From 47d8c15615c0a2046d2d90b04cb80b81ddf31fb1 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:16:59 -0700 Subject: include: move find.h from asm_generic to linux find_bit API and bitmap API are closely related, but inclusion paths are different - include/asm-generic and include/linux, correspondingly. In the past it made a lot of troubles due to circular dependencies and/or undefined symbols. Fix this by moving find.h under include/linux. Signed-off-by: Yury Norov Tested-by: Wolfram Sang Acked-by: Geert Uytterhoeven --- include/linux/bitmap.h | 1 + include/linux/find.h | 268 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 269 insertions(+) create mode 100644 include/linux/find.h (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index a241dcf50f39..ead4a150bd7f 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -6,6 +6,7 @@ #include #include +#include #include #include #include diff --git a/include/linux/find.h b/include/linux/find.h new file mode 100644 index 000000000000..c5410c243e04 --- /dev/null +++ b/include/linux/find.h @@ -0,0 +1,268 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_FIND_H_ +#define __LINUX_FIND_H_ + +#ifndef __LINUX_BITMAP_H +#error only can be included directly +#endif + +#include + +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); +extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); +extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); + +#ifndef find_next_bit +/** + * find_next_bit - find the next set bit in a memory region + * @addr: The address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_bit(addr, NULL, size, offset, 0UL, 0); +} +#endif + +#ifndef find_next_and_bit +/** + * find_next_and_bit - find the next set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr1 & *addr2 & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); +} +#endif + +#ifndef find_next_zero_bit +/** + * find_next_zero_bit - find the next cleared bit in a memory region + * @addr: The address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + * + * Returns the bit number of the next zero bit + * If no bits are zero, returns @size. + */ +static inline +unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr | ~GENMASK(size - 1, offset); + return val == ~0UL ? size : ffz(val); + } + + return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); +} +#endif + +#ifdef CONFIG_GENERIC_FIND_FIRST_BIT + +#ifndef find_first_bit +/** + * find_first_bit - find the first set bit in a memory region + * @addr: The address to start the search at + * @size: The maximum number of bits to search + * + * Returns the bit number of the first set bit. + * If no bits are set, returns @size. + */ +static inline +unsigned long find_first_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_bit(addr, size); +} +#endif + +#ifndef find_first_zero_bit +/** + * find_first_zero_bit - find the first cleared bit in a memory region + * @addr: The address to start the search at + * @size: The maximum number of bits to search + * + * Returns the bit number of the first cleared bit. + * If no bits are zero, returns @size. + */ +static inline +unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr | ~GENMASK(size - 1, 0); + + return val == ~0UL ? size : ffz(val); + } + + return _find_first_zero_bit(addr, size); +} +#endif + +#else /* CONFIG_GENERIC_FIND_FIRST_BIT */ + +#ifndef find_first_bit +#define find_first_bit(addr, size) find_next_bit((addr), (size), 0) +#endif +#ifndef find_first_zero_bit +#define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0) +#endif + +#endif /* CONFIG_GENERIC_FIND_FIRST_BIT */ + +#ifndef find_last_bit +/** + * find_last_bit - find the last set bit in a memory region + * @addr: The address to start the search at + * @size: The number of bits to search + * + * Returns the bit number of the last set bit, or size. + */ +static inline +unsigned long find_last_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr & GENMASK(size - 1, 0); + + return val ? __fls(val) : size; + } + + return _find_last_bit(addr, size); +} +#endif + +/** + * find_next_clump8 - find next 8-bit clump with set bits in a memory region + * @clump: location to store copy of found clump + * @addr: address to base the search on + * @size: bitmap size in number of bits + * @offset: bit offset