Merging upstream version 5.10.216.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

8 files changed, 198 insertions, 220 deletions

diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 8d842ff24..71ecdb134 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -346,6 +346,10 @@ struct mmc_blk_ioc_data {
 	struct mmc_ioc_cmd ic;
 	unsigned char *buf;
 	u64 buf_bytes;
+	unsigned int flags;
+#define MMC_BLK_IOC_DROP	BIT(0)	/* drop this mrq */
+#define MMC_BLK_IOC_SBC	BIT(1)	/* use mrq.sbc */
+
 	struct mmc_rpmb_data *rpmb;
 };
 
@@ -355,7 +359,7 @@ static struct mmc_blk_ioc_data *mmc_blk_ioctl_copy_from_user(
 	struct mmc_blk_ioc_data *idata;
 	int err;
 
-	idata = kmalloc(sizeof(*idata), GFP_KERNEL);
+	idata = kzalloc(sizeof(*idata), GFP_KERNEL);
 	if (!idata) {
 		err = -ENOMEM;
 		goto out;
@@ -447,7 +451,7 @@ static int card_busy_detect(struct mmc_card *card, unsigned int timeout_ms,
 }
 
 static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
-			       struct mmc_blk_ioc_data *idata)
+			       struct mmc_blk_ioc_data **idatas, int i)
 {
 	struct mmc_command cmd = {}, sbc = {};
 	struct mmc_data data = {};
@@ -455,10 +459,18 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 	struct scatterlist sg;
 	int err;
 	unsigned int target_part;
+	struct mmc_blk_ioc_data *idata = idatas[i];
+	struct mmc_blk_ioc_data *prev_idata = NULL;
 
 	if (!card || !md || !idata)
 		return -EINVAL;
 
+	if (idata->flags & MMC_BLK_IOC_DROP)
+		return 0;
+
+	if (idata->flags & MMC_BLK_IOC_SBC && i > 0)
+		prev_idata = idatas[i - 1];
+
 	/*
 	 * The RPMB accesses comes in from the character device, so we
 	 * need to target these explicitly. Else we just target the
@@ -525,7 +537,7 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 			return err;
 	}
 
-	if (idata->rpmb) {
+	if (idata->rpmb || prev_idata) {
 		sbc.opcode = MMC_SET_BLOCK_COUNT;
 		/*
 		 * We don't do any blockcount validation because the max size
@@ -533,6 +545,8 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 		 * 'Reliable Write' bit here.
 		 */
 		sbc.arg = data.blocks | (idata->ic.write_flag & BIT(31));
+		if (prev_idata)
+			sbc.arg = prev_idata->ic.arg;
 		sbc.flags = MMC_RSP_R1 | MMC_CMD_AC;
 		mrq.sbc = &sbc;
 	}
@@ -544,6 +558,15 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 	mmc_wait_for_req(card->host, &mrq);
 	memcpy(&idata->ic.response, cmd.resp, sizeof(cmd.resp));
 
+	if (prev_idata) {
+		memcpy(&prev_idata->ic.response, sbc.resp, sizeof(sbc.resp));
+		if (sbc.error) {
+			dev_err(mmc_dev(card->host), "%s: sbc error %d\n",
+							__func__, sbc.error);
+			return sbc.error;
+		}
+	}
+
 	if (cmd.error) {
 		dev_err(mmc_dev(card->host), "%s: cmd error %d\n",
 						__func__, cmd.error);
@@ -800,10 +823,11 @@ static const struct block_device_operations mmc_bdops = {
 static int mmc_blk_part_switch_pre(struct mmc_card *card,
 				   unsigned int part_type)
 {
-	const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB;
+	const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_MASK;
+	const unsigned int rpmb = EXT_CSD_PART_CONFIG_ACC_RPMB;
 	int ret = 0;
 
-	if ((part_type & mask) == mask) {
+	if ((part_type & mask) == rpmb) {
 		if (card->ext_csd.cmdq_en) {
 			ret = mmc_cmdq_disable(card);
 			if (ret)
@@ -818,10 +842,11 @@ static int mmc_blk_part_switch_pre(struct mmc_card *card,
 static int mmc_blk_part_switch_post(struct mmc_card *card,
 				    unsigned int part_type)
 {
-	const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB;
+	const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_MASK;
+	const unsigned int rpmb = EXT_CSD_PART_CONFIG_ACC_RPMB;
 	int ret = 0;
 
