10 files changed, 393 insertions, 411 deletions

diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index eea9cf2..852d5fb 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -81,6 +81,7 @@ struct atmel_mci_caps {
 	bool	has_bad_data_ordering;
 	bool	need_reset_after_xfer;
 	bool	need_blksz_mul_4;
+	bool	need_notbusy_for_read_ops;
 };
 
 struct atmel_mci_dma {
@@ -1625,7 +1626,8 @@ static void atmci_tasklet_func(unsigned long priv)
 				__func__);
 			atmci_set_completed(host, EVENT_XFER_COMPLETE);
 
-			if (host->data->flags & MMC_DATA_WRITE) {
+			if (host->caps.need_notbusy_for_read_ops ||
+			   (host->data->flags & MMC_DATA_WRITE)) {
 				atmci_writel(host, ATMCI_IER, ATMCI_NOTBUSY);
 				state = STATE_WAITING_NOTBUSY;
 			} else if (host->mrq->stop) {
@@ -2218,6 +2220,7 @@ static void __init atmci_get_cap(struct atmel_mci *host)
 	host->caps.has_bad_data_ordering = 1;
 	host->caps.need_reset_after_xfer = 1;
 	host->caps.need_blksz_mul_4 = 1;
+	host->caps.need_notbusy_for_read_ops = 0;
 
 	/* keep only major version number */
 	switch (version & 0xf00) {
@@ -2238,6 +2241,7 @@ static void __init atmci_get_cap(struct atmel_mci *host)
 	case 0x200:
 		host->caps.has_rwproof = 1;
 		host->caps.need_blksz_mul_4 = 0;
+		host->caps.need_notbusy_for_read_ops = 1;
 	case 0x100:
 		host->caps.has_bad_data_ordering = 0;
 		host->caps.need_reset_after_xfer = 0;
diff --git a/drivers/mmc/host/bfin_sdh.c b/drivers/mmc/host/bfin_sdh.c
index 0366617..a17dd73 100644
--- a/drivers/mmc/host/bfin_sdh.c
+++ b/drivers/mmc/host/bfin_sdh.c
@@ -49,13 +49,6 @@
 #define bfin_write_SDH_CFG		bfin_write_RSI_CFG
 #endif
 
-struct dma_desc_array {
-	unsigned long	start_addr;
-	unsigned short	cfg;
-	unsigned short	x_count;
-	short		x_modify;
-} __packed;
-
 struct sdh_host {
 	struct mmc_host		*mmc;
 	spinlock_t		lock;
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 72dc3cd..af40d22 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -627,6 +627,7 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot)
 {
 	struct dw_mci *host = slot->host;
 	u32 div;
+	u32 clk_en_a;
 
 	if (slot->clock != host->current_speed) {
 		div = host->bus_hz / slot->clock;
@@ -659,9 +660,11 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot)
 		mci_send_cmd(slot,
 			     SDMMC_CMD_UPD_CLK | SDMMC_CMD_PRV_DAT_WAIT, 0);
 
-		/* enable clock */
-		mci_writel(host, CLKENA, ((SDMMC_CLKEN_ENABLE |
-			   SDMMC_CLKEN_LOW_PWR) << slot->id));
+		/* enable clock; only low power if no SDIO */
+		clk_en_a = SDMMC_CLKEN_ENABLE << slot->id;
+		if (!(mci_readl(host, INTMASK) & SDMMC_INT_SDIO(slot->id)))
+			clk_en_a |= SDMMC_CLKEN_LOW_PWR << slot->id;
+		mci_writel(host, CLKENA, clk_en_a);
 
 		/* inform CIU */
 		mci_send_cmd(slot,
@@ -862,6 +865,30 @@ static int dw_mci_get_cd(struct mmc_host *mmc)
 	return present;
 }
 
+/*
+ * Disable lower power mode.
+ *
+ * Low power mode will stop the card clock when idle.  According to the
+ * description of the CLKENA register we should disable low power mode
+ * for SDIO cards if we need SDIO interrupts to work.
+ *
+ * This function is fast if low power mode is already disabled.
+ */
+static void dw_mci_disable_low_power(struct dw_mci_slot *slot)
+{
+	struct dw_mci *host = slot->host;
+	u32 clk_en_a;
+	const u32 clken_low_pwr = SDMMC_CLKEN_LOW_PWR << slot->id;
+
+	clk_en_a = mci_readl(host, CLKENA);
+
+	if (clk_en_a & clken_low_pwr) {
+		mci_writel(host, CLKENA, clk_en_a & ~clken_low_pwr);
+		mci_send_cmd(slot, SDMMC_CMD_UPD_CLK |
+			     SDMMC_CMD_PRV_DAT_WAIT, 0);
+	}
+}
+
 static void dw_mci_enable_sdio_irq(struct mmc_host *mmc, int enb)
 {
 	struct dw_mci_slot *slot = mmc_priv(mmc);
@@ -871,6 +898,14 @@ static void dw_mci_enable_sdio_irq(struct mmc_host *mmc, int enb)
 	/* Enable/disable Slot Specific SDIO interrupt */
 	int_mask = mci_readl(host, INTMASK);
 	if (enb) {
+		/*
+		 * Turn off low power mode if it was enabled.  This is a bit of
+		 * a heavy operation and we disable / enable IRQs a lot, so
+		 * we'll leave low power mode disabled and it will get
+		 * re-enabled again in dw_mci_setup_bus().
+		 */
+		dw_mci_disable_low_power(slot);
+
 		mci_writel(host, INTMASK,
 			   (int_mask | SDMMC_INT_SDIO(slot->id)));
 	} else {
@@ -1429,22 +1464,10 @@ static void dw_mci_read_data_pio(struct dw_mci *host)
 			nbytes += len;
 			remain -= len;
 		} while (remain);
-		sg_miter->consumed = offset;
 
+		sg_miter->consumed = offset;
 		status = mci_readl(host, MINTSTS);
 		mci_writel(host, RINTSTS, SDMMC_INT_RXDR);
-		if (status & DW_MCI_DATA_ERROR_FLAGS) {
-			host->data_status = status;
-			data->bytes_xfered += nbytes;
-			sg_miter_stop(sg_miter);
-			host->sg = NULL;
-			smp_wmb();
-
-			set_bit(EVENT_DATA_ERROR, &host->pending_events);
-
-			tasklet_schedule(&host->tasklet);
-			return;
-		}
 	} while (status & SDMMC_INT_RXDR); /*if the RXDR is ready read again*/
 	data->bytes_xfered += nbytes;
 
@@ -1497,23 +1520,10 @@ static void dw_mci_write_data_pio(struct dw_mci *host)
 			nbytes += len;
 			remain -= len;
 		} while (remain);
-		sg_miter->consumed = offset;
 