at which to start searching + * + * Returns the bit offset for the next set clump; the found clump value is + * copied to the location pointed by @clump. If no bits are set, returns @size. + */ +extern unsigned long find_next_clump8(unsigned long *clump, + const unsigned long *addr, + unsigned long size, unsigned long offset); + +#define find_first_clump8(clump, bits, size) \ + find_next_clump8((clump), (bits), (size), 0) + +#if defined(__LITTLE_ENDIAN) + +static inline unsigned long find_next_zero_bit_le(const void *addr, + unsigned long size, unsigned long offset) +{ + return find_next_zero_bit(addr, size, offset); +} + +static inline unsigned long find_next_bit_le(const void *addr, + unsigned long size, unsigned long offset) +{ + return find_next_bit(addr, size, offset); +} + +static inline unsigned long find_first_zero_bit_le(const void *addr, + unsigned long size) +{ + return find_first_zero_bit(addr, size); +} + +#elif defined(__BIG_ENDIAN) + +#ifndef find_next_zero_bit_le +static inline +unsigned long find_next_zero_bit_le(const void *addr, unsigned + long size, unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val = *(const unsigned long *)addr; + + if (unlikely(offset >= size)) + return size; + + val = swab(val) | ~GENMASK(size - 1, offset); + return val == ~0UL ? size : ffz(val); + } + + return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); +} +#endif + +#ifndef find_next_bit_le +static inline +unsigned long find_next_bit_le(const void *addr, unsigned + long size, unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val = *(const unsigned long *)addr; + + if (unlikely(offset >= size)) + return size; + + val = swab(val) & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_bit(addr, NULL, size, offset, 0UL, 1); +} +#endif + +#ifndef find_first_zero_bit_le +#define find_first_zero_bit_le(addr, size) \ + find_next_zero_bit_le((addr), (size), 0) +#endif + +#else +#error "Please fix " +#endif + +#endif /*__LINUX_FIND_H_ */ -- cgit v1.2.3-71-gd317 From c126a53c276048125b4a950072bab37ad0fea120 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:17:00 -0700 Subject: arch: remove GENERIC_FIND_FIRST_BIT entirely In 5.12 cycle we enabled GENERIC_FIND_FIRST_BIT config option for ARM64 and MIPS. It increased performance and shrunk .text size; and so far I didn't receive any negative feedback on the change. https://lore.kernel.org/linux-arch/20210225135700.1381396-1-yury.norov@gmail.com/ Now I think it's a good time to switch all architectures to use find_{first,last}_bit() unconditionally, and so remove corresponding config option. The patch does't introduce functioal changes for arc, arm, arm64, mips, m68k, s390 and x86, for other architectures I expect improvement both in performance and .text size. Signed-off-by: Yury Norov Tested-by: Alexander Lobakin (mips) Reviewed-by: Alexander Lobakin (mips) Reviewed-by: Andy Shevchenko Acked-by: Will Deacon Tested-by: Wolfram Sang --- arch/arc/Kconfig | 1 - arch/arm64/Kconfig | 1 - arch/mips/Kconfig | 1 - arch/s390/Kconfig | 1 - arch/x86/Kconfig | 1 - arch/x86/um/Kconfig | 1 - include/linux/find.h | 13 ------------- lib/Kconfig | 3 --- 8 files changed, 22 deletions(-) (limited to 'include/linux') diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index b4ae6058902a..4bec4b0b6ce1 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -20,7 +20,6 @@ config ARC select COMMON_CLK select DMA_DIRECT_REMAP select GENERIC_ATOMIC64 if !ISA_ARCV2 || !(ARC_HAS_LL64 && ARC_HAS_LLSC) - select GENERIC_FIND_FIRST_BIT # for now, we don't need GENERIC_IRQ_PROBE, CONFIG_GENERIC_IRQ_CHIP select GENERIC_IRQ_SHOW select GENERIC_PCI_IOMAP diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index c4207cf9bb17..517d26c8002d 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -120,7 +120,6 @@ config ARM64 select GENERIC_CPU_AUTOPROBE select GENERIC_CPU_VULNERABILITIES select GENERIC_EARLY_IOREMAP - select GENERIC_FIND_FIRST_BIT select GENERIC_IDLE_POLL_SETUP select GENERIC_IRQ_IPI select GENERIC_IRQ_PROBE diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 0215dc1529e9..00951bfdbab0 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -32,7 +32,6 @@ config MIPS select GENERIC_ATOMIC64 if !64BIT select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE - select GENERIC_FIND_FIRST_BIT select GENERIC_GETTIMEOFDAY select GENERIC_IOMAP select GENERIC_IRQ_PROBE diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 2a5bb4f29cfe..4f80f1c95468 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -127,7 +127,6 @@ config S390 select GENERIC_CPU_AUTOPROBE select GENERIC_CPU_VULNERABILITIES select GENERIC_ENTRY - select GENERIC_FIND_FIRST_BIT select GENERIC_GETTIMEOFDAY select GENERIC_PTDUMP select GENERIC_SMP_IDLE_THREAD diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5c2ccb85f2ef..60484b39257c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -136,7 +136,6 @@ config X86 select GENERIC_CPU_VULNERABILITIES select GENERIC_EARLY_IOREMAP select GENERIC_ENTRY - select GENERIC_FIND_FIRST_BIT select GENERIC_IOMAP select GENERIC_IRQ_EFFECTIVE_AFF_MASK if SMP select GENERIC_IRQ_MATRIX_ALLOCATOR if X86_LOCAL_APIC diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index 95d26a69088b..40d6a06e41c8 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -8,7 +8,6 @@ endmenu config UML_X86 def_bool y - select GENERIC_FIND_FIRST_BIT config 64BIT bool "64-bit kernel" if "$(SUBARCH)" = "x86" diff --git a/include/linux/find.h b/include/linux/find.h index c5410c243e04..ea57f7f38c49 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -101,8 +101,6 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, } #endif -#ifdef CONFIG_GENERIC_FIND_FIRST_BIT - #ifndef find_first_bit /** * find_first_bit - find the first set bit in a memory region @@ -147,17 +145,6 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) } #endif -#else /* CONFIG_GENERIC_FIND_FIRST_BIT */ - -#ifndef find_first_bit -#define find_first_bit(addr, size) find_next_bit((addr), (size), 0) -#endif -#ifndef find_first_zero_bit -#define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0) -#endif - -#endif /* CONFIG_GENERIC_FIND_FIRST_BIT */ - #ifndef find_last_bit /** * find_last_bit - find the last set bit in a memory region diff --git a/lib/Kconfig b/lib/Kconfig index 5e7165e6a346..6a6ae5312fa0 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -65,9 +65,6 @@ config GENERIC_STRNLEN_USER config GENERIC_NET_UTILS bool -config GENERIC_FIND_FIRST_BIT - bool - source "lib/math/Kconfig" config NO_GENERIC_PCI_IOPORT_MAP -- cgit v1.2.3-71-gd317 From f68edc9297bf3f7c94abb54b9b0b053607f7587b Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:17:01 -0700 Subject: lib: add find_first_and_bit() Currently find_first_and_bit() is an alias to find_next_and_bit(). However, it is widely used in cpumask, so it worth to optimize it. This patch adds its own implementation for find_first_and_bit(). On x86_64 find_bit_benchmark says: Before (#define find_first_and_bit(...) find_next_and_bit(..., 0): Start testing find_bit() with random-filled bitmap [ 140.291468] find_first_and_bit: 46890919 ns, 32671 iterations Start testing find_bit() with sparse bitmap [ 140.295028] find_first_and_bit: 7103 ns, 1 iterations After: Start testing find_bit() with random-filled bitmap [ 162.574907] find_first_and_bit: 25045813 ns, 32846 iterations Start testing find_bit() with sparse bitmap [ 162.578458] find_first_and_bit: 4900 ns, 1 iterations (Thanks to Alexey Klimov for thorough testing.) Signed-off-by: Yury Norov Tested-by: Wolfram Sang Tested-by: Alexey Klimov --- include/linux/find.h | 27 +++++++++++++++++++++++++++ lib/find_bit.c | 21 +++++++++++++++++++++ lib/find_bit_benchmark.c | 21 +++++++++++++++++++++ 3 files changed, 69 insertions(+) (limited to 'include/linux') diff --git a/include/linux/find.h b/include/linux/find.h index ea57f7f38c49..6048f8c97418 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); +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); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); @@ -123,6 +125,31 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) } #endif +#ifndef find_first_and_bit +/** + * find_first_and_bit - find the first set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_first_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_and_bit(addr1, addr2, size); +} +#endif + #ifndef find_first_zero_bit /** * find_first_zero_bit - find the first cleared bit in a memory region diff --git a/lib/find_bit.c b/lib/find_bit.c index 0f8e2e369b1d..1b8e4b2a9cba 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -89,6 +89,27 @@ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) EXPORT_SYMBOL(_find_first_bit); #endif +#ifndef find_first_and_bit +/* + * Find the first set bit in two memory regions. + */ +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; +} +EXPORT_SYMBOL(_find_first_and_bit); +#endif + #ifndef find_first_zero_bit /* * Find the first cleared bit in a memory region. diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c index 5637c5711db9..db904b57d4b8 100644 --- a/lib/find_bit_benchmark.c +++ b/lib/find_bit_benchmark.c @@ -49,6 +49,25 @@ static int __init test_find_first_bit(void *bitmap, unsigned long len) return 0; } +static int __init test_find_first_and_bit(void *bitmap, const void *bitmap2, unsigned long len) +{ + static DECLARE_BITMAP(cp, BITMAP_LEN) __initdata; + unsigned long i, cnt; + ktime_t time; + + bitmap_copy(cp, bitmap, BITMAP_LEN); + + time = ktime_get(); + for (cnt = i = 0; i < len; cnt++) { + i = find_first_and_bit(cp, bitmap2, len); + __clear_bit(i, cp); + } + time = ktime_get() - time; + pr_err("find_first_and_bit: %18llu ns, %6ld iterations\n", time, cnt); + + return 0; +} + static int __init test_find_next_bit(const void *bitmap, unsigned long len) { unsigned long i, cnt; @@ -129,6 +148,7 @@ static int __init find_bit_test(void) * traverse only part of bitmap to avoid soft lockup. */ test_find_first_bit(bitmap, BITMAP_LEN / 10); + test_find_first_and_bit(bitmap, bitmap2, BITMAP_LEN / 2); test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN); pr_err("\nStart testing find_bit() with sparse bitmap\n"); @@ -145,6 +165,7 @@ static int __init find_bit_test(void) test_find_next_zero_bit(bitmap, BITMAP_LEN); test_find_last_bit(bitmap, BITMAP_LEN); test_find_first_bit(bitmap, BITMAP_LEN); + test_find_first_and_bit(bitmap, bitmap2, BITMAP_LEN); test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN); /* -- cgit v1.2.3-71-gd317 From 93ba139ba8190c33009c5353ca43c8519443f467 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:17:02 -0700 Subject: cpumask: use find_first_and_bit() Now we have an efficient implementation for find_first_and_bit(), so switch cpumask to use it where appropriate. Signed-off-by: Yury Norov Tested-by: Wolfram Sang --- include/linux/cpumask.h | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 1e7399fc69c0..c4e1b9ea0ba4 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -123,6 +123,12 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) return 0; } +static inline unsigned int cpumask_first_and(const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return 0; +} + static inline unsigned int cpumask_last(const struct cpumask *srcp) { return 0; @@ -167,7 +173,7 @@ static inline unsigned int cpumask_local_spread(unsigned int i, int node) static inline int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { - return cpumask_next_and(-1, src1p, src2p); + return cpumask_first_and(src1p, src2p); } static inline int cpumask_any_distribute(const struct cpumask *srcp) @@ -195,6 +201,19 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits); } +/** + * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 + * @src1p: the first input + * @src2p: the second input + * + * Returns >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). + */ +static inline +unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) +{ + return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), nr_cpumask_bits); +} + /** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer @@ -585,15 +604,6 @@ static inline void cpumask_copy(struct cpumask *dstp, */ #define cpumask_any(srcp) cpumask_first(srcp) -/** - * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 - * @src1p: the first input - * @src2p: the second input - * - * Returns >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). - */ -#define cpumask_first_and(src1p, src2p) cpumask_next_and(-1, (src1p), (src2p)) - /** * cpumask_any_and - pick a "random" cpu from *mask1 & *mask2 * @mask1: the first input cpumask -- cgit v1.2.3-71-gd317 From 9b51d9d866482a703646fd4c07e433c3d9d88efd Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:17:05 -0700 Subject: cpumask: replace cpumask_next_* with cpumask_first_* where appropriate cpumask_first() is a more effective analogue of 'next' version if n == -1 (which means