-	if ((part_type & mask) == mask) {
+	if ((part_type & mask) == rpmb) {
 		mmc_retune_unpause(card->host);
 		if (card->reenable_cmdq && !card->ext_csd.cmdq_en)
 			ret = mmc_cmdq_enable(card);
@@ -985,6 +1010,20 @@ static inline void mmc_blk_reset_success(struct mmc_blk_data *md, int type)
 	md->reset_done &= ~type;
 }
 
+static void mmc_blk_check_sbc(struct mmc_queue_req *mq_rq)
+{
+	struct mmc_blk_ioc_data **idata = mq_rq->drv_op_data;
+	int i;
+
+	for (i = 1; i < mq_rq->ioc_count; i++) {
+		if (idata[i - 1]->ic.opcode == MMC_SET_BLOCK_COUNT &&
+		    mmc_op_multi(idata[i]->ic.opcode)) {
+			idata[i - 1]->flags |= MMC_BLK_IOC_DROP;
+			idata[i]->flags |= MMC_BLK_IOC_SBC;
+		}
+	}
+}
+
 /*
  * The non-block commands come back from the block layer after it queued it and
  * processed it with all other requests and then they get issued in this
@@ -1012,11 +1051,14 @@ static void mmc_blk_issue_drv_op(struct mmc_queue *mq, struct request *req)
 			if (ret)
 				break;
 		}
+
+		mmc_blk_check_sbc(mq_rq);
+
 		fallthrough;
 	case MMC_DRV_OP_IOCTL_RPMB:
 		idata = mq_rq->drv_op_data;
 		for (i = 0, ret = 0; i < mq_rq->ioc_count; i++) {
-			ret = __mmc_blk_ioctl_cmd(card, md, idata[i]);
+			ret = __mmc_blk_ioctl_cmd(card, md, idata, i);
 			if (ret)
 				break;
 		}
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 87807ef01..2059cd226 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -997,10 +997,12 @@ static int mmc_select_bus_width(struct mmc_card *card)
 	static unsigned ext_csd_bits[] = {
 		EXT_CSD_BUS_WIDTH_8,
 		EXT_CSD_BUS_WIDTH_4,
+		EXT_CSD_BUS_WIDTH_1,
 	};
 	static unsigned bus_widths[] = {
 		MMC_BUS_WIDTH_8,
 		MMC_BUS_WIDTH_4,
+		MMC_BUS_WIDTH_1,
 	};
 	struct mmc_host *host = card->host;
 	unsigned idx, bus_width = 0;
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index 05e907451..681653d09 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -62,11 +62,15 @@ int mmc_gpio_alloc(struct mmc_host *host)
 int mmc_gpio_get_ro(struct mmc_host *host)
 {
 	struct mmc_gpio *ctx = host->slot.handler_priv;
+	int cansleep;
 
 	if (!ctx || !ctx->ro_gpio)
 		return -ENOSYS;
 
-	return gpiod_get_value_cansleep(ctx->ro_gpio);
+	cansleep = gpiod_cansleep(ctx->ro_gpio);
+	return cansleep ?
+		gpiod_get_value_cansleep(ctx->ro_gpio) :
+		gpiod_get_value(ctx->ro_gpio);
 }
 EXPORT_SYMBOL(mmc_gpio_get_ro);
 
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 1d814919e..a1fb5d0e9 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -15,7 +15,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/bio.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direction.h>
 #include <linux/crc7.h>
 #include <linux/crc-itu-t.h>
 #include <linux/scatterlist.h>
@@ -119,19 +119,14 @@ struct mmc_spi_host {
 	struct spi_transfer	status;
 	struct spi_message	readback;
 
-	/* underlying DMA-aware controller, or null */
-	struct device		*dma_dev;
-
 	/* buffer used for commands and for message "overhead" */
 	struct scratch		*data;
-	dma_addr_t		data_dma;
 
 	/* Specs say to write ones most of the time, even when the card
 	 * has no need to read its input data; and many cards won't care.
 	 * This is our source of those ones.
 	 */
 	void			*ones;
-	dma_addr_t		ones_dma;
 };
 
 
@@ -147,11 +142,8 @@ static inline int mmc_cs_off(struct mmc_spi_host *host)
 	return spi_setup(host->spi);
 }
 
-static int
-mmc_spi_readbytes(struct mmc_spi_host *host, unsigned len)
+static int mmc_spi_readbytes(struct mmc_spi_host *host, unsigned int len)
 {
-	int status;
-
 	if (len > sizeof(*host->data)) {
 		WARN_ON(1);
 		return -EIO;
@@ -159,19 +151,7 @@ mmc_spi_readbytes(struct mmc_spi_host *host, unsigned len)
 
 	host->status.len = len;
 