+		sg_miter->consumed = offset;
 		status = mci_readl(host, MINTSTS);
 		mci_writel(host, RINTSTS, SDMMC_INT_TXDR);
-		if (status & DW_MCI_DATA_ERROR_FLAGS) {
-			host->data_status = status;
-			data->bytes_xfered += nbytes;
-			sg_miter_stop(sg_miter);
-			host->sg = NULL;
-
-			smp_wmb();
-
-			set_bit(EVENT_DATA_ERROR, &host->pending_events);
-
-			tasklet_schedule(&host->tasklet);
-			return;
-		}
 	} while (status & SDMMC_INT_TXDR); /* if TXDR write again */
 	data->bytes_xfered += nbytes;
 
@@ -1547,12 +1557,11 @@ static void dw_mci_cmd_interrupt(struct dw_mci *host, u32 status)
 static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 {
 	struct dw_mci *host = dev_id;
-	u32 status, pending;
+	u32 pending;
 	unsigned int pass_count = 0;
 	int i;
 
 	do {
-		status = mci_readl(host, RINTSTS);
 		pending = mci_readl(host, MINTSTS); /* read-only mask reg */
 
 		/*
@@ -1570,7 +1579,7 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 
 		if (pending & DW_MCI_CMD_ERROR_FLAGS) {
 			mci_writel(host, RINTSTS, DW_MCI_CMD_ERROR_FLAGS);
-			host->cmd_status = status;
+			host->cmd_status = pending;
 			smp_wmb();
 			set_bit(EVENT_CMD_COMPLETE, &host->pending_events);
 		}
@@ -1578,18 +1587,16 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 		if (pending & DW_MCI_DATA_ERROR_FLAGS) {
 			/* if there is an error report DATA_ERROR */
 			mci_writel(host, RINTSTS, DW_MCI_DATA_ERROR_FLAGS);
-			host->data_status = status;
+			host->data_status = pending;
 			smp_wmb();
 			set_bit(EVENT_DATA_ERROR, &host->pending_events);
-			if (!(pending & (SDMMC_INT_DTO | SDMMC_INT_DCRC |
-					 SDMMC_INT_SBE | SDMMC_INT_EBE)))
-				tasklet_schedule(&host->tasklet);
+			tasklet_schedule(&host->tasklet);
 		}
 
 		if (pending & SDMMC_INT_DATA_OVER) {
 			mci_writel(host, RINTSTS, SDMMC_INT_DATA_OVER);
 			if (!host->data_status)
-				host->data_status = status;
+				host->data_status = pending;
 			smp_wmb();
 			if (host->dir_status == DW_MCI_RECV_STATUS) {
 				if (host->sg != NULL)
@@ -1613,7 +1620,7 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 
 		if (pending & SDMMC_INT_CMD_DONE) {
 			mci_writel(host, RINTSTS, SDMMC_INT_CMD_DONE);
-			dw_mci_cmd_interrupt(host, status);
+			dw_mci_cmd_interrupt(host, pending);
 		}
 
 		if (pending & SDMMC_INT_CD) {
diff --git a/drivers/mmc/host/mvsdio.c b/drivers/mmc/host/mvsdio.c
index 3b9136c..a61cb5f 100644
--- a/drivers/mmc/host/mvsdio.c
+++ b/drivers/mmc/host/mvsdio.c
@@ -839,6 +839,10 @@ out:
 	if (r)
 		release_resource(r);
 	if (mmc)
+		if (!IS_ERR_OR_NULL(host->clk)) {
+			clk_disable_unprepare(host->clk);
+			clk_put(host->clk);
+		}
 		mmc_free_host(mmc);
 
 	return ret;
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index a51f930..ad3fcea 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -285,11 +285,11 @@ static irqreturn_t mxs_mmc_irq_handler(int irq, void *dev_id)
 	writel(stat & MXS_MMC_IRQ_BITS,
 	       host->base + HW_SSP_CTRL1(host) + STMP_OFFSET_REG_CLR);
 
+	spin_unlock(&host->lock);
+
 	if ((stat & BM_SSP_CTRL1_SDIO_IRQ) && (stat & BM_SSP_CTRL1_SDIO_IRQ_EN))
 		mmc_signal_sdio_irq(host->mmc);
 
-	spin_unlock(&host->lock);
-
 	if (stat & BM_SSP_CTRL1_RESP_TIMEOUT_IRQ)
 		cmd->error = -ETIMEDOUT;
 	else if (stat & BM_SSP_CTRL1_RESP_ERR_IRQ)
@@ -644,11 +644,6 @@ static void mxs_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable)
 		       host->base + HW_SSP_CTRL0 + STMP_OFFSET_REG_SET);
 		writel(BM_SSP_CTRL1_SDIO_IRQ_EN,
 		       host->base + HW_SSP_CTRL1(host) + STMP_OFFSET_REG_SET);
-
-		if (readl(host->base + HW_SSP_STATUS(host)) &
-				BM_SSP_STATUS_SDIO_IRQ)
-			mmc_signal_sdio_irq(host->mmc);
-
 	} else {
 		writel(BM_SSP_CTRL0_SDIO_IRQ_CHECK,
 		       host->base + HW_SSP_CTRL0 + STMP_OFFSET_REG_CLR);
@@ -657,6 +652,11 @@ static void mxs_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable)
 	}
 
 	spin_unlock_irqrestore(&host->lock, flags);
+
+	if (enable && readl(host->base + HW_SSP_STATUS(host)) &
+			BM_SSP_STATUS_SDIO_IRQ)
+		mmc_signal_sdio_irq(host->mmc);
+
 }
 
 static const struct mmc_host_ops mxs_mmc_ops = {
diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c
index 3e8dcf8..a5999a7 100644
--- a/drivers/mmc/host/omap.c
+++ b/drivers/mmc/host/omap.c
@@ -17,10 +17,12 @@
 #include <linux/ioport.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
+#include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
 #include <linux/delay.h>
 #include <linux/spinlock.h>
 #include <linux/timer.h>
+#include <linux/omap-dma.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/card.h>
 #include <linux/clk.h>
@@ -128,6 +130,10 @@ struct mmc_omap_host {
 	unsigned char		id; /* 16xx chips have 2 MMC blocks */
 	struct clk *		iclk;
 	struct clk *		fclk;
+	struct dma_chan		*dma_rx;
+	u32			dma_rx_burst;
+	struct dma_chan		*dma_tx;
+	u32			dma_tx_burst;
 	struct resource		*mem_res;
 	void __iomem		*virt_base;
 	unsigned int		phys_base;
@@ -153,12 +159,8 @@ struct mmc_omap_host {
 
 	unsigned		use_dma:1;
 	unsigned		brs_received:1, dma_done:1;
-	unsigned		dma_is_read:1;
 	unsigned		dma_in_use:1;
-	int			dma_ch;
 	spinlock_t		dma_lock;
-	struct timer_list	dma_timer;
-	unsigned		dma_len;
 
 	struct mmc_omap_slot    *slots[OMAP_MMC_MAX_SLOTS];
 	struct mmc_omap_slot    *current_slot;
@@ -406,18 +408,25 @@ mmc_omap_release_dma(struct mmc_omap_host *host, struct mmc_data *data,
 		     int abort)
 {
 	enum dma_data_direction dma_data_dir;
+	struct device *dev = mmc_dev(host->mmc);
+	struct dma_chan *c;
 
