bitmap: optimise bitmap_set and bitmap_clear of a single bit

We have eight users calling bitmap_clear for a single bit and seventeen
calling bitmap_set for a single bit.  Rather than fix all of them to
call __clear_bit or __set_bit, turn bitmap_clear and bitmap_set into
inline functions and make this special case efficient.

Link: http://lkml.kernel.org/r/20170628153221.11322-3-willy@infradead.org
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
Acked-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/bitmap.h

@@ -112,9 +112,8 @@ extern int __bitmap_intersects(const unsigned long *bitmap1,
 extern int __bitmap_subset(const unsigned long *bitmap1,
 			const unsigned long *bitmap2, unsigned int nbits);
 extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
-
-extern void bitmap_set(unsigned long *map, unsigned int start, int len);
-extern void bitmap_clear(unsigned long *map, unsigned int start, int len);
+extern void __bitmap_set(unsigned long *map, unsigned int start, int len);
+extern void __bitmap_clear(unsigned long *map, unsigned int start, int len);
 
 extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
 						    unsigned long size,
@@ -315,6 +314,24 @@ static __always_inline int bitmap_weight(const unsigned long *src, unsigned int
 	return __bitmap_weight(src, nbits);
 }
 
+static __always_inline void bitmap_set(unsigned long *map, unsigned int start,
+		unsigned int nbits)
+{
+	if (__builtin_constant_p(nbits) && nbits == 1)
+		__set_bit(start, map);
+	else
+		__bitmap_set(map, start, nbits);
+}
+
+static __always_inline void bitmap_clear(unsigned long *map, unsigned int start,
+		unsigned int nbits)
+{
+	if (__builtin_constant_p(nbits) && nbits == 1)
+		__clear_bit(start, map);
+	else
+		__bitmap_clear(map, start, nbits);
+}
+
 static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src,
 				unsigned int shift, int nbits)
 {

lib/bitmap.c

@@ -251,7 +251,7 @@ int __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
 }
 EXPORT_SYMBOL(__bitmap_weight);
 
-void bitmap_set(unsigned long *map, unsigned int start, int len)
+void __bitmap_set(unsigned long *map, unsigned int start, int len)
 {
 	unsigned long *p = map + BIT_WORD(start);
 	const unsigned int size = start + len;
@@ -270,9 +270,9 @@ void bitmap_set(unsigned long *map, unsigned int start, int len)
 		*p |= mask_to_set;
 	}
 }
-EXPORT_SYMBOL(bitmap_set);
+EXPORT_SYMBOL(__bitmap_set);
 
-void bitmap_clear(unsigned long *map, unsigned int start, int len)
+void __bitmap_clear(unsigned long *map, unsigned int start, int len)
 {
 	unsigned long *p = map + BIT_WORD(start);
 	const unsigned int size = start + len;
@@ -291,7 +291,7 @@ void bitmap_clear(unsigned long *map, unsigned int start, int len)
 		*p &= ~mask_to_clear;
 	}
 }
-EXPORT_SYMBOL(bitmap_clear);
+EXPORT_SYMBOL(__bitmap_clear);
 
 /**
  * bitmap_find_next_zero_area_off - find a contiguous aligned zero area

lib/test_bitmap.c

@@ -333,9 +333,6 @@ static void __init test_bitmap_u32_array_conversions(void)
 	}
 }
 
-#define __bitmap_set(a, b, c)	bitmap_set(a, b, c)
-#define __bitmap_clear(a, b, c)	bitmap_clear(a, b, c)
-
 static void noinline __init test_mem_optimisations(void)
 {
 	DECLARE_BITMAP(bmap1, 1024);