Merge tag 'mmc-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc

Pull MMC and MEMSTICK updates from Ulf Hansson:
 "MMC core:
   - Return a proper response in case of an ioctl error
   - Issue HPI to interrupt BKOPS for eMMC if it timed out
   - Avoid hogging the CPU while polling for busy
   - Extend sd8787 pwrseq to support the wilc1000 SDIO
   - Remove a couple of confusing warning messages
   - Clarify comment for ->card_busy() host ops

  MMC host:
   - dw_mmc: Add data CRC error injection
   - mmci: De-assert reset during ->probe()
   - rtsx_pci: Fix long reads when clock is pre-scaled
   - sdhci: Correct the tuning command handle for PIO mode
   - sdhci-esdhc-imx: Improve support for auto tuning
   - sdhci-msm: Add support for the sc7280
   - sdhci-of-arasan: Don't auto tune for DDR50 mode for ZynqMP
   - sdhci-of-arasan: Enable support for auto cmd12
   - sdhci-of-arasan: Use 19MHz for SD default speed for ZynqMP for level shifter
   - usdhi6rol0: Implement the ->card_busy() host ops

  MEMSTICK:
   - A couple of minor cleanups"

* tag 'mmc-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc: (52 commits)
  mmc: queue: Remove unused parameters(request_queue)
  mmc: pwrseq: sd8787: fix compilation warning
  mmc: core: Return correct emmc response in case of ioctl error
  mmc: sdhci-esdhc-imx: Select the correct mode for auto tuning
  mmc: sdhci-esdhc-imx: Remove redundant code for manual tuning
  mmc: core: Issue HPI in case the BKOPS timed out
  mmc: queue: Match the data type of max_segments
  mmc: switch from 'pci_' to 'dma_' API
  memstick: switch from 'pci_' to 'dma_' API
  memstick: r592: Change the name of the 'pci_driver' structure to be consistent
  mmc: pwrseq: add wilc1000_sdio dependency for pwrseq_sd8787
  mmc: pwrseq: sd8787: add support for wilc1000
  dt-bindings: mmc: Extend pwrseq-sd8787 binding for wilc1000
  dt-bindings: mmc: fsl-imx-esdhc: change the pinctrl-names rule
  dt-bindings: mmc: fsl-imx-esdhc: add a new compatible string
  dt-bindings: mmc: renesas,sdhi: Document RZ/G2L bindings
  dt-bindings: mmc: renesas,sdhi: Fix dtbs-check warning
  mmc: core: Update ->card_busy() callback comment
  mmc: usdhi6rol0: Implement card_busy function
  mmc: sdhci: Correct the tuning command handle for PIO mode
  ...

31 files changed, 529 insertions, 266 deletions

diff --git a/drivers/mmc/core/Kconfig b/drivers/mmc/core/Kconfig
index ae8b69aee619..6f25c34e4fec 100644
--- a/drivers/mmc/core/Kconfig
+++ b/drivers/mmc/core/Kconfig
@@ -15,7 +15,7 @@ config PWRSEQ_EMMC
 
 config PWRSEQ_SD8787
 	tristate "HW reset support for SD8787 BT + Wifi module"
-	depends on OF && (MWIFIEX || BT_MRVL_SDIO || LIBERTAS_SDIO)
+	depends on OF && (MWIFIEX || BT_MRVL_SDIO || LIBERTAS_SDIO || WILC1000_SDIO)
 	help
 	  This selects hardware reset support for the SD8787 BT + Wifi
 	  module. By default this option is set to n.
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 6a15fdf6e5f2..431af5e8be2f 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -98,6 +98,11 @@ static int max_devices;
 static DEFINE_IDA(mmc_blk_ida);
 static DEFINE_IDA(mmc_rpmb_ida);
 
+struct mmc_blk_busy_data {
+	struct mmc_card *card;
+	u32 status;
+};
+
 /*
  * There is one mmc_blk_data per slot.
  */
@@ -456,42 +461,6 @@ static int mmc_blk_ioctl_copy_to_user(struct mmc_ioc_cmd __user *ic_ptr,
 	return 0;
 }
 
-static int card_busy_detect(struct mmc_card *card, unsigned int timeout_ms,
-			    u32 *resp_errs)
-{
-	unsigned long timeout = jiffies + msecs_to_jiffies(timeout_ms);
-	int err = 0;
-	u32 status;
-
-	do {
-		bool done = time_after(jiffies, timeout);
-
-		err = __mmc_send_status(card, &status, 5);
-		if (err) {
-			dev_err(mmc_dev(card->host),
-				"error %d requesting status\n", err);
-			return err;
-		}
-
-		/* Accumulate any response error bits seen */
-		if (resp_errs)
-			*resp_errs |= status;
-
-		/*
-		 * Timeout if the device never becomes ready for data and never
-		 * leaves the program state.
-		 */
-		if (done) {
-			dev_err(mmc_dev(card->host),
-				"Card stuck in wrong state! %s status: %#x\n",
-				 __func__, status);
-			return -ETIMEDOUT;
-		}
-	} while (!mmc_ready_for_data(status));
-
-	return err;
-}
-
 static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 			       struct mmc_blk_ioc_data *idata)
 {
@@ -588,6 +557,7 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 		return mmc_sanitize(card, idata->ic.cmd_timeout_ms);
 
 	mmc_wait_for_req(card->host, &mrq);
+	memcpy(&idata->ic.response, cmd.resp, sizeof(cmd.resp));
 
 	if (cmd.error) {
 		dev_err(mmc_dev(card->host), "%s: cmd error %d\n",
@@ -637,14 +607,13 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 	if (idata->ic.postsleep_min_us)
 		usleep_range(idata->ic.postsleep_min_us, idata->ic.postsleep_max_us);
 
-	memcpy(&(idata->ic.response), cmd.resp, sizeof(cmd.resp));
-
 	if (idata->rpmb || (cmd.flags & MMC_RSP_R1B) == MMC_RSP_R1B) {
 		/*
 		 * Ensure RPMB/R1B command has completed by polling CMD13
 		 * "Send Status".
 		 */
-		err = card_busy_detect(card, MMC_BLK_TIMEOUT_MS, NULL);
+		err = mmc_poll_for_busy(card, MMC_BLK_TIMEOUT_MS, false,
+					MMC_BUSY_IO);
 	}
 
 	return err;
@@ -1696,7 +1665,7 @@ static int mmc_blk_fix_state(struct mmc_card *card, struct request *req)
 
 	mmc_blk_send_stop(card, timeout);
 
-	err = card_busy_detect(card, timeout, NULL);
+	err = mmc_poll_for_busy(card, timeout, false, MMC_BUSY_IO);
 
 	mmc_retune_release(card->host);
 
@@ -1911,28 +1880,48 @@ static inline bool mmc_blk_rq_error(struct mmc_blk_request *brq)
 	       brq->data.error || brq->cmd.resp[0] & CMD_ERRORS;
 }
 
+static int mmc_blk_busy_cb(void *cb_data, bool *busy)
+{
+	struct mmc_blk_busy_data *data = cb_data;
+	u32 status = 0;
+	int err;
+
+	err = mmc_send_status(data->card, &status);
+	if (err)
+		return err;
+
+	/* Accumulate response error bits. */
+	data->status |= status;
+
+	*busy = !mmc_ready_for_data(status);
+	return 0;
+}
+
 static int mmc_blk_card_busy(struct mmc_card *card, struct request *req)
 {
 	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
-	u32 status = 0;
+	struct mmc_blk_busy_data cb_data;
 	int err;
 
 	if (mmc_host_is_spi(card->host) || rq_data_dir(req) == READ)
 		return 0;
 
-	err = card_busy_detect(card, MMC_BLK_TIMEOUT_MS, &status);
+	cb_data.card = card;
+	cb_data.status = 0;
+	err = __mmc_poll_for_busy(card, MMC_BLK_TIMEOUT_MS, &mmc_blk_busy_cb,
+				  &cb_data);
 
 	/*
 	 * Do not assume data transferred correctly if there are any error bits
 	 * set.
 	 */
-	if (status & mmc_blk_stop_err_bits(&mqrq->brq)) {
+	if (cb_data.status & mmc_blk_stop_err_bits(&mqrq->brq)) {
 		mqrq->brq.data.bytes_xfered = 0;
 		err = err ? err : -EIO;
 	}
 
 	/* Copy the exception bit so it will be seen later on */
-	if (mmc_card_mmc(card) && status & R1_EXCEPTION_EVENT)
+	if (mmc_card_mmc(card) && cb_data.status & R1_EXCEPTION_EVENT)
 		mqrq->brq.cmd.resp[0] |= R1_EXCEPTION_EVENT;
 
 	return err;
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 605f5e8648c1..240c5af793dc 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -936,15 +936,16 @@ int mmc_execute_tuning(struct mmc_card *card)
 		opcode = MMC_SEND_TUNING_BLOCK;
 
 	err = host->ops->execute_tuning(host, opcode);
+	if (!err) {
+		mmc_retune_clear(host);
+		mmc_retune_enable(host);
+		return 0;
+	}
 