start == 0). This patch replaces 'next' with 'first' where things look trivial. There's no cpumask_first_zero() function, so create it. Signed-off-by: Yury Norov Tested-by: Wolfram Sang --- block/blk-mq.c | 2 +- drivers/net/virtio_net.c | 2 +- drivers/soc/fsl/qbman/bman_portal.c | 2 +- drivers/soc/fsl/qbman/qman_portal.c | 2 +- include/linux/cpumask.h | 16 ++++++++++++++++ kernel/time/clocksource.c | 4 ++-- 6 files changed, 22 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 8874a63ae952..ef56e753ab38 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2967,7 +2967,7 @@ static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx) static inline bool blk_mq_last_cpu_in_hctx(unsigned int cpu, struct blk_mq_hw_ctx *hctx) { - if (cpumask_next_and(-1, hctx->cpumask, cpu_online_mask) != cpu) + if (cpumask_first_and(hctx->cpumask, cpu_online_mask) != cpu) return false; if (cpumask_next_and(cpu, hctx->cpumask, cpu_online_mask) < nr_cpu_ids) return false; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index b107835242ad..8c70ab3c436a 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2101,7 +2101,7 @@ static void virtnet_set_affinity(struct virtnet_info *vi) stragglers = num_cpu >= vi->curr_queue_pairs ? num_cpu % vi->curr_queue_pairs : 0; - cpu = cpumask_next(-1, cpu_online_mask); + cpu = cpumask_first(cpu_online_mask); for (i = 0; i < vi->curr_queue_pairs; i++) { group_size = stride + (i < stragglers ? 1 : 0); diff --git a/drivers/soc/fsl/qbman/bman_portal.c b/drivers/soc/fsl/qbman/bman_portal.c index acda8a5637c5..4d7b9caee1c4 100644 --- a/drivers/soc/fsl/qbman/bman_portal.c +++ b/drivers/soc/fsl/qbman/bman_portal.c @@ -155,7 +155,7 @@ static int bman_portal_probe(struct platform_device *pdev) } spin_lock(&bman_lock); - cpu = cpumask_next_zero(-1, &portal_cpus); + cpu = cpumask_first_zero(&portal_cpus); if (cpu >= nr_cpu_ids) { __bman_portals_probed = 1; /* unassigned portal, skip init */ diff --git a/drivers/soc/fsl/qbman/qman_portal.c b/drivers/soc/fsl/qbman/qman_portal.c index 96f74a1dc603..e23b60618c1a 100644 --- a/drivers/soc/fsl/qbman/qman_portal.c +++ b/drivers/soc/fsl/qbman/qman_portal.c @@ -248,7 +248,7 @@ static int qman_portal_probe(struct platform_device *pdev) pcfg->pools = qm_get_pools_sdqcr(); spin_lock(&qman_lock); - cpu = cpumask_next_zero(-1, &portal_cpus); + cpu = cpumask_first_zero(&portal_cpus); if (cpu >= nr_cpu_ids) { __qman_portals_probed = 1; /* unassigned portal, skip init */ diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index c4e1b9ea0ba4..64dae70d31f5 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -123,6 +123,11 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) return 0; } +static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) +{ + return 0; +} + static inline unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { @@ -201,6 +206,17 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits); } +/** + * cpumask_first_zero - get the first unset cpu in a cpumask + * @srcp: the cpumask pointer + * + * Returns >= nr_cpu_ids if all cpus are set. + */ +static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) +{ + return find_first_zero_bit(cpumask_bits(srcp), nr_cpumask_bits); +} + /** * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 * @src1p: the first input diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index b8a14d2fb5ba..f29d1a524fa5 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -257,7 +257,7 @@ static void clocksource_verify_choose_cpus(void) return; /* Make sure to select at least one CPU other than the current CPU. */ - cpu = cpumask_next(-1, cpu_online_mask); + cpu = cpumask_first(cpu_online_mask); if (cpu == smp_processor_id()) cpu = cpumask_next(cpu, cpu_online_mask); if (WARN_ON_ONCE(cpu >= nr_cpu_ids)) @@ -279,7 +279,7 @@ static void clocksource_verify_choose_cpus(void) cpu = prandom_u32() % nr_cpu_ids; cpu = cpumask_next(cpu - 1, cpu_online_mask); if (cpu >= nr_cpu_ids) - cpu = cpumask_next(-1, cpu_online_mask); + cpu = cpumask_first(cpu_online_mask); if (!WARN_ON_ONCE(cpu >= nr_cpu_ids)) cpumask_set_cpu(cpu, &cpus_chosen); } -- cgit v1.2.3-71-gd317 From bc9d6635c293a2ac30c6319f7cfd08860ab7948a Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:17:06 -0700 Subject: include/linux: move for_each_bit() macros from bitops.h