lib: lz4: fixed zram with lz4 on big endian machines

Based on Sergey's test patch [1], this fixes zram with lz4 compression
on big endian cpus.

Note that the 64-bit preprocessor test is not a cleanup, it's part of
the fix, since those identifiers are bogus (for example, __ppc64__
isn't defined anywhere else in the kernel, which means we'd fall into
the 32-bit definitions on ppc64).

Tested on ppc64 with no regression on x86_64.

[1] http://marc.info/?l=linux-kernel&m=145994470805853&w=4

Cc: stable@vger.kernel.org
Suggested-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Rui Salvaterra <rsalvaterra@gmail.com>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

lib/lz4/lz4defs.h

@@ -11,8 +11,7 @@
 /*
  * Detects 64 bits mode
  */
-#if (defined(__x86_64__) || defined(__x86_64) || defined(__amd64__) \
-	|| defined(__ppc64__) || defined(__LP64__))
+#if defined(CONFIG_64BIT)
 #define LZ4_ARCH64 1
 #else
 #define LZ4_ARCH64 0
@@ -35,6 +34,10 @@ typedef struct _U64_S { u64 v; } U64_S;
 
 #define PUT4(s, d) (A32(d) = A32(s))
 #define PUT8(s, d) (A64(d) = A64(s))
+
+#define LZ4_READ_LITTLEENDIAN_16(d, s, p)	\
+	(d = s - A16(p))
+
 #define LZ4_WRITE_LITTLEENDIAN_16(p, v)	\
 	do {	\
 		A16(p) = v; \
@@ -51,9 +54,12 @@ typedef struct _U64_S { u64 v; } U64_S;
 #define PUT8(s, d) \
 	put_unaligned(get_unaligned((const u64 *) s), (u64 *) d)
 
+#define LZ4_READ_LITTLEENDIAN_16(d, s, p)	\
+	(d = s - get_unaligned_le16(p))
+
 #define LZ4_WRITE_LITTLEENDIAN_16(p, v)			\
 	do {						\
-		put_unaligned(v, (u16 *)(p)); \
+		put_unaligned_le16(v, (u16 *)(p));	\
 		p += 2;					\
 	} while (0)
 #endif
@@ -140,9 +146,6 @@ typedef struct _U64_S { u64 v; } U64_S;
 
 #endif
 
-#define LZ4_READ_LITTLEENDIAN_16(d, s, p) \
-	(d = s - get_unaligned_le16(p))
-
 #define LZ4_WILDCOPY(s, d, e)		\
 	do {				\
 		LZ4_COPYPACKET(s, d);	\