From: Biju Das <biju.das.jz@bp.renesas.com>

As per the RZ/{G2L,G3E} HW manual SD_BUF0 can be accessed by 16/32/64
bits. Most of the data transfer in SD/SDIO/eMMC mode is more than 8 bytes.
During testing it is found that, if the DMA buffer is not aligned to 128
bit it fallback to PIO mode. In such cases, 64-bit access is much more
efficient than the current 16-bit.

Tested-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
---
v2->v3:
 * Added header file linux/io.h
 * Replaced io{read,write}64_rep->{read,write}sq to fix the build error
   reported by the bot.
RFT->v2:
 * Collected tags
 * Fixed the build error reported by the bot by guarding the code with
   CONFIG_64BIT.
---
 drivers/mmc/host/tmio_mmc.h        | 15 ++++++++++++++
 drivers/mmc/host/tmio_mmc_core.c   | 33 ++++++++++++++++++++++++++++++
 include/linux/platform_data/tmio.h |  3 +++
 3 files changed, 51 insertions(+)

diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index d730b7633ae1..c8cdb1c0722e 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -16,6 +16,7 @@
 
 #include <linux/dmaengine.h>
 #include <linux/highmem.h>
+#include <linux/io.h>
 #include <linux/mutex.h>
 #include <linux/pagemap.h>
 #include <linux/scatterlist.h>
@@ -242,6 +243,20 @@ static inline void sd_ctrl_read32_rep(struct tmio_mmc_host *host, int addr,
 	ioread32_rep(host->ctl + (addr << host->bus_shift), buf, count);
 }
 
+#ifdef CONFIG_64BIT
+static inline void sd_ctrl_read64_rep(struct tmio_mmc_host *host, int addr,
+				      u64 *buf, int count)
+{
+	readsq(host->ctl + (addr << host->bus_shift), buf, count);
+}
+
+static inline void sd_ctrl_write64_rep(struct tmio_mmc_host *host, int addr,
+				       const u64 *buf, int count)
+{
+	writesq(host->ctl + (addr << host->bus_shift), buf, count);
+}
+#endif
+
 static inline void sd_ctrl_write16(struct tmio_mmc_host *host, int addr,
 				   u16 val)
 {
diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c
index 21c2f9095bac..775e0d9353d5 100644
--- a/drivers/mmc/host/tmio_mmc_core.c
+++ b/drivers/mmc/host/tmio_mmc_core.c
@@ -349,6 +349,39 @@ static void tmio_mmc_transfer_data(struct tmio_mmc_host *host,
 	/*
 	 * Transfer the data
 	 */
+#ifdef CONFIG_64BIT
+	if (host->pdata->flags & TMIO_MMC_64BIT_DATA_PORT) {
+		u64 *buf64 = (u64 *)buf;
+		u64 data = 0;
+
+		if (count >= 8) {
+			if (is_read)
+				sd_ctrl_read64_rep(host, CTL_SD_DATA_PORT,
+						   buf64, count >> 3);
+			else
+				sd_ctrl_write64_rep(host, CTL_SD_DATA_PORT,
+						    buf64, count >> 3);
+		}
+
+		/* if count was multiple of 8 */
+		if (!(count & 0x7))
+			return;
+
+		buf64 += count >> 3;
+		count %= 8;
+
+		if (is_read) {
+			sd_ctrl_read64_rep(host, CTL_SD_DATA_PORT, &data, 1);
+			memcpy(buf64, &data, count);
+		} else {
+			memcpy(&data, buf64, count);
+			sd_ctrl_write64_rep(host, CTL_SD_DATA_PORT, &data, 1);
+		}
+
+		return;
+	}
+#endif
+
 	if (host->pdata->flags & TMIO_MMC_32BIT_DATA_PORT) {
 		u32 data = 0;
 		u32 *buf32 = (u32 *)buf;
diff --git a/include/linux/platform_data/tmio.h b/include/linux/platform_data/tmio.h
index b060124ba1ae..426291713b83 100644
--- a/include/linux/platform_data/tmio.h
+++ b/include/linux/platform_data/tmio.h
@@ -47,6 +47,9 @@
 /* Some controllers have a CBSY bit */
 #define TMIO_MMC_HAVE_CBSY		BIT(11)
 
+/* Some controllers have a 64-bit wide data port register */
+#define TMIO_MMC_64BIT_DATA_PORT	BIT(12)
+
 struct tmio_mmc_data {
 	void				*chan_priv_tx;
 	void				*chan_priv_rx;
-- 
2.43.0