-	BUG_ON(host->dma_ch < 0);
-	if (data->error)
-		omap_stop_dma(host->dma_ch);
-	/* Release DMA channel lazily */
-	mod_timer(&host->dma_timer, jiffies + HZ);
-	if (data->flags & MMC_DATA_WRITE)
+	if (data->flags & MMC_DATA_WRITE) {
 		dma_data_dir = DMA_TO_DEVICE;
-	else
+		c = host->dma_tx;
+	} else {
 		dma_data_dir = DMA_FROM_DEVICE;
-	dma_unmap_sg(mmc_dev(host->mmc), data->sg, host->sg_len,
-		     dma_data_dir);
+		c = host->dma_rx;
+	}
+	if (c) {
+		if (data->error) {
+			dmaengine_terminate_all(c);
+			/* Claim nothing transferred on error... */
+			data->bytes_xfered = 0;
+		}
+		dev = c->device->dev;
+	}
+	dma_unmap_sg(dev, data->sg, host->sg_len, dma_data_dir);
 }
 
 static void mmc_omap_send_stop_work(struct work_struct *work)
@@ -525,16 +534,6 @@ mmc_omap_end_of_data(struct mmc_omap_host *host, struct mmc_data *data)
 }
 
 static void
-mmc_omap_dma_timer(unsigned long data)
-{
-	struct mmc_omap_host *host = (struct mmc_omap_host *) data;
-
-	BUG_ON(host->dma_ch < 0);
-	omap_free_dma(host->dma_ch);
-	host->dma_ch = -1;
-}
-
-static void
 mmc_omap_dma_done(struct mmc_omap_host *host, struct mmc_data *data)
 {
 	unsigned long flags;
@@ -669,7 +668,7 @@ mmc_omap_clk_timer(unsigned long data)
 static void
 mmc_omap_xfer_data(struct mmc_omap_host *host, int write)
 {
-	int n;
+	int n, nwords;
 
 	if (host->buffer_bytes_left == 0) {
 		host->sg_idx++;
@@ -679,15 +678,23 @@ mmc_omap_xfer_data(struct mmc_omap_host *host, int write)
 	n = 64;
 	if (n > host->buffer_bytes_left)
 		n = host->buffer_bytes_left;
+
+	nwords = n / 2;
+	nwords += n & 1; /* handle odd number of bytes to transfer */
+
 	host->buffer_bytes_left -= n;
 	host->total_bytes_left -= n;
 	host->data->bytes_xfered += n;
 
 	if (write) {
-		__raw_writesw(host->virt_base + OMAP_MMC_REG(host, DATA), host->buffer, n);
+		__raw_writesw(host->virt_base + OMAP_MMC_REG(host, DATA),
+			      host->buffer, nwords);
 	} else {
-		__raw_readsw(host->virt_base + OMAP_MMC_REG(host, DATA), host->buffer, n);
+		__raw_readsw(host->virt_base + OMAP_MMC_REG(host, DATA),
+			     host->buffer, nwords);
 	}
+
+	host->buffer += nwords;
 }
 
 static inline void mmc_omap_report_irq(u16 status)
@@ -891,159 +898,15 @@ static void mmc_omap_cover_handler(unsigned long param)
 		  jiffies + msecs_to_jiffies(OMAP_MMC_COVER_POLL_DELAY));
 }
 
-/* Prepare to transfer the next segment of a scatterlist */
-static void
-mmc_omap_prepare_dma(struct mmc_omap_host *host, struct mmc_data *data)
-{
-	int dma_ch = host->dma_ch;
-	unsigned long data_addr;
-	u16 buf, frame;
-	u32 count;
-	struct scatterlist *sg = &data->sg[host->sg_idx];
-	int src_port = 0;
-	int dst_port = 0;
-	int sync_dev = 0;
-
-	data_addr = host->phys_base + OMAP_MMC_REG(host, DATA);
-	frame = data->blksz;
-	count = sg_dma_len(sg);
-
-	if ((data->blocks == 1) && (count > data->blksz))
-		count = frame;
-
-	host->dma_len = count;
-
-	/* FIFO is 16x2 bytes on 15xx, and 32x2 bytes on 16xx and 24xx.
-	 * Use 16 or 32 word frames when the blocksize is at least that large.
-	 * Blocksize is usually 512 bytes; but not for some SD reads.
-	 */
-	if (cpu_is_omap15xx() && frame > 32)
-		frame = 32;
-	else if (frame > 64)
-		frame = 64;
-	count /= frame;
-	frame >>= 1;
-
-	if (!(data->flags & MMC_DATA_WRITE)) {
-		buf = 0x800f | ((frame - 1) << 8);
-
-		if (cpu_class_is_omap1()) {
-			src_port = OMAP_DMA_PORT_TIPB;
-			dst_port = OMAP_DMA_PORT_EMIFF;
-		}
-		if (cpu_is_omap24xx())
-			sync_dev = OMAP24XX_DMA_MMC1_RX;
-
-		omap_set_dma_src_params(dma_ch, src_port,
-					OMAP_DMA_AMODE_CONSTANT,
-					data_addr, 0, 0);
-		omap_set_dma_dest_params(dma_ch, dst_port,
-					 OMAP_DMA_AMODE_POST_INC,
-					 sg_dma_address(sg), 0, 0);
-		omap_set_dma_dest_data_pack(dma_ch, 1);
-		omap_set_dma_dest_burst_mode(dma_ch, OMAP_DMA_DATA_BURST_4);
-	} else {
-		buf = 0x0f80 | ((frame - 1) << 0);
-
-		if (cpu_class_is_omap1()) {
-			src_port = OMAP_DMA_PORT_EMIFF;
-			dst_port = OMAP_DMA_PORT_TIPB;
-		}
-		if (cpu_is_omap24xx())
-			sync_dev = OMAP24XX_DMA_MMC1_TX;
-
-		omap_set_dma_dest_params(dma_ch, dst_port,
-					 OMAP_DMA_AMODE_CONSTANT,
-					 data_addr, 0, 0);
-		omap_set_dma_src_params(dma_ch, src_port,
-					OMAP_DMA_AMODE_POST_INC,
-					sg_dma_address(sg), 0, 0);
-		omap_set_dma_src_data_pack(dma_ch, 1);
-		omap_set_dma_src_burst_mode(dma_ch, OMAP_DMA_DATA_BURST_4);
-	}
-
-	/* Max limit for DMA frame count is 0xffff */
-	BUG_ON(count > 0xffff);
-
-	OMAP_MMC_WRITE(host, BUF, buf);
-	omap_set_dma_transfer_params(dma_ch, OMAP_DMA_DATA_TYPE_S16,
-				     frame, count, OMAP_DMA_SYNC_FRAME,
-				     sync_dev, 0);
-}
-
-/* A scatterlist segment completed */
-static void mmc_omap_dma_cb(int lch, u16 ch_status, void *data)
+static void mmc_omap_dma_callback(void *priv)
 {
-	struct mmc_omap_host *host = (struct mmc_omap_host *) data;
-	struct mmc_data *mmcdat = host->data;
+	struct mmc_omap_host *host = priv;
+	struct mmc_data *data = host->data;
 