-	if (host->dma_dev)
-		dma_sync_single_for_device(host->dma_dev,
-				host->data_dma, sizeof(*host->data),
-				DMA_FROM_DEVICE);
-
-	status = spi_sync_locked(host->spi, &host->readback);
-
-	if (host->dma_dev)
-		dma_sync_single_for_cpu(host->dma_dev,
-				host->data_dma, sizeof(*host->data),
-				DMA_FROM_DEVICE);
-
-	return status;
+	return spi_sync_locked(host->spi, &host->readback);
 }
 
 static int mmc_spi_skip(struct mmc_spi_host *host, unsigned long timeout,
@@ -513,23 +493,11 @@ mmc_spi_command_send(struct mmc_spi_host *host,
 	t = &host->t;
 	memset(t, 0, sizeof(*t));
 	t->tx_buf = t->rx_buf = data->status;
-	t->tx_dma = t->rx_dma = host->data_dma;
 	t->len = cp - data->status;
 	t->cs_change = 1;
 	spi_message_add_tail(t, &host->m);
 
-	if (host->dma_dev) {
-		host->m.is_dma_mapped = 1;
-		dma_sync_single_for_device(host->dma_dev,
-				host->data_dma, sizeof(*host->data),
-				DMA_BIDIRECTIONAL);
-	}
 	status = spi_sync_locked(host->spi, &host->m);
-
-	if (host->dma_dev)
-		dma_sync_single_for_cpu(host->dma_dev,
-				host->data_dma, sizeof(*host->data),
-				DMA_BIDIRECTIONAL);
 	if (status < 0) {
 		dev_dbg(&host->spi->dev, "  ... write returned %d\n", status);
 		cmd->error = status;
@@ -547,9 +515,6 @@ mmc_spi_command_send(struct mmc_spi_host *host,
  * We always provide TX data for data and CRC.  The MMC/SD protocol
  * requires us to write ones; but Linux defaults to writing zeroes;
  * so we explicitly initialize it to all ones on RX paths.
- *
- * We also handle DMA mapping, so the underlying SPI controller does
- * not need to (re)do it for each message.
  */
 static void
 mmc_spi_setup_data_message(
@@ -559,11 +524,8 @@ mmc_spi_setup_data_message(
 {
 	struct spi_transfer	*t;
 	struct scratch		*scratch = host->data;
-	dma_addr_t		dma = host->data_dma;
 
 	spi_message_init(&host->m);
-	if (dma)
-		host->m.is_dma_mapped = 1;
 
 	/* for reads, readblock() skips 0xff bytes before finding
 	 * the token; for writes, this transfer issues that token.
@@ -577,8 +539,6 @@ mmc_spi_setup_data_message(
 		else
 			scratch->data_token = SPI_TOKEN_SINGLE;
 		t->tx_buf = &scratch->data_token;
-		if (dma)
-			t->tx_dma = dma + offsetof(struct scratch, data_token);
 		spi_message_add_tail(t, &host->m);
 	}
 
@@ -588,7 +548,6 @@ mmc_spi_setup_data_message(
 	t = &host->t;
 	memset(t, 0, sizeof(*t));
 	t->tx_buf = host->ones;
-	t->tx_dma = host->ones_dma;
 	/* length and actual buffer info are written later */
 	spi_message_add_tail(t, &host->m);
 
@@ -598,14 +557,9 @@ mmc_spi_setup_data_message(
 	if (direction == DMA_TO_DEVICE) {
 		/* the actual CRC may get written later */
 		t->tx_buf = &scratch->crc_val;
-		if (dma)
-			t->tx_dma = dma + offsetof(struct scratch, crc_val);
 	} else {
 		t->tx_buf = host->ones;
-		t->tx_dma = host->ones_dma;
 		t->rx_buf = &scratch->crc_val;
-		if (dma)
-			t->rx_dma = dma + offsetof(struct scratch, crc_val);
 	}
 	spi_message_add_tail(t, &host->m);
 