-	if (err) {
+	/* Only print error when we don't check for card removal */
+	if (!host->detect_change)
 		pr_err("%s: tuning execution failed: %d\n",
 			mmc_hostname(host), err);
-	} else {
-		host->retune_now = 0;
-		host->need_retune = 0;
-		mmc_retune_enable(host);
-	}
 
 	return err;
 }
diff --git a/drivers/mmc/core/crypto.c b/drivers/mmc/core/crypto.c
index 419a368f8402..67557808cada 100644
--- a/drivers/mmc/core/crypto.c
+++ b/drivers/mmc/core/crypto.c
@@ -31,18 +31,11 @@ void mmc_crypto_prepare_req(struct mmc_queue_req *mqrq)
 	struct request *req = mmc_queue_req_to_req(mqrq);
 	struct mmc_request *mrq = &mqrq->brq.mrq;
 
-	if (!req->crypt_keyslot)
+	if (!req->crypt_ctx)
 		return;
 
-	mrq->crypto_enabled = true;
-	mrq->crypto_key_slot = blk_ksm_get_slot_idx(req->crypt_keyslot);
-
-	/*
-	 * For now we assume that all MMC drivers set max_dun_bytes_supported=4,
-	 * which is the limit for CQHCI crypto.  So all DUNs should be 32-bit.
-	 */
-	WARN_ON_ONCE(req->crypt_ctx->bc_dun[0] > U32_MAX);
-
-	mrq->data_unit_num = req->crypt_ctx->bc_dun[0];
+	mrq->crypto_ctx = req->crypt_ctx;
+	if (req->crypt_keyslot)
+		mrq->crypto_key_slot = blk_ksm_get_slot_idx(req->crypt_keyslot);
 }
 EXPORT_SYMBOL_GPL(mmc_crypto_prepare_req);
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 0475d96047c4..d4683b1d263f 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -96,6 +96,10 @@ void mmc_unregister_host_class(void)
 	class_unregister(&mmc_host_class);
 }
 
+/**
+ * mmc_retune_enable() - enter a transfer mode that requires retuning
+ * @host: host which should retune now
+ */
 void mmc_retune_enable(struct mmc_host *host)
 {
 	host->can_retune = 1;
@@ -127,13 +131,18 @@ void mmc_retune_unpause(struct mmc_host *host)
 }
 EXPORT_SYMBOL(mmc_retune_unpause);
 
+/**
+ * mmc_retune_disable() - exit a transfer mode that requires retuning
+ * @host: host which should not retune anymore
+ *
+ * It is not meant for temporarily preventing retuning!
+ */
 void mmc_retune_disable(struct mmc_host *host)
 {
 	mmc_retune_unpause(host);
 	host->can_retune = 0;
 	del_timer_sync(&host->retune_timer);
-	host->retune_now = 0;
-	host->need_retune = 0;
+	mmc_retune_clear(host);
 }
 
 void mmc_retune_timer_stop(struct mmc_host *host)
diff --git a/drivers/mmc/core/host.h b/drivers/mmc/core/host.h
index ba407617ed23..48c4952512a5 100644
--- a/drivers/mmc/core/host.h
+++ b/drivers/mmc/core/host.h
@@ -21,6 +21,12 @@ int mmc_retune(struct mmc_host *host);
 void mmc_retune_pause(struct mmc_host *host);
 void mmc_retune_unpause(struct mmc_host *host);
 
+static inline void mmc_retune_clear(struct mmc_host *host)
+{
+	host->retune_now = 0;
+	host->need_retune = 0;
+}
+
 static inline void mmc_retune_hold_now(struct mmc_host *host)
 {
 	host->retune_now = 0;
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 973756ed4016..0c54858e89c0 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -435,7 +435,7 @@ static int mmc_busy_cb(void *cb_data, bool *busy)
 	u32 status = 0;
 	int err;
 
-	if (host->ops->card_busy) {
+	if (data->busy_cmd != MMC_BUSY_IO && host->ops->card_busy) {
 		*busy = host->ops->card_busy(host);
 		return 0;
 	}
@@ -457,6 +457,7 @@ static int mmc_busy_cb(void *cb_data, bool *busy)
 		break;
 	case MMC_BUSY_HPI:
 	case MMC_BUSY_EXTR_SINGLE:
+	case MMC_BUSY_IO:
 		break;
 	default:
 		err = -EINVAL;
@@ -509,6 +510,7 @@ int __mmc_poll_for_busy(struct mmc_card *card, unsigned int timeout_ms,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(__mmc_poll_for_busy);
 
 int mmc_poll_for_busy(struct mmc_card *card, unsigned int timeout_ms,
 		      bool retry_crc_err, enum mmc_busy_cmd busy_cmd)
@@ -521,6 +523,7 @@ int mmc_poll_for_busy(struct mmc_card *card, unsigned int timeout_ms,
 
 	return __mmc_poll_for_busy(card, timeout_ms, &mmc_busy_cb, &cb_data);
 }
+EXPORT_SYMBOL_GPL(mmc_poll_for_busy);
 
 bool mmc_prepare_busy_cmd(struct mmc_host *host, struct mmc_command *cmd,
 			  unsigned int timeout_ms)
@@ -956,8 +959,15 @@ void mmc_run_bkops(struct mmc_card *card)
 	 */
 	err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 			 EXT_CSD_BKOPS_START, 1, MMC_BKOPS_TIMEOUT_MS);
-	if (err)
-		pr_warn("%s: Error %d starting bkops\n",
+	/*
+	 * If the BKOPS timed out, the card is probably still busy in the
+	 * R1_STATE_PRG. Rather than continue to wait, let's try to abort
+	 * it with a HPI command to get back into R1_STATE_TRAN.
+	 */
+	if (err == -ETIMEDOUT && !mmc_interrupt_hpi(card))
+		pr_warn("%s: BKOPS aborted\n", mmc_hostname(card->host));
+	else if (err)
+		pr_warn("%s: Error %d running bkops\n",
 			mmc_hostname(card->host), err);
 
 	mmc_retune_release(card->host);
diff --git a/drivers/mmc/core/mmc_ops.h b/drivers/mmc/core/mmc_ops.h
index 41ab4f573a31..ae25ffc2e870 100644
--- a/drivers/mmc/core/mmc_ops.h
+++ b/drivers/mmc/core/mmc_ops.h
@@ -15,6 +15,7 @@ enum mmc_busy_cmd {
 	MMC_BUSY_ERASE,
 	MMC_BUSY_HPI,
 	MMC_BUSY_EXTR_SINGLE,
+	MMC_BUSY_IO,
 };
 
 struct mmc_host;
diff --git a/drivers/mmc/core/pwrseq_sd8787.c b/drivers/mmc/core/pwrseq_sd8787.c
index 68a826f1c0a1..2e120ad83020 100644
--- a/drivers/mmc/core/pwrseq_sd8787.c
+++ b/drivers/mmc/core/pwrseq_sd8787.c
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/device.h>
 #include <linux/err.h>
@@ -27,6 +28,7 @@ struct mmc_pwrseq_sd8787 {
 	struct mmc_pwrseq pwrseq;
 	struct gpio_desc *reset_gpio;
 	struct gpio_desc *pwrdn_gpio;
+	u32 reset_pwrdwn_delay_ms;
 };
 
 #define to_pwrseq_sd8787(p) container_of(p, struct mmc_pwrseq_sd8787, pwrseq)
@@ -37,7 +39,7 @@ static void mmc_pwrseq_sd8787_pre_power_on(struct mmc_host *host)
 
 	gpiod_set_value_cansleep(pwrseq->reset_gpio, 1);
 
-	msleep(300);
+	msleep(pwrseq->reset_pwrdwn_delay_ms);
 	gpiod_set_value_cansleep(pwrseq->pwrdn_gpio, 1);
 }
 
@@ -54,8 +56,12 @@ static const struct mmc_pwrseq_ops mmc_pwrseq_sd8787_ops = {
 	.power_off = mmc_pwrseq_sd8787_power_off,
 };
 
+static const u32 sd8787_delay_ms = 300;
+static const u32 wilc1000_delay_ms = 5;
+
 static const struct of_device_id mmc_pwrseq_sd8787_of_match[] = {
-	{ .compatible = "mmc-pwrseq-sd8787",},
+	{ .compatible = "mmc-pwrseq-sd8787", .data = &sd8787_delay_ms },
+	{ .compatible = "mmc-pwrseq-wilc1000", .data = &wilc1000_delay_ms },
 	{/* sentinel */},
 };
 MODULE_DEVICE_TABLE(of, mmc_pwrseq_sd8787_of_match);
@@ -64,11 +70,15 @@ static int mmc_pwrseq_sd8787_probe(struct platform_device *pdev)
 {
 	struct mmc_pwrseq_sd8787 *pwrseq;
 	struct device *dev = &pdev->dev;
+	const struct of_device_id *match;
 
 	pwrseq = devm_kzalloc(dev, sizeof(*pwrseq), GFP_KERNEL);
 	if (!pwrseq)
 		return -ENOMEM;
 
+	match = of_match_node(mmc_pwrseq_sd8787_of_match, pdev->dev.of_node);
+	pwrseq->reset_pwrdwn_delay_ms = *(u32 *)match->data;
+
 	pwrseq->pwrdn_gpio = devm_gpiod_get(dev, "powerdown", GPIOD_OUT_LOW);
 	if (IS_ERR(pwrseq->pwrdn_gpio))
 		return PTR_ERR(pwrseq->pwrdn_gpio);
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index cc3261777637..b15c034b42fb 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -163,7 +163,7 @@ static void mmc_mq_recovery_handler(struct work_struct *work)
 	blk_mq_run_hw_queues(q, true);
 }
 
-static struct scatterlist *mmc_alloc_sg(int sg_len, gfp_t gfp)
+static struct scatterlist *mmc_alloc_sg(unsigned short sg_len, gfp_t gfp)
 {
 	struct scatterlist *sg;
 
