diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
index 8e0acd197c43c03756f3263a7710d7f1326d0c89..6af946d16d241f685814fa8933f32fd672c40c22 100644
--- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c
+++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
@@ -9,6 +9,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/bitops.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/io-64-nonatomic-hi-lo.h>
@@ -62,6 +63,17 @@
  *   need a custom accessor.
  */
 
+static unsigned long global_flags;
+/*
+ * Workaround for avoiding to use RX DMAC by multiple channels.
+ * On R-Car H3 ES1.* and M3-W ES1.0, when multiple SDHI channels use
+ * RX DMAC simultaneously, sometimes hundreds of bytes data are not
+ * stored into the system memory even if the DMAC interrupt happened.
+ * So, this driver then uses one RX DMAC channel only.
+ */
+#define SDHI_INTERNAL_DMAC_ONE_RX_ONLY	0
+#define SDHI_INTERNAL_DMAC_RX_IN_USE	1
+
 /* Definitions for sampling clocks */
 static struct renesas_sdhi_scc rcar_gen3_scc_taps[] = {
 	{
@@ -126,6 +138,9 @@ renesas_sdhi_internal_dmac_abort_dma(struct tmio_mmc_host *host) {
 	renesas_sdhi_internal_dmac_dm_write(host, DM_CM_RST,
 					    RST_RESERVED_BITS | val);
 
+	if (host->data && host->data->flags & MMC_DATA_READ)
+		clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
+
 	renesas_sdhi_internal_dmac_enable_dma(host, true);
 }
 
@@ -155,6 +170,9 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host,
 	if (data->flags & MMC_DATA_READ) {
 		dtran_mode |= DTRAN_MODE_CH_NUM_CH1;
 		dir = DMA_FROM_DEVICE;
+		if (test_bit(SDHI_INTERNAL_DMAC_ONE_RX_ONLY, &global_flags) &&
+		    test_and_set_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags))
+			goto force_pio;
 	} else {
 		dtran_mode |= DTRAN_MODE_CH_NUM_CH0;
 		dir = DMA_TO_DEVICE;
@@ -208,6 +226,9 @@ static void renesas_sdhi_internal_dmac_complete_tasklet_fn(unsigned long arg)
 	renesas_sdhi_internal_dmac_enable_dma(host, false);
 	dma_unmap_sg(&host->pdev->dev, host->sg_ptr, host->sg_len, dir);
 
+	if (dir == DMA_FROM_DEVICE)
+		clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
+
 	tmio_mmc_do_data_irq(host);
 out:
 	spin_unlock_irq(&host->lock);
@@ -251,18 +272,24 @@ static const struct tmio_mmc_dma_ops renesas_sdhi_internal_dmac_dma_ops = {
  * implementation as others may use a different implementation.
  */
 static const struct soc_device_attribute gen3_soc_whitelist[] = {
-        { .soc_id = "r8a7795", .revision = "ES1.*" },
-        { .soc_id = "r8a7795", .revision = "ES2.0" },
-        { .soc_id = "r8a7796", .revision = "ES1.0" },
-        { .soc_id = "r8a77995", .revision = "ES1.0" },
-        { /* sentinel */ }
+	{ .soc_id = "r8a7795", .revision = "ES1.*",
+	  .data = (void *)BIT(SDHI_INTERNAL_DMAC_ONE_RX_ONLY) },
+	{ .soc_id = "r8a7795", .revision = "ES2.0" },
+	{ .soc_id = "r8a7796", .revision = "ES1.0",
+	  .data = (void *)BIT(SDHI_INTERNAL_DMAC_ONE_RX_ONLY) },
+	{ .soc_id = "r8a77995", .revision = "ES1.0" },
+	{ /* sentinel */ }
 };
 
 static int renesas_sdhi_internal_dmac_probe(struct platform_device *pdev)
 {
-	if (!soc_device_match(gen3_soc_whitelist))
+	const struct soc_device_attribute *soc = soc_device_match(gen3_soc_whitelist);
+
+	if (!soc)
 		return -ENODEV;
 
+	global_flags |= (unsigned long)soc->data;
+
 	return renesas_sdhi_probe(pdev, &renesas_sdhi_internal_dmac_dma_ops);
 }
 
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 787434e5589dbc15525eee7f2ca851ce224744e4..78c25ad35fd27f019b24f2f4045f214b0e8b5ed5 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -1312,7 +1312,7 @@ static void amd_enable_manual_tuning(struct pci_dev *pdev)
 	pci_write_config_dword(pdev, AMD_SD_MISC_CONTROL, val);
 }
 
-static int amd_execute_tuning(struct sdhci_host *host, u32 opcode)
+static int amd_execute_tuning_hs200(struct sdhci_host *host, u32 opcode)
 {
 	struct sdhci_pci_slot *slot = sdhci_priv(host);
 	struct pci_dev *pdev = slot->chip->pdev;
@@ -1351,6 +1351,27 @@ static int amd_execute_tuning(struct sdhci_host *host, u32 opcode)
 	return 0;
 }
 
+static int amd_execute_tuning(struct mmc_host *mmc, u32 opcode)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+
+	/* AMD requires custom HS200 tuning */
+	if (host->timing == MMC_TIMING_MMC_HS200)
+		return amd_execute_tuning_hs200(host, opcode);
+
+	/* Otherwise perform standard SDHCI tuning */
+	return sdhci_execute_tuning(mmc, opcode);
+}
+
+static int amd_probe_slot(struct sdhci_pci_slot *slot)
+{
+	struct mmc_host_ops *ops = &slot->host->mmc_host_ops;
+
+	ops->execute_tuning = amd_execute_tuning;
+
+	return 0;
+}
+
 static int amd_probe(struct sdhci_pci_chip *chip)
 {
 	struct pci_dev	*smbus_dev;
@@ -1385,12 +1406,12 @@ static const struct sdhci_ops amd_sdhci_pci_ops = {
 	.set_bus_width			= sdhci_set_bus_width,
 	.reset				= sdhci_reset,
 	.set_uhs_signaling		= sdhci_set_uhs_signaling,
-	.platform_execute_tuning	= amd_execute_tuning,
 };
 
 static const struct sdhci_pci_fixes sdhci_amd = {
 	.probe		= amd_probe,
 	.ops		= &amd_sdhci_pci_ops,
+	.probe_slot	= amd_probe_slot,
 };
 
 static const struct pci_device_id pci_ids[] = {