@@ -628,10 +582,7 @@ mmc_spi_setup_data_message(
 		memset(t, 0, sizeof(*t));
 		t->len = (direction == DMA_TO_DEVICE) ? sizeof(scratch->status) : 1;
 		t->tx_buf = host->ones;
-		t->tx_dma = host->ones_dma;
 		t->rx_buf = scratch->status;
-		if (dma)
-			t->rx_dma = dma + offsetof(struct scratch, status);
 		t->cs_change = 1;
 		spi_message_add_tail(t, &host->m);
 	}
@@ -660,23 +611,13 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t,
 
 	if (host->mmc->use_spi_crc)
 		scratch->crc_val = cpu_to_be16(crc_itu_t(0, t->tx_buf, t->len));
-	if (host->dma_dev)
-		dma_sync_single_for_device(host->dma_dev,
-				host->data_dma, sizeof(*scratch),
-				DMA_BIDIRECTIONAL);
 
 	status = spi_sync_locked(spi, &host->m);
-
 	if (status != 0) {
 		dev_dbg(&spi->dev, "write error (%d)\n", status);
 		return status;
 	}
 
-	if (host->dma_dev)
-		dma_sync_single_for_cpu(host->dma_dev,
-				host->data_dma, sizeof(*scratch),
-				DMA_BIDIRECTIONAL);
-
 	/*
 	 * Get the transmission data-response reply.  It must follow
 	 * immediately after the data block we transferred.  This reply
@@ -725,8 +666,6 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t,
 	}
 
 	t->tx_buf += t->len;
-	if (host->dma_dev)
-		t->tx_dma += t->len;
 
 	/* Return when not busy.  If we didn't collect that status yet,
 	 * we'll need some more I/O.
@@ -790,30 +729,12 @@ mmc_spi_readblock(struct mmc_spi_host *host, struct spi_transfer *t,
 	}
 	leftover = status << 1;
 
-	if (host->dma_dev) {
-		dma_sync_single_for_device(host->dma_dev,
-				host->data_dma, sizeof(*scratch),
-				DMA_BIDIRECTIONAL);
-		dma_sync_single_for_device(host->dma_dev,
-				t->rx_dma, t->len,
-				DMA_FROM_DEVICE);
-	}
-
 	status = spi_sync_locked(spi, &host->m);
 	if (status < 0) {
 		dev_dbg(&spi->dev, "read error %d\n", status);
 		return status;
 	}
 
-	if (host->dma_dev) {
-		dma_sync_single_for_cpu(host->dma_dev,
-				host->data_dma, sizeof(*scratch),
-				DMA_BIDIRECTIONAL);
-		dma_sync_single_for_cpu(host->dma_dev,
-				t->rx_dma, t->len,
-				DMA_FROM_DEVICE);
-	}
-
 	if (bitshift) {
 		/* Walk through the data and the crc and do
 		 * all the magic to get byte-aligned data.
@@ -848,8 +769,6 @@ mmc_spi_readblock(struct mmc_spi_host *host, struct spi_transfer *t,
 	}
 
 	t->rx_buf += t->len;
-	if (host->dma_dev)
-		t->rx_dma += t->len;
 
 	return 0;
 }
@@ -864,7 +783,6 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd,
 		struct mmc_data *data, u32 blk_size)
 {
 	struct spi_device	*spi = host->spi;
-	struct device		*dma_dev = host->dma_dev;
 	struct spi_transfer	*t;
 	enum dma_data_direction	direction;
 	struct scatterlist	*sg;
@@ -891,31 +809,8 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd,
 	 */
 	for_each_sg(data->sg, sg, data->sg_len, n_sg) {
 		int			status = 0;
-		dma_addr_t		dma_addr = 0;
 		void			*kmap_addr;
 		unsigned		length = sg->length;
-		enum dma_data_direction	dir = direction;
-
-		/* set up dma mapping for controller drivers that might
-		 * use DMA ... though they may fall back to PIO
-		 */
-		if (dma_dev) {
-			/* never invalidate whole *shared* pages ... */
-			if ((sg->offset != 0 || length != PAGE_SIZE)
-					&& dir == DMA_FROM_DEVICE)
-				dir = DMA_BIDIRECTIONAL;
-
-			dma_addr = dma_map_page(dma_dev, sg_page(sg), 0,
-						PAGE_SIZE, dir);
-			if (dma_mapping_error(dma_dev, dma_addr)) {
-				data->error = -EFAULT;
-				break;
-			}
-			if (direction == DMA_TO_DEVICE)
-				t->tx_dma = dma_addr + sg->offset;
-			else
-				t->rx_dma = dma_addr + sg->offset;
-		}
 