@@ -193,33 +193,29 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 		blk_queue_flag_set(QUEUE_FLAG_SECERASE, q);
 }
 
-static unsigned int mmc_get_max_segments(struct mmc_host *host)
+static unsigned short mmc_get_max_segments(struct mmc_host *host)
 {
 	return host->can_dma_map_merge ? MMC_DMA_MAP_MERGE_SEGMENTS :
 					 host->max_segs;
 }
 
-/**
- * mmc_init_request() - initialize the MMC-specific per-request data
- * @mq: the request queue
- * @req: the request
- * @gfp: memory allocation policy
- */
-static int __mmc_init_request(struct mmc_queue *mq, struct request *req,
-			      gfp_t gfp)
+static int mmc_mq_init_request(struct blk_mq_tag_set *set, struct request *req,
+			       unsigned int hctx_idx, unsigned int numa_node)
 {
 	struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req);
+	struct mmc_queue *mq = set->driver_data;
 	struct mmc_card *card = mq->card;
 	struct mmc_host *host = card->host;
 
-	mq_rq->sg = mmc_alloc_sg(mmc_get_max_segments(host), gfp);
+	mq_rq->sg = mmc_alloc_sg(mmc_get_max_segments(host), GFP_KERNEL);
 	if (!mq_rq->sg)
 		return -ENOMEM;
 
 	return 0;
 }
 
-static void mmc_exit_request(struct request_queue *q, struct request *req)
+static void mmc_mq_exit_request(struct blk_mq_tag_set *set, struct request *req,
+				unsigned int hctx_idx)
 {
 	struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req);
 
@@ -227,20 +223,6 @@ static void mmc_exit_request(struct request_queue *q, struct request *req)
 	mq_rq->sg = NULL;
 }
 
-static int mmc_mq_init_request(struct blk_mq_tag_set *set, struct request *req,
-			       unsigned int hctx_idx, unsigned int numa_node)
-{
-	return __mmc_init_request(set->driver_data, req, GFP_KERNEL);
-}
-
-static void mmc_mq_exit_request(struct blk_mq_tag_set *set, struct request *req,
-				unsigned int hctx_idx)
-{
-	struct mmc_queue *mq = set->driver_data;
-
-	mmc_exit_request(mq->queue, req);
-}
-
 static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
 				    const struct blk_mq_queue_data *bd)
 {
diff --git a/drivers/mmc/core/sdio_cis.c b/drivers/mmc/core/sdio_cis.c
index b23773583179..a705ba6eff5b 100644
--- a/drivers/mmc/core/sdio_cis.c
+++ b/drivers/mmc/core/sdio_cis.c
@@ -330,13 +330,25 @@ static int sdio_read_cis(struct mmc_card *card, struct sdio_func *func)
 			prev = &this->next;
 
 			if (ret == -ENOENT) {
+
 				if (time_after(jiffies, timeout))
 					break;
-				/* warn about unknown tuples */
-				pr_warn_ratelimited("%s: queuing unknown"
-				       " CIS tuple 0x%02x (%u bytes)\n",
-				       mmc_hostname(card->host),
-				       tpl_code, tpl_link);
+
+#define FMT(type) "%s: queuing " type " CIS tuple 0x%02x [%*ph] (%u bytes)\n"
+				/*
+				 * Tuples in this range are reserved for
+				 * vendors, so don't warn about them
+				 */
+				if (tpl_code >= 0x80 && tpl_code <= 0x8f)
+					pr_debug_ratelimited(FMT("vendor"),
+						mmc_hostname(card->host),
+						tpl_code, tpl_link, this->data,
+						tpl_link);
+				else
+					pr_warn_ratelimited(FMT("unknown"),
+						mmc_hostname(card->host),
+						tpl_code, tpl_link, this->data,
+						tpl_link);
 			}
 
 			/* keep on analyzing tuples */
diff --git a/drivers/mmc/host/cqhci-crypto.h b/drivers/mmc/host/cqhci-crypto.h
index 60b58ee0e625..d7fb084f563b 100644
--- a/drivers/mmc/host/cqhci-crypto.h
+++ b/drivers/mmc/host/cqhci-crypto.h
@@ -22,12 +22,15 @@ int cqhci_crypto_init(struct cqhci_host *host);
  */
 static inline u64 cqhci_crypto_prep_task_desc(struct mmc_request *mrq)
 {
-	if (!mrq->crypto_enabled)
+	if (!mrq->crypto_ctx)
 		return 0;
 
+	/* We set max_dun_bytes_supported=4, so all DUNs should be 32-bit. */
+	WARN_ON_ONCE(mrq->crypto_ctx->bc_dun[0] > U32_MAX);
+
 	return CQHCI_CRYPTO_ENABLE_BIT |
 	       CQHCI_CRYPTO_KEYSLOT(mrq->crypto_key_slot) |
-	       mrq->data_unit_num;
+	       mrq->crypto_ctx->bc_dun[0];
 }
 
 #else /* CONFIG_MMC_CRYPTO */
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index c3229d8c7041..6578cc64ae9e 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -17,9 +17,11 @@
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
 #include <linux/ioport.h>
+#include <linux/ktime.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/prandom.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/stat.h>
@@ -181,6 +183,9 @@ static void dw_mci_init_debugfs(struct dw_mci_slot *slot)
 			   &host->pending_events);
 	debugfs_create_xul("completed_events", S_IRUSR, root,
 			   &host->completed_events);
+#ifdef CONFIG_FAULT_INJECTION
+	fault_create_debugfs_attr("fail_data_crc", root, &host->fail_data_crc);
+#endif
 }
 #endif /* defined(CONFIG_DEBUG_FS) */
 
@@ -782,6 +787,7 @@ static int dw_mci_edmac_start_dma(struct dw_mci *host,
 	int ret = 0;
 
 	/* Set external dma config: burst size, burst width */
+	memset(&cfg, 0, sizeof(cfg));
 	cfg.dst_addr = host->phy_regs + fifo_offset;
 	cfg.src_addr = cfg.dst_addr;
 	cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
@@ -1788,6 +1794,68 @@ static const struct mmc_host_ops dw_mci_ops = {
 	.prepare_hs400_tuning	= dw_mci_prepare_hs400_tuning,
 };
 
+#ifdef CONFIG_FAULT_INJECTION
+static enum hrtimer_restart dw_mci_fault_timer(struct hrtimer *t)
+{
+	struct dw_mci *host = container_of(t, struct dw_mci, fault_timer);
+	unsigned long flags;
+
+	spin_lock_irqsave(&host->irq_lock, flags);
+
+	if (!host->data_status)
+		host->data_status = SDMMC_INT_DCRC;
+	set_bit(EVENT_DATA_ERROR, &host->pending_events);
+	tasklet_schedule(&host->tasklet);
+
+	spin_unlock_irqrestore(&host->irq_lock, flags);
+
+	return HRTIMER_NORESTART;
+}
+
+static void dw_mci_start_fault_timer(struct dw_mci *host)
+{
+	struct mmc_data *data = host->data;
+
+	if (!data || data->blocks <= 1)
+		return;
+
+	if (!should_fail(&host->fail_data_crc, 1))
+		return;
+
+	/*
+	 * Try to inject the error at random points during the data transfer.
+	 */
+	hrtimer_start(&host->fault_timer,
+		      ms_to_ktime(prandom_u32() % 25),
+		      HRTIMER_MODE_REL);
+}
+
+static void dw_mci_stop_fault_timer(struct dw_mci *host)
+{
+	hrtimer_cancel(&host->fault_timer);
+}
+
+static void dw_mci_init_fault(struct dw_mci *host)
+{
+	host->fail_data_crc = (struct fault_attr) FAULT_ATTR_INITIALIZER;
+
+	hrtimer_init(&host->fault_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	host->fault_timer.function = dw_mci_fault_timer;
+}
+#else
+static void dw_mci_init_fault(struct dw_mci *host)
+{
+}
+
+static void dw_mci_start_fault_timer(struct dw_mci *host)
+{
+}
+
+static void dw_mci_stop_fault_timer(struct dw_mci *host)
+{
+}
+#endif
+
 static void dw_mci_request_end(struct dw_mci *host, struct mmc_request *mrq)
 	__releases(&host->lock)
 	__acquires(&host->lock)
@@ -2102,6 +2170,7 @@ static void dw_mci_tasklet_func(struct tasklet_struct *t)
 				break;
 			}
 
+			dw_mci_stop_fault_timer(host);
 			host->data = NULL;
 			set_bit(EVENT_DATA_COMPLETE, &host->completed_events);
 			err = dw_mci_data_complete(host, data);
@@ -2151,6 +2220,7 @@ static void dw_mci_tasklet_func(struct tasklet_struct *t)
 			if (mrq->cmd->error && mrq->data)
 				dw_mci_reset(host);
 
+			dw_mci_stop_fault_timer(host);
 			host->cmd = NULL;
 			host->data = NULL;
 
@@ -2600,6 +2670,8 @@ static void dw_mci_cmd_interrupt(struct dw_mci *host, u32 status)
 
 	set_bit(EVENT_CMD_COMPLETE, &host->pending_events);
 	tasklet_schedule(&host->tasklet);
+
+	dw_mci_start_fault_timer(host);
 }
 
 static void dw_mci_handle_cd(struct dw_mci *host)
@@ -3223,6 +3295,8 @@ int dw_mci_probe(struct dw_mci *host)
 	spin_lock_init(&host->irq_lock);
 	INIT_LIST_HEAD(&host->queue);
 
