(void *d)
 			bool req_is_special = mmc_req_is_special(req);
 
 			set_current_state(TASK_RUNNING);
-			mq->issue_fn(mq, req);
+			mmc_blk_issue_rq(mq, req);
 			cond_resched();
 			if (mq->flags & MMC_QUEUE_NEW_REQUEST) {
 				mq->flags &= ~MMC_QUEUE_NEW_REQUEST;
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index fee5e1271465..3c15a75bae86 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -57,8 +57,6 @@ struct mmc_queue {
 	unsigned int		flags;
 #define MMC_QUEUE_SUSPENDED	(1 << 0)
 #define MMC_QUEUE_NEW_REQUEST	(1 << 1)
-
-	int			(*issue_fn)(struct mmc_queue *, struct request *);
 	void			*data;
 	struct request_queue	*queue;
 	struct mmc_queue_req	mqrq[2];
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index e55cde6d436d..2553d903a82b 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -58,6 +58,9 @@
  */
 #define MMC_BKOPS_MAX_TIMEOUT	(4 * 60 * 1000) /* max time to wait in ms */
 
+/* The max erase timeout, used when host->max_busy_timeout isn't specified */
+#define MMC_ERASE_TIMEOUT_MS	(60 * 1000) /* 60 s */
+
 static const unsigned freqs[] = { 400000, 300000, 200000, 100000 };
 
 /*
@@ -117,6 +120,24 @@ static inline void mmc_should_fail_request(struct mmc_host *host,
 
 #endif /* CONFIG_FAIL_MMC_REQUEST */
 
+static inline void mmc_complete_cmd(struct mmc_request *mrq)
+{
+	if (mrq->cap_cmd_during_tfr && !completion_done(&mrq->cmd_completion))
+		complete_all(&mrq->cmd_completion);
+}
+
+void mmc_command_done(struct mmc_host *host, struct mmc_request *mrq)
+{
+	if (!mrq->cap_cmd_during_tfr)
+		return;
+
+	mmc_complete_cmd(mrq);
+
+	pr_debug("%s: cmd done, tfr ongoing (CMD%u)\n",
+		 mmc_hostname(host), mrq->cmd->opcode);
+}
+EXPORT_SYMBOL(mmc_command_done);
+
 /**
  *	mmc_request_done - finish processing an MMC request
  *	@host: MMC host which completed request
@@ -143,6 +164,11 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq)
 			cmd->retries = 0;
 	}
 
+	if (host->ongoing_mrq == mrq)
+		host->ongoing_mrq = NULL;
+
+	mmc_complete_cmd(mrq);
+
 	trace_mmc_request_done(host, mrq);
 
 	if (err && cmd->retries && !mmc_card_removed(host->card)) {
@@ -155,7 +181,8 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq)
 	} else {
 		mmc_should_fail_request(host, mrq);
 
-		led_trigger_event(host->led, LED_OFF);
+		if (!host->ongoing_mrq)
+			led_trigger_event(host->led, LED_OFF);
 
 		if (mrq->sbc) {
 			pr_debug("%s: req done <CMD%u>: %d: %08x %08x %08x %08x\n",
@@ -220,6 +247,15 @@ static void __mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 		}
 	}
 
+	if (mrq->cap_cmd_during_tfr) {
+		host->ongoing_mrq = mrq;
+		/*
+		 * Retry path could come through here without having waiting on
+		 * cmd_completion, so ensure it is reinitialised.
+		 */
+		reinit_completion(&mrq->cmd_completion);
+	}
+
 	trace_mmc_request_start(host, mrq);
 
 	host->ops->request(host, mrq);
@@ -386,6 +422,18 @@ static void mmc_wait_done(struct mmc_request *mrq)
 	complete(&mrq->completion);
 }
 
+static inline void mmc_wait_ongoing_tfr_cmd(struct mmc_host *host)
+{
+	struct mmc_request *ongoing_mrq = READ_ONCE(host->ongoing_mrq);
+
+	/*
+	 * If there is an ongoing transfer, wait for the command line to become
+	 * available.
+	 */
+	if (ongoing_mrq && !completion_done(&ongoing_mrq->cmd_completion))
+		wait_for_completion(&ongoing_mrq->cmd_completion);
+}
+
 /*
  *__mmc_start_data_req() - starts data request
  * @host: MMC host to start the request
@@ -393,17 +441,24 @@ static void mmc_wait_done(struct mmc_request *mrq)
  *
  * Sets the done callback to be called when request is completed by the card.
  * Starts data mmc request execution
+ * If an ongoing transfer is already in progress, wait for the command line
+ * to become available before sending another command.
  */
 static int __mmc_start_data_req(struct mmc_host *host, struct mmc_request *mrq)
 {
 	int err;
 
+	mmc_wait_ongoing_tfr_cmd(host);
+
 	mrq->done = mmc_wait_data_done;
 	mrq->host = host;
 
+	init_completion(&mrq->cmd_completion);
+
 	err = mmc_start_request(host, mrq);
 	if (err) {
 		mrq->cmd->error = err;
+		mmc_complete_cmd(mrq);
 		mmc_wait_data_done(mrq);
 	}
 
@@ -414,12 +469,17 @@ static int __mmc_start_req(struct mmc_host *host, struct mmc_request *mrq)
 {
 	int err;
 
+	mmc_wait_ongoing_tfr_cmd(host);
+
 	init_completion(&mrq->completion);
 	mrq->done = mmc_wait_done;
 
+	init_completion(&mrq->cmd_completion);
+
 	err = mmc_start_request(host, mrq);
 	if (err) {
 		mrq->cmd->error = err;
+		mmc_complete_cmd(mrq);
 		complete(&mrq->completion);
 	}
 
@@ -483,8 +543,7 @@ static int mmc_wait_for_data_req_done(struct mmc_host *host,
 	return err;
 }
 
-static void mmc_wait_for_req_done(struct mmc_host *host,
-				  struct mmc_request *mrq)
+void mmc_wait_for_req_done(struct mmc_host *host, struct mmc_request *mrq)
 {
 	struct mmc_command *cmd;
 
@@ -525,6 +584,28 @@ static void mmc_wait_for_req_done(struct mmc_host *host,
 
 	mmc_retune_release(host);
 }
+EXPORT_SYMBOL(mmc_wait_for_req_done);
+
+/**
+ *	mmc_is_req_done - Determine if a 'cap_cmd_during_tfr' request is done
+ *	@host: MMC host
+ *	@mrq: MMC request
+ *
+ *	mmc_is_req_done() is used with requests that have
+ *	mrq->cap_cmd_during_tfr = true. mmc_is_req_done() must be called after
+ *	starting a request and before waiting for it to complete. That is,
+ *	either in between calls to mmc_start_req(), or after mmc_wait_for_req()
+ *	and before mmc_wait_for_req_done(). If it is called at other times the
+ *	result is not meaningful.
+ */
+bool mmc_is_req_done(struct mmc_host *host, struct mmc_request *mrq)
+{
+	if (host->areq)
+		return host->context_info.is_done_rcv;
+	else
+		return completion_done(&mrq->completion);
+}
+EXPORT_SYMBOL(mmc_is_req_done);
 
 /**
  *	mmc_pre_req - Prepare for a new request
@@ -645,13 +726,18 @@ EXPORT_SYMBOL(mmc_start_req);
  *	@mrq: MMC request to start
  *
  *	Start a new MMC custom command request for a host, and wait
- *	for the command to complete. Does not attempt to parse the
- *	response.
+ *	for the command to complete. In the case of 'cap_cmd_during_tfr'
+ *	requests, the transfer is ongoing and the caller can issue further
+ *	commands that do not use the data lines, and then wait by calling
+ *	mmc_wait_for_req_done().
+ *	Does not attempt to parse the response.
  */
 void mmc_wait_for_req(struct mmc_host *host, struct mmc_request *mrq)
 {
 	__mmc_start_req(host, mrq);
-	mmc_wait_for_req_done(host, mrq);
+
+	if (!mrq->cap_cmd_during_tfr)
+		mmc_wait_for_req_done(host, mrq);
 }
 EXPORT_SYMBOL(mmc_wait_for_req);
 
@@ -2202,6 +2288,54 @@ out:
 	return err;
 }
 
+static unsigned int mmc_align_erase_size(struct mmc_card *card,
+					 unsigned int *from,
+					 unsigned int *to,
+					 unsigned int nr)
+{
+	unsigned int from_new = *from, nr_new = nr, rem;
+
+	/*
+	 * When the 'card->erase_size' is power of 2, we can use round_up/down()
+	 * to align the erase size efficiently.
+	 */
+	if (is_power_of_2(card->erase_size)) {
+		unsigned int temp = from_new;
+
+		from_new = round_up(temp, card->erase_size);
+		rem = from_new - temp;
+
+		if (nr_new > rem)
+			nr_new -= rem;
+		else
+			return 0;
+
+		nr_new = round_down(nr_new, card->erase_size);
+	} else {
+		rem = from_new % card->erase_size;
+		if (rem) {
+			rem = card->erase_size - rem;
+			from_new += rem;
+			if (nr_new > rem)
+				nr_new -= rem;
+			else
+				return 0;
+		}
+
+		rem = nr_new % card->erase_size;
+		if (rem)
+			nr_new -= rem;
+	}
+
+	if (nr_new == 0)
+		return 0;
+
+	*to = from_new + nr_new;
+	*from = from_new;
+
+	return nr_new;
+}
+
 /**
  * mmc_erase - erase sectors.
  * @card: card to erase
@@ -2240,26 +2374,12 @@ int mmc_erase(struct mmc_card *card, unsigned int from, unsigned int nr,
 			return -EINVAL;
 	}
 
-	if (arg == MMC_ERASE_ARG) {
-		rem = from % card->erase_size;
-		if (rem) {
-			rem = card->erase_size - rem;
-			from += rem;
-			if (nr > rem)
-				nr -= rem;
-			else
-				return 0;
-		}
-		rem = nr % card->erase_size;
-		if (rem)
-			nr -= rem;
-	}
+	if (arg == MMC_ERASE_ARG)
+		nr = mmc_align_erase_size(card, &from, &to, nr);
 
 	if (nr == 0)
 		return 0;
 
-	to = from + nr;
-
 	if (to <= from)
 		return -EINVAL;
 
@@ -2352,6 +2472,8 @@ static unsigned int mmc_do_calc_max_discard(struct mmc_card *card,
 	struct mmc_host *host = card->host;
 	unsigned int max_discard, x, y, qty = 0, max_qty, min_qty, timeout;
 	unsigned int last_timeout = 0;
+	unsigned int max_busy_timeout = host->max_busy_timeout ?
+			host->max_busy_timeout : MMC_ERASE_TIMEOUT_MS;
 
 	if (card->erase_shift) {
 		max_qty = UINT_MAX >> card->erase_shift;
@@ -2374,15 +2496,15 @@ static unsigned int mmc_do_calc_max_discard(struct mmc_card *card,
 	 * matter what size of 'host->max_busy_timeout', but if the
 	 * 'host->max_busy_timeout' is large enough for more discard sectors,
 	 * then we can continue to increase the max discard sectors until we
-	 * get a balance value.
+	 * get a balance value. In cases when the 'host->max_busy_timeout'
+	 * isn't specified, use the default max erase timeout.
 	 */
 	do {
 		y = 0;
 		for (x = 1; x && x <= max_qty && max_qty - x >= qty; x <<= 1) {
 			timeout = mmc_erase_timeout(card, arg, qty + x);
 
-			if (qty + x > min_qty &&
-			    timeout > host->max_busy_timeout)
+			if (qty + x > min_qty && timeout > max_busy_timeout)
 				break;
 
 			if (timeout < last_timeout)
@@ -2427,9 +2549,6 @@ unsigned int mmc_calc_max_discard(struct mmc_card *card)
 	struct mmc_host *host = card->host;
 	unsigned int max_discard, max_trim;
 
-	if (!host->max_busy_timeout)
-		return UINT_MAX;
-
 	/*
 	 * Without erase_group_def set, MMC erase timeout depends on clock
 	 * frequence which can change.  In that case, the best choice is
@@ -2447,7 +2566,8 @@ unsigned int mmc_calc_max_discard(struct mmc_card *card)
 		max_discard = 0;
 	}
 	pr_debug("%s: calculated max. discard sectors %u for timeout %u ms\n",
-		 mmc_hostname(host), max_discard, host->max_busy_timeout);
+		mmc_hostname(host), max_discard, host->max_busy_timeout ?
+		host->max_busy_timeout : MMC_ERASE_TIMEOUT_MS);
 	return max_discard;
 }
 EXPORT_SYMBOL(mmc_calc_max_discard);
@@ -2456,7 +2576,8 @@ int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen)
 {
 	struct mmc_command cmd = {0};
 
-	if (mmc_card_blockaddr(card) || mmc_card_ddr52(card))
+	if (mmc_card_blockaddr(card) || mmc_card_ddr52(card) ||
+	    mmc_card_hs400(card) || mmc_card_hs400es(card))
 		return 0;
 
 	cmd.opcode = MMC_SET_BLOCKLEN;
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index f2d185cf8a8b..3486bc7fbb64 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1029,6 +1029,10 @@ static int mmc_select_hs(struct mmc_card *card)
 		err = mmc_switch_status(card);
 	}
 
+	if (err)
+		pr_warn("%s: switch to high-speed failed, err:%d\n",
+			mmc_hostname(card->host), err);
+
 	return err;
 }
 