-	if (unlikely(host->dma_ch < 0)) {
-		dev_err(mmc_dev(host->mmc),
-			"DMA callback while DMA not enabled\n");
-		return;
-	}
-	/* FIXME: We really should do something to _handle_ the errors */
-	if (ch_status & OMAP1_DMA_TOUT_IRQ) {
-		dev_err(mmc_dev(host->mmc),"DMA timeout\n");
-		return;
-	}
-	if (ch_status & OMAP_DMA_DROP_IRQ) {
-		dev_err(mmc_dev(host->mmc), "DMA sync error\n");
-		return;
-	}
-	if (!(ch_status & OMAP_DMA_BLOCK_IRQ)) {
-		return;
-	}
-	mmcdat->bytes_xfered += host->dma_len;
-	host->sg_idx++;
-	if (host->sg_idx < host->sg_len) {
-		mmc_omap_prepare_dma(host, host->data);
-		omap_start_dma(host->dma_ch);
-	} else
-		mmc_omap_dma_done(host, host->data);
-}
-
-static int mmc_omap_get_dma_channel(struct mmc_omap_host *host, struct mmc_data *data)
-{
-	const char *dma_dev_name;
-	int sync_dev, dma_ch, is_read, r;
-
-	is_read = !(data->flags & MMC_DATA_WRITE);
-	del_timer_sync(&host->dma_timer);
-	if (host->dma_ch >= 0) {
-		if (is_read == host->dma_is_read)
-			return 0;
-		omap_free_dma(host->dma_ch);
-		host->dma_ch = -1;
-	}
-
-	if (is_read) {
-		if (host->id == 0) {
-			sync_dev = OMAP_DMA_MMC_RX;
-			dma_dev_name = "MMC1 read";
-		} else {
-			sync_dev = OMAP_DMA_MMC2_RX;
-			dma_dev_name = "MMC2 read";
-		}
-	} else {
-		if (host->id == 0) {
-			sync_dev = OMAP_DMA_MMC_TX;
-			dma_dev_name = "MMC1 write";
-		} else {
-			sync_dev = OMAP_DMA_MMC2_TX;
-			dma_dev_name = "MMC2 write";
-		}
-	}
-	r = omap_request_dma(sync_dev, dma_dev_name, mmc_omap_dma_cb,
-			     host, &dma_ch);
-	if (r != 0) {
-		dev_dbg(mmc_dev(host->mmc), "omap_request_dma() failed with %d\n", r);
-		return r;
-	}
-	host->dma_ch = dma_ch;
-	host->dma_is_read = is_read;
+	/* If we got to the end of DMA, assume everything went well */
+	data->bytes_xfered += data->blocks * data->blksz;
 
-	return 0;
+	mmc_omap_dma_done(host, data);
 }
 
 static inline void set_cmd_timeout(struct mmc_omap_host *host, struct mmc_request *req)
@@ -1118,33 +981,85 @@ mmc_omap_prepare_data(struct mmc_omap_host *host, struct mmc_request *req)
 
 	host->sg_idx = 0;
 	if (use_dma) {
-		if (mmc_omap_get_dma_channel(host, data) == 0) {
-			enum dma_data_direction dma_data_dir;
-
-			if (data->flags & MMC_DATA_WRITE)
-				dma_data_dir = DMA_TO_DEVICE;
-			else
-				dma_data_dir = DMA_FROM_DEVICE;
-
-			host->sg_len = dma_map_sg(mmc_dev(host->mmc), data->sg,
-						sg_len, dma_data_dir);
-			host->total_bytes_left = 0;
-			mmc_omap_prepare_dma(host, req->data);
-			host->brs_received = 0;
-			host->dma_done = 0;
-			host->dma_in_use = 1;
-		} else
-			use_dma = 0;
+		enum dma_data_direction dma_data_dir;
+		struct dma_async_tx_descriptor *tx;
+		struct dma_chan *c;
+		u32 burst, *bp;
+		u16 buf;
+
+		/*
+		 * FIFO is 16x2 bytes on 15xx, and 32x2 bytes on 16xx
+		 * and 24xx. Use 16 or 32 word frames when the
+		 * blocksize is at least that large. Blocksize is
+		 * usually 512 bytes; but not for some SD reads.
+		 */
+		burst = cpu_is_omap15xx() ? 32 : 64;
+		if (burst > data->blksz)
+			burst = data->blksz;
+
+		burst >>= 1;
+
+		if (data->flags & MMC_DATA_WRITE) {
+			c = host->dma_tx;
+			bp = &host->dma_tx_burst;
+			buf = 0x0f80 | (burst - 1) << 0;
+			dma_data_dir = DMA_TO_DEVICE;
+		} else {
+			c = host->dma_rx;
+			bp = &host->dma_rx_burst;
+			buf = 0x800f | (burst - 1) << 8;
+			dma_data_dir = DMA_FROM_DEVICE;
+		}
+
+		if (!c)
+			goto use_pio;
+
+		/* Only reconfigure if we have a different burst size */
+		if (*bp != burst) {
+			struct dma_slave_config cfg;
+
+			cfg.src_addr = host->phys_base + OMAP_MMC_REG(host, DATA);
+			cfg.dst_addr = host->phys_base + OMAP_MMC_REG(host, DATA);
+			cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+			cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+			cfg.src_maxburst = burst;
+			cfg.dst_maxburst = burst;
+
+			if (dmaengine_slave_config(c, &cfg))
+				goto use_pio;
+
+			*bp = burst;
+		}
+
+		host->sg_len = dma_map_sg(c->device->dev, data->sg, sg_len,
+					  dma_data_dir);
+		if (host->sg_len == 0)
+			goto use_pio;
+
+		tx = dmaengine_prep_slave_sg(c, data->sg, host->sg_len,
+			data->flags & MMC_DATA_WRITE ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM,
+			DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+		if (!tx)
+			goto use_pio;
+
+		OMAP_MMC_WRITE(host, BUF, buf);
+
+		tx->callback = mmc_omap_dma_callback;
+		tx->callback_param = host;
+		dmaengine_submit(tx);
+		host->brs_received = 0;
+		host->dma_done = 0;
+		host->dma_in_use = 1;
+		return;
 	}
+ use_pio:
 