 		/* allow pio too; we don't allow highmem */
 		kmap_addr = kmap(sg_page(sg));
@@ -951,8 +846,6 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd,
 		if (direction == DMA_FROM_DEVICE)
 			flush_kernel_dcache_page(sg_page(sg));
 		kunmap(sg_page(sg));
-		if (dma_dev)
-			dma_unmap_page(dma_dev, dma_addr, PAGE_SIZE, dir);
 
 		if (status < 0) {
 			data->error = status;
@@ -989,21 +882,9 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd,
 		scratch->status[0] = SPI_TOKEN_STOP_TRAN;
 
 		host->early_status.tx_buf = host->early_status.rx_buf;
-		host->early_status.tx_dma = host->early_status.rx_dma;
 		host->early_status.len = statlen;
 
-		if (host->dma_dev)
-			dma_sync_single_for_device(host->dma_dev,
-					host->data_dma, sizeof(*scratch),
-					DMA_BIDIRECTIONAL);
-
 		tmp = spi_sync_locked(spi, &host->m);
-
-		if (host->dma_dev)
-			dma_sync_single_for_cpu(host->dma_dev,
-					host->data_dma, sizeof(*scratch),
-					DMA_BIDIRECTIONAL);
-
 		if (tmp < 0) {
 			if (!data->error)
 				data->error = tmp;
@@ -1278,52 +1159,6 @@ mmc_spi_detect_irq(int irq, void *mmc)
 	return IRQ_HANDLED;
 }
 
-#ifdef CONFIG_HAS_DMA
-static int mmc_spi_dma_alloc(struct mmc_spi_host *host)
-{
-	struct spi_device *spi = host->spi;
-	struct device *dev;
-
-	if (!spi->master->dev.parent->dma_mask)
-		return 0;
-
-	dev = spi->master->dev.parent;
-
-	host->ones_dma = dma_map_single(dev, host->ones, MMC_SPI_BLOCKSIZE,
-					DMA_TO_DEVICE);
-	if (dma_mapping_error(dev, host->ones_dma))
-		return -ENOMEM;
-
-	host->data_dma = dma_map_single(dev, host->data, sizeof(*host->data),
-					DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(dev, host->data_dma)) {
-		dma_unmap_single(dev, host->ones_dma, MMC_SPI_BLOCKSIZE,
-				 DMA_TO_DEVICE);
-		return -ENOMEM;
-	}
-
-	dma_sync_single_for_cpu(dev, host->data_dma, sizeof(*host->data),
-				DMA_BIDIRECTIONAL);
-
-	host->dma_dev = dev;
-	return 0;
-}
-
-static void mmc_spi_dma_free(struct mmc_spi_host *host)
-{
-	if (!host->dma_dev)
-		return;
-
-	dma_unmap_single(host->dma_dev, host->ones_dma, MMC_SPI_BLOCKSIZE,
-			 DMA_TO_DEVICE);
-	dma_unmap_single(host->dma_dev, host->data_dma,	sizeof(*host->data),
-			 DMA_BIDIRECTIONAL);
-}
-#else
-static inline int mmc_spi_dma_alloc(struct mmc_spi_host *host) { return 0; }
-static inline void mmc_spi_dma_free(struct mmc_spi_host *host) {}
-#endif
-
 static int mmc_spi_probe(struct spi_device *spi)
 {
 	void			*ones;
@@ -1415,24 +1250,17 @@ static int mmc_spi_probe(struct spi_device *spi)
 
 	dev_set_drvdata(&spi->dev, mmc);
 
-	/* preallocate dma buffers */
+	/* Preallocate buffers */
 	host->data = kmalloc(sizeof(*host->data), GFP_KERNEL);
 	if (!host->data)
 		goto fail_nobuf1;
 
-	status = mmc_spi_dma_alloc(host);
-	if (status)
-		goto fail_dma;
-
 	/* setup message for status/busy readback */
 	spi_message_init(&host->readback);
-	host->readback.is_dma_mapped = (host->dma_dev != NULL);
 
 	spi_message_add_tail(&host->status, &host->readback);
 	host->status.tx_buf = host->ones;
-	host->status.tx_dma = host->ones_dma;
 	host->status.rx_buf = &host->data->status;
-	host->status.rx_dma = host->data_dma + offsetof(struct scratch, status);
 	host->status.cs_change = 1;
 
 	/* register card detect irq */
@@ -1477,9 +1305,8 @@ static int mmc_spi_probe(struct spi_device *spi)
 	if (!status)
 		has_ro = true;
 
