diff --git a/drivers/mmc/host/alcor.c b/drivers/mmc/host/alcor.c
index c712b7d..82a9786 100644
--- a/drivers/mmc/host/alcor.c
+++ b/drivers/mmc/host/alcor.c
@@ -1044,14 +1044,27 @@ static void alcor_init_mmc(struct alcor_sdmmc_host *host)
 	mmc->caps2 = MMC_CAP2_NO_SDIO;
 	mmc->ops = &alcor_sdc_ops;
 
-	/* Hardware cannot do scatter lists */
+	/* The hardware does DMA data transfer of 4096 bytes to/from a single
+	 * buffer address. Scatterlists are not supported, but upon DMA
+	 * completion (signalled via IRQ), the original vendor driver does
+	 * then immediately set up another DMA transfer of the next 4096
+	 * bytes.
+	 *
+	 * This means that we need to handle the I/O in 4096 byte chunks.
+	 * Lacking a way to limit the sglist entries to 4096 bytes, we instead
+	 * impose that only one segment is provided, with maximum size 4096,
+	 * which also happens to be the minimum size. This means that the
+	 * single-entry sglist handled by this driver can be handed directly
+	 * to the hardware, nice and simple.
+	 *
+	 * Unfortunately though, that means we only do 4096 bytes I/O per
+	 * MMC command. A future improvement would be to make the driver
+	 * accept sg lists and entries of any size, and simply iterate
+	 * through them 4096 bytes at a time.
+	 */
 	mmc->max_segs = AU6601_MAX_DMA_SEGMENTS;
 	mmc->max_seg_size = AU6601_MAX_DMA_BLOCK_SIZE;
-
-	mmc->max_blk_size = mmc->max_seg_size;
-	mmc->max_blk_count = mmc->max_segs;
-
-	mmc->max_req_size = mmc->max_seg_size * mmc->max_segs;
+	mmc->max_req_size = mmc->max_seg_size;
 }
 
 static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev)
diff --git a/drivers/mmc/host/davinci_mmc.c b/drivers/mmc/host/davinci_mmc.c
index 49e0daf..f37003d 100644
--- a/drivers/mmc/host/davinci_mmc.c
+++ b/drivers/mmc/host/davinci_mmc.c
@@ -1117,7 +1117,7 @@ static inline void mmc_davinci_cpufreq_deregister(struct mmc_davinci_host *host)
 {
 }
 #endif
-static void __init init_mmcsd_host(struct mmc_davinci_host *host)
+static void init_mmcsd_host(struct mmc_davinci_host *host)
 {
 
 	mmc_davinci_reset_ctrl(host, 1);
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index d546122..45f7b9b 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -290,11 +290,8 @@ static void mxcmci_swap_buffers(struct mmc_data *data)
 	struct scatterlist *sg;
 	int i;
 
-	for_each_sg(data->sg, sg, data->sg_len, i) {
-		void *buf = kmap_atomic(sg_page(sg) + sg->offset);
-		buffer_swap32(buf, sg->length);
-		kunmap_atomic(buf);
-	}
+	for_each_sg(data->sg, sg, data->sg_len, i)
+		buffer_swap32(sg_virt(sg), sg->length);
 }
 #else
 static inline void mxcmci_swap_buffers(struct mmc_data *data) {}
@@ -611,7 +608,6 @@ static int mxcmci_transfer_data(struct mxcmci_host *host)
 {
 	struct mmc_data *data = host->req->data;
 	struct scatterlist *sg;
-	void *buf;
 	int stat, i;
 
 	host->data = data;
@@ -619,18 +615,14 @@ static int mxcmci_transfer_data(struct mxcmci_host *host)
 
 	if (data->flags & MMC_DATA_READ) {
 		for_each_sg(data->sg, sg, data->sg_len, i) {
-			buf = kmap_atomic(sg_page(sg) + sg->offset);
-			stat = mxcmci_pull(host, buf, sg->length);
-			kunmap(buf);
+			stat = mxcmci_pull(host, sg_virt(sg), sg->length);
 			if (stat)
 				return stat;
 			host->datasize += sg->length;
 		}
 	} else {
 		for_each_sg(data->sg, sg, data->sg_len, i) {
-			buf = kmap_atomic(sg_page(sg) + sg->offset);
-			stat = mxcmci_push(host, buf, sg->length);
-			kunmap(buf);
+			stat = mxcmci_push(host, sg_virt(sg), sg->length);
 			if (stat)
 				return stat;
 			host->datasize += sg->length;
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index c907bf5..c1d3f0e 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -162,7 +162,7 @@ static void pxamci_dma_irq(void *param);
 static void pxamci_setup_data(struct pxamci_host *host, struct mmc_data *data)
 {
 	struct dma_async_tx_descriptor *tx;
-	enum dma_data_direction direction;
+	enum dma_transfer_direction direction;
 	struct dma_slave_config	config;
 	struct dma_chan *chan;
 	unsigned int nob = data->blocks;
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index 71e1384..8742e27 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -641,6 +641,7 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 	struct renesas_sdhi *priv;
 	struct resource *res;
 	int irq, ret, i;
+	u16 ver;
 
 	of_data = of_device_get_match_data(&pdev->dev);
 
@@ -773,12 +774,17 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 	if (ret)
 		goto efree;
 
+	ver = sd_ctrl_read16(host, CTL_VERSION);
+	/* GEN2_SDR104 is first known SDHI to use 32bit block count */
+	if (ver < SDHI_VER_GEN2_SDR104 && mmc_data->max_blk_count > U16_MAX)
+		mmc_data->max_blk_count = U16_MAX;
+
 	ret = tmio_mmc_host_probe(host);
 	if (ret < 0)
 		goto edisclk;
 
 	/* One Gen2 SDHI incarnation does NOT have a CBSY bit */
-	if (sd_ctrl_read16(host, CTL_VERSION) == SDHI_VER_GEN2_SDR50)
+	if (ver == SDHI_VER_GEN2_SDR50)
 		mmc_data->flags &= ~TMIO_MMC_HAVE_CBSY;
 
 	/* Enable tuning iff we have an SCC and a supported mode */
diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c
index b1a66ca..5bbed47 100644
--- a/drivers/mmc/host/sdhci-omap.c
+++ b/drivers/mmc/host/sdhci-omap.c
@@ -1056,6 +1056,9 @@ static int sdhci_omap_probe(struct platform_device *pdev)
 			mmc->f_max = 48000000;
 	}
 
+	if (!mmc_can_gpio_ro(mmc))
+		mmc->caps2 |= MMC_CAP2_NO_WRITE_PROTECT;
+
 	pltfm_host->clk = devm_clk_get(dev, "fck");
 	if (IS_ERR(pltfm_host->clk)) {
 		ret = PTR_ERR(pltfm_host->clk);