bitmap: introduce generic optimized bitmap_size()

The number of times yet another open coded
`BITS_TO_LONGS(nbits) * sizeof(long)` can be spotted is huge.
Some generic helper is long overdue.

Add one, bitmap_size(), but with one detail.
BITS_TO_LONGS() uses DIV_ROUND_UP(). The latter works well when both
divident and divisor are compile-time constants or when the divisor
is not a pow-of-2. When it is however, the compilers sometimes tend
to generate suboptimal code (GCC 13):

48 83 c0 3f          	add    $0x3f,%rax
48 c1 e8 06          	shr    $0x6,%rax
48 8d 14 c5 00 00 00 00	lea    0x0(,%rax,8),%rdx

%BITS_PER_LONG is always a pow-2 (either 32 or 64), but GCC still does
full division of `nbits + 63` by it and then multiplication by 8.
Instead of BITS_TO_LONGS(), use ALIGN() and then divide by 8. GCC:

8d 50 3f             	lea    0x3f(%rax),%edx
c1 ea 03             	shr    $0x3,%edx
81 e2 f8 ff ff 1f    	and    $0x1ffffff8,%edx

Now it shifts `nbits + 63` by 3 positions (IOW performs fast division
by 8) and then masks bits[2:0]. bloat-o-meter:

add/remove: 0/0 grow/shrink: 20/133 up/down: 156/-773 (-617)

Clang does it better and generates the same code before/after starting
from -O1, except that with the ALIGN() approach it uses %edx and thus
still saves some bytes:

add/remove: 0/0 grow/shrink: 9/133 up/down: 18/-538 (-520)

Note that we can't expand DIV_ROUND_UP() by adding a check and using
this approach there, as it's used in array declarations where
expressions are not allowed.
Add this helper to tools/ as well.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Acked-by: Yury Norov <yury.norov@gmail.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 6 insertions, 4 deletions

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 914c23e96f26..363e0b184a45 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -226,9 +226,11 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig,
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
 #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))
 
+#define bitmap_size(nbits)	(ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE)
+
 static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 {
-	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+	unsigned int len = bitmap_size(nbits);
 
 	if (small_const_nbits(nbits))
 		*dst = 0;
@@ -238,7 +240,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 
 static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 {
-	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+	unsigned int len = bitmap_size(nbits);
 
 	if (small_const_nbits(nbits))
 		*dst = ~0UL;
@@ -249,7 +251,7 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 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);
+	unsigned int len = bitmap_size(nbits);
 
 	if (small_const_nbits(nbits))
 		*dst = *src;
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 1c29947db848..6519f9c77709 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -853,7 +853,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
  */
 static inline unsigned int cpumask_size(void)
 {
-	return BITS_TO_LONGS(large_cpumask_bits) * sizeof(long);
+	return bitmap_size(large_cpumask_bits);
 }
 
 /*