@@ -1265,11 +1269,8 @@ static int mmc_select_hs400es(struct mmc_card *card)
 
 	/* Switch card to HS mode */
 	err = mmc_select_hs(card);
-	if (err) {
-		pr_err("%s: switch to high-speed failed, err:%d\n",
-			mmc_hostname(host), err);
+	if (err)
 		goto out_err;
-	}
 
 	err = mmc_switch_status(card);
 	if (err)
diff --git a/drivers/mmc/core/pwrseq_simple.c b/drivers/mmc/core/pwrseq_simple.c
index 450d907c6e6c..1304160de168 100644
--- a/drivers/mmc/core/pwrseq_simple.c
+++ b/drivers/mmc/core/pwrseq_simple.c
@@ -16,6 +16,8 @@
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/gpio/consumer.h>
+#include <linux/delay.h>
+#include <linux/property.h>
 
 #include <linux/mmc/host.h>
 
@@ -24,6 +26,7 @@
 struct mmc_pwrseq_simple {
 	struct mmc_pwrseq pwrseq;
 	bool clk_enabled;
+	u32 post_power_on_delay_ms;
 	struct clk *ext_clk;
 	struct gpio_descs *reset_gpios;
 };
@@ -64,6 +67,9 @@ static void mmc_pwrseq_simple_post_power_on(struct mmc_host *host)
 	struct mmc_pwrseq_simple *pwrseq = to_pwrseq_simple(host->pwrseq);
 
 	mmc_pwrseq_simple_set_gpios_value(pwrseq, 0);
+
+	if (pwrseq->post_power_on_delay_ms)
+		msleep(pwrseq->post_power_on_delay_ms);
 }
 
 static void mmc_pwrseq_simple_power_off(struct mmc_host *host)
@@ -111,6 +117,9 @@ static int mmc_pwrseq_simple_probe(struct platform_device *pdev)
 		return PTR_ERR(pwrseq->reset_gpios);
 	}
 
+	device_property_read_u32(dev, "post-power-on-delay-ms",
+				 &pwrseq->post_power_on_delay_ms);
+
 	pwrseq->pwrseq.dev = dev;
 	pwrseq->pwrseq.ops = &mmc_pwrseq_simple_ops;
 	pwrseq->pwrseq.owner = THIS_MODULE;
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 0123936241b0..73c762a28dfe 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -223,8 +223,7 @@ static int mmc_decode_scr(struct mmc_card *card)
 static int mmc_read_ssr(struct mmc_card *card)
 {
 	unsigned int au, es, et, eo;
-	int err, i;
-	u32 *ssr;
+	int i;
 
 	if (!(card->csd.cmdclass & CCC_APP_SPEC)) {
 		pr_warn("%s: card lacks mandatory SD Status function\n",
@@ -232,33 +231,27 @@ static int mmc_read_ssr(struct mmc_card *card)
 		return 0;
 	}
 
-	ssr = kmalloc(64, GFP_KERNEL);
-	if (!ssr)
-		return -ENOMEM;
-
-	err = mmc_app_sd_status(card, ssr);
-	if (err) {
+	if (mmc_app_sd_status(card, card->raw_ssr)) {
 		pr_warn("%s: problem reading SD Status register\n",
 			mmc_hostname(card->host));
-		err = 0;
-		goto out;
+		return 0;
 	}
 
 	for (i = 0; i < 16; i++)
-		ssr[i] = be32_to_cpu(ssr[i]);
+		card->raw_ssr[i] = be32_to_cpu(card->raw_ssr[i]);
 
 	/*
 	 * UNSTUFF_BITS only works with four u32s so we have to offset the
 	 * bitfield positions accordingly.
 	 */
-	au = UNSTUFF_BITS(ssr, 428 - 384, 4);
+	au = UNSTUFF_BITS(card->raw_ssr, 428 - 384, 4);
 	if (au) {
 		if (au <= 9 || card->scr.sda_spec3) {
 			card->ssr.au = sd_au_size[au];
-			es = UNSTUFF_BITS(ssr, 408 - 384, 16);
-			et = UNSTUFF_BITS(ssr, 402 - 384, 6);
+			es = UNSTUFF_BITS(card->raw_ssr, 408 - 384, 16);
+			et = UNSTUFF_BITS(card->raw_ssr, 402 - 384, 6);
 			if (es && et) {
-				eo = UNSTUFF_BITS(ssr, 400 - 384, 2);
+				eo = UNSTUFF_BITS(card->raw_ssr, 400 - 384, 2);
 				card->ssr.erase_timeout = (et * 1000) / es;
 				card->ssr.erase_offset = eo * 1000;
 			}
@@ -267,9 +260,8 @@ static int mmc_read_ssr(struct mmc_card *card)
 				mmc_hostname(card->host));
 		}
 	}
-out:
-	kfree(ssr);
-	return err;
+
+	return 0;
 }
 
 /*
@@ -666,6 +658,14 @@ MMC_DEV_ATTR(cid, "%08x%08x%08x%08x\n", card->raw_cid[0], card->raw_cid[1],
 MMC_DEV_ATTR(csd, "%08x%08x%08x%08x\n", card->raw_csd[0], card->raw_csd[1],
 	card->raw_csd[2], card->raw_csd[3]);
 MMC_DEV_ATTR(scr, "%08x%08x\n", card->raw_scr[0], card->raw_scr[1]);
+MMC_DEV_ATTR(ssr,
+	"%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x\n",
+		card->raw_ssr[0], card->raw_ssr[1], card->raw_ssr[2],
+		card->raw_ssr[3], card->raw_ssr[4], card->raw_ssr[5],
+		card->raw_ssr[6], card->raw_ssr[7], card->raw_ssr[8],
+		card->raw_ssr[9], card->raw_ssr[10], card->raw_ssr[11],
+		card->raw_ssr[12], card->raw_ssr[13], card->raw_ssr[14],
+		card->raw_ssr[15]);
 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);
@@ -698,6 +698,7 @@ static struct attribute *sd_std_attrs[] = {
 	&dev_attr_cid.attr,
 	&dev_attr_csd.attr,
 	&dev_attr_scr.attr,
+	&dev_attr_ssr.attr,
 	&dev_attr_date.attr,
 	&dev_attr_erase_size.attr,
 	&dev_attr_preferred_erase_size.attr,
diff --git a/drivers/mmc/core/sdio_io.c b/drivers/mmc/core/sdio_io.c
index 78cb4d5d9d58..406e5f037e32 100644
--- a/drivers/mmc/core/sdio_io.c
+++ b/drivers/mmc/core/sdio_io.c
@@ -26,8 +26,8 @@
  */
 void sdio_claim_host(struct sdio_func *func)
 {
-	BUG_ON(!func);
-	BUG_ON(!func->card);
+	if (WARN_ON(!func))
+		return;
 
 	mmc_claim_host(func->card->host);
 }
@@ -42,8 +42,8 @@ EXPORT_SYMBOL_GPL(sdio_claim_host);
  */
 void sdio_release_host(struct sdio_func *func)
 {
-	BUG_ON(!func);
-	BUG_ON(!func->card);
+	if (WARN_ON(!func))
+		return;
 
 	mmc_release_host(func->card->host);
 }
@@ -62,8 +62,8 @@ int sdio_enable_func(struct sdio_func *func)
 	unsigned char reg;
 	unsigned long timeout;
 
-	BUG_ON(!func);
-	BUG_ON(!func->card);
+	if (!func)
+		return -EINVAL;
 
 	pr_debug("SDIO: Enabling device %s...\n", sdio_func_id(func));
 
@@ -112,8 +112,8 @@ int sdio_disable_func(struct sdio_func *func)
 	int ret;
 	unsigned char reg;
 
-	BUG_ON(!func);
-	BUG_ON(!func->card);
+	if (!func)
+		return -EINVAL;
 
 	pr_debug("SDIO: Disabling device %s...\n", sdio_func_id(func));
 
@@ -307,6 +307,9 @@ static int sdio_io_rw_ext_helper(struct sdio_func *func, int write,
 	unsigned max_blocks;
 	int ret;
 
+	if (!func || (func->num > 7))
+		return -EINVAL;
+
 	/* Do the bulk of the transfer using block mode (if supported). */
 	if (func->card->cccr.multi_block && (size > sdio_max_byte_size(func))) {
 		/* Blocks per command is limited by host count, host transfer
@@ -367,7 +370,10 @@ u8 sdio_readb(struct sdio_func *func, unsigned int addr, int *err_ret)
 	int ret;
 	u8 val;
 
-	BUG_ON(!func);
+	if (!func) {
+		*err_ret = -EINVAL;
+		return 0xFF;
+	}
 
 	if (err_ret)
 		*err_ret = 0;
@@ -398,7 +404,10 @@ void sdio_writeb(struct sdio_func *func, u8 b, unsigned int addr, int *err_ret)
 {
 	int ret;
 
-	BUG_ON(!func);
+	if (!func) {
+		*err_ret = -EINVAL;
+		return;
+	}
 
 	ret = mmc_io_rw_direct(func->card, 1, func->num, addr, b, NULL);
 	if (err_ret)
@@ -623,7 +632,10 @@ unsigned char sdio_f0_readb(struct sdio_func *func, unsigned int addr,
 	int ret;
 	unsigned char val;
 
-	BUG_ON(!func);
+	if (!func) {
+		*err_ret = -EINVAL;
+		return 0xFF;
+	}
 
 	if (err_ret)
 		*err_ret = 0;
@@ -658,7 +670,10 @@ void sdio_f0_writeb(struct sdio_func *func, unsigned char b, unsigned int addr,
 {
 	int ret;
 
-	BUG_ON(!func);
+	if (!func) {
+		*err_ret = -EINVAL;
+		return;
+	}
 
 	if ((addr < 0xF0 || addr > 0xFF) && (!mmc_card_lenient_fn0(func->card))) {
 		if (err_ret)
@@ -684,8 +699,8 @@ EXPORT_SYMBOL_GPL(sdio_f0_writeb);
  */
 mmc_pm_flag_t sdio_get_host_pm_caps(struct sdio_func *func)
 {
-	BUG_ON(!func);
-	BUG_ON(!func->card);
+	if (!func)
+		return 0;
 
 	return func->card->host->pm_caps;
 }
@@ -707,8 +722,8 @@ int sdio_set_host_pm_flags(struct sdio_func *func, mmc_pm_flag_t flags)
 {
 	struct mmc_host *host;
 
-	BUG_ON(!func);
-	BUG_ON(!func->card);
+	if (!func)
+		return -EINVAL;
 
 	host = func->card->host;
 
diff --git a/drivers/mmc/core/sdio_ops.c b/drivers/mmc/core/sdio_ops.c
index 34f6e8015306..90fe5545c677 100644
--- a/drivers/mmc/core/sdio_ops.c
+++ b/drivers/mmc/core/sdio_ops.c
@@ -24,8 +24,6 @@ int mmc_send_io_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr)
 	struct mmc_command cmd = {0};
 	int i, err = 0;
 
-	BUG_ON(!host);
-
 	cmd.opcode = SD_IO_SEND_OP_COND;
 	cmd.arg = ocr;
 	cmd.flags = MMC_RSP_SPI_R4 | MMC_RSP_R4 | MMC_CMD_BCR;
@@ -71,8 +69,8 @@ static int mmc_io_rw_direct_host(struct mmc_host *host, int write, unsigned fn,
 	struct mmc_command cmd = {0};
 	int err;
 
-	BUG_ON(!host);
-	BUG_ON(fn > 7);
+	if (fn > 7)
+		return -EINVAL;
 
 	/* sanity check */
 	if (addr & ~0x1FFFF)
@@ -114,7 +112,6 @@ static int mmc_io_rw_direct_host(struct mmc_host *host, int write, unsigned fn,
 int mmc_io_rw_direct(struct mmc_card *card, int write, unsigned fn,
 	unsigned addr, u8 in, u8 *out)
 {
-	BUG_ON(!card);
 	return mmc_io_rw_direct_host(card->host, write, fn, addr, in, out);
 }
 
@@ -129,8 +126,6 @@ int mmc_io_rw_extended(struct mmc_card *card, int write, unsigned fn,
 	unsigned int nents, left_size, i;
 	unsigned int seg_size = card->host->max_seg_size;
 
-	BUG_ON(!card);
-	BUG_ON(fn > 7);
 	WARN_ON(blksz == 0);
 