-	dev_info(&spi->dev, "SD/MMC host %s%s%s%s%s\n",
+	dev_info(&spi->dev, "SD/MMC host %s%s%s%s\n",
 			dev_name(&mmc->class_dev),
-			host->dma_dev ? "" : ", no DMA",
 			has_ro ? "" : ", no WP",
 			(host->pdata && host->pdata->setpower)
 				? "" : ", no poweroff",
@@ -1490,8 +1317,6 @@ static int mmc_spi_probe(struct spi_device *spi)
 fail_gpiod_request:
 	mmc_remove_host(mmc);
 fail_glue_init:
-	mmc_spi_dma_free(host);
-fail_dma:
 	kfree(host->data);
 fail_nobuf1:
 	mmc_free_host(mmc);
@@ -1513,7 +1338,6 @@ static int mmc_spi_remove(struct spi_device *spi)
 
 	mmc_remove_host(mmc);
 
-	mmc_spi_dma_free(host);
 	kfree(host->data);
 	kfree(host->ones);
 
diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c
index 4cceb9bab..e3201a621 100644
--- a/drivers/mmc/host/mmci_stm32_sdmmc.c
+++ b/drivers/mmc/host/mmci_stm32_sdmmc.c
@@ -43,6 +43,9 @@ struct sdmmc_lli_desc {
 struct sdmmc_idma {
 	dma_addr_t sg_dma;
 	void *sg_cpu;
+	dma_addr_t bounce_dma_addr;
+	void *bounce_buf;
+	bool use_bounce_buffer;
 };
 
 struct sdmmc_dlyb {
@@ -54,6 +57,8 @@ struct sdmmc_dlyb {
 static int sdmmc_idma_validate_data(struct mmci_host *host,
 				    struct mmc_data *data)
 {
+	struct sdmmc_idma *idma = host->dma_priv;
+	struct device *dev = mmc_dev(host->mmc);
 	struct scatterlist *sg;
 	int i;
 
@@ -61,41 +66,69 @@ static int sdmmc_idma_validate_data(struct mmci_host *host,
 	 * idma has constraints on idmabase & idmasize for each element
 	 * excepted the last element which has no constraint on idmasize
 	 */
+	idma->use_bounce_buffer = false;
 	for_each_sg(data->sg, sg, data->sg_len - 1, i) {
 		if (!IS_ALIGNED(sg->offset, sizeof(u32)) ||
 		    !IS_ALIGNED(sg->length, SDMMC_IDMA_BURST)) {
-			dev_err(mmc_dev(host->mmc),
+			dev_dbg(mmc_dev(host->mmc),
 				"unaligned scatterlist: ofst:%x length:%d\n",
 				data->sg->offset, data->sg->length);
-			return -EINVAL;
+			goto use_bounce_buffer;
 		}
 	}
 
 	if (!IS_ALIGNED(sg->offset, sizeof(u32))) {
-		dev_err(mmc_dev(host->mmc),
+		dev_dbg(mmc_dev(host->mmc),
 			"unaligned last scatterlist: ofst:%x length:%d\n",
 			data->sg->offset, data->sg->length);
-		return -EINVAL;
+		goto use_bounce_buffer;
 	}
 
 	return 0;
+
+use_bounce_buffer:
+	if (!idma->bounce_buf) {
+		idma->bounce_buf = dmam_alloc_coherent(dev,
+						       host->mmc->max_req_size,
+						       &idma->bounce_dma_addr,
+						       GFP_KERNEL);
+		if (!idma->bounce_buf) {
+			dev_err(dev, "Unable to map allocate DMA bounce buffer.\n");
+			return -ENOMEM;
+		}
+	}
+
+	idma->use_bounce_buffer = true;
+
+	return 0;
 }
 
 static int _sdmmc_idma_prep_data(struct mmci_host *host,
 				 struct mmc_data *data)
 {
-	int n_elem;
+	struct sdmmc_idma *idma = host->dma_priv;
 
-	n_elem = dma_map_sg(mmc_dev(host->mmc),
-			    data->sg,
-			    data->sg_len,
-			    mmc_get_dma_dir(data));
+	if (idma->use_bounce_buffer) {
+		if (data->flags & MMC_DATA_WRITE) {
+			unsigned int xfer_bytes = data->blksz * data->blocks;
 
-	if (!n_elem) {
-		dev_err(mmc_dev(host->mmc), "dma_map_sg failed\n");
-		return -EINVAL;
-	}
+			sg_copy_to_buffer(data->sg, data->sg_len,
+					  idma->bounce_buf, xfer_bytes);
+			dma_wmb();
+		}
+	} else {
+		int n_elem;
 
