diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-10-10 12:49:34 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-10-10 12:49:34 -0700 |
commit | d4013bc4d49f6da8178a340348369bb9920225c9 (patch) | |
tree | 3e7ad8a2b2d726179aca30d04d52c2fabef97e7c /lib/find_bit.c | |
parent | cdf072acb5baa18e5b05bdf3f13d6481f62396fc (diff) | |
parent | 585463f0d58aa4d29b744c7c53b222b8028de87f (diff) |
Merge tag 'bitmap-6.1-rc1' of https://github.com/norov/linux
Pull bitmap updates from Yury Norov:
- Fix unsigned comparison to -1 in CPUMAP_FILE_MAX_BYTES (Phil Auld)
- cleanup nr_cpu_ids vs nr_cpumask_bits mess (me)
This series cleans that mess and adds new config FORCE_NR_CPUS that
allows to optimize cpumask subsystem if the number of CPUs is known
at compile-time.
- optimize find_bit() functions (me)
Reworks find_bit() functions based on new FIND_{FIRST,NEXT}_BIT()
macros.
- add find_nth_bit() (me)
Adds find_nth_bit(), which is ~70 times faster than bitcounting with
for_each() loop:
for_each_set_bit(bit, mask, size)
if (n-- == 0)
return bit;
Also adds bitmap_weight_and() to let people replace this pattern:
tmp = bitmap_alloc(nbits);
bitmap_and(tmp, map1, map2, nbits);
weight = bitmap_weight(tmp, nbits);
bitmap_free(tmp);
with a single bitmap_weight_and() call.
- repair cpumask_check() (me)
After switching cpumask to use nr_cpu_ids, cpumask_check() started
generating many false-positive warnings. This series fixes it.
- Add for_each_cpu_andnot() and for_each_cpu_andnot() (Valentin
Schneider)
Extends the API with one more function and applies it in sched/core.
* tag 'bitmap-6.1-rc1' of https://github.com/norov/linux: (28 commits)
sched/core: Merge cpumask_andnot()+for_each_cpu() into for_each_cpu_andnot()
lib/test_cpumask: Add for_each_cpu_and(not) tests
cpumask: Introduce for_each_cpu_andnot()
lib/find_bit: Introduce find_next_andnot_bit()
cpumask: fix checking valid cpu range
lib/bitmap: add tests for for_each() loops
lib/find: optimize for_each() macros
lib/bitmap: introduce for_each_set_bit_wrap() macro
lib/find_bit: add find_next{,_and}_bit_wrap
cpumask: switch for_each_cpu{,_not} to use for_each_bit()
net: fix cpu_max_bits_warn() usage in netif_attrmask_next{,_and}
cpumask: add cpumask_nth_{,and,andnot}
lib/bitmap: remove bitmap_ord_to_pos
lib/bitmap: add tests for find_nth_bit()
lib: add find_nth{,_and,_andnot}_bit()
lib/bitmap: add bitmap_weight_and()
lib/bitmap: don't call __bitmap_weight() in kernel code
tools: sync find_bit() implementation
lib/find_bit: optimize find_next_bit() functions
lib/find_bit: create find_first_zero_bit_le()
...
Diffstat (limited to 'lib/find_bit.c')
-rw-r--r-- | lib/find_bit.c | 233 |
1 files changed, 161 insertions, 72 deletions
diff --git a/lib/find_bit.c b/lib/find_bit.c index 1b8e4b2a9cba..18bc0a7ac8ee 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -19,57 +19,78 @@ #include <linux/minmax.h> #include <linux/swab.h> -#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ - !defined(find_next_bit_le) || !defined(find_next_zero_bit_le) || \ - !defined(find_next_and_bit) /* - * This is a common helper function for find_next_bit, find_next_zero_bit, and - * find_next_and_bit. The differences are: - * - The "invert" argument, which is XORed with each fetched word before - * searching it for one bits. - * - The optional "addr2", which is anded with "addr1" if present. + * Common helper for find_bit() function family + * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) + * @MUNGE: The expression that post-processes a word containing found bit (may be empty) + * @size: The bitmap size in bits */ -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 tmp, mask; - - if (unlikely(start >= nbits)) - return nbits; - - tmp = addr1[start / BITS_PER_LONG]; - if (addr2) - tmp &= addr2[start / BITS_PER_LONG]; - tmp ^= invert; - - /* Handle 1st word. */ - mask = BITMAP_FIRST_WORD_MASK(start); - if (le) - mask = swab(mask); - - tmp &= mask; - - start = round_down(start, BITS_PER_LONG); - - while (!tmp) { - start += BITS_PER_LONG; - if (start >= nbits) - return nbits; - - tmp = addr1[start / BITS_PER_LONG]; - if (addr2) - tmp &= addr2[start / BITS_PER_LONG]; - tmp ^= invert; - } +#define FIND_FIRST_BIT(FETCH, MUNGE, size) \ +({ \ + unsigned long idx, val, sz = (size); \ + \ + for (idx = 0; idx * BITS_PER_LONG < sz; idx++) { \ + val = (FETCH); \ + if (val) { \ + sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(val)), sz); \ + break; \ + } \ + } \ + \ + sz; \ +}) - if (le) - tmp = swab(tmp); - - return min(start + __ffs(tmp), nbits); -} -EXPORT_SYMBOL(_find_next_bit); -#endif +/* + * Common helper for find_next_bit() function family + * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) + * @MUNGE: The expression that post-processes a word containing found bit (may be empty) + * @size: The bitmap size in bits + * @start: The bitnumber to start searching at + */ +#define FIND_NEXT_BIT(FETCH, MUNGE, size, start) \ +({ \ + unsigned long mask, idx, tmp, sz = (size), __start = (start); \ + \ + if (unlikely(__start >= sz)) \ + goto out; \ + \ + mask = MUNGE(BITMAP_FIRST_WORD_MASK(__start)); \ + idx = __start / BITS_PER_LONG; \ + \ + for (tmp = (FETCH) & mask; !tmp; tmp = (FETCH)) { \ + if ((idx + 1) * BITS_PER_LONG >= sz) \ + goto out; \ + idx++; \ + } \ + \ + sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(tmp)), sz); \ +out: \ + sz; \ +}) + +#define FIND_NTH_BIT(FETCH, size, num) \ +({ \ + unsigned long sz = (size), nr = (num), idx, w, tmp; \ + \ + for (idx = 0; (idx + 1) * BITS_PER_LONG <= sz; idx++) { \ + if (idx * BITS_PER_LONG + nr >= sz) \ + goto out; \ + \ + tmp = (FETCH); \ + w = hweight_long(tmp); \ + if (w > nr) \ + goto found; \ + \ + nr -= w; \ + } \ + \ + if (sz % BITS_PER_LONG) \ + tmp = (FETCH) & BITMAP_LAST_WORD_MASK(sz); \ +found: \ + sz = min(idx * BITS_PER_LONG + fns(tmp, nr), sz); \ +out: \ + sz; \ +}) #ifndef find_first_bit /* @@ -77,14 +98,7 @@ EXPORT_SYMBOL(_find_next_bit); */ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) { - unsigned long idx; - - for (idx = 0; idx * BITS_PER_LONG < size; idx++) { - if (addr[idx]) - return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size); - } - - return size; + return FIND_FIRST_BIT(addr[idx], /* nop */, size); } EXPORT_SYMBOL(_find_first_bit); #endif @@ -97,15 +111,7 @@ unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) { - unsigned long idx, val; - - for (idx = 0; idx * BITS_PER_LONG < size; idx++) { - val = addr1[idx] & addr2[idx]; - if (val) - return min(idx * BITS_PER_LONG + __ffs(val), size); - } - - return size; + return FIND_FIRST_BIT(addr1[idx] & addr2[idx], /* nop */, size); } EXPORT_SYMBOL(_find_first_and_bit); #endif @@ -116,16 +122,64 @@ EXPORT_SYMBOL(_find_first_and_bit); */ unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size) { - unsigned long idx; + return FIND_FIRST_BIT(~addr[idx], /* nop */, size); +} +EXPORT_SYMBOL(_find_first_zero_bit); +#endif - for (idx = 0; idx * BITS_PER_LONG < size; idx++) { - if (addr[idx] != ~0UL) - return min(idx * BITS_PER_LONG + ffz(addr[idx]), size); - } +#ifndef find_next_bit +unsigned long _find_next_bit(const unsigned long *addr, unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr[idx], /* nop */, nbits, start); +} +EXPORT_SYMBOL(_find_next_bit); +#endif - return size; +unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) +{ + return FIND_NTH_BIT(addr[idx], size, n); } -EXPORT_SYMBOL(_find_first_zero_bit); +EXPORT_SYMBOL(__find_nth_bit); + +unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n) +{ + return FIND_NTH_BIT(addr1[idx] & addr2[idx], size, n); +} +EXPORT_SYMBOL(__find_nth_and_bit); + +unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n) +{ + return FIND_NTH_BIT(addr1[idx] & ~addr2[idx], size, n); +} +EXPORT_SYMBOL(__find_nth_andnot_bit); + +#ifndef find_next_and_bit +unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr1[idx] & addr2[idx], /* nop */, nbits, start); +} +EXPORT_SYMBOL(_find_next_and_bit); +#endif + +#ifndef find_next_andnot_bit +unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr1[idx] & ~addr2[idx], /* nop */, nbits, start); +} +EXPORT_SYMBOL(_find_next_andnot_bit); +#endif + +#ifndef find_next_zero_bit +unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, + unsigned long start) +{ + return FIND_NEXT_BIT(~addr[idx], /* nop */, nbits, start); +} +EXPORT_SYMBOL(_find_next_zero_bit); #endif #ifndef find_last_bit @@ -161,3 +215,38 @@ unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, return offset; } EXPORT_SYMBOL(find_next_clump8); + +#ifdef __BIG_ENDIAN + +#ifndef find_first_zero_bit_le +/* + * Find the first cleared bit in an LE memory region. + */ +unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size) +{ + return FIND_FIRST_BIT(~addr[idx], swab, size); +} +EXPORT_SYMBOL(_find_first_zero_bit_le); + +#endif + +#ifndef find_next_zero_bit_le +unsigned long _find_next_zero_bit_le(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + return FIND_NEXT_BIT(~addr[idx], swab, size, offset); +} +EXPORT_SYMBOL(_find_next_zero_bit_le); +#endif + +#ifndef find_next_bit_le +unsigned long _find_next_bit_le(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + return FIND_NEXT_BIT(addr[idx], swab, size, offset); +} +EXPORT_SYMBOL(_find_next_bit_le); + +#endif + +#endif /* __BIG_ENDIAN */ |