memory: renesas-rpc-if: Avoid unaligned bus access for HyperFlash

HyperFlash devices in Renesas SoCs use 2-bytes addressing, according
to HW manual paragraph 62.3.3 (which officially describes Serial Flash
access, but seems to be applicable to HyperFlash too). And 1-byte bus
read operations to 2-bytes unaligned addresses in external address space
read mode work incorrectly (returns the other byte from the same word).

Function memcpy_fromio(), used by the driver to read data from the bus,
in ARM64 architecture (to which Renesas cores belong) uses 8-bytes
bus accesses for appropriate aligned addresses, and 1-bytes accesses
for other addresses. This results in incorrect data read from HyperFlash
in unaligned cases.

This issue can be reproduced using something like the following commands
(where mtd1 is a parition on Hyperflash storage, defined properly
in a device tree):

[Correct fragment, read from Hyperflash]

root@rcar-gen3:~# dd if=/dev/mtd1 of=/tmp/zz bs=32 count=1
root@rcar-gen3:~# hexdump -C /tmp/zz
00000000 f4 03 00 aa f5 03 01 aa f6 03 02 aa f7 03 03 aa |................|
00000010 00 00 80 d2 40 20 18 d5 00 06 81 d2 a0 18 a6 f2 |....@ ..........|
00000020

[Incorrect read of the same fragment: see the difference at offsets 8-11]

root@rcar-gen3:~# dd if=/dev/mtd1 of=/tmp/zz bs=12 count=1
root@rcar-gen3:~# hexdump -C /tmp/zz
00000000 f4 03 00 aa f5 03 01 aa 03 03 aa aa |............|
0000000c

Fix this issue by creating a local replacement of the copying function,
that performs only properly aligned bus accesses, and is used for reading
from HyperFlash.

Fixes: ca7d8b980b67f ("memory: add Renesas RPC-IF driver")
Cc: <[e-mail]>
Signed-off-by: Andrew Gabbasov <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Krzysztof Kozlowski <[e-mail]>

drivers/memory/renesas-rpc-if.c

···
 
 	*val = readl(rpc->base + reg);
 	return 0;
-
 }
 
 static int rpcif_reg_write(void *context, unsigned int reg, unsigned int val)
···
 }
 EXPORT_SYMBOL(rpcif_manual_xfer);
 
+static void memcpy_fromio_readw(void *to,
+				const void __iomem *from,
+				size_t count)
+{
+	const int maxw = (IS_ENABLED(CONFIG_64BIT)) ? 8 : 4;
+	u8 buf[2];
+
+	if (count && ((unsigned long)from & 1)) {
+		*(u16 *)buf = __raw_readw((void __iomem *)((unsigned long)from & ~1));
+		*(u8 *)to = buf[1];
+		from++;
+		to++;
+		count--;
+	}
+	while (count >= 2 && !IS_ALIGNED((unsigned long)from, maxw)) {
+		*(u16 *)to = __raw_readw(from);
+		from += 2;
+		to += 2;
+		count -= 2;
+	}
+	while (count >= maxw) {
+#ifdef CONFIG_64BIT
+		*(u64 *)to = __raw_readq(from);
+#else
+		*(u32 *)to = __raw_readl(from);
+#endif
+		from += maxw;
+		to += maxw;
+		count -= maxw;
+	}
+	while (count >= 2) {
+		*(u16 *)to = __raw_readw(from);
+		from += 2;
+		to += 2;
+		count -= 2;
+	}
+	if (count) {
+		*(u16 *)buf = __raw_readw(from);
+		*(u8 *)to = buf[0];
+	}
+}
+
 ssize_t rpcif_dirmap_read(struct rpcif *rpc, u64 offs, size_t len, void *buf)
 {
 	loff_t from = offs & (RPCIF_DIRMAP_SIZE - 1);
···
 	regmap_write(rpc->regmap, RPCIF_DRDMCR, rpc->dummy);
 	regmap_write(rpc->regmap, RPCIF_DRDRENR, rpc->ddr);
 
-	memcpy_fromio(buf, rpc->dirmap + from, len);
+	if (rpc->bus_size == 2)
+		memcpy_fromio_readw(buf, rpc->dirmap + from, len);
+	else
+		memcpy_fromio(buf, rpc->dirmap + from, len);
 
 	pm_runtime_put(rpc->dev);