Merge tag 'bitmap-5.17-rc1' of git://github.com/norov/linux

Pull bitmap updates from Yury Norov:

 - introduce for_each_set_bitrange()

 - use find_first_*_bit() instead of find_next_*_bit() where possible

 - unify for_each_bit() macros

* tag 'bitmap-5.17-rc1' of git://github.com/norov/linux:
  vsprintf: rework bitmap_list_string
  lib: bitmap: add performance test for bitmap_print_to_pagebuf
  bitmap: unify find_bit operations
  mm/percpu: micro-optimize pcpu_is_populated()
  Replace for_each_*_bit_from() with for_each_*_bit() where appropriate
  find: micro-optimize for_each_{set,clear}_bit()
  include/linux: move for_each_bit() macros from bitops.h to find.h
  cpumask: replace cpumask_next_* with cpumask_first_* where appropriate
  tools: sync tools/bitmap with mother linux
  all: replace find_next{,_zero}_bit with find_first{,_zero}_bit where appropriate
  cpumask: use find_first_and_bit()
  lib: add find_first_and_bit()
  arch: remove GENERIC_FIND_FIRST_BIT entirely
  include: move find.h from asm_generic to linux
  bitops: move find_bit_*_le functions from le.h to find.h
  bitops: protect find_first_{,zero}_bit properly
diff --git a/MAINTAINERS b/MAINTAINERS
index 45f8750..ea3e6c9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3410,14 +3410,14 @@
 R:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 R:	Rasmus Villemoes <linux@rasmusvillemoes.dk>
 S:	Maintained
-F:	include/asm-generic/bitops/find.h
 F:	include/linux/bitmap.h
+F:	include/linux/find.h
 F:	lib/bitmap.c
 F:	lib/find_bit.c
 F:	lib/find_bit_benchmark.c
 F:	lib/test_bitmap.c
-F:	tools/include/asm-generic/bitops/find.h
 F:	tools/include/linux/bitmap.h
+F:	tools/include/linux/find.h
 F:	tools/lib/bitmap.c
 F:	tools/lib/find_bit.c
 
diff --git a/arch/alpha/include/asm/bitops.h b/arch/alpha/include/asm/bitops.h
index 5adca78..e1d8483 100644
--- a/arch/alpha/include/asm/bitops.h
+++ b/arch/alpha/include/asm/bitops.h
@@ -430,8 +430,6 @@ static inline unsigned int __arch_hweight8(unsigned int w)
 
 #endif /* __KERNEL__ */
 
-#include <asm-generic/bitops/find.h>
-
 #ifdef __KERNEL__
 
 /*
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index f74d986..3c2a475 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -20,7 +20,6 @@
 	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/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index a7daaf6..bdb7e19 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -189,7 +189,6 @@ static inline __attribute__ ((const)) unsigned long __ffs(unsigned long x)
 #include <asm-generic/bitops/atomic.h>
 #include <asm-generic/bitops/non-atomic.h>
 
-#include <asm-generic/bitops/find.h>
 #include <asm-generic/bitops/le.h>
 #include <asm-generic/bitops/ext2-atomic-setbit.h>
 
diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
index c92e42a..8e94fe7 100644
--- a/arch/arm/include/asm/bitops.h
+++ b/arch/arm/include/asm/bitops.h
@@ -264,7 +264,6 @@ static inline int find_next_bit_le(const void *p, int size, int offset)
 
 #endif
 
-#include <asm-generic/bitops/find.h>
 #include <asm-generic/bitops/le.h>
 
 /*
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index dc10d26..6978140 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -120,7 +120,6 @@
 	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/arm64/include/asm/bitops.h b/arch/arm64/include/asm/bitops.h
index 81a3e51..9b3c787 100644
--- a/arch/arm64/include/asm/bitops.h
+++ b/arch/arm64/include/asm/bitops.h
@@ -18,7 +18,6 @@
 
 #include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/fls64.h>
-#include <asm-generic/bitops/find.h>
 