+	dw_mci_init_fault(host);
+
 	/*
 	 * Get the host data width - this assumes that HCON has been set with
 	 * the correct values.
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index da5923a92e60..ce05d81477d9 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -14,6 +14,8 @@
 #include <linux/mmc/core.h>
 #include <linux/dmaengine.h>
 #include <linux/reset.h>
+#include <linux/fault-inject.h>
+#include <linux/hrtimer.h>
 #include <linux/interrupt.h>
 
 enum dw_mci_state {
@@ -230,6 +232,11 @@ struct dw_mci {
 	struct timer_list       cmd11_timer;
 	struct timer_list       cto_timer;
 	struct timer_list       dto_timer;
+
+#ifdef CONFIG_FAULT_INJECTION
+	struct fault_attr	fail_data_crc;
+	struct hrtimer		fault_timer;
+#endif
 };
 
 /* DMA ops for Internal/External DMAC interface */
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 65c65bb5737f..a1bcde3395a6 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -180,7 +180,7 @@ static int mmc_spi_skip(struct mmc_spi_host *host, unsigned long timeout,
 	u8 *cp = host->data->status;
 	unsigned long start = jiffies;
 
-	while (1) {
+	do {
 		int		status;
 		unsigned	i;
 
@@ -193,16 +193,9 @@ static int mmc_spi_skip(struct mmc_spi_host *host, unsigned long timeout,
 				return cp[i];
 		}
 
-		if (time_is_before_jiffies(start + timeout))
-			break;
-
-		/* If we need long timeouts, we may release the CPU.
-		 * We use jiffies here because we want to have a relation
-		 * between elapsed time and the blocking of the scheduler.
-		 */
-		if (time_is_before_jiffies(start + 1))
-			schedule();
-	}
+		/* If we need long timeouts, we may release the CPU */
+		cond_resched();
+	} while (time_is_after_jiffies(start + timeout));
 	return -ETIMEDOUT;
 }
 
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 984d35055156..3765e2f4ad98 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -2126,6 +2126,9 @@ static int mmci_probe(struct amba_device *dev,
 		ret = PTR_ERR(host->rst);
 		goto clk_disable;
 	}
+	ret = reset_control_deassert(host->rst);
+	if (ret)
+		dev_err(mmc_dev(mmc), "failed to de-assert reset\n");
 
 	/* Get regulators and the supported OCR mask */
 	ret = mmc_regulator_get_supply(mmc);
diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c
index bde298887579..6c9d38132f74 100644
--- a/drivers/mmc/host/moxart-mmc.c
+++ b/drivers/mmc/host/moxart-mmc.c
@@ -628,6 +628,7 @@ static int moxart_probe(struct platform_device *pdev)
 			 host->dma_chan_tx, host->dma_chan_rx);
 		host->have_dma = true;
 
+		memset(&cfg, 0, sizeof(cfg));
 		cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 		cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 
diff --git a/drivers/mmc/host/renesas_sdhi.h b/drivers/mmc/host/renesas_sdhi.h
index 53eded81a53e..0c45e82ff0de 100644
--- a/drivers/mmc/host/renesas_sdhi.h
+++ b/drivers/mmc/host/renesas_sdhi.h
@@ -42,6 +42,11 @@ struct renesas_sdhi_quirks {
 	const u8 (*hs400_calib_table)[SDHI_CALIB_TABLE_MAX];
 };
 
+struct renesas_sdhi_of_data_with_quirks {
+	const struct renesas_sdhi_of_data *of_data;
+	const struct renesas_sdhi_quirks *quirks;
+};
+
 struct tmio_mmc_dma {
 	enum dma_slave_buswidth dma_buswidth;
 	bool (*filter)(struct dma_chan *chan, void *arg);
@@ -78,6 +83,8 @@ struct renesas_sdhi {
 	container_of((host)->pdata, struct renesas_sdhi, mmc_data)
 
 int renesas_sdhi_probe(struct platform_device *pdev,
-		       const struct tmio_mmc_dma_ops *dma_ops);
+		       const struct tmio_mmc_dma_ops *dma_ops,
+		       const struct renesas_sdhi_of_data *of_data,
+		       const struct renesas_sdhi_quirks *quirks);
 int renesas_sdhi_remove(struct platform_device *pdev);
 #endif
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index e49ca0f7fe9a..6fc4cf3c9dce 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -305,27 +305,6 @@ static int renesas_sdhi_start_signal_voltage_switch(struct mmc_host *mmc,
 #define SH_MOBILE_SDHI_SCC_TMPPORT_CALIB_CODE_MASK	0x1f
 #define SH_MOBILE_SDHI_SCC_TMPPORT_MANUAL_MODE		BIT(7)
 
-static const u8 r8a7796_es13_calib_table[2][SDHI_CALIB_TABLE_MAX] = {
-	{ 3,  3,  3,  3,  3,  3,  3,  4,  4,  5,  6,  7,  8,  9, 10, 15,
-	 16, 16, 16, 16, 16, 16, 17, 18, 18, 19, 20, 21, 22, 23, 24, 25 },
-	{ 5,  5,  5,  5,  5,  5,  5,  5,  5,  5,  5,  5,  6,  7,  8, 11,
-	 12, 17, 18, 18, 18, 18, 18, 18, 18, 19, 20, 21, 22, 23, 25, 25 }
-};
-
-static const u8 r8a77965_calib_table[2][SDHI_CALIB_TABLE_MAX] = {
-	{ 1,  2,  6,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 15, 15, 16,
-	 17, 18, 19, 20, 21, 22, 23, 24, 25, 25, 26, 27, 28, 29, 30, 31 },
-	{ 2,  3,  4,  4,  5,  6,  7,  9, 10, 11, 12, 13, 14, 15, 16, 17,
-	 17, 17, 20, 21, 22, 23, 24, 25, 27, 28, 29, 30, 31, 31, 31, 31 }
-};
-
-static const u8 r8a77990_calib_table[2][SDHI_CALIB_TABLE_MAX] = {
-	{ 0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
-	  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 },
-	{ 0,  0,  0,  1,  2,  3,  3,  4,  4,  4,  5,  5,  6,  8,  9, 10,
-	 11, 12, 13, 15, 16, 17, 17, 18, 18, 19, 20, 22, 24, 25, 26, 26 }
-};
-
 static inline u32 sd_scc_read32(struct tmio_mmc_host *host,
 				struct renesas_sdhi *priv, int addr)
 {
@@ -895,69 +874,12 @@ static void renesas_sdhi_enable_dma(struct tmio_mmc_host *host, bool enable)
 	renesas_sdhi_sdbuf_width(host, enable ? width : 16);
 }
 
-static const struct renesas_sdhi_quirks sdhi_quirks_4tap_nohs400 = {
-	.hs400_disabled = true,
-	.hs400_4taps = true,
-};
-
-static const struct renesas_sdhi_quirks sdhi_quirks_4tap = {
-	.hs400_4taps = true,
-	.hs400_bad_taps = BIT(2) | BIT(3) | BIT(6) | BIT(7),
-};
-
-static const struct renesas_sdhi_quirks sdhi_quirks_nohs400 = {
-	.hs400_disabled = true,
-};
-
-static const struct renesas_sdhi_quirks sdhi_quirks_bad_taps1357 = {
-	.hs400_bad_taps = BIT(1) | BIT(3) | BIT(5) | BIT(7),
-};
-
-static const struct renesas_sdhi_quirks sdhi_quirks_bad_taps2367 = {
-	.hs400_bad_taps = BIT(2) | BIT(3) | BIT(6) | BIT(7),
-};
-
-static const struct renesas_sdhi_quirks sdhi_quirks_r8a7796_es13 = {
-	.hs400_4taps = true,
-	.hs400_bad_taps = BIT(2) | BIT(3) | BIT(6) | BIT(7),
-	.hs400_calib_table = r8a7796_es13_calib_table,
-};
-
-static const struct renesas_sdhi_quirks sdhi_quirks_r8a77965 = {
-	.hs400_bad_taps = BIT(2) | BIT(3) | BIT(6) | BIT(7),
-	.hs400_calib_table = r8a77965_calib_table,
-};
-
-static const struct renesas_sdhi_quirks sdhi_quirks_r8a77990 = {
-	.hs400_calib_table = r8a77990_calib_table,
-};
-
-/*
- * Note for r8a7796 / r8a774a1: we can't distinguish ES1.1 and 1.2 as of now.
- * So, we want to treat them equally and only have a match for ES1.2 to enforce
- * this if there ever will be a way to distinguish ES1.2.
- */
-static const struct soc_device_attribute sdhi_quirks_match[]  = {
-	{ .soc_id = "r8a774a1", .revision = "ES1.[012]", .data = &sdhi_quirks_4tap_nohs400 },
-	{ .soc_id = "r8a7795", .revision = "ES1.*", .data = &sdhi_quirks_4tap_nohs400 },
-	{ .soc_id = "r8a7795", .revision = "ES2.0", .data = &sdhi_quirks_4tap },
-	{ .soc_id = "r8a7795", .revision = "ES3.*", .data = &sdhi_quirks_bad_taps2367 },
-	{ .soc_id = "r8a7796", .revision = "ES1.[012]", .data = &sdhi_quirks_4tap_nohs400 },
-	{ .soc_id = "r8a7796", .revision = "ES1.*", .data = &sdhi_quirks_r8a7796_es13 },
-	{ .soc_id = "r8a77961", .data = &sdhi_quirks_bad_taps1357 },
-	{ .soc_id = "r8a77965", .data = &sdhi_quirks_r8a77965 },
-	{ .soc_id = "r8a77980", .data = &sdhi_quirks_nohs400 },
-	{ .soc_id = "r8a77990", .data = &sdhi_quirks_r8a77990 },
-	{ /* Sentinel. */ },
-};
-
 int renesas_sdhi_probe(struct platform_device *pdev,
-		       const struct tmio_mmc_dma_ops *dma_ops)
+		       const struct tmio_mmc_dma_ops *dma_ops,
+		       const struct renesas_sdhi_of_data *of_data,
+		       const struct renesas_sdhi_quirks *quirks)
 {
 	struct tmio_mmc_data *mmd = pdev->dev.platform_data;
-	const struct renesas_sdhi_quirks *quirks = NULL;
-	const struct renesas_sdhi_of_data *of_data;
-	const struct soc_device_attribute *attr;
 	struct tmio_mmc_data *mmc_data;
 	struct tmio_mmc_dma *dma_priv;
 	struct tmio_mmc_host *host;
@@ -966,12 +888,6 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 	struct resource *res;
 	u16 ver;
 