 	/* Revert to PIO? */
-	if (!use_dma) {
-		OMAP_MMC_WRITE(host, BUF, 0x1f1f);
-		host->total_bytes_left = data->blocks * block_size;
-		host->sg_len = sg_len;
-		mmc_omap_sg_to_buf(host);
-		host->dma_in_use = 0;
-	}
+	OMAP_MMC_WRITE(host, BUF, 0x1f1f);
+	host->total_bytes_left = data->blocks * block_size;
+	host->sg_len = sg_len;
+	mmc_omap_sg_to_buf(host);
+	host->dma_in_use = 0;
 }
 
 static void mmc_omap_start_request(struct mmc_omap_host *host,
@@ -1157,8 +1072,12 @@ static void mmc_omap_start_request(struct mmc_omap_host *host,
 	/* only touch fifo AFTER the controller readies it */
 	mmc_omap_prepare_data(host, req);
 	mmc_omap_start_command(host, req->cmd);
-	if (host->dma_in_use)
-		omap_start_dma(host->dma_ch);
+	if (host->dma_in_use) {
+		struct dma_chan *c = host->data->flags & MMC_DATA_WRITE ?
+				host->dma_tx : host->dma_rx;
+
+		dma_async_issue_pending(c);
+	}
 }
 
 static void mmc_omap_request(struct mmc_host *mmc, struct mmc_request *req)
@@ -1400,6 +1319,8 @@ static int __devinit mmc_omap_probe(struct platform_device *pdev)
 	struct omap_mmc_platform_data *pdata = pdev->dev.platform_data;
 	struct mmc_omap_host *host = NULL;
 	struct resource *res;
+	dma_cap_mask_t mask;
+	unsigned sig;
 	int i, ret = 0;
 	int irq;
 
@@ -1439,7 +1360,6 @@ static int __devinit mmc_omap_probe(struct platform_device *pdev)
 	setup_timer(&host->clk_timer, mmc_omap_clk_timer, (unsigned long) host);
 
 	spin_lock_init(&host->dma_lock);
-	setup_timer(&host->dma_timer, mmc_omap_dma_timer, (unsigned long) host);
 	spin_lock_init(&host->slot_lock);
 	init_waitqueue_head(&host->slot_wq);
 
@@ -1450,11 +1370,7 @@ static int __devinit mmc_omap_probe(struct platform_device *pdev)
 	host->id = pdev->id;
 	host->mem_res = res;
 	host->irq = irq;
-
 	host->use_dma = 1;
-	host->dev->dma_mask = &pdata->dma_mask;
-	host->dma_ch = -1;
-
 	host->irq = irq;
 	host->phys_base = host->mem_res->start;
 	host->virt_base = ioremap(res->start, resource_size(res));
@@ -1474,9 +1390,48 @@ static int __devinit mmc_omap_probe(struct platform_device *pdev)
 		goto err_free_iclk;
 	}
 
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+
+	host->dma_tx_burst = -1;
+	host->dma_rx_burst = -1;
+
+	if (cpu_is_omap24xx())
+		sig = host->id == 0 ? OMAP24XX_DMA_MMC1_TX : OMAP24XX_DMA_MMC2_TX;
+	else
+		sig = host->id == 0 ? OMAP_DMA_MMC_TX : OMAP_DMA_MMC2_TX;
+	host->dma_tx = dma_request_channel(mask, omap_dma_filter_fn, &sig);
+#if 0
+	if (!host->dma_tx) {
+		dev_err(host->dev, "unable to obtain TX DMA engine channel %u\n",
+			sig);
+		goto err_dma;
+	}
+#else
+	if (!host->dma_tx)
+		dev_warn(host->dev, "unable to obtain TX DMA engine channel %u\n",
+			sig);
+#endif
+	if (cpu_is_omap24xx())
+		sig = host->id == 0 ? OMAP24XX_DMA_MMC1_RX : OMAP24XX_DMA_MMC2_RX;
+	else
+		sig = host->id == 0 ? OMAP_DMA_MMC_RX : OMAP_DMA_MMC2_RX;
+	host->dma_rx = dma_request_channel(mask, omap_dma_filter_fn, &sig);
+#if 0
+	if (!host->dma_rx) {
+		dev_err(host->dev, "unable to obtain RX DMA engine channel %u\n",
+			sig);
+		goto err_dma;
+	}
+#else
+	if (!host->dma_rx)
+		dev_warn(host->dev, "unable to obtain RX DMA engine channel %u\n",
+			sig);
+#endif
+
 	ret = request_irq(host->irq, mmc_omap_irq, 0, DRIVER_NAME, host);
 	if (ret)
-		goto err_free_fclk;
+		goto err_free_dma;
 
 	if (pdata->init != NULL) {
 		ret = pdata->init(&pdev->dev);
@@ -1510,7 +1465,11 @@ err_plat_cleanup:
 		pdata->cleanup(&pdev->dev);
 err_free_irq:
 	free_irq(host->irq, host);
-err_free_fclk:
+err_free_dma:
+	if (host->dma_tx)
+		dma_release_channel(host->dma_tx);
+	if (host->dma_rx)
+		dma_release_channel(host->dma_rx);
 	clk_put(host->fclk);
 err_free_iclk:
 	clk_disable(host->iclk);
@@ -1545,6 +1504,11 @@ static int __devexit mmc_omap_remove(struct platform_device *pdev)
 	clk_disable(host->iclk);
 	clk_put(host->iclk);
 
+	if (host->dma_tx)
+		dma_release_channel(host->dma_tx);
+	if (host->dma_rx)
+		dma_release_channel(host->dma_rx);
+
 	iounmap(host->virt_base);
 	release_mem_region(pdev->resource[0].start,
 			   pdev->resource[0].end - pdev->resource[0].start + 1);
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 9684538..686e256 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/debugfs.h>
+#include <linux/dmaengine.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
@@ -29,6 +30,7 @@
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 #include <linux/of_device.h>
+#include <linux/omap-dma.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/core.h>
 #include <linux/mmc/mmc.h>
@@ -37,7 +39,6 @@
 #include <linux/gpio.h>
 #include <linux/regulator/consumer.h>
 #include <linux/pm_runtime.h>
-#include <plat/dma.h>
 #include <mach/hardware.h>
 #include <plat/board.h>
 #include <plat/mmc.h>
@@ -166,7 +167,8 @@ struct omap_hsmmc_host {
 	int			suspended;
 	int			irq;
 	int			use_dma, dma_ch;
-	int			dma_line_tx, dma_line_rx;
+	struct dma_chan		*tx_chan;
+	struct dma_chan		*rx_chan;
 	int			slot_id;
 	int			response_busy;
 	int			context_loss;
@@ -797,6 +799,12 @@ omap_hsmmc_get_dma_dir(struct omap_hsmmc_host *host, struct mmc_data *data)
 		return DMA_FROM_DEVICE;
 }
 