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/hweight.h>
diff --git a/arch/csky/include/asm/bitops.h b/arch/csky/include/asm/bitops.h
index 02b72a0..72e1b2a 100644
--- a/arch/csky/include/asm/bitops.h
+++ b/arch/csky/include/asm/bitops.h
@@ -59,7 +59,6 @@ static __always_inline unsigned long __fls(unsigned long x)
 
 #include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/fls64.h>
-#include <asm-generic/bitops/find.h>
 
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
diff --git a/arch/h8300/include/asm/bitops.h b/arch/h8300/include/asm/bitops.h
index c867a80..4489e3d 100644
--- a/arch/h8300/include/asm/bitops.h
+++ b/arch/h8300/include/asm/bitops.h
@@ -168,7 +168,6 @@ static inline unsigned long __ffs(unsigned long word)
 	return result;
 }
 
-#include <asm-generic/bitops/find.h>
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/hweight.h>
 #include <asm-generic/bitops/lock.h>
diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h
index 71429f7..75d6ba3 100644
--- a/arch/hexagon/include/asm/bitops.h
+++ b/arch/hexagon/include/asm/bitops.h
@@ -271,7 +271,6 @@ static inline unsigned long __fls(unsigned long word)
 }
 
 #include <asm-generic/bitops/lock.h>
-#include <asm-generic/bitops/find.h>
 
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
diff --git a/arch/ia64/include/asm/bitops.h b/arch/ia64/include/asm/bitops.h
index 2f24ee64..577be93 100644
--- a/arch/ia64/include/asm/bitops.h
+++ b/arch/ia64/include/asm/bitops.h
@@ -441,8 +441,6 @@ static __inline__ unsigned long __arch_hweight64(unsigned long x)
 
 #endif /* __KERNEL__ */
 
-#include <asm-generic/bitops/find.h>
-
 #ifdef __KERNEL__
 
 #include <asm-generic/bitops/le.h>
diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h
index 7b93e1f..51283db 100644
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -529,6 +529,4 @@ static inline int __fls(int x)
 #include <asm-generic/bitops/le.h>
 #endif /* __KERNEL__ */
 
-#include <asm-generic/bitops/find.h>
-
 #endif /* _M68K_BITOPS_H */
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index edf6c15..058446f 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -32,7 +32,6 @@
 	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/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h
index 3812082..b4bf754 100644
--- a/arch/mips/include/asm/bitops.h
+++ b/arch/mips/include/asm/bitops.h
@@ -444,7 +444,6 @@ static inline int ffs(int word)
 }
 
 #include <asm-generic/bitops/ffz.h>
-#include <asm-generic/bitops/find.h>
 
 #ifdef __KERNEL__
 
diff --git a/arch/openrisc/include/asm/bitops.h b/arch/openrisc/include/asm/bitops.h
index 7f1ca35..d773ed9 100644
--- a/arch/openrisc/include/asm/bitops.h
+++ b/arch/openrisc/include/asm/bitops.h
@@ -30,7 +30,6 @@
 #include <asm/bitops/fls.h>
 #include <asm/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
-#include <asm-generic/bitops/find.h>
 
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h
index daa2afd..0ec9cfc 100644
--- a/arch/parisc/include/asm/bitops.h
+++ b/arch/parisc/include/asm/bitops.h
@@ -203,7 +203,6 @@ static __inline__ int fls(unsigned int x)
 #include <asm-generic/bitops/hweight.h>
 #include <asm-generic/bitops/lock.h>
 #include <asm-generic/bitops/sched.h>
-#include <asm-generic/bitops/find.h>
 #include <asm-generic/bitops/le.h>
 #include <asm-generic/bitops/ext2-atomic-setbit.h>
 
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index a05d8c6..ea5d27d 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -328,8 +328,6 @@ unsigned long __arch_hweight64(__u64 w);
 #include <asm-generic/bitops/hweight.h>
 #endif
 