 	/* sanity check */
diff --git a/drivers/mmc/host/davinci_mmc.c b/drivers/mmc/host/davinci_mmc.c
index a56373c75983..8fa478c3b0db 100644
--- a/drivers/mmc/host/davinci_mmc.c
+++ b/drivers/mmc/host/davinci_mmc.c
@@ -1216,9 +1216,11 @@ static int __init davinci_mmcsd_probe(struct platform_device *pdev)
 	}
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	irq = platform_get_irq(pdev, 0);
-	if (!r || irq == NO_IRQ)
+	if (!r)
 		return -ENODEV;
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
 
 	mem_size = resource_size(r);
 	mem = devm_request_mem_region(&pdev->dev, r->start, mem_size,
diff --git a/drivers/mmc/host/dw_mmc-exynos.c b/drivers/mmc/host/dw_mmc-exynos.c
index da0ef1765735..7ab3d749b5ae 100644
--- a/drivers/mmc/host/dw_mmc-exynos.c
+++ b/drivers/mmc/host/dw_mmc-exynos.c
@@ -225,8 +225,12 @@ static void dw_mci_exynos_config_hs400(struct dw_mci *host, u32 timing)
 	 * Not supported to configure register
 	 * related to HS400
 	 */
-	if (priv->ctrl_type < DW_MCI_TYPE_EXYNOS5420)
+	if (priv->ctrl_type < DW_MCI_TYPE_EXYNOS5420) {
+		if (timing == MMC_TIMING_MMC_HS400)
+			dev_warn(host->dev,
+				 "cannot configure HS400, unsupported chipset\n");
 		return;
+	}
 
 	dqs = priv->saved_dqs_en;
 	strobe = priv->saved_strobe_ctrl;
diff --git a/drivers/mmc/host/dw_mmc-k3.c b/drivers/mmc/host/dw_mmc-k3.c
index 8e9d886bfcda..624789496dce 100644
--- a/drivers/mmc/host/dw_mmc-k3.c
+++ b/drivers/mmc/host/dw_mmc-k3.c
@@ -131,11 +131,17 @@ static void dw_mci_hi6220_set_ios(struct dw_mci *host, struct mmc_ios *ios)
 	host->bus_hz = clk_get_rate(host->biu_clk);
 }
 
+static int dw_mci_hi6220_execute_tuning(struct dw_mci_slot *slot, u32 opcode)
+{
+	return 0;
+}
+
 static const struct dw_mci_drv_data hi6220_data = {
 	.caps			= dw_mci_hi6220_caps,
 	.switch_voltage		= dw_mci_hi6220_switch_voltage,
 	.set_ios		= dw_mci_hi6220_set_ios,
 	.parse_dt		= dw_mci_hi6220_parse_dt,
+	.execute_tuning		= dw_mci_hi6220_execute_tuning,
 };
 
 static const struct of_device_id dw_mci_k3_match[] = {
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 767af2026f8b..4fcbc4012ed0 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -61,6 +61,8 @@
 				 SDMMC_IDMAC_INT_FBE | SDMMC_IDMAC_INT_RI | \
 				 SDMMC_IDMAC_INT_TI)
 
+#define DESC_RING_BUF_SZ	PAGE_SIZE
+
 struct idmac_desc_64addr {
 	u32		des0;	/* Control Descriptor */
 
@@ -467,136 +469,6 @@ static void dw_mci_dmac_complete_dma(void *arg)
 	}
 }
 
-static void dw_mci_translate_sglist(struct dw_mci *host, struct mmc_data *data,
-				    unsigned int sg_len)
-{
-	unsigned int desc_len;
-	int i;
-
-	if (host->dma_64bit_address == 1) {
-		struct idmac_desc_64addr *desc_first, *desc_last, *desc;
-
-		desc_first = desc_last = desc = host->sg_cpu;
-
-		for (i = 0; i < sg_len; i++) {
-			unsigned int length = sg_dma_len(&data->sg[i]);
-
-			u64 mem_addr = sg_dma_address(&data->sg[i]);
-
-			for ( ; length ; desc++) {
-				desc_len = (length <= DW_MCI_DESC_DATA_LENGTH) ?
-					   length : DW_MCI_DESC_DATA_LENGTH;
-
-				length -= desc_len;
-
-				/*
-				 * Set the OWN bit and disable interrupts
-				 * for this descriptor
-				 */
-				desc->des0 = IDMAC_DES0_OWN | IDMAC_DES0_DIC |
-							IDMAC_DES0_CH;
-
-				/* Buffer length */
-				IDMAC_64ADDR_SET_BUFFER1_SIZE(desc, desc_len);
-
-				/* Physical address to DMA to/from */
-				desc->des4 = mem_addr & 0xffffffff;
-				desc->des5 = mem_addr >> 32;
-
-				/* Update physical address for the next desc */
-				mem_addr += desc_len;
-
-				/* Save pointer to the last descriptor */
-				desc_last = desc;
-			}
-		}
-
-		/* Set first descriptor */
-		desc_first->des0 |= IDMAC_DES0_FD;
-
-		/* Set last descriptor */
-		desc_last->des0 &= ~(IDMAC_DES0_CH | IDMAC_DES0_DIC);
-		desc_last->des0 |= IDMAC_DES0_LD;
-
-	} else {
-		struct idmac_desc *desc_first, *desc_last, *desc;
-
-		desc_first = desc_last = desc = host->sg_cpu;
-
-		for (i = 0; i < sg_len; i++) {
-			unsigned int length = sg_dma_len(&data->sg[i]);
-
-			u32 mem_addr = sg_dma_address(&data->sg[i]);
-
-			for ( ; length ; desc++) {
-				desc_len = (length <= DW_MCI_DESC_DATA_LENGTH) ?
-					   length : DW_MCI_DESC_DATA_LENGTH;
-
-				length -= desc_len;
-
-				/*
-				 * Set the OWN bit and disable interrupts
-				 * for this descriptor
-				 */
-				desc->des0 = cpu_to_le32(IDMAC_DES0_OWN |
-							 IDMAC_DES0_DIC |
-							 IDMAC_DES0_CH);
-
-				/* Buffer length */
-				IDMAC_SET_BUFFER1_SIZE(desc, desc_len);
-
-				/* Physical address to DMA to/from */
-				desc->des2 = cpu_to_le32(mem_addr);
-
-				/* Update physical address for the next desc */
-				mem_addr += desc_len;
-
-				/* Save pointer to the last descriptor */
-				desc_last = desc;
-			}
-		}
-
-		/* Set first descriptor */
-		desc_first->des0 |= cpu_to_le32(IDMAC_DES0_FD);
-
-		/* Set last descriptor */
-		desc_last->des0 &= cpu_to_le32(~(IDMAC_DES0_CH |
-					       IDMAC_DES0_DIC));
-		desc_last->des0 |= cpu_to_le32(IDMAC_DES0_LD);
-	}
-
-	wmb(); /* drain writebuffer */
-}
-
-static int dw_mci_idmac_start_dma(struct dw_mci *host, unsigned int sg_len)
-{
-	u32 temp;
-
-	dw_mci_translate_sglist(host, host->data, sg_len);
-
-	/* Make sure to reset DMA in case we did PIO before this */
-	dw_mci_ctrl_reset(host, SDMMC_CTRL_DMA_RESET);
-	dw_mci_idmac_reset(host);
-
-	/* Select IDMAC interface */
-	temp = mci_readl(host, CTRL);
-	temp |= SDMMC_CTRL_USE_IDMAC;
-	mci_writel(host, CTRL, temp);
-
-	/* drain writebuffer */
-	wmb();
-
-	/* Enable the IDMAC */
-	temp = mci_readl(host, BMOD);
-	temp |= SDMMC_IDMAC_ENABLE | SDMMC_IDMAC_FB;
-	mci_writel(host, BMOD, temp);
-
-	/* Start it running */
-	mci_writel(host, PLDMND, 1);
-
-	return 0;
-}
-
 static int dw_mci_idmac_init(struct dw_mci *host)
 {
 	int i;
@@ -604,7 +476,8 @@ static int dw_mci_idmac_init(struct dw_mci *host)
 	if (host->dma_64bit_address == 1) {
 		struct idmac_desc_64addr *p;
 		/* Number of descriptors in the ring buffer */
-		host->ring_size = PAGE_SIZE / sizeof(struct idmac_desc_64addr);
+		host->ring_size =
+			DESC_RING_BUF_SZ / sizeof(struct idmac_desc_64addr);
 
 		/* Forward link the descriptor list */
 		for (i = 0, p = host->sg_cpu; i < host->ring_size - 1;
@@ -630,7 +503,8 @@ static int dw_mci_idmac_init(struct dw_mci *host)
 	} else {
 		struct idmac_desc *p;
 		/* Number of descriptors in the ring buffer */
-		host->ring_size = PAGE_SIZE / sizeof(struct idmac_desc);
+		host->ring_size =
+			DESC_RING_BUF_SZ / sizeof(struct idmac_desc);
 
 		/* Forward link the descriptor list */
 		for (i = 0, p = host->sg_cpu;
@@ -671,6 +545,195 @@ static int dw_mci_idmac_init(struct dw_mci *host)
 	return 0;
 }
 
+static inline int dw_mci_prepare_desc64(struct dw_mci *host,
+					 struct mmc_data *data,
+					 unsigned int sg_len)
+{
+	unsigned int desc_len;
+	struct idmac_desc_64addr *desc_first, *desc_last, *desc;
+	unsigned long timeout;
+	int i;
+
+	desc_first = desc_last = desc = host->sg_cpu;
+
+	for (i = 0; i < sg_len; i++) {
+		unsigned int length = sg_dma_len(&data->sg[i]);
+
+		u64 mem_addr = sg_dma_address(&data->sg[i]);
+
+		for ( ; length ; desc++) {
+			desc_len = (length <= DW_MCI_DESC_DATA_LENGTH) ?
+				   length : DW_MCI_DESC_DATA_LENGTH;
+
+			length -= desc_len;
+
+			/*
+			 * Wait for the former clear OWN bit operation
+			 * of IDMAC to make sure that this descriptor
+			 * isn't still owned by IDMAC as IDMAC's write
+			 * ops and CPU's read ops are asynchronous.
+			 */
+			timeout = jiffies + msecs_to_jiffies(100);
+			while (readl(&desc->des0) & IDMAC_DES0_OWN) {
+				if (time_after(jiffies, timeout))
+					goto err_own_bit;
+				udelay(10);
+			}
+
+			/*
+			 * Set the OWN bit and disable interrupts
+			 * for this descriptor
+			 */
+			desc->des0 = IDMAC_DES0_OWN | IDMAC_DES0_DIC |
+						IDMAC_DES0_CH;
+
+			/* Buffer length */
+			IDMAC_64ADDR_SET_BUFFER1_SIZE(desc, desc_len);
+
+			/* Physical address to DMA to/from */
+			desc->des4 = mem_addr & 0xffffffff;
+			desc->des5 = mem_addr >> 32;
+
+			/* Update physical address for the next desc */
+			mem_addr += desc_len;
+
+			/* Save pointer to the last descriptor */
+			desc_last = desc;
+		}
+	}
+
+	/* Set first descriptor */
+	desc_first->des0 |= IDMAC_DES0_FD;
+
+	/* Set last descriptor */
+	desc_last->des0 &= ~(IDMAC_DES0_CH | IDMAC_DES0_DIC);
+	desc_last->des0 |= IDMAC_DES0_LD;
+
+	return 0;
+err_own_bit:
+	/* restore the descriptor chain as it's polluted */
+	dev_dbg(host->dev, "desciptor is still owned by IDMAC.\n");
+	memset(host->sg_cpu, 0, DESC_RING_BUF_SZ);
+	dw_mci_idmac_init(host);
+	return -EINVAL;
+}
+
+
+static inline int dw_mci_prepare_desc32(struct dw_mci *host,
+					 struct mmc_data *data,
+					 unsigned int sg_len)
+{
+	unsigned int desc_len;
+	struct idmac_desc *desc_first, *desc_last, *desc;
+	unsigned long timeout;
+	int i;
+
+	desc_first = desc_last = desc = host->sg_cpu;
+
+	for (i = 0; i < sg_len; i++) {
+		unsigned int length = sg_dma_len(&data->sg[i]);
+
+		u32 mem_addr = sg_dma_address(&data->sg[i]);
+
+		for ( ; length ; desc++) {
+			desc_len = (length <= DW_MCI_DESC_DATA_LENGTH) ?
+				   length : DW_MCI_DESC_DATA_LENGTH;
+
+			length -= desc_len;
+
+			/*
+			 * Wait for the former clear OWN bit operation
+			 * of IDMAC to make sure that this descriptor
+			 * isn't still owned by IDMAC as IDMAC's write
+			 * ops and CPU's read ops are asynchronous.
+			 */
+			timeout = jiffies + msecs_to_jiffies(100);
+			while (readl(&desc->des0) &
+			       cpu_to_le32(IDMAC_DES0_OWN)) {
+				if (time_after(jiffies, timeout))
+					goto err_own_bit;
+				udelay(10);
+			}
+
+			/*
+			 * Set the OWN bit and disable interrupts
+			 * for this descriptor
+			 */
+			desc->des0 = cpu_to_le32(IDMAC_DES0_OWN |
+						 IDMAC_DES0_DIC |
+						 IDMAC_DES0_CH);
+
+			/* Buffer length */
+			IDMAC_SET_BUFFER1_SIZE(desc, desc_len);
+
+			/* Physical address to DMA to/from */
+			desc->des2 = cpu_to_le32(mem_addr);
+
+			/* Update physical address for the next desc */
+			mem_addr += desc_len;
+
+			/* Save pointer to the last descriptor */
+			desc_last = desc;
+		}
+	}
+
+	/* Set first descriptor */
+	desc_first->des0 |= cpu_to_le32(IDMAC_DES0_FD);
+
+	/* Set last descriptor */
+	desc_last->des0 &= cpu_to_le32(~(IDMAC_DES0_CH |
+				       IDMAC_DES0_DIC));
+	desc_last->des0 |= cpu_to_le32(IDMAC_DES0_LD);
+
+	return 0;
+err_own_bit:
+	/* restore the descriptor chain as it's polluted */
+	dev_dbg(host->dev, "desciptor is still owned by IDMAC.\n");
+	memset(host->sg_cpu, 0, DESC_RING_BUF_SZ);
+	dw_mci_idmac_init(host);
+	return -EINVAL;
+}
+
+static int dw_mci_idmac_start_dma(struct dw_mci *host, unsigned int sg_len)
+{
+	u32 temp;
+	int ret;
+
+	if (host->dma_64bit_address == 1)
+		ret = dw_mci_prepare_desc64(host, host->data, sg_len);
+	else
+		ret = dw_mci_prepare_desc32(host, host->data, sg_len);
+
+	if (ret)
+		goto out;
+
+	/* drain writebuffer */
+	wmb();
+
+	/* Make sure to reset DMA in case we did PIO before this */
+	dw_mci_ctrl_reset(host, SDMMC_CTRL_DMA_RESET);
+	dw_mci_idmac_reset(host);
+
+	/* Select IDMAC interface */
+	temp = mci_readl(host, CTRL);
+	temp |= SDMMC_CTRL_USE_IDMAC;
+	mci_writel(host, CTRL, temp);
+
+	/* drain writebuffer */
+	wmb();
+
+	/* Enable the IDMAC */
+	temp = mci_readl(host, BMOD);
+	temp |= SDMMC_IDMAC_ENABLE | SDMMC_IDMAC_FB;
+	mci_writel(host, BMOD, temp);
+
+	/* Start it running */
+	mci_writel(host, PLDMND, 1);
+
+out:
+	return ret;
+}
+
 static const struct dw_mci_dma_ops dw_mci_idmac_ops = {
 	.init = dw_mci_idmac_init,
 	.start = dw_mci_idmac_start_dma,
@@ -876,11 +939,8 @@ static void dw_mci_adjust_fifoth(struct dw_mci *host, struct mmc_data *data)
 	 * MSIZE is '1',
 	 * if blksz is not a multiple of the FIFO width
 	 */
-	if (blksz % fifo_width) {
-		msize = 0;
-		rx_wmark = 1;
+	if (blksz % fifo_width)
 		goto done;
-	}
 