+static struct dma_chan *omap_hsmmc_get_dma_chan(struct omap_hsmmc_host *host,
+	struct mmc_data *data)
+{
+	return data->flags & MMC_DATA_WRITE ? host->tx_chan : host->rx_chan;
+}
+
 static void omap_hsmmc_request_done(struct omap_hsmmc_host *host, struct mmc_request *mrq)
 {
 	int dma_ch;
@@ -889,10 +897,13 @@ static void omap_hsmmc_dma_cleanup(struct omap_hsmmc_host *host, int errno)
 	spin_unlock_irqrestore(&host->irq_lock, flags);
 
 	if (host->use_dma && dma_ch != -1) {
-		dma_unmap_sg(mmc_dev(host->mmc), host->data->sg,
-			host->data->sg_len,
+		struct dma_chan *chan = omap_hsmmc_get_dma_chan(host, host->data);
+
+		dmaengine_terminate_all(chan);
+		dma_unmap_sg(chan->device->dev,
+			host->data->sg, host->data->sg_len,
 			omap_hsmmc_get_dma_dir(host, host->data));
-		omap_free_dma(dma_ch);
+
 		host->data->host_cookie = 0;
 	}
 	host->data = NULL;
@@ -1190,90 +1201,29 @@ static irqreturn_t omap_hsmmc_detect(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int omap_hsmmc_get_dma_sync_dev(struct omap_hsmmc_host *host,
-				     struct mmc_data *data)
-{
-	int sync_dev;
-
-	if (data->flags & MMC_DATA_WRITE)
-		sync_dev = host->dma_line_tx;
-	else
-		sync_dev = host->dma_line_rx;
-	return sync_dev;
-}
-
-static void omap_hsmmc_config_dma_params(struct omap_hsmmc_host *host,
-				       struct mmc_data *data,
-				       struct scatterlist *sgl)
-{
-	int blksz, nblk, dma_ch;
-
-	dma_ch = host->dma_ch;
-	if (data->flags & MMC_DATA_WRITE) {
-		omap_set_dma_dest_params(dma_ch, 0, OMAP_DMA_AMODE_CONSTANT,
-			(host->mapbase + OMAP_HSMMC_DATA), 0, 0);
-		omap_set_dma_src_params(dma_ch, 0, OMAP_DMA_AMODE_POST_INC,
-			sg_dma_address(sgl), 0, 0);
-	} else {
-		omap_set_dma_src_params(dma_ch, 0, OMAP_DMA_AMODE_CONSTANT,
-			(host->mapbase + OMAP_HSMMC_DATA), 0, 0);
-		omap_set_dma_dest_params(dma_ch, 0, OMAP_DMA_AMODE_POST_INC,
-			sg_dma_address(sgl), 0, 0);
-	}
-
-	blksz = host->data->blksz;
-	nblk = sg_dma_len(sgl) / blksz;
-
-	omap_set_dma_transfer_params(dma_ch, OMAP_DMA_DATA_TYPE_S32,
-			blksz / 4, nblk, OMAP_DMA_SYNC_FRAME,
-			omap_hsmmc_get_dma_sync_dev(host, data),
-			!(data->flags & MMC_DATA_WRITE));
-
-	omap_start_dma(dma_ch);
-}
-
-/*
- * DMA call back function
- */
-static void omap_hsmmc_dma_cb(int lch, u16 ch_status, void *cb_data)
+static void omap_hsmmc_dma_callback(void *param)
 {
-	struct omap_hsmmc_host *host = cb_data;
+	struct omap_hsmmc_host *host = param;
+	struct dma_chan *chan;
 	struct mmc_data *data;
-	int dma_ch, req_in_progress;
-	unsigned long flags;
-
-	if (!(ch_status & OMAP_DMA_BLOCK_IRQ)) {
-		dev_warn(mmc_dev(host->mmc), "unexpected dma status %x\n",
-			ch_status);
-		return;
-	}
+	int req_in_progress;
 
-	spin_lock_irqsave(&host->irq_lock, flags);
+	spin_lock_irq(&host->irq_lock);
 	if (host->dma_ch < 0) {
-		spin_unlock_irqrestore(&host->irq_lock, flags);
+		spin_unlock_irq(&host->irq_lock);
 		return;
 	}
 
 	data = host->mrq->data;
-	host->dma_sg_idx++;
-	if (host->dma_sg_idx < host->dma_len) {
-		/* Fire up the next transfer. */
-		omap_hsmmc_config_dma_params(host, data,
-					   data->sg + host->dma_sg_idx);
-		spin_unlock_irqrestore(&host->irq_lock, flags);
-		return;
-	}
-
+	chan = omap_hsmmc_get_dma_chan(host, data);
 	if (!data->host_cookie)
-		dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
+		dma_unmap_sg(chan->device->dev,
+			     data->sg, data->sg_len,
 			     omap_hsmmc_get_dma_dir(host, data));
 
 	req_in_progress = host->req_in_progress;
-	dma_ch = host->dma_ch;
 	host->dma_ch = -1;
-	spin_unlock_irqrestore(&host->irq_lock, flags);
-
-	omap_free_dma(dma_ch);
+	spin_unlock_irq(&host->irq_lock);
 
 	/* If DMA has finished after TC, complete the request */
 	if (!req_in_progress) {
@@ -1286,7 +1236,8 @@ static void omap_hsmmc_dma_cb(int lch, u16 ch_status, void *cb_data)
 
 static int omap_hsmmc_pre_dma_transfer(struct omap_hsmmc_host *host,
 				       struct mmc_data *data,
-				       struct omap_hsmmc_next *next)
+				       struct omap_hsmmc_next *next,
+				       struct dma_chan *chan)
 {
 	int dma_len;
 
@@ -1301,8 +1252,7 @@ static int omap_hsmmc_pre_dma_transfer(struct omap_hsmmc_host *host,
 	/* Check if next job is already prepared */
 	if (next ||
 	    (!next && data->host_cookie != host->next_data.cookie)) {
-		dma_len = dma_map_sg(mmc_dev(host->mmc), data->sg,
-				     data->sg_len,
+		dma_len = dma_map_sg(chan->device->dev, data->sg, data->sg_len,
 				     omap_hsmmc_get_dma_dir(host, data));
 
 	} else {
@@ -1329,8 +1279,11 @@ static int omap_hsmmc_pre_dma_transfer(struct omap_hsmmc_host *host,
 static int omap_hsmmc_start_dma_transfer(struct omap_hsmmc_host *host,
 					struct mmc_request *req)
 {
-	int dma_ch = 0, ret = 0, i;
+	struct dma_slave_config cfg;
+	struct dma_async_tx_descriptor *tx;
+	int ret = 0, i;
 	struct mmc_data *data = req->data;
+	struct dma_chan *chan;
 