-#include <asm-generic/bitops/find.h>
-
 /* wrappers that deal with KASAN instrumentation */
 #include <asm-generic/bitops/instrumented-atomic.h>
 #include <asm-generic/bitops/instrumented-lock.h>
diff --git a/arch/powerpc/platforms/pasemi/dma_lib.c b/arch/powerpc/platforms/pasemi/dma_lib.c
index 270fa3c..2642731 100644
--- a/arch/powerpc/platforms/pasemi/dma_lib.c
+++ b/arch/powerpc/platforms/pasemi/dma_lib.c
@@ -375,7 +375,7 @@ int pasemi_dma_alloc_flag(void)
 	int bit;
 
 retry:
-	bit = find_next_bit(flags_free, MAX_FLAGS, 0);
+	bit = find_first_bit(flags_free, MAX_FLAGS);
 	if (bit >= MAX_FLAGS)
 		return -ENOSPC;
 	if (!test_and_clear_bit(bit, flags_free))
@@ -440,7 +440,7 @@ int pasemi_dma_alloc_fun(void)
 	int bit;
 
 retry:
-	bit = find_next_bit(fun_free, MAX_FLAGS, 0);
+	bit = find_first_bit(fun_free, MAX_FLAGS);
 	if (bit >= MAX_FLAGS)
 		return -ENOSPC;
 	if (!test_and_clear_bit(bit, fun_free))
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 396a330..3540b69 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -20,7 +20,6 @@
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
-#include <asm-generic/bitops/find.h>
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/ffs.h>
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index f6a9475..9750f92 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -127,7 +127,6 @@
 	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/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 5a530c5..1d40630 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -387,7 +387,6 @@ static inline int fls(unsigned int word)
 #endif /* CONFIG_HAVE_MARCH_Z9_109_FEATURES */
 
 #include <asm-generic/bitops/ffz.h>
-#include <asm-generic/bitops/find.h>
 #include <asm-generic/bitops/hweight.h>
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/le.h>
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 9c6d45d..577f1ea 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1990,7 +1990,7 @@ static unsigned long kvm_s390_next_dirty_cmma(struct kvm_memslots *slots,
 	ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, ofs);
 	while (ofs >= ms->npages && (mnode = rb_next(mnode))) {
 		ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]);
-		ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, 0);
+		ofs = find_first_bit(kvm_second_dirty_bitmap(ms), ms->npages);
 	}
 	return ms->base_gfn + ofs;
 }
diff --git a/arch/sh/include/asm/bitops.h b/arch/sh/include/asm/bitops.h
index 3b6c7b5..10ceb0d 100644
--- a/arch/sh/include/asm/bitops.h
+++ b/arch/sh/include/asm/bitops.h
@@ -68,6 +68,5 @@ static inline unsigned long __ffs(unsigned long word)
 #include <asm-generic/bitops/fls64.h>
 
 #include <asm-generic/bitops/le.h>
-#include <asm-generic/bitops/find.h>
 
 #endif /* __ASM_SH_BITOPS_H */
diff --git a/arch/sparc/include/asm/bitops_32.h b/arch/sparc/include/asm/bitops_32.h
index 0ceff3b..889afa9 100644
--- a/arch/sparc/include/asm/bitops_32.h
+++ b/arch/sparc/include/asm/bitops_32.h
@@ -100,7 +100,6 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/hweight.h>
 #include <asm-generic/bitops/lock.h>
-#include <asm-generic/bitops/find.h>
 #include <asm-generic/bitops/le.h>
 #include <asm-generic/bitops/ext2-atomic.h>
 
diff --git a/arch/sparc/include/asm/bitops_64.h b/arch/sparc/include/asm/bitops_64.h
index ca7ea59..005a8ae 100644
--- a/arch/sparc/include/asm/bitops_64.h
+++ b/arch/sparc/include/asm/bitops_64.h
@@ -52,8 +52,6 @@ unsigned int __arch_hweight8(unsigned int w);
 #include <asm-generic/bitops/lock.h>
 #endif /* __KERNEL__ */
 
-#include <asm-generic/bitops/find.h>
-
 #ifdef __KERNEL__
 
 #include <asm-generic/bitops/le.h>
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6fddb63..ebe8fc7 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -137,7 +137,6 @@
 	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/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 0367efd..a288ecd 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -380,8 +380,6 @@ static __always_inline int fls64(__u64 x)
 #include <asm-generic/bitops/fls64.h>
 #endif
 