 	do {
 		if (!((blksz_depth % mszs[idx]) ||
@@ -998,8 +1058,10 @@ static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data)
 	spin_unlock_irqrestore(&host->irq_lock, irqflags);
 
 	if (host->dma_ops->start(host, sg_len)) {
-		/* We can't do DMA */
-		dev_err(host->dev, "%s: failed to start DMA.\n", __func__);
+		/* We can't do DMA, try PIO for this one */
+		dev_dbg(host->dev,
+			"%s: fall back to PIO mode for current transfer\n",
+			__func__);
 		return -ENODEV;
 	}
 
@@ -1695,11 +1757,11 @@ static int dw_mci_data_complete(struct dw_mci *host, struct mmc_data *data)
 				data->error = -ETIMEDOUT;
 			} else if (host->dir_status ==
 					DW_MCI_RECV_STATUS) {
-				data->error = -EIO;
+				data->error = -EILSEQ;
 			}
 		} else {
 			/* SDMMC_INT_SBE is included */
-			data->error = -EIO;
+			data->error = -EILSEQ;
 		}
 
 		dev_dbg(host->dev, "data error, status 0x%08x\n", status);
@@ -2527,47 +2589,6 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-#ifdef CONFIG_OF
-/* given a slot, find out the device node representing that slot */
-static struct device_node *dw_mci_of_find_slot_node(struct dw_mci_slot *slot)
-{
-	struct device *dev = slot->mmc->parent;
-	struct device_node *np;
-	const __be32 *addr;
-	int len;
-
-	if (!dev || !dev->of_node)
-		return NULL;
-
-	for_each_child_of_node(dev->of_node, np) {
-		addr = of_get_property(np, "reg", &len);
-		if (!addr || (len < sizeof(int)))
-			continue;
-		if (be32_to_cpup(addr) == slot->id)
-			return np;
-	}
-	return NULL;
-}
-
-static void dw_mci_slot_of_parse(struct dw_mci_slot *slot)
-{
-	struct device_node *np = dw_mci_of_find_slot_node(slot);
-
-	if (!np)
-		return;
-
-	if (of_property_read_bool(np, "disable-wp")) {
-		slot->mmc->caps2 |= MMC_CAP2_NO_WRITE_PROTECT;
-		dev_warn(slot->mmc->parent,
-			"Slot quirk 'disable-wp' is deprecated\n");
-	}
-}
-#else /* CONFIG_OF */
-static void dw_mci_slot_of_parse(struct dw_mci_slot *slot)
-{
-}
-#endif /* CONFIG_OF */
-
 static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 {
 	struct mmc_host *mmc;
@@ -2630,8 +2651,6 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	if (host->pdata->caps2)
 		mmc->caps2 = host->pdata->caps2;
 
-	dw_mci_slot_of_parse(slot);
-
 	ret = mmc_of_parse(mmc);
 	if (ret)
 		goto err_host_allocated;
@@ -2736,7 +2755,8 @@ static void dw_mci_init_dma(struct dw_mci *host)
 		}
 
 		/* Alloc memory for sg translation */
-		host->sg_cpu = dmam_alloc_coherent(host->dev, PAGE_SIZE,
+		host->sg_cpu = dmam_alloc_coherent(host->dev,
+						   DESC_RING_BUF_SZ,
 						   &host->sg_dma, GFP_KERNEL);
 		if (!host->sg_cpu) {
 			dev_err(host->dev,
@@ -2919,6 +2939,13 @@ static struct dw_mci_board *dw_mci_parse_dt(struct dw_mci *host)
 	if (!pdata)
 		return ERR_PTR(-ENOMEM);
 
+	/* find reset controller when exist */
+	pdata->rstc = devm_reset_control_get_optional(dev, NULL);
+	if (IS_ERR(pdata->rstc)) {
+		if (PTR_ERR(pdata->rstc) == -EPROBE_DEFER)
+			return ERR_PTR(-EPROBE_DEFER);
+	}
+
 	/* find out number of slots supported */
 	of_property_read_u32(np, "num-slots", &pdata->num_slots);
 
@@ -2937,11 +2964,6 @@ static struct dw_mci_board *dw_mci_parse_dt(struct dw_mci *host)
 			return ERR_PTR(ret);
 	}
 
-	if (of_find_property(np, "supports-highspeed", NULL)) {
-		dev_info(dev, "supports-highspeed property is deprecated.\n");
-		pdata->caps |= MMC_CAP_SD_HIGHSPEED | MMC_CAP_MMC_HIGHSPEED;
-	}
-
 	return pdata;
 }
 
@@ -2990,7 +3012,9 @@ int dw_mci_probe(struct dw_mci *host)
 
 	if (!host->pdata) {
 		host->pdata = dw_mci_parse_dt(host);
-		if (IS_ERR(host->pdata)) {
+		if (PTR_ERR(host->pdata) == -EPROBE_DEFER) {
+			return -EPROBE_DEFER;
+		} else if (IS_ERR(host->pdata)) {
 			dev_err(host->dev, "platform data not available\n");
 			return -EINVAL;
 		}
@@ -3044,6 +3068,12 @@ int dw_mci_probe(struct dw_mci *host)
 		}
 	}
 
+	if (!IS_ERR(host->pdata->rstc)) {
+		reset_control_assert(host->pdata->rstc);
+		usleep_range(10, 50);
+		reset_control_deassert(host->pdata->rstc);
+	}
+
 	setup_timer(&host->cmd11_timer,
 		    dw_mci_cmd11_timer, (unsigned long)host);
 
@@ -3193,13 +3223,14 @@ err_dmaunmap:
 	if (host->use_dma && host->dma_ops->exit)
 		host->dma_ops->exit(host);
 
+	if (!IS_ERR(host->pdata->rstc))
+		reset_control_assert(host->pdata->rstc);
+
 err_clk_ciu:
-	if (!IS_ERR(host->ciu_clk))
-		clk_disable_unprepare(host->ciu_clk);
+	clk_disable_unprepare(host->ciu_clk);
 
 err_clk_biu:
-	if (!IS_ERR(host->biu_clk))
-		clk_disable_unprepare(host->biu_clk);
+	clk_disable_unprepare(host->biu_clk);
 
 	return ret;
 }
@@ -3225,11 +3256,11 @@ void dw_mci_remove(struct dw_mci *host)
 	if (host->use_dma && host->dma_ops->exit)
 		host->dma_ops->exit(host);
 
-	if (!IS_ERR(host->ciu_clk))
-		clk_disable_unprepare(host->ciu_clk);
+	if (!IS_ERR(host->pdata->rstc))
+		reset_control_assert(host->pdata->rstc);
 
-	if (!IS_ERR(host->biu_clk))
-		clk_disable_unprepare(host->biu_clk);
+	clk_disable_unprepare(host->ciu_clk);
+	clk_disable_unprepare(host->biu_clk);
 }
 EXPORT_SYMBOL(dw_mci_remove);
 
diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c
index 79905ce895ad..bbad309679cf 100644
--- a/drivers/mmc/host/moxart-mmc.c
+++ b/drivers/mmc/host/moxart-mmc.c
@@ -257,7 +257,7 @@ static void moxart_dma_complete(void *param)
 static void moxart_transfer_dma(struct mmc_data *data, struct moxart_host *host)
 {
 	u32 len, dir_data, dir_slave;
-	unsigned long dma_time;
+	long dma_time;
 	struct dma_async_tx_descriptor *desc = NULL;
 	struct dma_chan *dma_chan;
 
@@ -397,7 +397,8 @@ static void moxart_prepare_data(struct moxart_host *host)
 static void moxart_request(struct mmc_host *mmc, struct mmc_request *mrq)
 {
 	struct moxart_host *host = mmc_priv(mmc);
-	unsigned long pio_time, flags;
+	long pio_time;
+	unsigned long flags;
 	u32 status;
 
 	spin_lock_irqsave(&host->lock, flags);
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index 396c9b7e4121..3ccaa1415f33 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -126,7 +126,7 @@ static int sd_response_type(struct mmc_command *cmd)
 		return SD_RSP_TYPE_R0;
 	case MMC_RSP_R1:
 		return SD_RSP_TYPE_R1;
-	case MMC_RSP_R1 & ~MMC_RSP_CRC:
+	case MMC_RSP_R1_NO_CRC:
 		return SD_RSP_TYPE_R1 | SD_NO_CHECK_CRC7;
 	case MMC_RSP_R1B:
 		return SD_RSP_TYPE_R1b;
diff --git a/drivers/mmc/host/rtsx_usb_sdmmc.c b/drivers/mmc/host/rtsx_usb_sdmmc.c
index 6c71fc9f76c7..4106295527b9 100644
--- a/drivers/mmc/host/rtsx_usb_sdmmc.c
+++ b/drivers/mmc/host/rtsx_usb_sdmmc.c
@@ -324,7 +324,7 @@ static void sd_send_cmd_get_rsp(struct rtsx_usb_sdmmc *host,
 	case MMC_RSP_R1:
 		rsp_type = SD_RSP_TYPE_R1;
 		break;
-	case MMC_RSP_R1 & ~MMC_RSP_CRC:
+	case MMC_RSP_R1_NO_CRC:
 		rsp_type = SD_RSP_TYPE_R1 | SD_NO_CHECK_CRC7;
 		break;
 	case MMC_RSP_R1B:
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 8fe0756c8e1e..81d4dc034793 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -275,7 +275,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_emmc = {
 	.chip    = &sdhci_acpi_chip_int,
 	.caps    = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
 		   MMC_CAP_HW_RESET | MMC_CAP_1_8V_DDR |
-		   MMC_CAP_WAIT_WHILE_BUSY,
+		   MMC_CAP_CMD_DURING_TFR | MMC_CAP_WAIT_WHILE_BUSY,
 	.caps2   = MMC_CAP2_HC_ERASE_SZ,
 	.flags   = SDHCI_ACPI_RUNTIME_PM,
 	.quirks  = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
diff --git a/drivers/mmc/host/sdhci-bcm-kona.c b/drivers/mmc/host/sdhci-bcm-kona.c
index e5c634bdfdd9..51dd2fd65000 100644
--- a/drivers/mmc/host/sdhci-bcm-kona.c
+++ b/drivers/mmc/host/sdhci-bcm-kona.c
@@ -253,12 +253,14 @@ static int sdhci_bcm_kona_probe(struct platform_device *pdev)
 		goto err_pltfm_free;
 	}
 
-	if (clk_set_rate(pltfm_priv->clk, host->mmc->f_max) != 0) {
+	ret = clk_set_rate(pltfm_priv->clk, host->mmc->f_max);
+	if (ret) {
 		dev_err(dev, "Failed to set rate core clock\n");
 		goto err_pltfm_free;
 	}
 