-	of_data = of_device_get_match_data(&pdev->dev);
-
-	attr = soc_device_match(sdhi_quirks_match);
-	if (attr)
-		quirks = attr->data;
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res)
 		return -EINVAL;
diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
index e8f4863d8f1a..7660f7ea74dd 100644
--- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c
+++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
@@ -15,6 +15,7 @@
 #include <linux/mmc/host.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/pagemap.h>
 #include <linux/scatterlist.h>
 #include <linux/sys_soc.h>
@@ -92,7 +93,7 @@ static struct renesas_sdhi_scc rcar_gen3_scc_taps[] = {
 	},
 };
 
-static const struct renesas_sdhi_of_data of_rza2_compatible = {
+static const struct renesas_sdhi_of_data of_data_rza2 = {
 	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_CLK_ACTUAL |
 			  TMIO_MMC_HAVE_CBSY,
 	.tmio_ocr_mask	= MMC_VDD_32_33,
@@ -107,7 +108,11 @@ static const struct renesas_sdhi_of_data of_rza2_compatible = {
 	.max_segs	= 1,
 };
 
-static const struct renesas_sdhi_of_data of_rcar_gen3_compatible = {
+static const struct renesas_sdhi_of_data_with_quirks of_rza2_compatible = {
+	.of_data	= &of_data_rza2,
+};
+
+static const struct renesas_sdhi_of_data of_data_rcar_gen3 = {
 	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_CLK_ACTUAL |
 			  TMIO_MMC_HAVE_CBSY | TMIO_MMC_MIN_RCAR2,
 	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |
@@ -122,11 +127,116 @@ static const struct renesas_sdhi_of_data of_rcar_gen3_compatible = {
 	.max_segs	= 1,
 };
 
+static const u8 r8a7796_es13_calib_table[2][SDHI_CALIB_TABLE_MAX] = {
+	{ 3,  3,  3,  3,  3,  3,  3,  4,  4,  5,  6,  7,  8,  9, 10, 15,
+	 16, 16, 16, 16, 16, 16, 17, 18, 18, 19, 20, 21, 22, 23, 24, 25 },
+	{ 5,  5,  5,  5,  5,  5,  5,  5,  5,  5,  5,  5,  6,  7,  8, 11,
+	 12, 17, 18, 18, 18, 18, 18, 18, 18, 19, 20, 21, 22, 23, 25, 25 }
+};
+
+static const u8 r8a77965_calib_table[2][SDHI_CALIB_TABLE_MAX] = {
+	{ 1,  2,  6,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 15, 15, 16,
+	 17, 18, 19, 20, 21, 22, 23, 24, 25, 25, 26, 27, 28, 29, 30, 31 },
+	{ 2,  3,  4,  4,  5,  6,  7,  9, 10, 11, 12, 13, 14, 15, 16, 17,
+	 17, 17, 20, 21, 22, 23, 24, 25, 27, 28, 29, 30, 31, 31, 31, 31 }
+};
+
+static const u8 r8a77990_calib_table[2][SDHI_CALIB_TABLE_MAX] = {
+	{ 0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
+	  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 },
+	{ 0,  0,  0,  1,  2,  3,  3,  4,  4,  4,  5,  5,  6,  8,  9, 10,
+	 11, 12, 13, 15, 16, 17, 17, 18, 18, 19, 20, 22, 24, 25, 26, 26 }
+};
+
+static const struct renesas_sdhi_quirks sdhi_quirks_4tap_nohs400 = {
+	.hs400_disabled = true,
+	.hs400_4taps = true,
+};
+
+static const struct renesas_sdhi_quirks sdhi_quirks_4tap = {
+	.hs400_4taps = true,
+	.hs400_bad_taps = BIT(2) | BIT(3) | BIT(6) | BIT(7),
+};
+
+static const struct renesas_sdhi_quirks sdhi_quirks_nohs400 = {
+	.hs400_disabled = true,
+};
+
+static const struct renesas_sdhi_quirks sdhi_quirks_bad_taps1357 = {
+	.hs400_bad_taps = BIT(1) | BIT(3) | BIT(5) | BIT(7),
+};
+
+static const struct renesas_sdhi_quirks sdhi_quirks_bad_taps2367 = {
+	.hs400_bad_taps = BIT(2) | BIT(3) | BIT(6) | BIT(7),
+};
+
+static const struct renesas_sdhi_quirks sdhi_quirks_r8a7796_es13 = {
+	.hs400_4taps = true,
+	.hs400_bad_taps = BIT(2) | BIT(3) | BIT(6) | BIT(7),
+	.hs400_calib_table = r8a7796_es13_calib_table,
+};
+
+static const struct renesas_sdhi_quirks sdhi_quirks_r8a77965 = {
+	.hs400_bad_taps = BIT(2) | BIT(3) | BIT(6) | BIT(7),
+	.hs400_calib_table = r8a77965_calib_table,
+};
+
+static const struct renesas_sdhi_quirks sdhi_quirks_r8a77990 = {
+	.hs400_calib_table = r8a77990_calib_table,
+};
+
+/*
+ * Note for r8a7796 / r8a774a1: we can't distinguish ES1.1 and 1.2 as of now.
+ * So, we want to treat them equally and only have a match for ES1.2 to enforce
+ * this if there ever will be a way to distinguish ES1.2.
+ */
+static const struct soc_device_attribute sdhi_quirks_match[]  = {
+	{ .soc_id = "r8a774a1", .revision = "ES1.[012]", .data = &sdhi_quirks_4tap_nohs400 },
+	{ .soc_id = "r8a7795", .revision = "ES1.*", .data = &sdhi_quirks_4tap_nohs400 },
+	{ .soc_id = "r8a7795", .revision = "ES2.0", .data = &sdhi_quirks_4tap },
+	{ .soc_id = "r8a7796", .revision = "ES1.[012]", .data = &sdhi_quirks_4tap_nohs400 },
+	{ .soc_id = "r8a7796", .revision = "ES1.*", .data = &sdhi_quirks_r8a7796_es13 },
+	{ /* Sentinel. */ },
+};
+
+static const struct renesas_sdhi_of_data_with_quirks of_r8a7795_compatible = {
+	.of_data = &of_data_rcar_gen3,
+	.quirks = &sdhi_quirks_bad_taps2367,
+};
+
+static const struct renesas_sdhi_of_data_with_quirks of_r8a77961_compatible = {
+	.of_data = &of_data_rcar_gen3,
+	.quirks = &sdhi_quirks_bad_taps1357,
+};
+
+static const struct renesas_sdhi_of_data_with_quirks of_r8a77965_compatible = {
+	.of_data = &of_data_rcar_gen3,
+	.quirks = &sdhi_quirks_r8a77965,
+};
+
+static const struct renesas_sdhi_of_data_with_quirks of_r8a77980_compatible = {
+	.of_data = &of_data_rcar_gen3,
+	.quirks = &sdhi_quirks_nohs400,
+};
+
+static const struct renesas_sdhi_of_data_with_quirks of_r8a77990_compatible = {
+	.of_data = &of_data_rcar_gen3,
+	.quirks = &sdhi_quirks_r8a77990,
+};
+
+static const struct renesas_sdhi_of_data_with_quirks of_rcar_gen3_compatible = {
+	.of_data = &of_data_rcar_gen3,
+};
+
 static const struct of_device_id renesas_sdhi_internal_dmac_of_match[] = {
 	{ .compatible = "renesas,sdhi-r7s9210", .data = &of_rza2_compatible, },
 	{ .compatible = "renesas,sdhi-mmc-r8a77470", .data = &of_rcar_gen3_compatible, },
-	{ .compatible = "renesas,sdhi-r8a7795", .data = &of_rcar_gen3_compatible, },
+	{ .compatible = "renesas,sdhi-r8a7795", .data = &of_r8a7795_compatible, },
 	{ .compatible = "renesas,sdhi-r8a7796", .data = &of_rcar_gen3_compatible, },
+	{ .compatible = "renesas,sdhi-r8a77961", .data = &of_r8a77961_compatible, },
+	{ .compatible = "renesas,sdhi-r8a77965", .data = &of_r8a77965_compatible, },
+	{ .compatible = "renesas,sdhi-r8a77980", .data = &of_r8a77980_compatible, },
+	{ .compatible = "renesas,sdhi-r8a77990", .data = &of_r8a77990_compatible, },
 	{ .compatible = "renesas,rcar-gen3-sdhi", .data = &of_rcar_gen3_compatible, },
 	{},
 };
@@ -405,16 +515,27 @@ static const struct soc_device_attribute soc_dma_quirks[] = {
 
 static int renesas_sdhi_internal_dmac_probe(struct platform_device *pdev)
 {
-	const struct soc_device_attribute *soc = soc_device_match(soc_dma_quirks);
+	const struct soc_device_attribute *attr;
+	const struct renesas_sdhi_of_data_with_quirks *of_data_quirks;
+	const struct renesas_sdhi_quirks *quirks;
 	struct device *dev = &pdev->dev;
 