+		n_elem = dma_map_sg(mmc_dev(host->mmc),
+				    data->sg,
+				    data->sg_len,
+				    mmc_get_dma_dir(data));
+
+		if (!n_elem) {
+			dev_err(mmc_dev(host->mmc), "dma_map_sg failed\n");
+			return -EINVAL;
+		}
+	}
 	return 0;
 }
 
@@ -112,8 +145,19 @@ static int sdmmc_idma_prep_data(struct mmci_host *host,
 static void sdmmc_idma_unprep_data(struct mmci_host *host,
 				   struct mmc_data *data, int err)
 {
-	dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
-		     mmc_get_dma_dir(data));
+	struct sdmmc_idma *idma = host->dma_priv;
+
+	if (idma->use_bounce_buffer) {
+		if (data->flags & MMC_DATA_READ) {
+			unsigned int xfer_bytes = data->blksz * data->blocks;
+
+			sg_copy_from_buffer(data->sg, data->sg_len,
+					    idma->bounce_buf, xfer_bytes);
+		}
+	} else {
+		dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
+			     mmc_get_dma_dir(data));
+	}
 }
 
 static int sdmmc_idma_setup(struct mmci_host *host)
@@ -137,6 +181,8 @@ static int sdmmc_idma_setup(struct mmci_host *host)
 		host->mmc->max_segs = SDMMC_LLI_BUF_LEN /
 			sizeof(struct sdmmc_lli_desc);
 		host->mmc->max_seg_size = host->variant->stm32_idmabsize_mask;
+
+		host->mmc->max_req_size = SZ_1M;
 	} else {
 		host->mmc->max_segs = 1;
 		host->mmc->max_seg_size = host->mmc->max_req_size;
@@ -154,8 +200,18 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl)
 	struct scatterlist *sg;
 	int i;
 
-	if (!host->variant->dma_lli || data->sg_len == 1) {
-		writel_relaxed(sg_dma_address(data->sg),
+	host->dma_in_progress = true;
+
+	if (!host->variant->dma_lli || data->sg_len == 1 ||
+	    idma->use_bounce_buffer) {
+		u32 dma_addr;
+
+		if (idma->use_bounce_buffer)
+			dma_addr = idma->bounce_dma_addr;
+		else
+			dma_addr = sg_dma_address(data->sg);
+
+		writel_relaxed(dma_addr,
 			       host->base + MMCI_STM32_IDMABASE0R);
 		writel_relaxed(MMCI_STM32_IDMAEN,
 			       host->base + MMCI_STM32_IDMACTRLR);
@@ -184,9 +240,30 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl)
 	return 0;
 }
 
+static void sdmmc_idma_error(struct mmci_host *host)
+{
+	struct mmc_data *data = host->data;
+	struct sdmmc_idma *idma = host->dma_priv;
+
+	if (!dma_inprogress(host))
+		return;
+
+	writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR);
+	host->dma_in_progress = false;
+	data->host_cookie = 0;
+
+	if (!idma->use_bounce_buffer)
+		dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
+			     mmc_get_dma_dir(data));
+}
+
 static void sdmmc_idma_finalize(struct mmci_host *host, struct mmc_data *data)
 {
+	if (!dma_inprogress(host))
+		return;
+
 	writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR);
+	host->dma_in_progress = false;
 
 	if (!data->host_cookie)
 		sdmmc_idma_unprep_data(host, data, 0);
@@ -512,6 +589,7 @@ static struct mmci_host_ops sdmmc_variant_ops = {
 	.dma_setup = sdmmc_idma_setup,
 	.dma_start = sdmmc_idma_start,
 	.dma_finalize = sdmmc_idma_finalize,
+	.dma_error = sdmmc_idma_error,
 	.set_clkreg = mmci_sdmmc_set_clkreg,
 	.set_pwrreg = mmci_sdmmc_set_pwrreg,
 	.busy_complete = sdmmc_busy_complete,
diff --git a/drivers/mmc/host/sdhci-xenon-phy.c b/drivers/mmc/host/sdhci-xenon-phy.c
index 03ce57ef4..53bf9870c 100644
--- a/drivers/mmc/host/sdhci-xenon-phy.c
+++ b/drivers/mmc/host/sdhci-xenon-phy.c
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/ktime.h>
+#include <linux/iopoll.h>
 #include <linux/of_address.h>
 
 #include "sdhci-pltfm.h"
@@ -109,6 +110,8 @@
 #define XENON_EMMC_PHY_LOGIC_TIMING_ADJUST	(XENON_EMMC_PHY_REG_BASE + 0x18)
 #define XENON_LOGIC_TIMING_VALUE		0x00AA8977
 