to find.h for_each_bit() macros depend on find_bit() machinery, and so the proper place for them is the find.h header. Signed-off-by: Yury Norov Tested-by: Wolfram Sang --- include/linux/bitops.h | 34 ---------------------------------- include/linux/find.h | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 5e62e2383b7f..7aaed501f768 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -32,40 +32,6 @@ extern unsigned long __sw_hweight64(__u64 w); */ #include -#define for_each_set_bit(bit, addr, size) \ - for ((bit) = find_first_bit((addr), (size)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) - -/* same as for_each_set_bit() but use bit as value to start with */ -#define for_each_set_bit_from(bit, addr, size) \ - for ((bit) = find_next_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) - -#define for_each_clear_bit(bit, addr, size) \ - for ((bit) = find_first_zero_bit((addr), (size)); \ - (bit) < (size); \ - (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) - -/* same as for_each_clear_bit() but use bit as value to start with */ -#define for_each_clear_bit_from(bit, addr, size) \ - for ((bit) = find_next_zero_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) - -/** - * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits - * @start: bit offset to start search and to store the current iteration offset - * @clump: location to store copy of current 8-bit clump - * @bits: bitmap address to base the search on - * @size: bitmap size in number of bits - */ -#define for_each_set_clump8(start, clump, bits, size) \ - for ((start) = find_first_clump8(&(clump), (bits), (size)); \ - (start) < (size); \ - (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) - static inline int get_bitmask_order(unsigned int count) { int order; diff --git a/include/linux/find.h b/include/linux/find.h index 6048f8c97418..4500e8ab93e2 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -279,4 +279,38 @@ unsigned long find_next_bit_le(const void *addr, unsigned #error "Please fix " #endif +#define for_each_set_bit(bit, addr, size) \ + for ((bit) = find_first_bit((addr), (size)); \ + (bit) < (size); \ + (bit) = find_next_bit((addr), (size), (bit) + 1)) + +/* same as for_each_set_bit() but use bit as value to start with */ +#define for_each_set_bit_from(bit, addr, size) \ + for ((bit) = find_next_bit((addr), (size), (bit)); \ + (bit) < (size); \ + (bit) = find_next_bit((addr), (size), (bit) + 1)) + +#define for_each_clear_bit(bit, addr, size) \ + for ((bit) = find_first_zero_bit((addr), (size)); \ + (bit) < (size); \ + (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) + +/* same as for_each_clear_bit() but use bit as value to start with */ +#define for_each_clear_bit_from(bit, addr, size) \ + for ((bit) = find_next_zero_bit((addr), (size), (bit)); \ + (bit) < (size); \ + (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) + +/** + * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits + * @start: bit offset to start search and to store the current iteration offset + * @clump: location to store copy of current 8-bit clump + * @bits: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_set_clump8(start, clump, bits, size) \ + for ((start) = find_first_clump8(&(clump), (bits), (size)); \ + (start) < (size); \ + (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) + #endif /*__LINUX_FIND_H_ */ -- cgit v1.2.3-71-gd317 From 7516be9931b8bc8bcaac8531f490b42ab11ded1e Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:17:07 -0700 Subject: find: micro-optimize for_each_{set,clear}_bit() The macros iterate thru all set/clear bits in a bitmap. They search a first bit using find_first_bit(), and the rest bits using find_next_bit(). Since find_next_bit() is called shortly after find_first_bit(), we can save few lines of I-cache by not using find_first_bit(). Signed-off-by: Yury Norov Tested-by: Wolfram Sang --- include/linux/find.