diff options
author | Yury Norov <yury.norov@gmail.com> | 2022-09-14 19:07:29 -0700 |
---|---|---|
committer | Yury Norov <yury.norov@gmail.com> | 2022-09-21 12:21:32 -0700 |
commit | e79864f3164c573afce09ec4b72b75ebe061c14d (patch) | |
tree | 56ab7f1d70fec5d7005493c512ff221c3a4e29f1 /include/linux/find.h | |
parent | 14a99e130f2758bc826a7e7a8bdf6f7400b54f0f (diff) |
lib/find_bit: optimize find_next_bit() functions
Over the past couple years, the function _find_next_bit() was extended
with parameters that modify its behavior to implement and- zero- and le-
flavors. The parameters are passed at compile time, but current design
prevents a compiler from optimizing out the conditionals.
As find_next_bit() API grows, I expect that more parameters will be added.
Current design would require more conditional code in _find_next_bit(),
which would bloat the helper even more and make it barely readable.
This patch replaces _find_next_bit() with a macro FIND_NEXT_BIT, and adds
a set of wrappers, so that the compile-time optimizations become possible.
The common logic is moved to the new macro, and all flavors may be
generated by providing a FETCH macro parameter, like in this example:
#define FIND_NEXT_BIT(FETCH, MUNGE, size, start) ...
find_next_xornot_and_bit(addr1, addr2, addr3, size, start)
{
return FIND_NEXT_BIT(addr1[idx] ^ ~addr2[idx] & addr3[idx],
/* nop */, size, start);
}
The FETCH may be of any complexity, as soon as it only refers the bitmap(s)
and an iterator idx.
MUNGE is here to support _le code generation for BE builds. May be
empty.
I ran find_bit_benchmark 16 times on top of 6.0-rc2 and 16 times on top
of 6.0-rc2 + this series. The results for kvm/x86_64 are:
v6.0-rc2 Optimized Difference Z-score
Random dense bitmap ns ns ns %
find_next_bit: 787735 670546 117189 14.9 3.97
find_next_zero_bit: 777492 664208 113284 14.6 10.51
find_last_bit: 830925 687573 143352 17.3 2.35
find_first_bit: 3874366 3306635 567731 14.7 1.84
find_first_and_bit: 40677125 37739887 2937238 7.2 1.36
find_next_and_bit: 347865 304456 43409 12.5 1.35
Random sparse bitmap
find_next_bit: 19816 14021 5795 29.2 6.10
find_next_zero_bit: 1318901 1223794 95107 7.2 1.41
find_last_bit: 14573 13514 1059 7.3 6.92
find_first_bit: 1313321 1249024 64297 4.9 1.53
find_first_and_bit: 8921 8098 823 9.2 4.56
find_next_and_bit: 9796 7176 2620 26.7 5.39
Where the statistics is significant (z-score > 3), the improvement
is ~15%.
According to the bloat-o-meter, the Image size is 10-11K less:
x86_64/defconfig:
add/remove: 32/14 grow/shrink: 61/782 up/down: 6344/-16521 (-10177)
arm64/defconfig:
add/remove: 3/2 grow/shrink: 50/714 up/down: 608/-11556 (-10948)
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Yury Norov <yury.norov@gmail.com>
Diffstat (limited to 'include/linux/find.h')
-rw-r--r-- | include/linux/find.h | 23 |
1 files changed, 15 insertions, 8 deletions
diff --git a/include/linux/find.h b/include/linux/find.h index 2464bff5de04..dead6f53a97b 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -8,9 +8,12 @@ #include <linux/bitops.h> -extern unsigned long _find_next_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long nbits, - unsigned long start, unsigned long invert, unsigned long le); +unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits, + unsigned long start); +unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start); +unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, + unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); @@ -19,6 +22,10 @@ extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long siz #ifdef __BIG_ENDIAN unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size); +unsigned long _find_next_zero_bit_le(const unsigned long *addr, unsigned + long size, unsigned long offset); +unsigned long _find_next_bit_le(const unsigned long *addr, unsigned + long size, unsigned long offset); #endif #ifndef find_next_bit @@ -45,7 +52,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, return val ? __ffs(val) : size; } - return _find_next_bit(addr, NULL, size, offset, 0UL, 0); + return _find_next_bit(addr, size, offset); } #endif @@ -75,7 +82,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1, return val ? __ffs(val) : size; } - return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); + return _find_next_and_bit(addr1, addr2, size, offset); } #endif @@ -103,7 +110,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, return val == ~0UL ? size : ffz(val); } - return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); + return _find_next_zero_bit(addr, size, offset); } #endif @@ -251,7 +258,7 @@ unsigned long find_next_zero_bit_le(const void *addr, unsigned return val == ~0UL ? size : ffz(val); } - return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); + return _find_next_zero_bit_le(addr, size, offset); } #endif @@ -284,7 +291,7 @@ unsigned long find_next_bit_le(const void *addr, unsigned return val ? __ffs(val) : size; } - return _find_next_bit(addr, NULL, size, offset, 0UL, 1); + return _find_next_bit_le(addr, size, offset); } #endif |