lkml.org 
[lkml]   [2022]   [Jul]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 1/5] lib: add find_nth(,and,andnot)_bit()
Date
Kernel lacks for a function that searches for Nth bit in a bitmap.
Usually people do it like this:
for_each_set_bit(bit, mask, size)
if (--n == 0)
return bit;

We can do it more efficiently, if we:
1. find a word containing Nth bit, using hweight(); and
2. find the bit, using a helper fns(), that works similarly to
__ffs() and ffz().

fns() is implemented as a simple loop. For x86_64, there's PDEP instruction
to do that: ret = clz(pdep(1 << idx, num)). However, for large bitmaps the
most of improvement comes from using hweight(), so I kept fns() simple.

New find_nth_bit() is ~70 times faster on x86_64/kvm:
find_nth_bit: 7154190 ns, 16411 iterations
for_each_bit: 505493126 ns, 16315 iterations

With all that, a family of 3 new functions is added, and used where
appropriate in the following patches.

Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
include/linux/bitops.h | 19 ++++++++++
include/linux/find.h | 83 ++++++++++++++++++++++++++++++++++++++++++
lib/find_bit.c | 20 ++++++++++
3 files changed, 122 insertions(+)

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index cf9bf65039f2..8b2189878afa 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -246,6 +246,25 @@ static inline unsigned long __ffs64(u64 word)
return __ffs((unsigned long)word);
}

+/**
+ * fns - find N'th set bit in a word
+ * @word: The word to search
+ * @n: Bit to find
+ */
+static inline unsigned long fns(unsigned long word, unsigned int n)
+{
+ unsigned int bit;
+
+ while (word) {
+ bit = __ffs(word);
+ if (n-- == 0)
+ return bit;
+ __clear_bit(bit, &word);
+ }
+
+ return BITS_PER_LONG;
+}
+
/**
* assign_bit - Assign value to a bit in memory
* @nr: the bit to set
diff --git a/include/linux/find.h b/include/linux/find.h
index 424ef67d4a42..4c7f82dcc38a 100644
--- a/include/linux/find.h
+++ b/include/linux/find.h
@@ -12,6 +12,8 @@ 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);
extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size);
+unsigned long _find_nth_bit(const unsigned long *addr1, const unsigned long *addr2,
+ unsigned long size, unsigned long n, unsigned long invert);
extern unsigned long _find_first_and_bit(const unsigned long *addr1,
const unsigned long *addr2, unsigned long size);
extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size);
@@ -125,6 +127,87 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
}
#endif

+/**
+ * find_nth_bit - find N'th set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum number of bits to search
+ * @n: The number of set bit, which position is needed, counting from 0
+ *
+ * The following is semantically equivalent:
+ * idx = find_nth_bit(addr, size, 0);
+ * idx = find_first_bit(addr, size);
+ *
+ * Returns the bit number of the N'th set bit.
+ * If no such, returns @size.
+ */
+static inline
+unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n)
+{
+ if (n >= size)
+ return size;
+
+ if (small_const_nbits(size)) {
+ unsigned long val = *addr & GENMASK(size - 1, 0);
+
+ return val ? fns(val, n) : size;
+ }
+
+ return _find_nth_bit(addr, NULL, size, n, 0UL);
+}
+
+/**
+ * find_nth_and_bit - find N'th set bit in 2 memory regions
+ * @addr1: The 1st address to start the search at
+ * @addr2: The 2nd address to start the search at
+ * @size: The maximum number of bits to search
+ * @n: The number of set bit, which position is needed, counting from 0
+ *
+ * Returns the bit number of the N'th set bit.
+ * If no such, returns @size.
+ */
+static inline
+unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2,
+ unsigned long size, unsigned long n)
+{
+ if (n >= size)
+ return size;
+
+ if (small_const_nbits(size)) {
+ unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0);
+
+ return val ? fns(val, n) : size;
+ }
+
+ return _find_nth_bit(addr1, addr2, size, n, 0UL);
+}
+
+/**
+ * find_nth_andnot_bit - find N'th set bit in 2 memory regions,
+ * flipping bits in 2nd region
+ * @addr1: The 1st address to start the search at
+ * @addr2: The 2nd address to start the search at
+ * @size: The maximum number of bits to search
+ * @n: The number of set bit, which position is needed, counting from 0
+ *
+ * Returns the bit number of the N'th set bit.
+ * If no such, returns @size.
+ */
+static inline
+unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
+ unsigned long size, unsigned long n)
+{
+ if (n >= size)
+ return size;
+
+ if (small_const_nbits(size)) {
+ unsigned long val = *addr1 & (~*addr2) & GENMASK(size - 1, 0);
+
+ return val ? fns(val, n) : size;
+ }
+
+ return _find_nth_bit(addr1, addr2, size, n, ~0UL);
+}
+
#ifndef find_first_and_bit
/**
* find_first_and_bit - find the first set bit in both memory regions
diff --git a/lib/find_bit.c b/lib/find_bit.c
index 1b8e4b2a9cba..43cb1f781056 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -89,6 +89,26 @@ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size)
EXPORT_SYMBOL(_find_first_bit);
#endif

+unsigned long _find_nth_bit(const unsigned long *addr1, const unsigned long *addr2,
+ unsigned long size, unsigned long n, unsigned long invert)
+{
+ unsigned long val, idx, w;
+
+ for (idx = 0; idx * BITS_PER_LONG < size; idx++, n -= w) {
+ val = addr1[idx];
+ if (addr2)
+ val &= addr2[idx] ^ invert;
+
+ w = hweight_long(val);
+ if (w > n)
+ return min(idx * BITS_PER_LONG + fns(val, n), size);
+ }
+
+ return size;
+
+}
+EXPORT_SYMBOL(_find_nth_bit);
+
#ifndef find_first_and_bit
/*
* Find the first set bit in two memory regions.
--
2.34.1
\
 
 \ /
  Last update: 2022-07-11 06:48    [W:0.137 / U:0.036 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site