-	if (soc)
-		global_flags |= (unsigned long)soc->data;
+	of_data_quirks = of_device_get_match_data(&pdev->dev);
+	quirks = of_data_quirks->quirks;
+
+	attr = soc_device_match(soc_dma_quirks);
+	if (attr)
+		global_flags |= (unsigned long)attr->data;
+
+	attr = soc_device_match(sdhi_quirks_match);
+	if (attr)
+		quirks = attr->data;
 
 	/* value is max of SD_SECCNT. Confirmed by HW engineers */
 	dma_set_max_seg_size(dev, 0xffffffff);
 
-	return renesas_sdhi_probe(pdev, &renesas_sdhi_internal_dmac_dma_ops);
+	return renesas_sdhi_probe(pdev, &renesas_sdhi_internal_dmac_dma_ops,
+				  of_data_quirks->of_data, quirks);
 }
 
 static const struct dev_pm_ops renesas_sdhi_internal_dmac_dev_pm_ops = {
diff --git a/drivers/mmc/host/renesas_sdhi_sys_dmac.c b/drivers/mmc/host/renesas_sdhi_sys_dmac.c
index ffa64211f4de..99e3426df702 100644
--- a/drivers/mmc/host/renesas_sdhi_sys_dmac.c
+++ b/drivers/mmc/host/renesas_sdhi_sys_dmac.c
@@ -108,9 +108,9 @@ static void renesas_sdhi_sys_dmac_abort_dma(struct tmio_mmc_host *host)
 	renesas_sdhi_sys_dmac_enable_dma(host, false);
 
 	if (host->chan_rx)
-		dmaengine_terminate_all(host->chan_rx);
+		dmaengine_terminate_sync(host->chan_rx);
 	if (host->chan_tx)
-		dmaengine_terminate_all(host->chan_tx);
+		dmaengine_terminate_sync(host->chan_tx);
 
 	renesas_sdhi_sys_dmac_enable_dma(host, true);
 }
@@ -451,7 +451,8 @@ static const struct tmio_mmc_dma_ops renesas_sdhi_sys_dmac_dma_ops = {
 
 static int renesas_sdhi_sys_dmac_probe(struct platform_device *pdev)
 {
-	return renesas_sdhi_probe(pdev, &renesas_sdhi_sys_dmac_dma_ops);
+	return renesas_sdhi_probe(pdev, &renesas_sdhi_sys_dmac_dma_ops,
+				  of_device_get_match_data(&pdev->dev), NULL);
 }
 
 static const struct dev_pm_ops renesas_sdhi_sys_dmac_dev_pm_ops = {
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index 4ca937415734..58cfaffa3c2d 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -542,9 +542,22 @@ static int sd_write_long_data(struct realtek_pci_sdmmc *host,
 	return 0;
 }
 
+static inline void sd_enable_initial_mode(struct realtek_pci_sdmmc *host)
+{
+	rtsx_pci_write_register(host->pcr, SD_CFG1,
+			SD_CLK_DIVIDE_MASK, SD_CLK_DIVIDE_128);
+}
+
+static inline void sd_disable_initial_mode(struct realtek_pci_sdmmc *host)
+{
+	rtsx_pci_write_register(host->pcr, SD_CFG1,
+			SD_CLK_DIVIDE_MASK, SD_CLK_DIVIDE_0);
+}
+
 static int sd_rw_multi(struct realtek_pci_sdmmc *host, struct mmc_request *mrq)
 {
 	struct mmc_data *data = mrq->data;
+	int err;
 
 	if (host->sg_count < 0) {
 		data->error = host->sg_count;
@@ -553,22 +566,19 @@ static int sd_rw_multi(struct realtek_pci_sdmmc *host, struct mmc_request *mrq)
 		return data->error;
 	}
 
-	if (data->flags & MMC_DATA_READ)
-		return sd_read_long_data(host, mrq);
+	if (data->flags & MMC_DATA_READ) {
+		if (host->initial_mode)
+			sd_disable_initial_mode(host);
 
-	return sd_write_long_data(host, mrq);
-}
+		err = sd_read_long_data(host, mrq);
 
-static inline void sd_enable_initial_mode(struct realtek_pci_sdmmc *host)
-{
-	rtsx_pci_write_register(host->pcr, SD_CFG1,
-			SD_CLK_DIVIDE_MASK, SD_CLK_DIVIDE_128);
-}
+		if (host->initial_mode)
+			sd_enable_initial_mode(host);
 
-static inline void sd_disable_initial_mode(struct realtek_pci_sdmmc *host)
-{
-	rtsx_pci_write_register(host->pcr, SD_CFG1,
-			SD_CLK_DIVIDE_MASK, SD_CLK_DIVIDE_0);
+		return err;
+	}
+
+	return sd_write_long_data(host, mrq);
 }
 
 static void sd_normal_rw(struct realtek_pci_sdmmc *host,
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 72c0bf0c1887..f18d169bc8ff 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -24,7 +24,6 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
-#include <linux/platform_data/mmc-esdhc-imx.h>
 #include <linux/pm_runtime.h>
 #include "sdhci-pltfm.h"
 #include "sdhci-esdhc.h"
@@ -95,6 +94,11 @@
 
 #define ESDHC_VEND_SPEC2		0xc8
 #define ESDHC_VEND_SPEC2_EN_BUSY_IRQ	(1 << 8)
+#define ESDHC_VEND_SPEC2_AUTO_TUNE_8BIT_EN	(1 << 4)
+#define ESDHC_VEND_SPEC2_AUTO_TUNE_4BIT_EN	(0 << 4)
+#define ESDHC_VEND_SPEC2_AUTO_TUNE_1BIT_EN	(2 << 4)
+#define ESDHC_VEND_SPEC2_AUTO_TUNE_CMD_EN	(1 << 6)
+#define ESDHC_VEND_SPEC2_AUTO_TUNE_MODE_MASK	(7 << 4)
 
 #define ESDHC_TUNING_CTRL		0xcc
 #define ESDHC_STD_TUNING_EN		(1 << 24)
@@ -115,6 +119,7 @@
 #define ESDHC_CTRL_4BITBUS		(0x1 << 1)
 #define ESDHC_CTRL_8BITBUS		(0x2 << 1)
 #define ESDHC_CTRL_BUSWIDTH_MASK	(0x3 << 1)
+#define USDHC_GET_BUSWIDTH(c) (c & ESDHC_CTRL_BUSWIDTH_MASK)
 
 /*
  * There is an INT DMA ERR mismatch between eSDHC and STD SDHC SPEC:
@@ -191,6 +196,38 @@
  */
 #define ESDHC_FLAG_BROKEN_AUTO_CMD23	BIT(16)
 
+enum wp_types {
+	ESDHC_WP_NONE,		/* no WP, neither controller nor gpio */
+	ESDHC_WP_CONTROLLER,	/* mmc controller internal WP */
+	ESDHC_WP_GPIO,		/* external gpio pin for WP */
+};
+
+enum cd_types {
+	ESDHC_CD_NONE,		/* no CD, neither controller nor gpio */
+	ESDHC_CD_CONTROLLER,	/* mmc controller internal CD */
+	ESDHC_CD_GPIO,		/* external gpio pin for CD */
+	ESDHC_CD_PERMANENT,	/* no CD, card permanently wired to host */
+};
+
+/*
+ * struct esdhc_platform_data - platform data for esdhc on i.MX
+ *
+ * ESDHC_WP(CD)_CONTROLLER type is not available on i.MX25/35.
+ *
+ * @wp_type:	type of write_protect method (see wp_types enum above)
+ * @cd_type:	type of card_detect method (see cd_types enum above)
+ */
+
+struct esdhc_platform_data {
+	enum wp_types wp_type;
+	enum cd_types cd_type;
+	int max_bus_width;
+	unsigned int delay_line;
+	unsigned int tuning_step;       /* The delay cell steps in tuning procedure */
+	unsigned int tuning_start_tap;	/* The start delay cell point in tuning procedure */
+	unsigned int strobe_dll_delay_target;	/* The delay cell for strobe pad (read clock) */
+};
+
 struct esdhc_soc_data {
 	u32 flags;
 };
@@ -376,6 +413,30 @@ static inline void esdhc_wait_for_card_clock_gate_off(struct sdhci_host *host)
 		dev_warn(mmc_dev(host->mmc), "%s: card clock still not gate off in 100us!.\n", __func__);
 }
 
