From 63c15822b8dd02a2423cfd92232245ace3f7a11b Mon Sep 17 00:00:00 2001 From: Syed Nayyar Waris Date: Wed, 27 Mar 2024 16:23:38 +0100 Subject: lib/bitmap: add bitmap_{read,write}() The two new functions allow reading/writing values of length up to BITS_PER_LONG bits at arbitrary position in the bitmap. The code was taken from "bitops: Introduce the for_each_set_clump macro" by Syed Nayyar Waris with a number of changes and simplifications: - instead of using roundup(), which adds an unnecessary dependency on , we calculate space as BITS_PER_LONG-offset; - indentation is reduced by not using else-clauses (suggested by checkpatch for bitmap_get_value()); - bitmap_get_value()/bitmap_set_value() are renamed to bitmap_read() and bitmap_write(); - some redundant computations are omitted. Cc: Arnd Bergmann Signed-off-by: Syed Nayyar Waris Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/lkml/fe12eedf3666f4af5138de0e70b67a07c7f40338.1592224129.git.syednwaris@gmail.com/ Suggested-by: Yury Norov Co-developed-by: Alexander Potapenko Signed-off-by: Alexander Potapenko Reviewed-by: Andy Shevchenko Acked-by: Yury Norov Signed-off-by: Yury Norov Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- include/linux/bitmap.h | 77 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 77 insertions(+) (limited to 'include/linux/bitmap.h') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index aa4096126553..914c23e96f26 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -83,6 +83,10 @@ struct device; * bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst * bitmap_get_value8(map, start) Get 8bit value from map at start * bitmap_set_value8(map, value, start) Set 8bit value to map at start + * bitmap_read(map, start, nbits) Read an nbits-sized value from + * map at start + * bitmap_write(map, value, start, nbits) Write an nbits-sized value to + * map at start * * Note, bitmap_zero() and bitmap_fill() operate over the region of * unsigned longs, that is, bits behind bitmap till the unsigned long @@ -754,6 +758,79 @@ static inline void bitmap_set_value8(unsigned long *map, unsigned long value, map[index] |= value << offset; } +/** + * bitmap_read - read a value of n-bits from the memory region + * @map: address to the bitmap memory region + * @start: bit offset of the n-bit value + * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG + * + * Returns: value of @nbits bits located at the @start bit offset within the + * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return + * value is undefined. + */ +static inline unsigned long bitmap_read(const unsigned long *map, + unsigned long start, + unsigned long nbits) +{ + size_t index = BIT_WORD(start); + unsigned long offset = start % BITS_PER_LONG; + unsigned long space = BITS_PER_LONG - offset; + unsigned long value_low, value_high; + + if (unlikely(!nbits || nbits > BITS_PER_LONG)) + return 0; + + if (space >= nbits) + return (map[index] >> offset) & BITMAP_LAST_WORD_MASK(nbits); + + value_low = map[index] & BITMAP_FIRST_WORD_MASK(start); + value_high = map[index + 1] & BITMAP_LAST_WORD_MASK(start + nbits); + return (value_low >> offset) | (value_high << space); +} + +/** + * bitmap_write - write n-bit value within a memory region + * @map: address to the bitmap memory region + * @value: value to write, clamped to nbits + * @start: bit offset of the n-bit value + * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG. + * + * bitmap_write() behaves as-if implemented as @nbits calls of __assign_bit(), + * i.e. bits beyond @nbits are ignored: + * + * for (bit = 0; bit < nbits; bit++) + * __assign_bit(start + bit, bitmap, val & BIT(bit)); + * + * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed. + */ +static inline void bitmap_write(unsigned long *map, unsigned long value, + unsigned long start, unsigned long nbits) +{ + size_t index; + unsigned long offset; + unsigned long space; + unsigned long mask; + bool fit; + + if (unlikely(!nbits || nbits > BITS_PER_LONG)) + return; + + mask = BITMAP_LAST_WORD_MASK(nbits); + value &= mask; + offset = start % BITS_PER_LONG; + space = BITS_PER_LONG - offset; + fit = space >= nbits; + index = BIT_WORD(start); + + map[index] &= (fit ? (~(mask << offset)) : ~BITMAP_FIRST_WORD_MASK(start)); + map[index] |= value << offset; + if (fit) + return; + + map[index + 1] &= BITMAP_FIRST_WORD_MASK(start + nbits); + map[index + 1] |= (value >> space); +} + #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ -- cgit v1.2.3 From a37fbe666c016fd89e4460d0ebfcea05baba46dc Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Wed, 27 Mar 2024 16:23:49 +0100 Subject: 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 Acked-by: Yury Norov Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- drivers/md/dm-clone-metadata.c | 5 ----- drivers/s390/cio/idset.c | 2 +- include/linux/bitmap.h | 8 +++++--- include/linux/cpumask.h | 2 +- lib/math/prime_numbers.c | 2 -- tools/include/linux/bitmap.h | 7 ++++--- 6 files changed, 11 insertions(+), 15 deletions(-) (limited to 'include/linux/bitmap.h') diff --git a/drivers/md/dm-clone-metadata.c b/drivers/md/dm-clone-metadata.c index c43d55672bce..47c1fa7aad8b 100644 --- a/drivers/md/dm-clone-metadata.c +++ b/drivers/md/dm-clone-metadata.c @@ -465,11 +465,6 @@ static void __destroy_persistent_data_structures(struct dm_clone_metadata *cmd) /*---------------------------------------------------------------------------*/ -static size_t bitmap_size(unsigned long nr_bits) -{ - return BITS_TO_LONGS(nr_bits) * sizeof(long); -} - static int __dirty_map_init(struct dirty_map *dmap, unsigned long nr_words, unsigned long nr_regions) { diff --git a/drivers/s390/cio/idset.c b/drivers/s390/cio/idset.c index 0a1105a483bf..e5f28370a903 100644 --- a/drivers/s390/cio/idset.c +++ b/drivers/s390/cio/idset.c @@ -18,7 +18,7 @@ struct idset { static inline unsigned long idset_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) 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); } /* diff --git a/lib/math/prime_numbers.c b/lib/math/prime_numbers.c index d42cebf7407f..d3b64b10da1c 100644 --- a/lib/math/prime_numbers.c +++ b/lib/math/prime_numbers.c @@ -6,8 +6,6 @@ #include #include -#define bitmap_size(nbits) (BITS_TO_LONGS(nbits) * sizeof(unsigned long)) - struct primes { struct rcu_head rcu; unsigned long last, sz; diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 8c6852dba04f..210c13b1b857 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -26,13 +26,14 @@ bool __bitmap_intersects(const unsigned long *bitmap1, #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) { 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)); } } @@ -84,7 +85,7 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, */ static inline unsigned long *bitmap_zalloc(int nbits) { - return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long)); + return calloc(1, bitmap_size(nbits)); } /* -- cgit v1.2.3 From b44759705f7dc95d539d145b4c2edcaf079e7c33 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Wed, 27 Mar 2024 16:23:50 +0100 Subject: bitmap: make bitmap_{get,set}_value8() use bitmap_{read,write}() Now that we have generic bitmap_read() and bitmap_write(), which are inline and try to take care of non-bound-crossing and aligned cases to keep them optimized, collapse bitmap_{get,set}_value8() into simple wrappers around the former ones. bloat-o-meter shows no difference in vmlinux and -2 bytes for gpio-pca953x.ko, which says the optimization didn't suffer due to that change. The converted helpers have the value width embedded and always compile-time constant and that helps a lot. Suggested-by: Yury Norov Signed-off-by: Yury Norov Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- include/linux/bitmap.h | 38 +++++--------------------------------- 1 file changed, 5 insertions(+), 33 deletions(-) (limited to 'include/linux/bitmap.h') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 363e0b184a45..8c4768c44a01 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -727,39 +727,6 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) bitmap_from_arr64(dst, &mask, 64); } -/** - * bitmap_get_value8 - get an 8-bit value within a memory region - * @map: address to the bitmap memory region - * @start: bit offset of the 8-bit value; must be a multiple of 8 - * - * Returns the 8-bit value located at the @start bit offset within the @src - * memory region. - */ -static inline unsigned long bitmap_get_value8(const unsigned long *map, - unsigned long start) -{ - const size_t index = BIT_WORD(start); - const unsigned long offset = start % BITS_PER_LONG; - - return (map[index] >> offset) & 0xFF; -} - -/** - * bitmap_set_value8 - set an 8-bit value within a memory region - * @map: address to the bitmap memory region - * @value: the 8-bit value; values wider than 8 bits may clobber bitmap - * @start: bit offset of the 8-bit value; must be a multiple of 8 - */ -static inline void bitmap_set_value8(unsigned long *map, unsigned long value, - unsigned long start) -{ - const size_t index = BIT_WORD(start); - const unsigned long offset = start % BITS_PER_LONG; - - map[index] &= ~(0xFFUL << offset); - map[index] |= value << offset; -} - /** * bitmap_read - read a value of n-bits from the memory region * @map: address to the bitmap memory region @@ -833,6 +800,11 @@ static inline void bitmap_write(unsigned long *map, unsigned long value, map[index + 1] |= (value >> space); } +#define bitmap_get_value8(map, start) \ + bitmap_read(map, start, BITS_PER_BYTE) +#define bitmap_set_value8(map, value, start) \ + bitmap_write(map, value, start, BITS_PER_BYTE) + #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ -- cgit v1.2.3