dw_mmc: add an option to force 32-bit accesses to 64-bit device registers

index 581614196..eee430620 100644
@@ -2575,6 +2575,119 @@ static void dw_mci_pull_data64(struct dw_mci *host, void *buf, int cnt)
 	}
 }
 
+/*
+  Some dw_mmc devices have 64-bit FIFOs, but expect them to be
+  accessed using two 32-bit accesses. If such controller is used
+  with a 64-bit kernel, this has to be done explicitly.
+
+  XXX: Is this issue specific to Exynos7?
+*/
+
+static inline uint64_t mci_fifo_readq_32(void __iomem *addr)
+{
+	uint64_t ans;
+	uint32_t proxy[2];
+
+	proxy[0] = mci_fifo_readl(addr);
+	proxy[1] = mci_fifo_readl(addr+4);
+	memcpy(&ans, proxy, 8);
+	return ans;
+}
+
+static inline void mci_fifo_writeq_32(void __iomem *addr, uint64_t value)
+{
+	uint32_t proxy[2];
+
+	memcpy(proxy, &value, 8);
+	mci_fifo_writel(addr, proxy[0]);
+	mci_fifo_writel(addr+4, proxy[1]);
+}
+
+static void dw_mci_push_data64_32(struct dw_mci *host, void *buf, int cnt)
+{
+	struct mmc_data *data = host->data;
+	int init_cnt = cnt;
+
+	/* try and push anything in the part_buf */
+	if (unlikely(host->part_buf_count)) {
+		int len = dw_mci_push_part_bytes(host, buf, cnt);
+
+		buf += len;
+		cnt -= len;
+
+		if (host->part_buf_count == 8) {
+			mci_fifo_writeq_32(host->fifo_reg, host->part_buf);
+			host->part_buf_count = 0;
+		}
+	}
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	if (unlikely((unsigned long)buf & 0x7)) {
+		while (cnt >= 8) {
+			u64 aligned_buf[16];
+			int len = min(cnt & -8, (int)sizeof(aligned_buf));
+			int items = len >> 3;
+			int i;
+			/* memcpy from input buffer into aligned buffer */
+			memcpy(aligned_buf, buf, len);
+			buf += len;
+			cnt -= len;
+			/* push data from aligned buffer into fifo */
+			for (i = 0; i < items; ++i)
+				mci_fifo_writeq_32(host->fifo_reg, aligned_buf[i]);
+		}
+	} else
+#endif
+	{
+		u64 *pdata = buf;
+
+		for (; cnt >= 8; cnt -= 8)
+			mci_fifo_writeq_32(host->fifo_reg, *pdata++);
+		buf = pdata;
+	}
+	/* put anything remaining in the part_buf */
+	if (cnt) {
+		dw_mci_set_part_bytes(host, buf, cnt);
+		/* Push data if we have reached the expected data length */
+		if ((data->bytes_xfered + init_cnt) ==
+		    (data->blksz * data->blocks))
+			mci_fifo_writeq_32(host->fifo_reg, host->part_buf);
+	}
+}
+
+static void dw_mci_pull_data64_32(struct dw_mci *host, void *buf, int cnt)
+{
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	if (unlikely((unsigned long)buf & 0x7)) {
+		while (cnt >= 8) {
+			/* pull data from fifo into aligned buffer */
+			u64 aligned_buf[16];
+			int len = min(cnt & -8, (int)sizeof(aligned_buf));
+			int items = len >> 3;
+			int i;
+
+			for (i = 0; i < items; ++i)
+				aligned_buf[i] = mci_fifo_readq_32(host->fifo_reg);
+
+			/* memcpy from aligned buffer into output buffer */
+			memcpy(buf, aligned_buf, len);
+			buf += len;
+			cnt -= len;
+		}
+	} else
+#endif
+	{
+		u64 *pdata = buf;
+
+		for (; cnt >= 8; cnt -= 8)
+			*pdata++ = mci_fifo_readq_32(host->fifo_reg);
+		buf = pdata;
+	}
+	if (cnt) {
+		host->part_buf = mci_fifo_readq_32(host->fifo_reg);
+		dw_mci_pull_final_bytes(host, buf, cnt);
+	}
+}
+
 static void dw_mci_pull_data(struct dw_mci *host, void *buf, int cnt)
 {
 	int len;

@@ -3239,6 +3352,9 @@ static struct dw_mci_board *dw_mci_parse_dt(struct dw_mci *host)
 	if (device_property_present(dev, "fifo-watermark-aligned"))
 		host->wm_aligned = true;
 
+	if (device_property_present(dev, "fifo-access-32bit"))
+		host->quirks |= DW_MMC_QUIRK_FIFO64_32;
+
 	if (!device_property_read_u32(dev, "clock-frequency", &clock_frequency))
 		pdata->bus_hz = clock_frequency;
 

@@ -3367,8 +3483,13 @@ int dw_mci_probe(struct dw_mci *host)
 		width = 16;
 		host->data_shift = 1;
 	} else if (i == 2) {
-		host->push_data = dw_mci_push_data64;
-		host->pull_data = dw_mci_pull_data64;
+		if ((host->quirks & DW_MMC_QUIRK_FIFO64_32)) {
+			host->push_data = dw_mci_push_data64_32;
+			host->pull_data = dw_mci_pull_data64_32;
+		} else {
+			host->push_data = dw_mci_push_data64;
+			host->pull_data = dw_mci_pull_data64;
+		}
 		width = 64;
 		host->data_shift = 3;
 	} else {

index 4ed81f94f..edd642b92 100644
@@ -280,6 +280,8 @@ struct dw_mci_board {
 
 /* Support for longer data read timeout */
 #define DW_MMC_QUIRK_EXTENDED_TMOUT            BIT(0)
+/* Force 32-bit access to the FIFO */
+#define DW_MMC_QUIRK_FIFO64_32                 BIT(1)
 
 #define DW_MMC_240A		0x240a
 #define DW_MMC_280A		0x280a