bitmap: don't assume compiler evaluates small mem*() builtins calls

Intel kernel bot triggered the build bug on ARC architecture that
in fact is as follows:

	DECLARE_BITMAP(bitmap, BITS_PER_LONG);

	bitmap_clear(bitmap, 0, BITS_PER_LONG);
	BUILD_BUG_ON(!__builtin_constant_p(*bitmap));

which can be expanded to:

	unsigned long bitmap[1];

	memset(bitmap, 0, sizeof(*bitmap));
	BUILD_BUG_ON(!__builtin_constant_p(*bitmap));

In most cases, a compiler is able to expand small/simple mem*()
calls to simple assignments or bitops, in this case that would mean:

	unsigned long bitmap[1] = { 0 };

	BUILD_BUG_ON(!__builtin_constant_p(*bitmap));

and on most architectures this works, but not on ARC, despite having
-O3 for every build.
So, to make this work, in case when the last bit to modify is still
within the first long (small_const_nbits()), just use plain
assignments for the rest of bitmap_*() functions which still use
mem*(), but didn't receive such compile-time optimizations yet.
This doesn't have the same coverage as compilers provide, but at
least something to start:

text: add/remove: 3/7 grow/shrink: 43/78 up/down: 1848/-3370 (-1546)
data: add/remove: 1/11 grow/shrink: 0/8 up/down: 4/-356 (-352)

notably cpumask_*() family when NR_CPUS <= BITS_PER_LONG:

netif_get_num_default_rss_queues              38       4     -34
cpumask_copy                                  90       -     -90
cpumask_clear                                146       -    -146

and the abovementioned assertion started passing.

Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Signed-off-by: Yury Norov <yury.norov@gmail.com>

Author: alobakin

include/linux/bitmap.h

@@ -238,20 +238,32 @@ extern int bitmap_print_list_to_buf(char *buf, const unsigned long *maskp,
 static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 {
 	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
-	memset(dst, 0, len);
+
+	if (small_const_nbits(nbits))
+		*dst = 0;
+	else
+		memset(dst, 0, len);
 }
 
 static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 {
 	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
-	memset(dst, 0xff, len);
+
+	if (small_const_nbits(nbits))
+		*dst = ~0UL;
+	else
+		memset(dst, 0xff, len);
 }
 
 static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
 			unsigned int nbits)
 {
 	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
-	memcpy(dst, src, len);
+
+	if (small_const_nbits(nbits))
+		*dst = *src;
+	else
+		memcpy(dst, src, len);
 }
 
 /*
@@ -431,6 +443,8 @@ 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 (small_const_nbits(start + nbits))
+		*map |= GENMASK(start + nbits - 1, start);
 	else if (__builtin_constant_p(start & BITMAP_MEM_MASK) &&
 		 IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) &&
 		 __builtin_constant_p(nbits & BITMAP_MEM_MASK) &&
@@ -445,6 +459,8 @@ 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 (small_const_nbits(start + nbits))
+		*map &= ~GENMASK(start + nbits - 1, start);
 	else if (__builtin_constant_p(start & BITMAP_MEM_MASK) &&
 		 IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) &&
 		 __builtin_constant_p(nbits & BITMAP_MEM_MASK) &&