-	if (clk_prepare_enable(pltfm_priv->clk) != 0) {
+	ret = clk_prepare_enable(pltfm_priv->clk);
+	if (ret) {
 		dev_err(dev, "Failed to enable core clock\n");
 		goto err_pltfm_free;
 	}
diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c
index cce10fe3e19e..159f6f64c68e 100644
--- a/drivers/mmc/host/sdhci-brcmstb.c
+++ b/drivers/mmc/host/sdhci-brcmstb.c
@@ -98,6 +98,8 @@ static int sdhci_brcmstb_probe(struct platform_device *pdev)
 	 * properties through mmc_of_parse().
 	 */
 	host->caps = sdhci_readl(host, SDHCI_CAPABILITIES);
+	if (of_device_is_compatible(pdev->dev.of_node, "brcm,bcm7425-sdhci"))
+		host->caps &= ~SDHCI_CAN_64BIT;
 	host->caps1 = sdhci_readl(host, SDHCI_CAPABILITIES_1);
 	host->caps1 &= ~(SDHCI_SUPPORT_SDR50 | SDHCI_SUPPORT_SDR104 |
 			SDHCI_SUPPORT_DDR50);
@@ -121,6 +123,7 @@ err_clk:
 
 static const struct of_device_id sdhci_brcm_of_match[] = {
 	{ .compatible = "brcm,bcm7425-sdhci" },
+	{ .compatible = "brcm,bcm7445-sdhci" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, sdhci_brcm_of_match);
@@ -128,7 +131,6 @@ MODULE_DEVICE_TABLE(of, sdhci_brcm_of_match);
 static struct platform_driver sdhci_brcmstb_driver = {
 	.driver		= {
 		.name	= "sdhci-brcmstb",
-		.owner	= THIS_MODULE,
 		.pm	= &sdhci_brcmstb_pmops,
 		.of_match_table = of_match_ptr(sdhci_brcm_of_match),
 	},
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 99e0b334f9df..1f54fd8755c8 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -31,6 +31,7 @@
 #include "sdhci-pltfm.h"
 #include "sdhci-esdhc.h"
 
+#define ESDHC_SYS_CTRL_DTOCV_MASK	0x0f
 #define	ESDHC_CTRL_D3CD			0x08
 #define ESDHC_BURST_LEN_EN_INCR		(1 << 27)
 /* VENDOR SPEC register */
@@ -928,7 +929,8 @@ static unsigned int esdhc_get_max_timeout_count(struct sdhci_host *host)
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host);
 
-	return esdhc_is_usdhc(imx_data) ? 1 << 28 : 1 << 27;
+	/* Doc Errata: the uSDHC actual maximum timeout count is 1 << 29 */
+	return esdhc_is_usdhc(imx_data) ? 1 << 29 : 1 << 27;
 }
 
 static void esdhc_set_timeout(struct sdhci_host *host, struct mmc_command *cmd)
@@ -937,7 +939,8 @@ static void esdhc_set_timeout(struct sdhci_host *host, struct mmc_command *cmd)
 	struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host);
 
 	/* use maximum timeout counter */
-	sdhci_writeb(host, esdhc_is_usdhc(imx_data) ? 0xF : 0xE,
+	esdhc_clrset_le(host, ESDHC_SYS_CTRL_DTOCV_MASK,
+			esdhc_is_usdhc(imx_data) ? 0xF : 0xE,
 			SDHCI_TIMEOUT_CONTROL);
 }
 
diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index e0f193f7e3e5..da8e40af6f85 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -26,6 +26,7 @@
 #include <linux/phy/phy.h>
 #include <linux/regmap.h>
 #include "sdhci-pltfm.h"
+#include <linux/of.h>
 
 #define SDHCI_ARASAN_CLK_CTRL_OFFSET	0x2c
 #define SDHCI_ARASAN_VENDOR_REGISTER	0x78
@@ -35,6 +36,8 @@
 #define CLK_CTRL_TIMEOUT_MASK		(0xf << CLK_CTRL_TIMEOUT_SHIFT)
 #define CLK_CTRL_TIMEOUT_MIN_EXP	13
 
+#define PHY_CLK_TOO_SLOW_HZ		400000
+
 /*
  * On some SoCs the syscon area has a feature where the upper 16-bits of
  * each 32-bit register act as a write mask for the lower 16-bits.  This allows
@@ -65,10 +68,12 @@ struct sdhci_arasan_soc_ctl_field {
  * accessible via the syscon API.
  *
  * @baseclkfreq:	Where to find corecfg_baseclkfreq
+ * @clockmultiplier:	Where to find corecfg_clockmultiplier
  * @hiword_update:	If true, use HIWORD_UPDATE to access the syscon
  */
 struct sdhci_arasan_soc_ctl_map {
 	struct sdhci_arasan_soc_ctl_field	baseclkfreq;
+	struct sdhci_arasan_soc_ctl_field	clockmultiplier;
 	bool					hiword_update;
 };
 
@@ -77,6 +82,7 @@ struct sdhci_arasan_soc_ctl_map {
  * @host:		Pointer to the main SDHCI host structure.
  * @clk_ahb:		Pointer to the AHB clock
  * @phy:		Pointer to the generic phy
+ * @is_phy_on:		True if the PHY is on; false if not.
  * @sdcardclk_hw:	Struct for the clock we might provide to a PHY.
  * @sdcardclk:		Pointer to normal 'struct clock' for sdcardclk_hw.
  * @soc_ctl_base:	Pointer to regmap for syscon for soc_ctl registers.
@@ -86,16 +92,22 @@ struct sdhci_arasan_data {
 	struct sdhci_host *host;
 	struct clk	*clk_ahb;
 	struct phy	*phy;
+	bool		is_phy_on;
 
 	struct clk_hw	sdcardclk_hw;
 	struct clk      *sdcardclk;
 
 	struct regmap	*soc_ctl_base;
 	const struct sdhci_arasan_soc_ctl_map *soc_ctl_map;
+	unsigned int	quirks; /* Arasan deviations from spec */
+
+/* Controller does not have CD wired and will not function normally without */
+#define SDHCI_ARASAN_QUIRK_FORCE_CDTEST	BIT(0)
 };
 
 static const struct sdhci_arasan_soc_ctl_map rk3399_soc_ctl_map = {
 	.baseclkfreq = { .reg = 0xf000, .width = 8, .shift = 8 },
+	.clockmultiplier = { .reg = 0xf02c, .width = 8, .shift = 0},
 	.hiword_update = true,
 };
 
@@ -170,13 +182,47 @@ static void sdhci_arasan_set_clock(struct sdhci_host *host, unsigned int clock)
 	struct sdhci_arasan_data *sdhci_arasan = sdhci_pltfm_priv(pltfm_host);
 	bool ctrl_phy = false;
 
-	if (clock > MMC_HIGH_52_MAX_DTR && (!IS_ERR(sdhci_arasan->phy)))
-		ctrl_phy = true;
+	if (!IS_ERR(sdhci_arasan->phy)) {
+		if (!sdhci_arasan->is_phy_on && clock <= PHY_CLK_TOO_SLOW_HZ) {
+			/*
+			 * If PHY off, set clock to max speed and power PHY on.
+			 *
+			 * Although PHY docs apparently suggest power cycling
+			 * when changing the clock the PHY doesn't like to be
+			 * powered on while at low speeds like those used in ID
+			 * mode.  Even worse is powering the PHY on while the
+			 * clock is off.
+			 *
+			 * To workaround the PHY limitations, the best we can
+			 * do is to power it on at a faster speed and then slam
+			 * through low speeds without power cycling.
+			 */
+			sdhci_set_clock(host, host->max_clk);
+			spin_unlock_irq(&host->lock);
+			phy_power_on(sdhci_arasan->phy);
+			spin_lock_irq(&host->lock);
+			sdhci_arasan->is_phy_on = true;
+
+			/*
+			 * We'll now fall through to the below case with
+			 * ctrl_phy = false (so we won't turn off/on).  The
+			 * sdhci_set_clock() will set the real clock.
+			 */
+		} else if (clock > PHY_CLK_TOO_SLOW_HZ) {
+			/*
+			 * At higher clock speeds the PHY is fine being power
+			 * cycled and docs say you _should_ power cycle when
+			 * changing clock speeds.
+			 */
+			ctrl_phy = true;
+		}
+	}
 
-	if (ctrl_phy) {
+	if (ctrl_phy && sdhci_arasan->is_phy_on) {
 		spin_unlock_irq(&host->lock);
 		phy_power_off(sdhci_arasan->phy);
 		spin_lock_irq(&host->lock);
+		sdhci_arasan->is_phy_on = false;
 	}
 
 	sdhci_set_clock(host, clock);
@@ -185,6 +231,7 @@ static void sdhci_arasan_set_clock(struct sdhci_host *host, unsigned int clock)
 		spin_unlock_irq(&host->lock);
 		phy_power_on(sdhci_arasan->phy);
 		spin_lock_irq(&host->lock);
+		sdhci_arasan->is_phy_on = true;
 	}
 }
 
@@ -203,12 +250,27 @@ static void sdhci_arasan_hs400_enhanced_strobe(struct mmc_host *mmc,
 	writel(vendor, host->ioaddr + SDHCI_ARASAN_VENDOR_REGISTER);
 }
 
+void sdhci_arasan_reset(struct sdhci_host *host, u8 mask)
+{
+	u8 ctrl;
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_arasan_data *sdhci_arasan = sdhci_pltfm_priv(pltfm_host);
+
+	sdhci_reset(host, mask);
+
+	if (sdhci_arasan->quirks & SDHCI_ARASAN_QUIRK_FORCE_CDTEST) {
+		ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
+		ctrl |= SDHCI_CTRL_CDTEST_INS | SDHCI_CTRL_CDTEST_EN;
+		sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
+	}
+}
+
 static struct sdhci_ops sdhci_arasan_ops = {
 	.set_clock = sdhci_arasan_set_clock,
 	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
 	.get_timeout_clock = sdhci_arasan_get_timeout_clock,
 	.set_bus_width = sdhci_set_bus_width,
-	.reset = sdhci_reset,
+	.reset = sdhci_arasan_reset,
 	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
@@ -239,13 +301,14 @@ static int sdhci_arasan_suspend(struct device *dev)
 	if (ret)
 		return ret;
 
-	if (!IS_ERR(sdhci_arasan->phy)) {
+	if (!IS_ERR(sdhci_arasan->phy) && sdhci_arasan->is_phy_on) {
 		ret = phy_power_off(sdhci_arasan->phy);
 		if (ret) {
 			dev_err(dev, "Cannot power off phy.\n");
 			sdhci_resume_host(host);
 			return ret;
 		}
+		sdhci_arasan->is_phy_on = false;
 	}
 
 	clk_disable(pltfm_host->clk);
@@ -281,12 +344,13 @@ static int sdhci_arasan_resume(struct device *dev)
 		return ret;
 	}
 
-	if (!IS_ERR(sdhci_arasan->phy)) {
+	if (!IS_ERR(sdhci_arasan->phy) && host->mmc->actual_clock) {
 		ret = phy_power_on(sdhci_arasan->phy);
 		if (ret) {
 			dev_err(dev, "Cannot power on phy.\n");
 			return ret;
 		}
+		sdhci_arasan->is_phy_on = true;
 	}
 
 	return sdhci_resume_host(host);
@@ -338,6 +402,45 @@ static const struct clk_ops arasan_sdcardclk_ops = {
 };
 
 /**
+ * sdhci_arasan_update_clockmultiplier - Set corecfg_clockmultiplier
+ *
+ * The corecfg_clockmultiplier is supposed to contain clock multiplier
+ * value of programmable clock generator.
+ *
+ * NOTES:
+ * - Many existing devices don't seem to do this and work fine.  To keep
+ *   compatibility for old hardware where the device tree doesn't provide a
+ *   register map, this function is a noop if a soc_ctl_map hasn't been provided
+ *   for this platform.
+ * - The value of corecfg_clockmultiplier should sync with that of corresponding
+ *   value reading from sdhci_capability_register. So this function is called
+ *   once at probe time and never called again.
+ *
+ * @host:		The sdhci_host
+ */
+static void sdhci_arasan_update_clockmultiplier(struct sdhci_host *host,
+						u32 value)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_arasan_data *sdhci_arasan = sdhci_pltfm_priv(pltfm_host);
+	const struct sdhci_arasan_soc_ctl_map *soc_ctl_map =
+		sdhci_arasan->soc_ctl_map;
+
+	/* Having a map is optional */
+	if (!soc_ctl_map)
+		return;
+
+	/* If we have a map, we expect to have a syscon */
+	if (!sdhci_arasan->soc_ctl_base) {
+		pr_warn("%s: Have regmap, but no soc-ctl-syscon\n",
+			mmc_hostname(host->mmc));
+		return;
+	}
+
+	sdhci_arasan_syscon_write(host, &soc_ctl_map->clockmultiplier, value);
+}
+
+/**
  * sdhci_arasan_update_baseclkfreq - Set corecfg_baseclkfreq
  *
  * The corecfg_baseclkfreq is supposed to contain the MHz of clk_xin.  This
@@ -462,6 +565,7 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 	struct sdhci_host *host;
 	struct sdhci_pltfm_host *pltfm_host;
 	struct sdhci_arasan_data *sdhci_arasan;
+	struct device_node *np = pdev->dev.of_node;
 
 	host = sdhci_pltfm_init(pdev, &sdhci_arasan_pdata,
 				sizeof(*sdhci_arasan));
@@ -516,8 +620,16 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 	}
 
 	sdhci_get_of_property(pdev);
+
+	if (of_property_read_bool(np, "xlnx,fails-without-test-cd"))
+		sdhci_arasan->quirks |= SDHCI_ARASAN_QUIRK_FORCE_CDTEST;
+
 	pltfm_host->clk = clk_xin;
 
+	if (of_device_is_compatible(pdev->dev.of_node,
+				    "rockchip,rk3399-sdhci-5.1"))
+		sdhci_arasan_update_clockmultiplier(host, 0x0);
+
 	sdhci_arasan_update_baseclkfreq(host);
 
 	ret = sdhci_arasan_register_sdclk(sdhci_arasan, clk_xin, &pdev->dev);
@@ -547,12 +659,6 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 			goto unreg_clk;
 		}
 
