[PATCH] mmc: meson-gx: do not use memcpy_to/fromio for dram-access-quirk

[Neil Armstrong]

The memory at the end of the controller only accepts 32bit read/write
accesses, but the arm64 memcpy_to/fromio implementation only uses 64bit
(which will be split into two 32bit access) and 8bit leading to incomplete
copies to/from this memory when the buffer is not multiple of 8bytes.

Add a local copy using writel/readl accesses to make sure we use the right
memory access width.

The switch to memcpy_to/fromio was done because of 285133040e6c
("arm64: Import latest memcpy()/memmove() implementation"), but using memcpy
worked before since it mainly used 32bit memory acceses.

Fixes: 103a5348c22c ("mmc: meson-gx: use memcpy_to/fromio for dram-access-quirk")
Reported-by: Christian Hewitt <christianshewitt@xxxxxxxxx>
Suggested-by: Martin Blumenstingl <martin.blumenstingl@xxxxxxxxxxxxxx>
Signed-off-by: Neil Armstrong <narmstrong@xxxxxxxxxxxx>
---
 drivers/mmc/host/meson-gx-mmc.c | 49 +++++++++++++++++++++++----------
 1 file changed, 35 insertions(+), 14 deletions(-)

diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c
index 3f28eb4d17fe..08c0ff0bfa8b 100644
--- a/drivers/mmc/host/meson-gx-mmc.c
+++ b/drivers/mmc/host/meson-gx-mmc.c
@@ -746,7 +746,7 @@ static void meson_mmc_desc_chain_transfer(struct mmc_host *mmc, u32 cmd_cfg)
 	writel(start, host->regs + SD_EMMC_START);
 }
 
-/* local sg copy to buffer version with _to/fromio usage for dram_access_quirk */
+/* local sg copy for dram_access_quirk */
 static void meson_mmc_copy_buffer(struct meson_host *host, struct mmc_data *data,
 				  size_t buflen, bool to_buffer)
 {
@@ -764,21 +764,34 @@ static void meson_mmc_copy_buffer(struct meson_host *host, struct mmc_data *data
 	sg_miter_start(&miter, sgl, nents, sg_flags);
 
 	while ((offset < buflen) && sg_miter_next(&miter)) {
-		unsigned int len;
+		unsigned int buf_offset = 0;
+		unsigned int len, left;
+		u32 *buf = miter.addr;
+
+		if (((unsigned long int)miter.addr % 4))
+			dev_err(host->dev, "non word aligned sg");
 
 		len = min(miter.length, buflen - offset);
 
-		/* When dram_access_quirk, the bounce buffer is a iomem mapping */
-		if (host->dram_access_quirk) {
-			if (to_buffer)
-				memcpy_toio(host->bounce_iomem_buf + offset, miter.addr, len);
-			else
-				memcpy_fromio(miter.addr, host->bounce_iomem_buf + offset, len);
+		if ((len % 4))
+			dev_err(host->dev, "non word multiple sg");
+
+		left = len;
+
+		if (to_buffer) {
+			do {
+				writel(*buf++, host->bounce_iomem_buf + offset + buf_offset);
+
+				buf_offset += 4;
+				left -= 4;
+			} while (left);
 		} else {
-			if (to_buffer)
-				memcpy(host->bounce_buf + offset, miter.addr, len);
-			else
-				memcpy(miter.addr, host->bounce_buf + offset, len);
+			do {
+				*buf++ = readl(host->bounce_iomem_buf + offset + buf_offset);
+
+				buf_offset += 4;
+				left -= 4;
+			} while (left);
 		}
 
 		offset += len;
@@ -830,7 +843,11 @@ static void meson_mmc_start_cmd(struct mmc_host *mmc, struct mmc_command *cmd)
 		if (data->flags & MMC_DATA_WRITE) {
 			cmd_cfg |= CMD_CFG_DATA_WR;
 			WARN_ON(xfer_bytes > host->bounce_buf_size);
-			meson_mmc_copy_buffer(host, data, xfer_bytes, true);
+			if (host->dram_access_quirk)
+				meson_mmc_copy_buffer(host, data, xfer_bytes, true);
+			else
+				sg_copy_to_buffer(data->sg, data->sg_len,
+						  host->bounce_buf, xfer_bytes);
 			dma_wmb();
 		}
 
@@ -999,7 +1016,11 @@ static irqreturn_t meson_mmc_irq_thread(int irq, void *dev_id)
 	if (meson_mmc_bounce_buf_read(data)) {
 		xfer_bytes = data->blksz * data->blocks;
 		WARN_ON(xfer_bytes > host->bounce_buf_size);
-		meson_mmc_copy_buffer(host, data, xfer_bytes, false);
+		if (host->dram_access_quirk)
+			meson_mmc_copy_buffer(host, data, xfer_bytes, false);
+		else
+			sg_copy_from_buffer(data->sg, data->sg_len,
+					    host->bounce_buf, xfer_bytes);
 	}
 
 	next_cmd = meson_mmc_get_next_command(cmd);
-- 
2.25.1