+#define XENON_MAX_PHY_TIMEOUT_LOOPS		100
+
 /*
  * List offset of PHY registers and some special register values
  * in eMMC PHY 5.0 or eMMC PHY 5.1
@@ -216,6 +219,19 @@ static int xenon_alloc_emmc_phy(struct sdhci_host *host)
 	return 0;
 }
 
+static int xenon_check_stability_internal_clk(struct sdhci_host *host)
+{
+	u32 reg;
+	int err;
+
+	err = read_poll_timeout(sdhci_readw, reg, reg & SDHCI_CLOCK_INT_STABLE,
+				1100, 20000, false, host, SDHCI_CLOCK_CONTROL);
+	if (err)
+		dev_err(mmc_dev(host->mmc), "phy_init: Internal clock never stabilized.\n");
+
+	return err;
+}
+
 /*
  * eMMC 5.0/5.1 PHY init/re-init.
  * eMMC PHY init should be executed after:
@@ -232,6 +248,11 @@ static int xenon_emmc_phy_init(struct sdhci_host *host)
 	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
 	struct xenon_emmc_phy_regs *phy_regs = priv->emmc_phy_regs;
 
+	int ret = xenon_check_stability_internal_clk(host);
+
+	if (ret)
+		return ret;
+
 	reg = sdhci_readl(host, phy_regs->timing_adj);
 	reg |= XENON_PHY_INITIALIZAION;
 	sdhci_writel(host, reg, phy_regs->timing_adj);
@@ -259,18 +280,27 @@ static int xenon_emmc_phy_init(struct sdhci_host *host)
 	/* get the wait time */
 	wait /= clock;
 	wait++;
-	/* wait for host eMMC PHY init completes */
-	udelay(wait);
 
-	reg = sdhci_readl(host, phy_regs->timing_adj);
-	reg &= XENON_PHY_INITIALIZAION;
-	if (reg) {
+	/*
+	 * AC5X spec says bit must be polled until zero.
+	 * We see cases in which timeout can take longer
+	 * than the standard calculation on AC5X, which is
+	 * expected following the spec comment above.
+	 * According to the spec, we must wait as long as
+	 * it takes for that bit to toggle on AC5X.
+	 * Cap that with 100 delay loops so we won't get
+	 * stuck here forever:
+	 */
+
+	ret = read_poll_timeout(sdhci_readl, reg,
+				!(reg & XENON_PHY_INITIALIZAION),
+				wait, XENON_MAX_PHY_TIMEOUT_LOOPS * wait,
+				false, host, phy_regs->timing_adj);
+	if (ret)
 		dev_err(mmc_dev(host->mmc), "eMMC PHY init cannot complete after %d us\n",
-			wait);
-		return -ETIMEDOUT;
-	}
+			wait * XENON_MAX_PHY_TIMEOUT_LOOPS);
 
-	return 0;
+	return ret;
 }
 
 #define ARMADA_3700_SOC_PAD_1_8V	0x1
diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c
index abf36acb2..0482920a7 100644
--- a/drivers/mmc/host/tmio_mmc_core.c
+++ b/drivers/mmc/host/tmio_mmc_core.c
@@ -216,6 +216,8 @@ static void tmio_mmc_reset_work(struct work_struct *work)
 	else
 		mrq->cmd->error = -ETIMEDOUT;
 
+	/* No new calls yet, but disallow concurrent tmio_mmc_done_work() */
+	host->mrq = ERR_PTR(-EBUSY);
 	host->cmd = NULL;
 	host->data = NULL;
 
diff --git a/drivers/mmc/host/wmt-sdmmc.c b/drivers/mmc/host/wmt-sdmmc.c
index 393319548..3fcc81e48 100644
--- a/drivers/mmc/host/wmt-sdmmc.c
+++ b/drivers/mmc/host/wmt-sdmmc.c
@@ -889,7 +889,6 @@ static int wmt_mci_remove(struct platform_device *pdev)
 {
 	struct mmc_host *mmc;
 	struct wmt_mci_priv *priv;
-	struct resource *res;
 	u32 reg_tmp;
 
 	mmc = platform_get_drvdata(pdev);
@@ -917,9 +916,6 @@ static int wmt_mci_remove(struct platform_device *pdev)
 	clk_disable_unprepare(priv->clk_sdmmc);
 	clk_put(priv->clk_sdmmc);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(res->start, resource_size(res));
-
 	mmc_free_host(mmc);
 
 	dev_info(&pdev->dev, "WMT MCI device removed\n");