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/find.h b/include/linux/find.h index 4500e8ab93e2..ae9ed52b52b8 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -280,7 +280,7 @@ unsigned long find_next_bit_le(const void *addr, unsigned #endif #define for_each_set_bit(bit, addr, size) \ - for ((bit) = find_first_bit((addr), (size)); \ + for ((bit) = find_next_bit((addr), (size), 0); \ (bit) < (size); \ (bit) = find_next_bit((addr), (size), (bit) + 1)) @@ -291,7 +291,7 @@ unsigned long find_next_bit_le(const void *addr, unsigned (bit) = find_next_bit((addr), (size), (bit) + 1)) #define for_each_clear_bit(bit, addr, size) \ - for ((bit) = find_first_zero_bit((addr), (size)); \ + for ((bit) = find_next_zero_bit((addr), (size), 0); \ (bit) < (size); \ (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) -- cgit v1.2.3-71-gd317 From ec288a2cf7ca40a939316b6df206ab845bb112d1 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:17:11 -0700 Subject: bitmap: unify find_bit operations bitmap_for_each_{set,clear}_region() are similar to for_each_bit() macros in include/linux/find.h, but interface and implementation of them are different. This patch adds for_each_bitrange() macros and drops unused bitmap_*_region() API in sake of unification. Signed-off-by: Yury Norov Tested-by: Wolfram Sang Acked-by: Dennis Zhou Acked-by: Ulf Hansson # For MMC --- drivers/mmc/host/renesas_sdhi_core.c | 2 +- include/linux/bitmap.h | 33 --------------------- include/linux/find.h | 56 ++++++++++++++++++++++++++++++++++++ mm/percpu.c | 20 ++++++------- 4 files changed, 65 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index f5b2684ad805..6de30a2719a3 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -628,7 +628,7 @@ static int renesas_sdhi_select_tuning(struct tmio_mmc_host *host) * is at least SH_MOBILE_SDHI_MIN_TAP_ROW probes long then use the * center index as the tap, otherwise bail out. */ - bitmap_for_each_set_region(bitmap, rs, re, 0, taps_size) { + for_each_set_bitrange(rs, re, bitmap, taps_size) { if (re - rs > tap_cnt) { tap_end = re; tap_start = rs; diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index ead4a150bd7f..7dba0847510c 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -55,12 +55,6 @@ struct device; * bitmap_clear(dst, pos, nbits) Clear specified bit area * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area * bitmap_find_next_zero_area_off(buf, len, pos, n, mask, mask_off) as above - * bitmap_next_clear_region(map, &start, &end, nbits) Find next clear region - * bitmap_next_set_region(map, &start, &end, nbits) Find next set region - * bitmap_for_each_clear_region(map, rs, re, start, end) - * Iterate over all clear regions - * bitmap_for_each_set_region(map, rs, re, start, end) - * Iterate over all set regions * bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n * bitmap_cut(dst, src, first, n, nbits) Cut n bits from first, copy rest @@ -467,14 +461,6 @@ static inline void bitmap_replace(unsigned long *dst, __bitmap_replace(dst, old, new, mask, nbits); } -static inline void bitmap_next_clear_region(unsigned long *bitmap, - unsigned int *rs, unsigned int *re, - unsigned int end) -{ - *rs = find_next_zero_bit(bitmap, end, *rs); - *re = find_next_bit(bitmap, end, *rs + 1); -} - static inline void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) @@ -483,25 +469,6 @@ static inline void bitmap_next_set_region(unsigned long *bitmap, *re = find_next_zero_bit(bitmap, end, *rs + 1); } -/* - * Bitmap region iterators. Iterates over the bitmap between [@start, @end). - * @rs and @re should be integer variables and will be set to start and end - * index of the current clear or set region. - */ -#define bitmap_for_each_clear_region(bitmap, rs, re, start, end) \ - for ((rs) = (start), \ - bitmap_next_clear_region((bitmap), &(rs), &(re), (end)); \ - (rs) < (re); \ - (rs) = (re) + 1, \ - bitmap_next_clear_region((bitmap), &(rs), &(re), (end))) - -#define bitmap_for_each_set_region(bitmap, rs, re, start, end) \ - for ((rs) = (start), \ - bitmap_next_set_region((bitmap), &(rs), &(re), (end)); \ - (rs) < (re); \ - (rs) = (re) + 1, \ - bitmap_next_set_region((bitmap), &(rs), &(re), (end))) - /** * BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap. * @n: u64 value diff --git a/include/linux/find.h b/include/linux/find.h index ae9ed52b52b8..5bb6db213bcb 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -301,6 +301,62 @@ unsigned long find_next_bit_le(const void *addr, unsigned (bit) < (size); \ (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) +/** + * for_each_set_bitrange - iterate over all set bit ranges [b; e) + * @b: bit offset of start of current bitrange (first