-		ret = phy_power_on(sdhci_arasan->phy);
-		if (ret < 0) {
-			dev_err(&pdev->dev, "phy_power_on err.\n");
-			goto err_phy_power;
-		}
-
 		host->mmc_host_ops.hs400_enhanced_strobe =
 					sdhci_arasan_hs400_enhanced_strobe;
 	}
@@ -565,9 +671,6 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 
 err_add_host:
 	if (!IS_ERR(sdhci_arasan->phy))
-		phy_power_off(sdhci_arasan->phy);
-err_phy_power:
-	if (!IS_ERR(sdhci_arasan->phy))
 		phy_exit(sdhci_arasan->phy);
 unreg_clk:
 	sdhci_arasan_unregister_sdclk(&pdev->dev);
@@ -589,7 +692,8 @@ static int sdhci_arasan_remove(struct platform_device *pdev)
 	struct clk *clk_ahb = sdhci_arasan->clk_ahb;
 
 	if (!IS_ERR(sdhci_arasan->phy)) {
-		phy_power_off(sdhci_arasan->phy);
+		if (sdhci_arasan->is_phy_on)
+			phy_power_off(sdhci_arasan->phy);
 		phy_exit(sdhci_arasan->phy);
 	}
 
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 239be2fde242..fb71c866eacc 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -583,7 +583,7 @@ static int sdhci_esdhc_probe(struct platform_device *pdev)
 
 	np = pdev->dev.of_node;
 
-	if (of_get_property(np, "little-endian", NULL))
+	if (of_property_read_bool(np, "little-endian"))
 		host = sdhci_pltfm_init(pdev, &sdhci_esdhc_le_pdata,
 					sizeof(struct sdhci_esdhc));
 	else
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 897cfd24ca2e..72a1f1f5180a 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -156,7 +156,7 @@ static void sdhci_pci_add_own_cd(struct sdhci_pci_slot *slot)
 	if (!gpio_is_valid(gpio))
 		return;
 
-	err = gpio_request(gpio, "sd_cd");
+	err = devm_gpio_request(&slot->chip->pdev->dev, gpio, "sd_cd");
 	if (err < 0)
 		goto out;
 
@@ -179,7 +179,7 @@ static void sdhci_pci_add_own_cd(struct sdhci_pci_slot *slot)
 	return;
 
 out_free:
-	gpio_free(gpio);
+	devm_gpio_free(&slot->chip->pdev->dev, gpio);
 out:
 	dev_warn(&slot->chip->pdev->dev, "failed to setup card detect wake up\n");
 }
@@ -188,8 +188,6 @@ static void sdhci_pci_remove_own_cd(struct sdhci_pci_slot *slot)
 {
 	if (slot->cd_irq >= 0)
 		free_irq(slot->cd_irq, slot);
-	if (gpio_is_valid(slot->cd_gpio))
-		gpio_free(slot->cd_gpio);
 }
 
 #else
@@ -356,6 +354,7 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 {
 	slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
 				 MMC_CAP_HW_RESET | MMC_CAP_1_8V_DDR |
+				 MMC_CAP_CMD_DURING_TFR |
 				 MMC_CAP_WAIT_WHILE_BUSY;
 	slot->host->mmc->caps2 |= MMC_CAP2_HC_ERASE_SZ;
 	slot->hw_reset = sdhci_pci_int_hw_reset;
@@ -421,17 +420,30 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_sd = {
 /* Define Host controllers for Intel Merrifield platform */
 #define INTEL_MRFLD_EMMC_0	0
 #define INTEL_MRFLD_EMMC_1	1
+#define INTEL_MRFLD_SD		2
+#define INTEL_MRFLD_SDIO	3
 
 static int intel_mrfld_mmc_probe_slot(struct sdhci_pci_slot *slot)
 {
-	if ((PCI_FUNC(slot->chip->pdev->devfn) != INTEL_MRFLD_EMMC_0) &&
-	    (PCI_FUNC(slot->chip->pdev->devfn) != INTEL_MRFLD_EMMC_1))
-		/* SD support is not ready yet */
+	unsigned int func = PCI_FUNC(slot->chip->pdev->devfn);
+
+	switch (func) {
+	case INTEL_MRFLD_EMMC_0:
+	case INTEL_MRFLD_EMMC_1:
+		slot->host->mmc->caps |= MMC_CAP_NONREMOVABLE |
+					 MMC_CAP_8_BIT_DATA |
+					 MMC_CAP_1_8V_DDR;
+		break;
+	case INTEL_MRFLD_SD:
+		slot->host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
+		break;
+	case INTEL_MRFLD_SDIO:
+		slot->host->mmc->caps |= MMC_CAP_NONREMOVABLE |
+					 MMC_CAP_POWER_OFF_CARD;
+		break;
+	default:
 		return -ENODEV;
-
-	slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
-				 MMC_CAP_1_8V_DDR;
-
+	}
 	return 0;
 }
 
@@ -1615,7 +1627,6 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
 
 	slot->chip = chip;
 	slot->host = host;
-	slot->pci_bar = bar;
 	slot->rst_n_gpio = -EINVAL;
 	slot->cd_gpio = -EINVAL;
 	slot->cd_idx = -1;
@@ -1643,27 +1654,22 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
 
 	host->irq = pdev->irq;
 
-	ret = pci_request_region(pdev, bar, mmc_hostname(host->mmc));
+	ret = pcim_iomap_regions(pdev, BIT(bar), mmc_hostname(host->mmc));
 	if (ret) {
 		dev_err(&pdev->dev, "cannot request region\n");
 		goto cleanup;
 	}
 
-	host->ioaddr = pci_ioremap_bar(pdev, bar);
-	if (!host->ioaddr) {
-		dev_err(&pdev->dev, "failed to remap registers\n");
-		ret = -ENOMEM;
-		goto release;
-	}
+	host->ioaddr = pcim_iomap_table(pdev)[bar];
 
 	if (chip->fixes && chip->fixes->probe_slot) {
 		ret = chip->fixes->probe_slot(slot);
 		if (ret)
-			goto unmap;
+			goto cleanup;
 	}
 
 	if (gpio_is_valid(slot->rst_n_gpio)) {
-		if (!gpio_request(slot->rst_n_gpio, "eMMC_reset")) {
+		if (!devm_gpio_request(&pdev->dev, slot->rst_n_gpio, "eMMC_reset")) {
 			gpio_direction_output(slot->rst_n_gpio, 1);
 			slot->host->mmc->caps |= MMC_CAP_HW_RESET;
 			slot->hw_reset = sdhci_pci_gpio_hw_reset;
@@ -1702,18 +1708,9 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
 	return slot;
 
 remove:
-	if (gpio_is_valid(slot->rst_n_gpio))
-		gpio_free(slot->rst_n_gpio);
-
 	if (chip->fixes && chip->fixes->remove_slot)
 		chip->fixes->remove_slot(slot, 0);
 
-unmap:
-	iounmap(host->ioaddr);
-
-release:
-	pci_release_region(pdev, bar);
-
 cleanup:
 	if (slot->data && slot->data->cleanup)
 		slot->data->cleanup(slot->data);
@@ -1738,17 +1735,12 @@ static void sdhci_pci_remove_slot(struct sdhci_pci_slot *slot)
 
 	sdhci_remove_host(slot->host, dead);
 
-	if (gpio_is_valid(slot->rst_n_gpio))
-		gpio_free(slot->rst_n_gpio);
-
 	if (slot->chip->fixes && slot->chip->fixes->remove_slot)
 		slot->chip->fixes->remove_slot(slot, dead);
 
 	if (slot->data && slot->data->cleanup)
 		slot->data->cleanup(slot->data);
 
-	pci_release_region(slot->chip->pdev, slot->pci_bar);
-
 	sdhci_free_host(slot->host);
 }
 
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index 7e0788712e1a..9c7c08b93223 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -72,7 +72,6 @@ struct sdhci_pci_slot {
 	struct sdhci_host	*host;
 	struct sdhci_pci_data	*data;
 
-	int			pci_bar;
 	int			rst_n_gpio;
 	int			cd_gpio;
 	int			cd_irq;
diff --git a/drivers/mmc/host/sdhci-pltfm.c b/drivers/mmc/host/sdhci-pltfm.c
index 1d17dcfc3ffb..ad49bfaf5bf8 100644
--- a/drivers/mmc/host/sdhci-pltfm.c
+++ b/drivers/mmc/host/sdhci-pltfm.c
@@ -156,13 +156,6 @@ struct sdhci_host *sdhci_pltfm_init(struct platform_device *pdev,
 		host->quirks2 = pdata->quirks2;
 	}
 
-	/*
-	 * Some platforms need to probe the controller to be able to
-	 * determine which caps should be used.
-	 */
-	if (host->ops && host->ops->platform_init)
-		host->ops->platform_init(host);
-
 	platform_set_drvdata(pdev, host);
 
 	return host;
diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
index 1e93dc4e303e..20b6ff5b4af1 100644
--- a/drivers/mmc/host/sdhci-tegra.c
+++ b/drivers/mmc/host/sdhci-tegra.c
@@ -391,6 +391,31 @@ static const struct sdhci_tegra_soc_data soc_data_tegra114 = {
 	.pdata = &sdhci_tegra114_pdata,
 };
 
+static const struct sdhci_pltfm_data sdhci_tegra124_pdata = {
+	.quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL |
+		  SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
+		  SDHCI_QUIRK_SINGLE_POWER_WRITE |
+		  SDHCI_QUIRK_NO_HISPD_BIT |
+		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC |
+		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+		   /*
+		    * The TRM states that the SD/MMC controller found on
+		    * Tegra124 can address 34 bits (the maximum supported by
+		    * the Tegra memory controller), but tests show that DMA
+		    * to or from above 4 GiB doesn't work. This is possibly
+		    * caused by missing programming, though it's not obvious
+		    * what sequence is required. Mark 64-bit DMA broken for
+		    * now to fix this for existing users (e.g. Nyan boards).
+		    */
+		   SDHCI_QUIRK2_BROKEN_64_BIT_DMA,
+	.ops  = &tegra114_sdhci_ops,
+};
+
+static const struct sdhci_tegra_soc_data soc_data_tegra124 = {
+	.pdata = &sdhci_tegra124_pdata,
+};
+
 static const struct sdhci_pltfm_data sdhci_tegra210_pdata = {
 	.quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL |
 		  SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
@@ -408,7 +433,7 @@ static const struct sdhci_tegra_soc_data soc_data_tegra210 = {
 
 static const struct of_device_id sdhci_tegra_dt_match[] = {
 	{ .compatible = "nvidia,tegra210-sdhci", .data = &soc_data_tegra210 },
-	{ .compatible = "nvidia,tegra124-sdhci", .data = &soc_data_tegra114 },
+	{ .compatible = "nvidia,tegra124-sdhci", .data = &soc_data_tegra124 },
 	{ .compatible = "nvidia,tegra114-sdhci", .data = &soc_data_tegra114 },
 	{ .compatible = "nvidia,tegra30-sdhci", .data = &soc_data_tegra30 },
 	{ .compatible = "nvidia,tegra20-sdhci", .data = &soc_data_tegra20 },
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index cd65d474afa2..48055666c655 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -888,7 +888,8 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
 static inline bool sdhci_auto_cmd12(struct sdhci_host *host,
 				    struct mmc_request *mrq)
 {
-	return !mrq->sbc && (host->flags & SDHCI_AUTO_CMD12);
+	return !mrq->sbc && (host->flags & SDHCI_AUTO_CMD12) &&
+	       !mrq->cap_cmd_during_tfr;
 }
 
 static void sdhci_set_transfer_mode(struct sdhci_host *host,
@@ -1031,9 +1032,18 @@ static void sdhci_finish_data(struct sdhci_host *host)
 			sdhci_do_reset(host, SDHCI_RESET_DATA);
 		}
 
-		/* Avoid triggering warning in sdhci_send_command() */
-		host->cmd = NULL;
-		sdhci_send_command(host, data->stop);
+		/*
+		 * 'cap_cmd_during_tfr' request must not use the command line
+		 * after mmc_command_done() has been called. It is upper layer's
+		 * responsibility to send the stop command if required.
+		 */
+		if (data->mrq->cap_cmd_during_tfr) {
+			sdhci_finish_mrq(host, data->mrq);
+		} else {
+			/* Avoid triggering warning in sdhci_send_command() */
+			host->cmd = NULL;
+			sdhci_send_command(host, data->stop);
+		}
 	} else {
 		sdhci_finish_mrq(host, data->mrq);
 	}
@@ -1165,6 +1175,9 @@ static void sdhci_finish_command(struct sdhci_host *host)
 		}
 	}
 
+	if (cmd->mrq->cap_cmd_during_tfr && cmd == cmd->mrq->cmd)
+		mmc_command_done(host->mmc, cmd->mrq);
+
 	/*
 	 * The host can send and interrupt when the busy state has
 	 * ended, allowing us to wait without wasting CPU cycles.
@@ -2062,7 +2075,7 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 
 		spin_unlock_irqrestore(&host->lock, flags);
 		/* Wait for Buffer Read Ready interrupt */
-		wait_event_interruptible_timeout(host->buf_ready_int,
+		wait_event_timeout(host->buf_ready_int,
 					(host->tuning_done == 1),
 					msecs_to_jiffies(50));
 		spin_lock_irqsave(&host->lock, flags);
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 0411c9f36461..c722cd23205c 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -84,6 +84,8 @@
 #define   SDHCI_CTRL_ADMA32	0x10
 #define   SDHCI_CTRL_ADMA64	0x18
 #define   SDHCI_CTRL_8BITBUS	0x20
+#define  SDHCI_CTRL_CDTEST_INS	0x40
+#define  SDHCI_CTRL_CDTEST_EN	0x80
 