 	/* Sanity check: all the SG entries must be aligned by block size. */
 	for (i = 0; i < data->sg_len; i++) {
@@ -1348,22 +1301,41 @@ static int omap_hsmmc_start_dma_transfer(struct omap_hsmmc_host *host,
 
 	BUG_ON(host->dma_ch != -1);
 
-	ret = omap_request_dma(omap_hsmmc_get_dma_sync_dev(host, data),
-			       "MMC/SD", omap_hsmmc_dma_cb, host, &dma_ch);
-	if (ret != 0) {
-		dev_err(mmc_dev(host->mmc),
-			"%s: omap_request_dma() failed with %d\n",
-			mmc_hostname(host->mmc), ret);
+	chan = omap_hsmmc_get_dma_chan(host, data);
+
+	cfg.src_addr = host->mapbase + OMAP_HSMMC_DATA;
+	cfg.dst_addr = host->mapbase + OMAP_HSMMC_DATA;
+	cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	cfg.src_maxburst = data->blksz / 4;
+	cfg.dst_maxburst = data->blksz / 4;
+
+	ret = dmaengine_slave_config(chan, &cfg);
+	if (ret)
 		return ret;
-	}
-	ret = omap_hsmmc_pre_dma_transfer(host, data, NULL);
+
+	ret = omap_hsmmc_pre_dma_transfer(host, data, NULL, chan);
 	if (ret)
 		return ret;
 
-	host->dma_ch = dma_ch;
-	host->dma_sg_idx = 0;
+	tx = dmaengine_prep_slave_sg(chan, data->sg, data->sg_len,
+		data->flags & MMC_DATA_WRITE ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM,
+		DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!tx) {
+		dev_err(mmc_dev(host->mmc), "prep_slave_sg() failed\n");
+		/* FIXME: cleanup */
+		return -1;
+	}
+
+	tx->callback = omap_hsmmc_dma_callback;
+	tx->callback_param = host;
 
-	omap_hsmmc_config_dma_params(host, data, data->sg);
+	/* Does not fail */
+	dmaengine_submit(tx);
+
+	host->dma_ch = 1;
+
+	dma_async_issue_pending(chan);
 
 	return 0;
 }
@@ -1445,11 +1417,11 @@ static void omap_hsmmc_post_req(struct mmc_host *mmc, struct mmc_request *mrq,
 	struct omap_hsmmc_host *host = mmc_priv(mmc);
 	struct mmc_data *data = mrq->data;
 
-	if (host->use_dma) {
-		if (data->host_cookie)
-			dma_unmap_sg(mmc_dev(host->mmc), data->sg,
-				     data->sg_len,
-				     omap_hsmmc_get_dma_dir(host, data));
+	if (host->use_dma && data->host_cookie) {
+		struct dma_chan *c = omap_hsmmc_get_dma_chan(host, data);
+
+		dma_unmap_sg(c->device->dev, data->sg, data->sg_len,
+			     omap_hsmmc_get_dma_dir(host, data));
 		data->host_cookie = 0;
 	}
 }
@@ -1464,10 +1436,13 @@ static void omap_hsmmc_pre_req(struct mmc_host *mmc, struct mmc_request *mrq,
 		return ;
 	}
 
-	if (host->use_dma)
+	if (host->use_dma) {
+		struct dma_chan *c = omap_hsmmc_get_dma_chan(host, mrq->data);
+
 		if (omap_hsmmc_pre_dma_transfer(host, mrq->data,
-						&host->next_data))
+						&host->next_data, c))
 			mrq->data->host_cookie = 0;
+	}
 }
 
 /*
@@ -1800,6 +1775,8 @@ static int __devinit omap_hsmmc_probe(struct platform_device *pdev)
 	struct resource *res;
 	int ret, irq;
 	const struct of_device_id *match;
+	dma_cap_mask_t mask;
+	unsigned tx_req, rx_req;
 
 	match = of_match_device(of_match_ptr(omap_mmc_of_match), &pdev->dev);
 	if (match) {
@@ -1844,7 +1821,6 @@ static int __devinit omap_hsmmc_probe(struct platform_device *pdev)
 	host->pdata	= pdata;
 	host->dev	= &pdev->dev;
 	host->use_dma	= 1;
-	host->dev->dma_mask = &pdata->dma_mask;
 	host->dma_ch	= -1;
 	host->irq	= irq;
 	host->slot_id	= 0;
@@ -1934,7 +1910,7 @@ static int __devinit omap_hsmmc_probe(struct platform_device *pdev)
 		ret = -ENXIO;
 		goto err_irq;
 	}
-	host->dma_line_tx = res->start;
+	tx_req = res->start;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_DMA, "rx");
 	if (!res) {
@@ -1942,7 +1918,24 @@ static int __devinit omap_hsmmc_probe(struct platform_device *pdev)
 		ret = -ENXIO;
 		goto err_irq;
 	}
-	host->dma_line_rx = res->start;
+	rx_req = res->start;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+
+	host->rx_chan = dma_request_channel(mask, omap_dma_filter_fn, &rx_req);
+	if (!host->rx_chan) {
+		dev_err(mmc_dev(host->mmc), "unable to obtain RX DMA engine channel %u\n", rx_req);
+		ret = -ENXIO;
+		goto err_irq;
+	}
+
+	host->tx_chan = dma_request_channel(mask, omap_dma_filter_fn, &tx_req);
+	if (!host->tx_chan) {
+		dev_err(mmc_dev(host->mmc), "unable to obtain TX DMA engine channel %u\n", tx_req);
+		ret = -ENXIO;
+		goto err_irq;
+	}
 
 	/* Request IRQ for MMC operations */
 	ret = request_irq(host->irq, omap_hsmmc_irq, 0,
@@ -2021,6 +2014,10 @@ err_reg:
 err_irq_cd_init:
 	free_irq(host->irq, host);
 err_irq:
+	if (host->tx_chan)
+		dma_release_channel(host->tx_chan);
+	if (host->rx_chan)
+		dma_release_channel(host->rx_chan);
 	pm_runtime_put_sync(host->dev);
 	pm_runtime_disable(host->dev);
 	clk_put(host->fclk);
@@ -2056,6 +2053,11 @@ static int __devexit omap_hsmmc_remove(struct platform_device *pdev)
 	if (mmc_slot(host).card_detect_irq)
 		free_irq(mmc_slot(host).card_detect_irq, host);
 
