From: Alexander Lobakin <aleksander.lobakin@xxxxxxxxx>
commit a37fbe666c016fd89e4460d0ebfcea05baba46dc upstream.
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@xxxxxxxxx>
Acked-by: Yury Norov <yury.norov@xxxxxxxxx>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@xxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/s390/cio/idset.c | 2 +-
include/linux/bitmap.h | 8 +++++---
include/linux/cpumask.h | 2 +-
tools/include/linux/bitmap.h | 7 ++++---
4 files changed, 11 insertions(+), 8 deletions(-)
--- a/drivers/s390/cio/idset.c
+++ b/drivers/s390/cio/idset.c
@@ -18,7 +18,7 @@ struct idset {
static inline unsigned long bitmap_size(int num_ssid, int num_id)
{
- return BITS_TO_LONGS(num_ssid * num_id) * sizeof(unsigned long);
+ return bitmap_size(size_mul(num_ssid, num_id));
}
static struct idset *idset_new(int num_ssid, int num_id)
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -212,12 +212,14 @@ extern int bitmap_print_to_pagebuf(bool
#define small_const_nbits(nbits) \
(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG && (nbits) > 0)
+#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE)
+
static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
{
if (small_const_nbits(nbits))
*dst = 0UL;
else {
- unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+ unsigned int len = bitmap_size(nbits);
memset(dst, 0, len);
}
}
@@ -227,7 +229,7 @@ static inline void bitmap_fill(unsigned
if (small_const_nbits(nbits))
*dst = ~0UL;
else {
- unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+ unsigned int len = bitmap_size(nbits);
memset(dst, 0xff, len);
}
}
@@ -238,7 +240,7 @@ static inline void bitmap_copy(unsigned
if (small_const_nbits(nbits))
*dst = *src;
else {
- unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+ unsigned int len = bitmap_size(nbits);
memcpy(dst, src, len);
}
}
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -656,7 +656,7 @@ static inline int cpulist_parse(const ch
*/
static inline unsigned int cpumask_size(void)
{
- return BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long);
+ return bitmap_size(nr_cpumask_bits);
}
/*
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -27,13 +27,14 @@ int __bitmap_and(unsigned long *dst, con
#define small_const_nbits(nbits) \
(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG)
+#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE)
+
static inline void bitmap_zero(unsigned long *dst, int nbits)
{
if (small_const_nbits(nbits))
*dst = 0UL;
else {
- int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
- memset(dst, 0, len);
+ memset(dst, 0, bitmap_size(nbits));
}
}
@@ -119,7 +120,7 @@ static inline int test_and_clear_bit(int
*/
static inline unsigned long *bitmap_alloc(int nbits)
{
- return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long));
+ return calloc(1, bitmap_size(nbits));
}
/*
Patches currently in stable-queue which might be from aleksander.lobakin@xxxxxxxxx are
queue-4.19/bitmap-introduce-generic-optimized-bitmap_size.patch