 #define SDHCI_POWER_CONTROL	0x29
 #define  SDHCI_POWER_ON		0x01
@@ -555,7 +557,6 @@ struct sdhci_ops {
 	void	(*set_uhs_signaling)(struct sdhci_host *host, unsigned int uhs);
 	void	(*hw_reset)(struct sdhci_host *host);
 	void    (*adma_workaround)(struct sdhci_host *host, u32 intmask);
-	void	(*platform_init)(struct sdhci_host *host);
 	void    (*card_event)(struct sdhci_host *host);
 	void	(*voltage_switch)(struct sdhci_host *host);
 	int	(*select_drive_strength)(struct sdhci_host *host,
diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index c3b651bf89cb..49edff7fee49 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -94,6 +94,7 @@ static const struct of_device_id sh_mobile_sdhi_of_match[] = {
 	{ .compatible = "renesas,sdhi-r8a7793", .data = &of_rcar_gen2_compatible, },
 	{ .compatible = "renesas,sdhi-r8a7794", .data = &of_rcar_gen2_compatible, },
 	{ .compatible = "renesas,sdhi-r8a7795", .data = &of_rcar_gen3_compatible, },
+	{ .compatible = "renesas,sdhi-r8a7796", .data = &of_rcar_gen3_compatible, },
 	{},
 };
 MODULE_DEVICE_TABLE(of, sh_mobile_sdhi_of_match);
@@ -213,6 +214,13 @@ static void sh_mobile_sdhi_clk_disable(struct tmio_mmc_host *host)
 	clk_disable_unprepare(priv->clk);
 }
 
+static int sh_mobile_sdhi_card_busy(struct mmc_host *mmc)
+{
+	struct tmio_mmc_host *host = mmc_priv(mmc);
+
+	return !(sd_ctrl_read16_and_16_as_32(host, CTL_STATUS) & TMIO_STAT_DAT0);
+}
+
 static int sh_mobile_sdhi_start_signal_voltage_switch(struct mmc_host *mmc,
 						      struct mmc_ios *ios)
 {
@@ -369,7 +377,14 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	host->clk_update	= sh_mobile_sdhi_clk_update;
 	host->clk_disable	= sh_mobile_sdhi_clk_disable;
 	host->multi_io_quirk	= sh_mobile_sdhi_multi_io_quirk;
-	host->start_signal_voltage_switch = sh_mobile_sdhi_start_signal_voltage_switch;
+
+	/* SDR speeds are only available on Gen2+ */
+	if (mmc_data->flags & TMIO_MMC_MIN_RCAR2) {
+		/* card_busy caused issues on r8a73a4 (pre-Gen2) CD-less SDHI */
+		host->card_busy	= sh_mobile_sdhi_card_busy;
+		host->start_signal_voltage_switch =
+			sh_mobile_sdhi_start_signal_voltage_switch;
+	}
 
 	/* Orginally registers were 16 bit apart, could be 32 or 64 nowadays */
 	if (!host->bus_shift && resource_size(res) > 0x100) /* old way to determine the shift */
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index 2ee4c21ec55e..c0a5c676d0e8 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -72,6 +72,13 @@
 #define SDXC_REG_CHDA	(0x90)
 #define SDXC_REG_CBDA	(0x94)
 
+/* New registers introduced in A64 */
+#define SDXC_REG_A12A		0x058 /* SMC Auto Command 12 Register */
+#define SDXC_REG_SD_NTSR	0x05C /* SMC New Timing Set Register */
+#define SDXC_REG_DRV_DL		0x140 /* Drive Delay Control Register */
+#define SDXC_REG_SAMP_DL_REG	0x144 /* SMC sample delay control */
+#define SDXC_REG_DS_DL_REG	0x148 /* SMC data strobe delay control */
+
 #define mmc_readl(host, reg) \
 	readl((host)->reg_base + SDXC_##reg)
 #define mmc_writel(host, reg, value) \
@@ -217,21 +224,41 @@
 #define SDXC_CLK_50M_DDR	3
 #define SDXC_CLK_50M_DDR_8BIT	4
 
+#define SDXC_2X_TIMING_MODE	BIT(31)
+
+#define SDXC_CAL_START		BIT(15)
+#define SDXC_CAL_DONE		BIT(14)
+#define SDXC_CAL_DL_SHIFT	8
+#define SDXC_CAL_DL_SW_EN	BIT(7)
+#define SDXC_CAL_DL_SW_SHIFT	0
+#define SDXC_CAL_DL_MASK	0x3f
+
+#define SDXC_CAL_TIMEOUT	3	/* in seconds, 3s is enough*/
+
 struct sunxi_mmc_clk_delay {
 	u32 output;
 	u32 sample;
 };
 
 struct sunxi_idma_des {
-	u32	config;
-	u32	buf_size;
-	u32	buf_addr_ptr1;
-	u32	buf_addr_ptr2;
+	__le32 config;
+	__le32 buf_size;
+	__le32 buf_addr_ptr1;
+	__le32 buf_addr_ptr2;
+};
+
+struct sunxi_mmc_cfg {
+	u32 idma_des_size_bits;
+	const struct sunxi_mmc_clk_delay *clk_delays;
+
+	/* does the IP block support autocalibration? */
+	bool can_calibrate;
 };
 
 struct sunxi_mmc_host {
 	struct mmc_host	*mmc;
 	struct reset_control *reset;
+	const struct sunxi_mmc_cfg *cfg;
 
 	/* IO mapping base */
 	void __iomem	*reg_base;
@@ -241,7 +268,6 @@ struct sunxi_mmc_host {
 	struct clk	*clk_mmc;
 	struct clk	*clk_sample;
 	struct clk	*clk_output;
-	const struct sunxi_mmc_clk_delay *clk_delays;
 
 	/* irq */
 	spinlock_t	lock;
@@ -250,7 +276,6 @@ struct sunxi_mmc_host {
 	u32		sdio_imask;
 
 	/* dma */
-	u32		idma_des_size_bits;
 	dma_addr_t	sg_dma;
 	void		*sg_cpu;
 	bool		wait_dma;
@@ -322,25 +347,28 @@ static void sunxi_mmc_init_idma_des(struct sunxi_mmc_host *host,
 {
 	struct sunxi_idma_des *pdes = (struct sunxi_idma_des *)host->sg_cpu;
 	dma_addr_t next_desc = host->sg_dma;
-	int i, max_len = (1 << host->idma_des_size_bits);
+	int i, max_len = (1 << host->cfg->idma_des_size_bits);
 
 	for (i = 0; i < data->sg_len; i++) {
-		pdes[i].config = SDXC_IDMAC_DES0_CH | SDXC_IDMAC_DES0_OWN |
-				 SDXC_IDMAC_DES0_DIC;
+		pdes[i].config = cpu_to_le32(SDXC_IDMAC_DES0_CH |
+					     SDXC_IDMAC_DES0_OWN |
+					     SDXC_IDMAC_DES0_DIC);
 
 		if (data->sg[i].length == max_len)
 			pdes[i].buf_size = 0; /* 0 == max_len */
 		else
-			pdes[i].buf_size = data->sg[i].length;
+			pdes[i].buf_size = cpu_to_le32(data->sg[i].length);
 
 		next_desc += sizeof(struct sunxi_idma_des);
-		pdes[i].buf_addr_ptr1 = sg_dma_address(&data->sg[i]);
-		pdes[i].buf_addr_ptr2 = (u32)next_desc;
+		pdes[i].buf_addr_ptr1 =
+			cpu_to_le32(sg_dma_address(&data->sg[i]));
+		pdes[i].buf_addr_ptr2 = cpu_to_le32((u32)next_desc);
 	}
 
-	pdes[0].config |= SDXC_IDMAC_DES0_FD;
-	pdes[i - 1].config |= SDXC_IDMAC_DES0_LD | SDXC_IDMAC_DES0_ER;
-	pdes[i - 1].config &= ~SDXC_IDMAC_DES0_DIC;
+	pdes[0].config |= cpu_to_le32(SDXC_IDMAC_DES0_FD);
+	pdes[i - 1].config |= cpu_to_le32(SDXC_IDMAC_DES0_LD |
+					  SDXC_IDMAC_DES0_ER);
+	pdes[i - 1].config &= cpu_to_le32(~SDXC_IDMAC_DES0_DIC);
 	pdes[i - 1].buf_addr_ptr2 = 0;
 
 	/*
@@ -653,11 +681,84 @@ static int sunxi_mmc_oclk_onoff(struct sunxi_mmc_host *host, u32 oclk_en)
 	return 0;
 }
 
+static int sunxi_mmc_calibrate(struct sunxi_mmc_host *host, int reg_off)
+{
+	u32 reg = readl(host->reg_base + reg_off);
+	u32 delay;
+	unsigned long timeout;
+
+	if (!host->cfg->can_calibrate)
+		return 0;
+
+	reg &= ~(SDXC_CAL_DL_MASK << SDXC_CAL_DL_SW_SHIFT);
+	reg &= ~SDXC_CAL_DL_SW_EN;
+
+	writel(reg | SDXC_CAL_START, host->reg_base + reg_off);
+
+	dev_dbg(mmc_dev(host->mmc), "calibration started\n");
+
+	timeout = jiffies + HZ * SDXC_CAL_TIMEOUT;
+
+	while (!((reg = readl(host->reg_base + reg_off)) & SDXC_CAL_DONE)) {
+		if (time_before(jiffies, timeout))
+			cpu_relax();
+		else {
+			reg &= ~SDXC_CAL_START;
+			writel(reg, host->reg_base + reg_off);
+
+			return -ETIMEDOUT;
+		}
+	}
+
+	delay = (reg >> SDXC_CAL_DL_SHIFT) & SDXC_CAL_DL_MASK;
+
+	reg &= ~SDXC_CAL_START;
+	reg |= (delay << SDXC_CAL_DL_SW_SHIFT) | SDXC_CAL_DL_SW_EN;
+
+	writel(reg, host->reg_base + reg_off);
+
+	dev_dbg(mmc_dev(host->mmc), "calibration ended, reg is 0x%x\n", reg);
+
+	return 0;
+}
+
+static int sunxi_mmc_clk_set_phase(struct sunxi_mmc_host *host,
+				   struct mmc_ios *ios, u32 rate)
+{
+	int index;
+
+	if (!host->cfg->clk_delays)
+		return 0;
+
+	/* determine delays */
+	if (rate <= 400000) {
+		index = SDXC_CLK_400K;
+	} else if (rate <= 25000000) {
+		index = SDXC_CLK_25M;
+	} else if (rate <= 52000000) {
+		if (ios->timing != MMC_TIMING_UHS_DDR50 &&
+		    ios->timing != MMC_TIMING_MMC_DDR52) {
+			index = SDXC_CLK_50M;
+		} else if (ios->bus_width == MMC_BUS_WIDTH_8) {
+			index = SDXC_CLK_50M_DDR_8BIT;
+		} else {
+			index = SDXC_CLK_50M_DDR;
+		}
+	} else {
+		return -EINVAL;
+	}
+
+	clk_set_phase(host->clk_sample, host->cfg->clk_delays[index].sample);
+	clk_set_phase(host->clk_output, host->cfg->clk_delays[index].output);
+
+	return 0;
+}
+
 static int sunxi_mmc_clk_set_rate(struct sunxi_mmc_host *host,
 				  struct mmc_ios *ios)
 {
-	u32 rate, oclk_dly, rval, sclk_dly;
-	u32 clock = ios->clock;
+	long rate;
+	u32 rval, clock = ios->clock;
 	int ret;
 
 	/* 8 bit DDR requires a higher module clock */
@@ -666,13 +767,18 @@ static int sunxi_mmc_clk_set_rate(struct sunxi_mmc_host *host,
 		clock <<= 1;
 
 	rate = clk_round_rate(host->clk_mmc, clock);
-	dev_dbg(mmc_dev(host->mmc), "setting clk to %d, rounded %d\n",
+	if (rate < 0) {
+		dev_err(mmc_dev(host->mmc), "error rounding clk to %d: %ld\n",
+			clock, rate);
+		return rate;
+	}
+	dev_dbg(mmc_dev(host->mmc), "setting clk to %d, rounded %ld\n",
 		clock, rate);
 
 	/* setting clock rate */
 	ret = clk_set_rate(host->clk_mmc, rate);
 	if (ret) {
-		dev_err(mmc_dev(host->mmc), "error setting clk to %d: %d\n",
+		dev_err(mmc_dev(host->mmc), "error setting clk to %ld: %d\n",
 			rate, ret);
 		return ret;
 	}
@@ -692,31 +798,15 @@ static int sunxi_mmc_clk_set_rate(struct sunxi_mmc_host *host,
 	}
 	mmc_writel(host, REG_CLKCR, rval);
 