-#include <asm-generic/bitops/find.h>
-
 #include <asm-generic/bitops/sched.h>
 
 #include <asm/arch_hweight.h>
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index c132daa..3e6f6b4 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -760,9 +760,9 @@ void __init lapic_update_legacy_vectors(void)
 
 void __init lapic_assign_system_vectors(void)
 {
-	unsigned int i, vector = 0;
+	unsigned int i, vector;
 
-	for_each_set_bit_from(vector, system_vectors, NR_VECTORS)
+	for_each_set_bit(vector, system_vectors, NR_VECTORS)
 		irq_matrix_assign_system(vector_matrix, vector, false);
 
 	if (nr_legacy_irqs() > 1)
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 95d26a6..40d6a06 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -8,7 +8,6 @@
 
 config UML_X86
 	def_bool y
-	select GENERIC_FIND_FIRST_BIT
 
 config 64BIT
 	bool "64-bit kernel" if "$(SUBARCH)" = "x86"
diff --git a/arch/xtensa/include/asm/bitops.h b/arch/xtensa/include/asm/bitops.h
index 3f71d36..cd22589 100644
--- a/arch/xtensa/include/asm/bitops.h
+++ b/arch/xtensa/include/asm/bitops.h
@@ -205,7 +205,6 @@ BIT_OPS(change, "xor", )
 #undef BIT_OP
 #undef TEST_AND_BIT_OP
 
-#include <asm-generic/bitops/find.h>
 #include <asm-generic/bitops/le.h>
 
 #include <asm-generic/bitops/ext2-atomic-setbit.h>
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b5e35e6..f3bf335 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3285,7 +3285,7 @@ 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/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index 8f8443e..c08971d 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -196,7 +196,7 @@ rnbd_get_cpu_qlist(struct rnbd_clt_session *sess, int cpu)
 		return per_cpu_ptr(sess->cpu_queues, bit);
 	} else if (cpu != 0) {
 		/* Search from 0 to cpu */
-		bit = find_next_bit(sess->cpu_queues_bm, cpu, 0);
+		bit = find_first_bit(sess->cpu_queues_bm, cpu);
 		if (bit < cpu)
 			return per_cpu_ptr(sess->cpu_queues, bit);
 	}
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index ba5fd01..37018bc 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -1047,7 +1047,7 @@ int etnaviv_gpu_debugfs(struct etnaviv_gpu *gpu, struct seq_file *m)
 
 void etnaviv_gpu_recover_hang(struct etnaviv_gpu *gpu)
 {
-	unsigned int i = 0;
+	unsigned int i;
 
 	dev_err(gpu->dev, "recover hung GPU!\n");
 
@@ -1060,7 +1060,7 @@ void etnaviv_gpu_recover_hang(struct etnaviv_gpu *gpu)
 
 	/* complete all events, the GPU won't do it after the reset */
 	spin_lock(&gpu->event_spinlock);
-	for_each_set_bit_from(i, gpu->event_bitmap, ETNA_NR_EVENTS)
+	for_each_set_bit(i, gpu->event_bitmap, ETNA_NR_EVENTS)
 		complete(&gpu->event_free);
 	bitmap_zero(gpu->event_bitmap, ETNA_NR_EVENTS);
 	spin_unlock(&gpu->event_spinlock);
diff --git a/drivers/hwmon/ltc2992.c b/drivers/hwmon/ltc2992.c
index 2a4bed0a..7352d2b 100644
--- a/drivers/hwmon/ltc2992.c
+++ b/drivers/hwmon/ltc2992.c
@@ -248,8 +248,7 @@ static int ltc2992_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask
 
 	gpio_status = reg;
 
-	gpio_nr = 0;
-	for_each_set_bit_from(gpio_nr, mask, LTC2992_GPIO_NR) {
+	for_each_set_bit(gpio_nr, mask, LTC2992_GPIO_NR) {
 		if (test_bit(LTC2992_GPIO_BIT(gpio_nr), &gpio_status))
 			set_bit(gpio_nr, bits);
 	}
diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c
index e45c600f..bc2cfa5 100644
--- a/drivers/iio/adc/ad7124.c
+++ b/drivers/iio/adc/ad7124.c
@@ -347,7 +347,7 @@ static int ad7124_find_free_config_slot(struct ad7124_state *st)
 {
 	unsigned int free_cfg_slot;
 