+/* Enable the auto tuning circuit to check the CMD line and BUS line */
+static inline void usdhc_auto_tuning_mode_sel(struct sdhci_host *host)
+{
+	u32 buswidth, auto_tune_buswidth;
+
+	buswidth = USDHC_GET_BUSWIDTH(readl(host->ioaddr + SDHCI_HOST_CONTROL));
+
+	switch (buswidth) {
+	case ESDHC_CTRL_8BITBUS:
+		auto_tune_buswidth = ESDHC_VEND_SPEC2_AUTO_TUNE_8BIT_EN;
+		break;
+	case ESDHC_CTRL_4BITBUS:
+		auto_tune_buswidth = ESDHC_VEND_SPEC2_AUTO_TUNE_4BIT_EN;
+		break;
+	default:	/* 1BITBUS */
+		auto_tune_buswidth = ESDHC_VEND_SPEC2_AUTO_TUNE_1BIT_EN;
+		break;
+	}
+
+	esdhc_clrset_le(host, ESDHC_VEND_SPEC2_AUTO_TUNE_MODE_MASK,
+			auto_tune_buswidth | ESDHC_VEND_SPEC2_AUTO_TUNE_CMD_EN,
+			ESDHC_VEND_SPEC2);
+}
+
 static u32 esdhc_readl_le(struct sdhci_host *host, int reg)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
@@ -597,17 +658,7 @@ static void esdhc_writew_le(struct sdhci_host *host, u16 val, int reg)
 		else
 			new_val &= ~ESDHC_VENDOR_SPEC_VSELECT;
 		writel(new_val, host->ioaddr + ESDHC_VENDOR_SPEC);
-		if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING) {
-			new_val = readl(host->ioaddr + ESDHC_MIX_CTRL);
-			if (val & SDHCI_CTRL_TUNED_CLK) {
-				new_val |= ESDHC_MIX_CTRL_SMPCLK_SEL;
-				new_val |= ESDHC_MIX_CTRL_AUTO_TUNE_EN;
-			} else {
-				new_val &= ~ESDHC_MIX_CTRL_SMPCLK_SEL;
-				new_val &= ~ESDHC_MIX_CTRL_AUTO_TUNE_EN;
-			}
-			writel(new_val , host->ioaddr + ESDHC_MIX_CTRL);
-		} else if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) {
+		if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) {
 			u32 v = readl(host->ioaddr + SDHCI_AUTO_CMD_STATUS);
 			u32 m = readl(host->ioaddr + ESDHC_MIX_CTRL);
 			if (val & SDHCI_CTRL_TUNED_CLK) {
@@ -622,6 +673,7 @@ static void esdhc_writew_le(struct sdhci_host *host, u16 val, int reg)
 				v |= ESDHC_MIX_CTRL_EXE_TUNE;
 				m |= ESDHC_MIX_CTRL_FBCLK_SEL;
 				m |= ESDHC_MIX_CTRL_AUTO_TUNE_EN;
+				usdhc_auto_tuning_mode_sel(host);
 			} else {
 				v &= ~ESDHC_MIX_CTRL_EXE_TUNE;
 			}
@@ -991,6 +1043,8 @@ static void esdhc_post_tuning(struct sdhci_host *host)
 {
 	u32 reg;
 
+	usdhc_auto_tuning_mode_sel(host);
+
 	reg = readl(host->ioaddr + ESDHC_MIX_CTRL);
 	reg &= ~ESDHC_MIX_CTRL_EXE_TUNE;
 	reg |= ESDHC_MIX_CTRL_AUTO_TUNE_EN;
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 290a14cdc1cf..50c71e0ba5e4 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -2714,6 +2714,9 @@ static int sdhci_msm_probe(struct platform_device *pdev)
 
 	msm_host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY | MMC_CAP_NEED_RSP_BUSY;
 
+	/* Set the timeout value to max possible */
+	host->max_timeout_count = 0xF;
+
 	pm_runtime_get_noresume(&pdev->dev);
 	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index 0e7c07ed9690..737e2bfdedc2 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -159,6 +159,12 @@ struct sdhci_arasan_data {
 /* Controller immediately reports SDHCI_CLOCK_INT_STABLE after enabling the
  * internal clock even when the clock isn't stable */
 #define SDHCI_ARASAN_QUIRK_CLOCK_UNSTABLE BIT(1)
+/*
+ * Some of the Arasan variations might not have timing requirements
+ * met at 25MHz for Default Speed mode, those controllers work at
+ * 19MHz instead
+ */
+#define SDHCI_ARASAN_QUIRK_CLOCK_25_BROKEN BIT(2)
 };
 
 struct sdhci_arasan_of_data {
@@ -267,7 +273,12 @@ static void sdhci_arasan_set_clock(struct sdhci_host *host, unsigned int clock)
 			 * through low speeds without power cycling.
 			 */
 			sdhci_set_clock(host, host->max_clk);
-			phy_power_on(sdhci_arasan->phy);
+			if (phy_power_on(sdhci_arasan->phy)) {
+				pr_err("%s: Cannot power on phy.\n",
+				       mmc_hostname(host->mmc));
+				return;
+			}
+
 			sdhci_arasan->is_phy_on = true;
 
 			/*
@@ -290,6 +301,16 @@ static void sdhci_arasan_set_clock(struct sdhci_host *host, unsigned int clock)
 		sdhci_arasan->is_phy_on = false;
 	}
 
+	if (sdhci_arasan->quirks & SDHCI_ARASAN_QUIRK_CLOCK_25_BROKEN) {
+		/*
+		 * Some of the Arasan variations might not have timing
+		 * requirements met at 25MHz for Default Speed mode,
+		 * those controllers work at 19MHz instead.
+		 */
+		if (clock == DEFAULT_SPEED_MAX_DTR)
+			clock = (DEFAULT_SPEED_MAX_DTR * 19) / 25;
+	}
+
 	/* Set the Input and Output Clock Phase Delays */
 	if (clk_data->set_clk_delays)
 		clk_data->set_clk_delays(host);
@@ -307,7 +328,12 @@ static void sdhci_arasan_set_clock(struct sdhci_host *host, unsigned int clock)
 		msleep(20);
 
 	if (ctrl_phy) {
-		phy_power_on(sdhci_arasan->phy);
+		if (phy_power_on(sdhci_arasan->phy)) {
+			pr_err("%s: Cannot power on phy.\n",
+			       mmc_hostname(host->mmc));
+			return;
+		}
+
 		sdhci_arasan->is_phy_on = true;
 	}
 }
@@ -463,7 +489,9 @@ static int sdhci_arasan_suspend(struct device *dev)
 		ret = phy_power_off(sdhci_arasan->phy);
 		if (ret) {
 			dev_err(dev, "Cannot power off phy.\n");
-			sdhci_resume_host(host);
+			if (sdhci_resume_host(host))
+				dev_err(dev, "Cannot resume host.\n");
+
 			return ret;
 		}
 		sdhci_arasan->is_phy_on = false;
@@ -878,6 +906,10 @@ static int arasan_zynqmp_execute_tuning(struct mmc_host *mmc, u32 opcode)
 							   NODE_SD_1;
 	int err;
 
+	/* ZynqMP SD controller does not perform auto tuning in DDR50 mode */
+	if (mmc->ios.timing == MMC_TIMING_UHS_DDR50)
+		return 0;
+
 	arasan_zynqmp_dll_reset(host, device_id);
 
 	err = sdhci_execute_tuning(mmc, opcode);
@@ -952,7 +984,7 @@ static void sdhci_arasan_update_baseclkfreq(struct sdhci_host *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;
-	u32 mhz = DIV_ROUND_CLOSEST(clk_get_rate(pltfm_host->clk), 1000000);
+	u32 mhz = DIV_ROUND_CLOSEST_ULL(clk_get_rate(pltfm_host->clk), 1000000);
 
 	/* Having a map is optional */
 	if (!soc_ctl_map)
@@ -986,14 +1018,16 @@ static void arasan_dt_read_clk_phase(struct device *dev,
 {
 	struct device_node *np = dev->of_node;
 
-	int clk_phase[2] = {0};
+	u32 clk_phase[2] = {0};
+	int ret;
 
 	/*
 	 * Read Tap Delay values from DT, if the DT does not contain the
 	 * Tap Values then use the pre-defined values.
 	 */
-	if (of_property_read_variable_u32_array(np, prop, &clk_phase[0],
-						2, 0)) {
+	ret = of_property_read_variable_u32_array(np, prop, &clk_phase[0],
+						  2, 0);
+	if (ret < 0) {
 		dev_dbg(dev, "Using predefined clock phase for %s = %d %d\n",
 			prop, clk_data->clk_phase_in[timing],
 			clk_data->clk_phase_out[timing]);
@@ -1608,6 +1642,9 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 	if (of_device_is_compatible(np, "xlnx,zynqmp-8.9a")) {
 		host->mmc_host_ops.execute_tuning =
 			arasan_zynqmp_execute_tuning;
+
+		sdhci_arasan->quirks |= SDHCI_ARASAN_QUIRK_CLOCK_25_BROKEN;
+		host->quirks |= SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12;
 	}
 
 	arasan_dt_parse_clk_phases(dev, &sdhci_arasan->clk_data);
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index aba6e10b8605..8eefa7d5fe85 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -934,21 +934,21 @@ static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd,
 
 	/*
 	 * If the host controller provides us with an incorrect timeout
-	 * value, just skip the check and use 0xE.  The hardware may take
+	 * value, just skip the check and use the maximum. The hardware may take
 	 * longer to time out, but that's much better than having a too-short
 	 * timeout value.
 	 */
 	if (host->quirks & SDHCI_QUIRK_BROKEN_TIMEOUT_VAL)
-		return 0xE;
+		return host->max_timeout_count;
 
