bitmap: fix memset optimization on big-endian systems

Commit 2a98dc028f91 ("include/linux/bitmap.h: turn bitmap_set and
bitmap_clear into memset when possible") introduced an optimization to
bitmap_{set,clear}() which uses memset() when the start and length are
constants aligned to a byte.

This is wrong on big-endian systems; our bitmaps are arrays of unsigned
long, so bit n is not at byte n / 8 in memory.  This was caught by the
Btrfs selftests, but the bitmap selftests also fail when run on a
big-endian machine.

We can still use memset if the start and length are aligned to an
unsigned long, so do that on big-endian.  The same problem applies to
the memcmp in bitmap_equal(), so fix it there, too.

Fixes: 2a98dc028f91 ("include/linux/bitmap.h: turn bitmap_set and bitmap_clear into memset when possible")
Fixes: 2c6deb01525a ("bitmap: use memcmp optimisation in more situations")
Cc: stable@kernel.org
Reported-by: "Erhard F." <erhard_f@mailbox.org>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/bitmap.h

@@ -302,12 +302,20 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr
 		__bitmap_complement(dst, src, nbits);
 }
 
+#ifdef __LITTLE_ENDIAN
+#define BITMAP_MEM_ALIGNMENT 8
+#else
+#define BITMAP_MEM_ALIGNMENT (8 * sizeof(unsigned long))
+#endif
+#define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1)
+
 static inline int bitmap_equal(const unsigned long *src1,
 			const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
-	if (__builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8))
+	if (__builtin_constant_p(nbits & BITMAP_MEM_MASK) &&
+	    IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT))
 		return !memcmp(src1, src2, nbits / 8);
 	return __bitmap_equal(src1, src2, nbits);
 }
@@ -358,8 +366,10 @@ static __always_inline void bitmap_set(unsigned long *map, unsigned int start,
 {
 	if (__builtin_constant_p(nbits) && nbits == 1)
 		__set_bit(start, map);
-	else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) &&
-		 __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8))
+	else if (__builtin_constant_p(start & BITMAP_MEM_MASK) &&
+		 IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) &&
+		 __builtin_constant_p(nbits & BITMAP_MEM_MASK) &&
+		 IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT))
 		memset((char *)map + start / 8, 0xff, nbits / 8);
 	else
 		__bitmap_set(map, start, nbits);
@@ -370,8 +380,10 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start,
 {
 	if (__builtin_constant_p(nbits) && nbits == 1)
 		__clear_bit(start, map);
-	else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) &&
-		 __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8))
+	else if (__builtin_constant_p(start & BITMAP_MEM_MASK) &&
+		 IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) &&
+		 __builtin_constant_p(nbits & BITMAP_MEM_MASK) &&
+		 IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT))
 		memset((char *)map + start / 8, 0, nbits / 8);
 	else
 		__bitmap_clear(map, start, nbits);