From e5af323c9badd5dc09af7ccf9d45616ebffc623c Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 10 Jul 2017 15:51:29 -0700 Subject: bitmap: optimise bitmap_set and bitmap_clear of a single bit We have eight users calling bitmap_clear for a single bit and seventeen calling bitmap_set for a single bit. Rather than fix all of them to call __clear_bit or __set_bit, turn bitmap_clear and bitmap_set into inline functions and make this special case efficient. Link: http://lkml.kernel.org/r/20170628153221.11322-3-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Rasmus Villemoes Cc: Martin Schwidefsky Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) (limited to 'include/linux/bitmap.h') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 3b77588a9360..4e0f0c8167af 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -112,9 +112,8 @@ extern int __bitmap_intersects(const unsigned long *bitmap1, extern int __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); - -extern void bitmap_set(unsigned long *map, unsigned int start, int len); -extern void bitmap_clear(unsigned long *map, unsigned int start, int len); +extern void __bitmap_set(unsigned long *map, unsigned int start, int len); +extern void __bitmap_clear(unsigned long *map, unsigned int start, int len); extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, @@ -315,6 +314,24 @@ static __always_inline int bitmap_weight(const unsigned long *src, unsigned int return __bitmap_weight(src, nbits); } +static __always_inline void bitmap_set(unsigned long *map, unsigned int start, + unsigned int nbits) +{ + if (__builtin_constant_p(nbits) && nbits == 1) + __set_bit(start, map); + else + __bitmap_set(map, start, nbits); +} + +static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, + unsigned int nbits) +{ + if (__builtin_constant_p(nbits) && nbits == 1) + __clear_bit(start, map); + else + __bitmap_clear(map, start, nbits); +} + static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, int nbits) { -- cgit v1.2.3 From 2a98dc028f911a7c59c87d11d4eed6626be1605b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 10 Jul 2017 15:51:32 -0700 Subject: include/linux/bitmap.h: turn bitmap_set and bitmap_clear into memset when possible Several callers have constant 'start' and an 'nbits' that is a multiple of 8, so we can turn them into calls to memset. We don't need the entirety of 'start' and 'nbits' to be constant, we just need to know whether they're divisible by 8. Link: http://lkml.kernel.org/r/20170628153221.11322-4-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Rasmus Villemoes Cc: Martin Schwidefsky Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/bitmap.h') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 4e0f0c8167af..c04c9d155e59 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -319,6 +319,9 @@ static __always_inline void bitmap_set(unsigned long *map, unsigned int start, { if (__builtin_constant_p(nbits) && nbits == 1) __set_bit(start, map); + else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) && + __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) + memset((char *)map + start / 8, 0xff, nbits / 8); else __bitmap_set(map, start, nbits); } @@ -328,6 +331,9 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, { if (__builtin_constant_p(nbits) && nbits == 1) __clear_bit(start, map); + else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) && + __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) + memset((char *)map + start / 8, 0, nbits / 8); else __bitmap_clear(map, start, nbits); } -- cgit v1.2.3 From 2c6deb01525ac11cc03c44fe31e3f45ce2cadaf9 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 10 Jul 2017 15:51:35 -0700 Subject: bitmap: use memcmp optimisation in more situations Commit 7dd968163f7c ("bitmap: bitmap_equal memcmp optimization") was rather more restrictive than necessary; we can use memcmp() to implement bitmap_equal() as long as the number of bits can be proved to be a multiple of 8. And architectures other than s390 may be able to make good use of this optimisation. [arnd@arndb.de: fix build: add a memcmp() declaration] Link: http://lkml.kernel.org/r/20170630153908.3439707-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628153221.11322-5-willy@infradead.org Signed-off-by: Matthew Wilcox Signed-off-by: Arnd Bergmann Acked-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/boot/compressed/decompress.c | 1 + include/linux/bitmap.h | 4 +--- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux/bitmap.h') diff --git a/arch/arm/boot/compressed/decompress.c b/arch/arm/boot/compressed/decompress.c index ea7832702a8f..f3a4bedd1afc 100644 --- a/arch/arm/boot/compressed/decompress.c +++ b/arch/arm/boot/compressed/decompress.c @@ -33,6 +33,7 @@ extern void error(char *); /* Not needed, but used in some headers pulled in by decompressors */ extern char * strstr(const char * s1, const char *s2); extern size_t strlen(const char *s); +extern int memcmp(const void *cs, const void *ct, size_t count); #ifdef CONFIG_KERNEL_GZIP #include "../../../../lib/decompress_inflate.c" diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index c04c9d155e59..5797ca6fdfe2 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -266,10 +266,8 @@ static inline int bitmap_equal(const unsigned long *src1, { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); -#ifdef CONFIG_S390 - if (__builtin_constant_p(nbits) && (nbits % BITS_PER_LONG) == 0) + if (__builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) return !memcmp(src1, src2, nbits / 8); -#endif return __bitmap_equal(src1, src2, nbits); } -- cgit v1.2.3