-	/* determine delays */
-	if (rate <= 400000) {
-		oclk_dly = host->clk_delays[SDXC_CLK_400K].output;
-		sclk_dly = host->clk_delays[SDXC_CLK_400K].sample;
-	} else if (rate <= 25000000) {
-		oclk_dly = host->clk_delays[SDXC_CLK_25M].output;
-		sclk_dly = host->clk_delays[SDXC_CLK_25M].sample;
-	} else if (rate <= 52000000) {
-		if (ios->timing != MMC_TIMING_UHS_DDR50 &&
-		    ios->timing != MMC_TIMING_MMC_DDR52) {
-			oclk_dly = host->clk_delays[SDXC_CLK_50M].output;
-			sclk_dly = host->clk_delays[SDXC_CLK_50M].sample;
-		} else if (ios->bus_width == MMC_BUS_WIDTH_8) {
-			oclk_dly = host->clk_delays[SDXC_CLK_50M_DDR_8BIT].output;
-			sclk_dly = host->clk_delays[SDXC_CLK_50M_DDR_8BIT].sample;
-		} else {
-			oclk_dly = host->clk_delays[SDXC_CLK_50M_DDR].output;
-			sclk_dly = host->clk_delays[SDXC_CLK_50M_DDR].sample;
-		}
-	} else {
-		return -EINVAL;
-	}
+	ret = sunxi_mmc_clk_set_phase(host, ios, rate);
+	if (ret)
+		return ret;
+
+	ret = sunxi_mmc_calibrate(host, SDXC_REG_SAMP_DL_REG);
+	if (ret)
+		return ret;
 
-	clk_set_phase(host->clk_sample, sclk_dly);
-	clk_set_phase(host->clk_output, oclk_dly);
+	/* TODO: enable calibrate on sdc2 SDXC_REG_DS_DL_REG of A64 */
 
 	return sunxi_mmc_oclk_onoff(host, 1);
 }
@@ -938,14 +1028,6 @@ static int sunxi_mmc_card_busy(struct mmc_host *mmc)
 	return !!(mmc_readl(host, REG_STAS) & SDXC_CARD_DATA_BUSY);
 }
 
-static const struct of_device_id sunxi_mmc_of_match[] = {
-	{ .compatible = "allwinner,sun4i-a10-mmc", },
-	{ .compatible = "allwinner,sun5i-a13-mmc", },
-	{ .compatible = "allwinner,sun9i-a80-mmc", },
-	{ /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(of, sunxi_mmc_of_match);
-
 static struct mmc_host_ops sunxi_mmc_ops = {
 	.request	 = sunxi_mmc_request,
 	.set_ios	 = sunxi_mmc_set_ios,
@@ -974,21 +1056,54 @@ static const struct sunxi_mmc_clk_delay sun9i_mmc_clk_delays[] = {
 	[SDXC_CLK_50M_DDR_8BIT]	= { .output =  72, .sample =  72 },
 };
 
+static const struct sunxi_mmc_cfg sun4i_a10_cfg = {
+	.idma_des_size_bits = 13,
+	.clk_delays = NULL,
+	.can_calibrate = false,
+};
+
+static const struct sunxi_mmc_cfg sun5i_a13_cfg = {
+	.idma_des_size_bits = 16,
+	.clk_delays = NULL,
+	.can_calibrate = false,
+};
+
+static const struct sunxi_mmc_cfg sun7i_a20_cfg = {
+	.idma_des_size_bits = 16,
+	.clk_delays = sunxi_mmc_clk_delays,
+	.can_calibrate = false,
+};
+
+static const struct sunxi_mmc_cfg sun9i_a80_cfg = {
+	.idma_des_size_bits = 16,
+	.clk_delays = sun9i_mmc_clk_delays,
+	.can_calibrate = false,
+};
+
+static const struct sunxi_mmc_cfg sun50i_a64_cfg = {
+	.idma_des_size_bits = 16,
+	.clk_delays = NULL,
+	.can_calibrate = true,
+};
+
+static const struct of_device_id sunxi_mmc_of_match[] = {
+	{ .compatible = "allwinner,sun4i-a10-mmc", .data = &sun4i_a10_cfg },
+	{ .compatible = "allwinner,sun5i-a13-mmc", .data = &sun5i_a13_cfg },
+	{ .compatible = "allwinner,sun7i-a20-mmc", .data = &sun7i_a20_cfg },
+	{ .compatible = "allwinner,sun9i-a80-mmc", .data = &sun9i_a80_cfg },
+	{ .compatible = "allwinner,sun50i-a64-mmc", .data = &sun50i_a64_cfg },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, sunxi_mmc_of_match);
+
 static int sunxi_mmc_resource_request(struct sunxi_mmc_host *host,
 				      struct platform_device *pdev)
 {
-	struct device_node *np = pdev->dev.of_node;
 	int ret;
 
-	if (of_device_is_compatible(np, "allwinner,sun4i-a10-mmc"))
-		host->idma_des_size_bits = 13;
-	else
-		host->idma_des_size_bits = 16;
-
-	if (of_device_is_compatible(np, "allwinner,sun9i-a80-mmc"))
-		host->clk_delays = sun9i_mmc_clk_delays;
-	else
-		host->clk_delays = sunxi_mmc_clk_delays;
+	host->cfg = of_device_get_match_data(&pdev->dev);
+	if (!host->cfg)
+		return -EINVAL;
 
 	ret = mmc_regulator_get_supply(host->mmc);
 	if (ret) {
@@ -1014,16 +1129,18 @@ static int sunxi_mmc_resource_request(struct sunxi_mmc_host *host,
 		return PTR_ERR(host->clk_mmc);
 	}
 
-	host->clk_output = devm_clk_get(&pdev->dev, "output");
-	if (IS_ERR(host->clk_output)) {
-		dev_err(&pdev->dev, "Could not get output clock\n");
-		return PTR_ERR(host->clk_output);
-	}
+	if (host->cfg->clk_delays) {
+		host->clk_output = devm_clk_get(&pdev->dev, "output");
+		if (IS_ERR(host->clk_output)) {
+			dev_err(&pdev->dev, "Could not get output clock\n");
+			return PTR_ERR(host->clk_output);
+		}
 
-	host->clk_sample = devm_clk_get(&pdev->dev, "sample");
-	if (IS_ERR(host->clk_sample)) {
-		dev_err(&pdev->dev, "Could not get sample clock\n");
-		return PTR_ERR(host->clk_sample);
+		host->clk_sample = devm_clk_get(&pdev->dev, "sample");
+		if (IS_ERR(host->clk_sample)) {
+			dev_err(&pdev->dev, "Could not get sample clock\n");
+			return PTR_ERR(host->clk_sample);
+		}
 	}
 
 	host->reset = devm_reset_control_get_optional(&pdev->dev, "ahb");
@@ -1120,15 +1237,17 @@ static int sunxi_mmc_probe(struct platform_device *pdev)
 	mmc->max_blk_count	= 8192;
 	mmc->max_blk_size	= 4096;
 	mmc->max_segs		= PAGE_SIZE / sizeof(struct sunxi_idma_des);
-	mmc->max_seg_size	= (1 << host->idma_des_size_bits);
+	mmc->max_seg_size	= (1 << host->cfg->idma_des_size_bits);
 	mmc->max_req_size	= mmc->max_seg_size * mmc->max_segs;
 	/* 400kHz ~ 52MHz */
 	mmc->f_min		=   400000;
 	mmc->f_max		= 52000000;
 	mmc->caps	       |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED |
-				  MMC_CAP_1_8V_DDR |
 				  MMC_CAP_ERASE | MMC_CAP_SDIO_IRQ;
 
+	if (host->cfg->clk_delays)
+		mmc->caps      |= MMC_CAP_1_8V_DDR;
+
 	ret = mmc_of_parse(mmc);
 	if (ret)
 		goto error_free_dma;
@@ -1160,6 +1279,8 @@ static int sunxi_mmc_remove(struct platform_device *pdev)
 	if (!IS_ERR(host->reset))
 		reset_control_assert(host->reset);
 
+	clk_disable_unprepare(host->clk_sample);
+	clk_disable_unprepare(host->clk_output);
 	clk_disable_unprepare(host->clk_mmc);
 	clk_disable_unprepare(host->clk_ahb);
 
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 7f63ec05bdf4..8e126afd988c 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -79,6 +79,9 @@
 #define	CLK_CTL_DIV_MASK	0xff
 #define	CLK_CTL_SCLKEN		BIT(8)
 
+#define CARD_OPT_WIDTH8		BIT(13)
+#define CARD_OPT_WIDTH		BIT(15)
+
 #define TMIO_BBS		512		/* Boot block size */
 
 /* Definitions for values the CTRL_SDIO_STATUS register can take. */
@@ -158,6 +161,7 @@ struct tmio_mmc_host {
 	void (*clk_disable)(struct tmio_mmc_host *host);
 	int (*multi_io_quirk)(struct mmc_card *card,
 			      unsigned int direction, int blk_size);
+	int (*card_busy)(struct mmc_host *mmc);
 	int (*start_signal_voltage_switch)(struct mmc_host *mmc,
 					   struct mmc_ios *ios);
 };
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index 92467efc4e2c..700567603107 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -336,7 +336,9 @@ static int tmio_mmc_start_command(struct tmio_mmc_host *host, struct mmc_command
 
 	switch (mmc_resp_type(cmd)) {
 	case MMC_RSP_NONE: c |= RESP_NONE; break;
-	case MMC_RSP_R1:   c |= RESP_R1;   break;
+	case MMC_RSP_R1:
+	case MMC_RSP_R1_NO_CRC:
+			   c |= RESP_R1;   break;
 	case MMC_RSP_R1B:  c |= RESP_R1B;  break;
 	case MMC_RSP_R2:   c |= RESP_R2;   break;
 	case MMC_RSP_R3:   c |= RESP_R3;   break;
@@ -730,12 +732,13 @@ static int tmio_mmc_start_data(struct tmio_mmc_host *host,
 	pr_debug("setup data transfer: blocksize %08x  nr_blocks %d\n",
 		 data->blksz, data->blocks);
 
-	/* Some hardware cannot perform 2 byte requests in 4 bit mode */
-	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_4) {
+	/* Some hardware cannot perform 2 byte requests in 4/8 bit mode */
+	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_4 ||
+	    host->mmc->ios.bus_width == MMC_BUS_WIDTH_8) {
 		int blksz_2bytes = pdata->flags & TMIO_MMC_BLKSZ_2BYTES;
 
 		if (data->blksz < 2 || (data->blksz < 4 && !blksz_2bytes)) {
-			pr_err("%s: %d byte block unsupported in 4 bit mode\n",
+			pr_err("%s: %d byte block unsupported in 4/8 bit mode\n",
 			       mmc_hostname(host->mmc), data->blksz);
 			return -EINVAL;
 		}
@@ -857,14 +860,16 @@ static void tmio_mmc_power_off(struct tmio_mmc_host *host)
 static void tmio_mmc_set_bus_width(struct tmio_mmc_host *host,
 				unsigned char bus_width)
 {
-	switch (bus_width) {
-	case MMC_BUS_WIDTH_1:
-		sd_ctrl_write16(host, CTL_SD_MEM_CARD_OPT, 0x80e0);
-		break;
-	case MMC_BUS_WIDTH_4:
-		sd_ctrl_write16(host, CTL_SD_MEM_CARD_OPT, 0x00e0);
-		break;
-	}
+	u16 reg = sd_ctrl_read16(host, CTL_SD_MEM_CARD_OPT)
+				& ~(CARD_OPT_WIDTH | CARD_OPT_WIDTH8);
+
+	/* reg now applies to MMC_BUS_WIDTH_4 */
+	if (bus_width == MMC_BUS_WIDTH_1)
+		reg |= CARD_OPT_WIDTH;
+	else if (bus_width == MMC_BUS_WIDTH_8)
+		reg |= CARD_OPT_WIDTH8;
+
+	sd_ctrl_write16(host, CTL_SD_MEM_CARD_OPT, reg);
 }
 
 /* Set MMC clock / power.
@@ -960,20 +965,12 @@ static int tmio_multi_io_quirk(struct mmc_card *card,
 	return blk_size;
 }
 
-static int tmio_mmc_card_busy(struct mmc_host *mmc)
-{
-	struct tmio_mmc_host *host = mmc_priv(mmc);
-
-	return !(sd_ctrl_read16_and_16_as_32(host, CTL_STATUS) & TMIO_STAT_DAT0);
-}
-
 static struct mmc_host_ops tmio_mmc_ops = {
 	.request	= tmio_mmc_request,
 	.set_ios	= tmio_mmc_set_ios,
 	.get_ro         = tmio_mmc_get_ro,
 	.get_cd		= mmc_gpio_get_cd,
 	.enable_sdio_irq = tmio_mmc_enable_sdio_irq,
-	.card_busy	= tmio_mmc_card_busy,
 	.multi_io_quirk	= tmio_multi_io_quirk,
 };
 
@@ -1072,6 +1069,7 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 		goto host_free;
 	}
 
+	tmio_mmc_ops.card_busy = _host->card_busy;
 	tmio_mmc_ops.start_signal_voltage_switch = _host->start_signal_voltage_switch;
 	mmc->ops = &tmio_mmc_ops;
 
@@ -1089,6 +1087,15 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 				  !mmc_card_is_removable(mmc) ||
 				  mmc->slot.cd_irq >= 0);
 
+	/*
+	 * On Gen2+, eMMC with NONREMOVABLE currently fails because native
+	 * hotplug gets disabled. It seems RuntimePM related yet we need further
+	 * research. Since we are planning a PM overhaul anyway, let's enforce
+	 * for now the device being active by enabling native hotplug always.
+	 */
+	if (pdata->flags & TMIO_MMC_MIN_RCAR2)
+		_host->native_hotplug = true;
+
 	if (tmio_mmc_clk_enable(_host) < 0) {
 		mmc->f_max = pdata->hclk;
 		mmc->f_min = mmc->f_max / 512;