-	free_cfg_slot = find_next_zero_bit(&st->cfg_slots_status, AD7124_MAX_CONFIGS, 0);
+	free_cfg_slot = find_first_zero_bit(&st->cfg_slots_status, AD7124_MAX_CONFIGS);
 	if (free_cfg_slot == AD7124_MAX_CONFIGS)
 		return -1;
 
diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c
index 4b1b16e..89234d0 100644
--- a/drivers/infiniband/hw/irdma/hw.c
+++ b/drivers/infiniband/hw/irdma/hw.c
@@ -1709,14 +1709,14 @@ static enum irdma_status_code irdma_setup_init_state(struct irdma_pci_f *rf)
  */
 static void irdma_get_used_rsrc(struct irdma_device *iwdev)
 {
-	iwdev->rf->used_pds = find_next_zero_bit(iwdev->rf->allocated_pds,
-						 iwdev->rf->max_pd, 0);
-	iwdev->rf->used_qps = find_next_zero_bit(iwdev->rf->allocated_qps,
-						 iwdev->rf->max_qp, 0);
-	iwdev->rf->used_cqs = find_next_zero_bit(iwdev->rf->allocated_cqs,
-						 iwdev->rf->max_cq, 0);
-	iwdev->rf->used_mrs = find_next_zero_bit(iwdev->rf->allocated_mrs,
-						 iwdev->rf->max_mr, 0);
+	iwdev->rf->used_pds = find_first_zero_bit(iwdev->rf->allocated_pds,
+						 iwdev->rf->max_pd);
+	iwdev->rf->used_qps = find_first_zero_bit(iwdev->rf->allocated_qps,
+						 iwdev->rf->max_qp);
+	iwdev->rf->used_cqs = find_first_zero_bit(iwdev->rf->allocated_cqs,
+						 iwdev->rf->max_cq);
+	iwdev->rf->used_mrs = find_first_zero_bit(iwdev->rf->allocated_mrs,
+						 iwdev->rf->max_mr);
 }
 
 void irdma_ctrl_deinit_hw(struct irdma_pci_f *rf)
diff --git a/drivers/media/cec/core/cec-core.c b/drivers/media/cec/core/cec-core.c
index ec67065..a3ab6a4 100644
--- a/drivers/media/cec/core/cec-core.c
+++ b/drivers/media/cec/core/cec-core.c
@@ -106,7 +106,7 @@ static int __must_check cec_devnode_register(struct cec_devnode *devnode,
 
 	/* Part 1: Find a free minor number */
 	mutex_lock(&cec_devnode_lock);
-	minor = find_next_zero_bit(cec_devnode_nums, CEC_NUM_DEVICES, 0);
+	minor = find_first_zero_bit(cec_devnode_nums, CEC_NUM_DEVICES);
 	if (minor == CEC_NUM_DEVICES) {
 		mutex_unlock(&cec_devnode_lock);
 		pr_err("could not get a free minor\n");
diff --git a/drivers/media/mc/mc-devnode.c b/drivers/media/mc/mc-devnode.c
index f11382a..680fbb3 100644
--- a/drivers/media/mc/mc-devnode.c
+++ b/drivers/media/mc/mc-devnode.c
@@ -217,7 +217,7 @@ int __must_check media_devnode_register(struct media_device *mdev,
 
 	/* Part 1: Find a free minor number */
 	mutex_lock(&media_devnode_lock);
-	minor = find_next_zero_bit(media_devnode_nums, MEDIA_NUM_DEVICES, 0);
+	minor = find_first_zero_bit(media_devnode_nums, MEDIA_NUM_DEVICES);
 	if (minor == MEDIA_NUM_DEVICES) {
 		mutex_unlock(&media_devnode_lock);
 		pr_err("could not get a free minor\n");
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index 084c61b..2797a9c 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -642,7 +642,7 @@ 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/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 3d97f15..a801ea4 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/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index 12d1918..dfcdeb4 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -213,7 +213,7 @@ static int dra7xx_pcie_handle_msi(struct pcie_port *pp, int index)
 	if (!val)
 		return 0;
 