 	/* Unspecified command, asume max */
 	if (cmd == NULL)
-		return 0xE;
+		return host->max_timeout_count;
 
 	data = cmd->data;
 	/* Unspecified timeout, assume max */
 	if (!data && !cmd->busy_timeout)
-		return 0xE;
+		return host->max_timeout_count;
 
 	/* timeout in us */
 	target_timeout = sdhci_target_timeout(host, cmd, data);
@@ -968,15 +968,15 @@ static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd,
 	while (current_timeout < target_timeout) {
 		count++;
 		current_timeout <<= 1;
-		if (count >= 0xF)
+		if (count > host->max_timeout_count)
 			break;
 	}
 
-	if (count >= 0xF) {
+	if (count > host->max_timeout_count) {
 		if (!(host->quirks2 & SDHCI_QUIRK2_DISABLE_HW_TIMEOUT))
 			DBG("Too large timeout 0x%x requested for CMD%d!\n",
 			    count, cmd->opcode);
-		count = 0xE;
+		count = host->max_timeout_count;
 	} else {
 		*too_big = false;
 	}
@@ -1222,6 +1222,7 @@ static int sdhci_external_dma_setup(struct sdhci_host *host,
 	if (!host->mapbase)
 		return -EINVAL;
 
+	memset(&cfg, 0, sizeof(cfg));
 	cfg.src_addr = host->mapbase + SDHCI_BUFFER;
 	cfg.dst_addr = host->mapbase + SDHCI_BUFFER;
 	cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
@@ -3278,8 +3279,14 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask)
 {
 	u32 command;
 
-	/* CMD19 generates _only_ Buffer Read Ready interrupt */
-	if (intmask & SDHCI_INT_DATA_AVAIL) {
+	/*
+	 * CMD19 generates _only_ Buffer Read Ready interrupt if
+	 * use sdhci_send_tuning.
+	 * Need to exclude this case: PIO mode and use mmc_send_tuning,
+	 * If not, sdhci_transfer_pio will never be called, make the
+	 * SDHCI_INT_DATA_AVAIL always there, stuck in irq storm.
+	 */
+	if (intmask & SDHCI_INT_DATA_AVAIL && !host->data) {
 		command = SDHCI_GET_CMD(sdhci_readw(host, SDHCI_COMMAND));
 		if (command == MMC_SEND_TUNING_BLOCK ||
 		    command == MMC_SEND_TUNING_BLOCK_HS200) {
@@ -3940,6 +3947,8 @@ struct sdhci_host *sdhci_alloc_host(struct device *dev,
 	 */
 	host->adma_table_cnt = SDHCI_MAX_SEGS * 2 + 1;
 
+	host->max_timeout_count = 0xE;
+
 	return host;
 }
 
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 074dc182b184..e8d04e42a5af 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -517,6 +517,7 @@ struct sdhci_host {
 
 	unsigned int max_clk;	/* Max possible freq (MHz) */
 	unsigned int timeout_clk;	/* Timeout freq (KHz) */
+	u8 max_timeout_count;	/* Vendor specific max timeout count */
 	unsigned int clk_mul;	/* Clock Muliplier value */
 
 	unsigned int clock;	/* Current clock (MHz) */
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index e5e457037235..bcc595c70a9f 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -1164,9 +1164,9 @@ static bool sh_mmcif_end_cmd(struct sh_mmcif_host *host)
 		data->bytes_xfered = 0;
 		/* Abort DMA */
 		if (data->flags & MMC_DATA_READ)
-			dmaengine_terminate_all(host->chan_rx);
+			dmaengine_terminate_sync(host->chan_rx);
 		else
-			dmaengine_terminate_all(host->chan_tx);
+			dmaengine_terminate_sync(host->chan_tx);
 	}
 
 	return false;
diff --git a/drivers/mmc/host/tifm_sd.c b/drivers/mmc/host/tifm_sd.c
index 9fdf7ea06e3f..63917070b1a7 100644
--- a/drivers/mmc/host/tifm_sd.c
+++ b/drivers/mmc/host/tifm_sd.c
@@ -669,8 +669,8 @@ static void tifm_sd_request(struct mmc_host *mmc, struct mmc_request *mrq)
 
 			if(1 != tifm_map_sg(sock, &host->bounce_buf, 1,
 					    r_data->flags & MMC_DATA_WRITE
-					    ? PCI_DMA_TODEVICE
-					    : PCI_DMA_FROMDEVICE)) {
+					    ? DMA_TO_DEVICE
+					    : DMA_FROM_DEVICE)) {
 				pr_err("%s : scatterlist map failed\n",
 				       dev_name(&sock->dev));
 				mrq->cmd->error = -ENOMEM;
@@ -680,15 +680,15 @@ static void tifm_sd_request(struct mmc_host *mmc, struct mmc_request *mrq)
 						   r_data->sg_len,
 						   r_data->flags
 						   & MMC_DATA_WRITE
-						   ? PCI_DMA_TODEVICE
-						   : PCI_DMA_FROMDEVICE);
+						   ? DMA_TO_DEVICE
+						   : DMA_FROM_DEVICE);
 			if (host->sg_len < 1) {
 				pr_err("%s : scatterlist map failed\n",
 				       dev_name(&sock->dev));
 				tifm_unmap_sg(sock, &host->bounce_buf, 1,
 					      r_data->flags & MMC_DATA_WRITE
-					      ? PCI_DMA_TODEVICE
-					      : PCI_DMA_FROMDEVICE);
+					      ? DMA_TO_DEVICE
+					      : DMA_FROM_DEVICE);
 				mrq->cmd->error = -ENOMEM;
 				goto err_out;
 			}
@@ -762,10 +762,10 @@ static void tifm_sd_end_cmd(struct tasklet_struct *t)
 		} else {
 			tifm_unmap_sg(sock, &host->bounce_buf, 1,
 				      (r_data->flags & MMC_DATA_WRITE)
-				      ? PCI_DMA_TODEVICE : PCI_DMA_FROMDEVICE);
+				      ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 			tifm_unmap_sg(sock, r_data->sg, r_data->sg_len,
 				      (r_data->flags & MMC_DATA_WRITE)
-				      ? PCI_DMA_TODEVICE : PCI_DMA_FROMDEVICE);
+				      ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 		}
 
 		r_data->bytes_xfered = r_data->blocks
diff --git a/drivers/mmc/host/usdhi6rol0.c b/drivers/mmc/host/usdhi6rol0.c
index b9b79b1089a0..99515be6e5e5 100644
--- a/drivers/mmc/host/usdhi6rol0.c
+++ b/drivers/mmc/host/usdhi6rol0.c
@@ -631,9 +631,9 @@ static void usdhi6_dma_kill(struct usdhi6_host *host)
 		__func__, data->sg_len, data->blocks, data->blksz);
 	/* Abort DMA */
 	if (data->flags & MMC_DATA_READ)
-		dmaengine_terminate_all(host->chan_rx);
+		dmaengine_terminate_sync(host->chan_rx);
 	else
-		dmaengine_terminate_all(host->chan_tx);
+		dmaengine_terminate_sync(host->chan_tx);
 }
 
 static void usdhi6_dma_check_error(struct usdhi6_host *host)
@@ -1186,6 +1186,15 @@ static int usdhi6_sig_volt_switch(struct mmc_host *mmc, struct mmc_ios *ios)
 	return ret;
 }
 
+static int usdhi6_card_busy(struct mmc_host *mmc)
+{
+	struct usdhi6_host *host = mmc_priv(mmc);
+	u32 tmp = usdhi6_read(host, USDHI6_SD_INFO2);
+
+	/* Card is busy if it is pulling dat[0] low */
+	return !(tmp & USDHI6_SD_INFO2_SDDAT0);
+}
+
 static const struct mmc_host_ops usdhi6_ops = {
 	.request	= usdhi6_request,
 	.set_ios	= usdhi6_set_ios,
@@ -1193,6 +1202,7 @@ static const struct mmc_host_ops usdhi6_ops = {
 	.get_ro		= usdhi6_get_ro,
 	.enable_sdio_irq = usdhi6_enable_sdio_irq,
 	.start_signal_voltage_switch = usdhi6_sig_volt_switch,
+	.card_busy = usdhi6_card_busy,
 };
 
 /*			State machine handlers				*/
diff --git a/drivers/mmc/host/via-sdmmc.c b/drivers/mmc/host/via-sdmmc.c
index c32df5530b94..88662a90ed96 100644
--- a/drivers/mmc/host/via-sdmmc.c
+++ b/drivers/mmc/host/via-sdmmc.c
@@ -491,7 +491,7 @@ static void via_sdc_preparedata(struct via_crdr_mmc_host *host,
 
 	count = dma_map_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
 		((data->flags & MMC_DATA_READ) ?
-		PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE));
+		DMA_FROM_DEVICE : DMA_TO_DEVICE));
 	BUG_ON(count != 1);
 
 	via_set_ddma(host, sg_dma_address(data->sg), sg_dma_len(data->sg),
@@ -638,7 +638,7 @@ static void via_sdc_finish_data(struct via_crdr_mmc_host *host)
 
 	dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
 		((data->flags & MMC_DATA_READ) ?
-		PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE));
+		DMA_FROM_DEVICE : DMA_TO_DEVICE));
 
 	if (data->stop)
 		via_sdc_send_command(host, data->stop);