set bit) + * @e: bit offset of end of current bitrange (first unset bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_set_bitrange(b, e, addr, size) \ + for ((b) = find_next_bit((addr), (size), 0), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1); \ + (b) < (size); \ + (b) = find_next_bit((addr), (size), (e) + 1), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1)) + +/** + * for_each_set_bitrange_from - iterate over all set bit ranges [b; e) + * @b: bit offset of start of current bitrange (first set bit); must be initialized + * @e: bit offset of end of current bitrange (first unset bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_set_bitrange_from(b, e, addr, size) \ + for ((b) = find_next_bit((addr), (size), (b)), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1); \ + (b) < (size); \ + (b) = find_next_bit((addr), (size), (e) + 1), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1)) + +/** + * for_each_clear_bitrange - iterate over all unset bit ranges [b; e) + * @b: bit offset of start of current bitrange (first unset bit) + * @e: bit offset of end of current bitrange (first set bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_clear_bitrange(b, e, addr, size) \ + for ((b) = find_next_zero_bit((addr), (size), 0), \ + (e) = find_next_bit((addr), (size), (b) + 1); \ + (b) < (size); \ + (b) = find_next_zero_bit((addr), (size), (e) + 1), \ + (e) = find_next_bit((addr), (size), (b) + 1)) + +/** + * for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e) + * @b: bit offset of start of current bitrange (first set bit); must be initialized + * @e: bit offset of end of current bitrange (first unset bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_clear_bitrange_from(b, e, addr, size) \ + for ((b) = find_next_zero_bit((addr), (size), (b)), \ + (e) = find_next_bit((addr), (size), (b) + 1); \ + (b) < (size); \ + (b) = find_next_zero_bit((addr), (size), (e) + 1), \ + (e) = find_next_bit((addr), (size), (b) + 1)) + /** * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits * @start: bit offset to start search and to store the current iteration offset diff --git a/mm/percpu.c b/mm/percpu.c index 0c6f85c5514f..293009cc03ef 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -779,7 +779,7 @@ static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index) { struct pcpu_block_md *block = chunk->md_blocks + index; unsigned long *alloc_map = pcpu_index_alloc_map(chunk, index); - unsigned int rs, re, start; /* region start, region end */ + unsigned int start, end; /* region start, region end */ /* promote scan_hint to contig_hint */ if (block->scan_hint) { @@ -795,9 +795,8 @@ static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index) block->right_free = 0; /* iterate over free areas and update the contig hints */ - bitmap_for_each_clear_region(alloc_map, rs, re, start, - PCPU_BITMAP_BLOCK_BITS) - pcpu_block_update(block, rs, re); + for_each_clear_bitrange_from(start, end, alloc_map, PCPU_BITMAP_BLOCK_BITS) + pcpu_block_update(block, start, end); } /** @@ -1852,13 +1851,12 @@ area_found: /* populate if not all pages are already there */ if (!is_atomic) { - unsigned int page_start, page_end, rs, re; + unsigned int page_end, rs, re; - page_start = PFN_DOWN(off); + rs = PFN_DOWN(off); page_end = PFN_UP(off + size); - bitmap_for_each_clear_region(chunk->populated, rs, re, - page_start, page_end) { + for_each_clear_bitrange_from(rs, re, chunk->populated, page_end) { WARN_ON(chunk->immutable); ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp); @@ -2014,8 +2012,7 @@ static void pcpu_balance_free(bool empty_only) list_for_each_entry_safe(chunk, next, &to_free, list) { unsigned int rs, re; - bitmap_for_each_set_region(chunk->populated, rs, re, 0, - chunk->nr_pages) { + for_each_set_bitrange(rs, re, chunk->populated, chunk->nr_pages) { pcpu_depopulate_chunk(chunk, rs, re); spin_lock_irq(&pcpu_lock); pcpu_chunk_depopulated(chunk, rs, re); @@ -2085,8 +2082,7 @@ retry_pop: continue; /* @chunk can't go away while pcpu_alloc_mutex is held */ - bitmap_for_each_clear_region(chunk->populated, rs, re, 0, - chunk->nr_pages) { + for_each_clear_bitrange(rs, re, chunk->populated, chunk->nr_pages) { int nr = min_t(int, re - rs, nr_to_pop); spin_unlock_irq(&pcpu_lock); -- cgit v1.2.3-71-gd317