+	if (host->tx_chan)
+		dma_release_channel(host->tx_chan);
+	if (host->rx_chan)
+		dma_release_channel(host->rx_chan);
+
 	pm_runtime_put_sync(host->dev);
 	pm_runtime_disable(host->dev);
 	clk_put(host->fclk);
diff --git a/drivers/mmc/host/sdhci-esdhc.h b/drivers/mmc/host/sdhci-esdhc.h
index b97b2f5..d25f9ab 100644
--- a/drivers/mmc/host/sdhci-esdhc.h
+++ b/drivers/mmc/host/sdhci-esdhc.h
@@ -48,14 +48,14 @@ static inline void esdhc_set_clock(struct sdhci_host *host, unsigned int clock)
 	int div = 1;
 	u32 temp;
 
+	if (clock == 0)
+		goto out;
+
 	temp = sdhci_readl(host, ESDHC_SYSTEM_CONTROL);
 	temp &= ~(ESDHC_CLOCK_IPGEN | ESDHC_CLOCK_HCKEN | ESDHC_CLOCK_PEREN
 		| ESDHC_CLOCK_MASK);
 	sdhci_writel(host, temp, ESDHC_SYSTEM_CONTROL);
 
-	if (clock == 0)
-		goto out;
-
 	while (host->max_clk / pre_div / 16 > clock && pre_div < 256)
 		pre_div *= 2;
 
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index b2af713..5d81427 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -213,8 +213,6 @@ struct sh_mmcif_host {
 	struct mmc_host *mmc;
 	struct mmc_request *mrq;
 	struct platform_device *pd;
-	struct sh_dmae_slave dma_slave_tx;
-	struct sh_dmae_slave dma_slave_rx;
 	struct clk *hclk;
 	unsigned int clk;
 	int bus_width;
@@ -373,59 +371,69 @@ static void sh_mmcif_start_dma_tx(struct sh_mmcif_host *host)
 		desc, cookie);
 }
 
-static bool sh_mmcif_filter(struct dma_chan *chan, void *arg)
-{
-	dev_dbg(chan->device->dev, "%s: slave data %p\n", __func__, arg);
-	chan->private = arg;
-	return true;
-}
-
 static void sh_mmcif_request_dma(struct sh_mmcif_host *host,
 				 struct sh_mmcif_plat_data *pdata)
 {
-	struct sh_dmae_slave *tx, *rx;
+	struct resource *res = platform_get_resource(host->pd, IORESOURCE_MEM, 0);
+	struct dma_slave_config cfg;
+	dma_cap_mask_t mask;
+	int ret;
+
 	host->dma_active = false;
 
 	if (!pdata)
 		return;
 
+	if (pdata->slave_id_tx <= 0 || pdata->slave_id_rx <= 0)
+		return;
+
 	/* We can only either use DMA for both Tx and Rx or not use it at all */
-	if (pdata->dma) {
-		dev_warn(&host->pd->dev,
-			 "Update your platform to use embedded DMA slave IDs\n");
-		tx = &pdata->dma->chan_priv_tx;
-		rx = &pdata->dma->chan_priv_rx;
-	} else {
-		tx = &host->dma_slave_tx;
-		tx->slave_id = pdata->slave_id_tx;
-		rx = &host->dma_slave_rx;
-		rx->slave_id = pdata->slave_id_rx;
-	}
-	if (tx->slave_id > 0 && rx->slave_id > 0) {
-		dma_cap_mask_t mask;
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
 
-		dma_cap_zero(mask);
-		dma_cap_set(DMA_SLAVE, mask);
+	host->chan_tx = dma_request_channel(mask, shdma_chan_filter,
+					    (void *)pdata->slave_id_tx);
+	dev_dbg(&host->pd->dev, "%s: TX: got channel %p\n", __func__,
+		host->chan_tx);
 
-		host->chan_tx = dma_request_channel(mask, sh_mmcif_filter, tx);
-		dev_dbg(&host->pd->dev, "%s: TX: got channel %p\n", __func__,
-			host->chan_tx);
+	if (!host->chan_tx)
+		return;
 
-		if (!host->chan_tx)
-			return;
+	cfg.slave_id = pdata->slave_id_tx;
+	cfg.direction = DMA_MEM_TO_DEV;
+	cfg.dst_addr = res->start + MMCIF_CE_DATA;
+	cfg.src_addr = 0;
+	ret = dmaengine_slave_config(host->chan_tx, &cfg);
+	if (ret < 0)
+		goto ecfgtx;
 
-		host->chan_rx = dma_request_channel(mask, sh_mmcif_filter, rx);
-		dev_dbg(&host->pd->dev, "%s: RX: got channel %p\n", __func__,
-			host->chan_rx);
+	host->chan_rx = dma_request_channel(mask, shdma_chan_filter,
+					    (void *)pdata->slave_id_rx);
+	dev_dbg(&host->pd->dev, "%s: RX: got channel %p\n", __func__,
+		host->chan_rx);
 
-		if (!host->chan_rx) {
-			dma_release_channel(host->chan_tx);
-			host->chan_tx = NULL;
-			return;
-		}
+	if (!host->chan_rx)
+		goto erqrx;
 
-		init_completion(&host->dma_complete);
-	}
+	cfg.slave_id = pdata->slave_id_rx;
+	cfg.direction = DMA_DEV_TO_MEM;
+	cfg.dst_addr = 0;
+	cfg.src_addr = res->start + MMCIF_CE_DATA;
+	ret = dmaengine_slave_config(host->chan_rx, &cfg);
+	if (ret < 0)
+		goto ecfgrx;
+
+	init_completion(&host->dma_complete);
+
+	return;
+
+ecfgrx:
+	dma_release_channel(host->chan_rx);
+	host->chan_rx = NULL;
+erqrx:
+ecfgtx:
+	dma_release_channel(host->chan_tx);
+	host->chan_tx = NULL;
 }
 
 static void sh_mmcif_release_dma(struct sh_mmcif_host *host)
diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index a842939..0bdc146 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -169,10 +169,10 @@ static int __devinit sh_mobile_sdhi_probe(struct platform_device *pdev)
 			mmc_data->get_cd = sh_mobile_sdhi_get_cd;
 
 		if (p->dma_slave_tx > 0 && p->dma_slave_rx > 0) {
-			priv->param_tx.slave_id = p->dma_slave_tx;
-			priv->param_rx.slave_id = p->dma_slave_rx;
-			priv->dma_priv.chan_priv_tx = &priv->param_tx;
-			priv->dma_priv.chan_priv_rx = &priv->param_rx;
+			priv->param_tx.shdma_slave.slave_id = p->dma_slave_tx;
+			priv->param_rx.shdma_slave.slave_id = p->dma_slave_rx;
+			priv->dma_priv.chan_priv_tx = &priv->param_tx.shdma_slave;
+			priv->dma_priv.chan_priv_rx = &priv->param_rx.shdma_slave;
 			priv->dma_priv.alignment_shift = 1; /* 2-byte alignment */
 			mmc_data->dma = &priv->dma_priv;
 		}