-	pos = find_next_bit(&val, MAX_MSI_IRQS_PER_CTRL, 0);
+	pos = find_first_bit(&val, MAX_MSI_IRQS_PER_CTRL);
 	while (pos != MAX_MSI_IRQS_PER_CTRL) {
 		generic_handle_domain_irq(pp->irq_domain,
 					  (index * MAX_MSI_IRQS_PER_CTRL) + pos);
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index cd26c0f..1bc0db5 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -17982,8 +17982,8 @@ lpfc_sli4_alloc_xri(struct lpfc_hba *phba)
 	 * the driver starts at 0 each time.
 	 */
 	spin_lock_irq(&phba->hbalock);
-	xri = find_next_zero_bit(phba->sli4_hba.xri_bmask,
-				 phba->sli4_hba.max_cfg_param.max_xri, 0);
+	xri = find_first_zero_bit(phba->sli4_hba.xri_bmask,
+				 phba->sli4_hba.max_cfg_param.max_xri);
 	if (xri >= phba->sli4_hba.max_cfg_param.max_xri) {
 		spin_unlock_irq(&phba->hbalock);
 		return NO_XRI;
@@ -19660,7 +19660,7 @@ lpfc_sli4_alloc_rpi(struct lpfc_hba *phba)
 	max_rpi = phba->sli4_hba.max_cfg_param.max_rpi;
 	rpi_limit = phba->sli4_hba.next_rpi;
 
-	rpi = find_next_zero_bit(phba->sli4_hba.rpi_bmask, rpi_limit, 0);
+	rpi = find_first_zero_bit(phba->sli4_hba.rpi_bmask, rpi_limit);
 	if (rpi >= rpi_limit)
 		rpi = LPFC_RPI_ALLOC_ERROR;
 	else {
@@ -20303,8 +20303,8 @@ lpfc_sli4_fcf_rr_next_index_get(struct lpfc_hba *phba)
 		 * have been tested so that we can detect when we should
 		 * change the priority level.
 		 */
-		next_fcf_index = find_next_bit(phba->fcf.fcf_rr_bmask,
-					       LPFC_SLI4_FCF_TBL_INDX_MAX, 0);
+		next_fcf_index = find_first_bit(phba->fcf.fcf_rr_bmask,
+					       LPFC_SLI4_FCF_TBL_INDX_MAX);
 	}
 
 
diff --git a/drivers/soc/fsl/qbman/bman_portal.c b/drivers/soc/fsl/qbman/bman_portal.c
index acda8a5..4d7b9ca 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 96f74a1..e23b606 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/drivers/soc/ti/k3-ringacc.c b/drivers/soc/ti/k3-ringacc.c
index 56be391..31ab6c6 100644
--- a/drivers/soc/ti/k3-ringacc.c
+++ b/drivers/soc/ti/k3-ringacc.c
@@ -358,8 +358,8 @@ struct k3_ring *k3_ringacc_request_ring(struct k3_ringacc *ringacc,
 		goto out;
 
 	if (flags & K3_RINGACC_RING_USE_PROXY) {
-		proxy_id = find_next_zero_bit(ringacc->proxy_inuse,
-					      ringacc->num_proxies, 0);
+		proxy_id = find_first_zero_bit(ringacc->proxy_inuse,
+					      ringacc->num_proxies);
 		if (proxy_id == ringacc->num_proxies)
 			goto error;
 	}
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index a38fd65..8933ef1 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -1938,7 +1938,7 @@ static bool canon_copy_from_read_buf(struct tty_struct *tty,
 	more = n - (size - tail);
 	if (eol == N_TTY_BUF_SIZE && more) {
 		/* scan wrapped without finding set bit */
-		eol = find_next_bit(ldata->read_flags, more, 0);
+		eol = find_first_bit(ldata->read_flags, more);
 		found = eol != more;
 	} else
 		found = eol != size;
diff --git a/drivers/virt/acrn/ioreq.c b/drivers/virt/acrn/ioreq.c
index 80b2e3f..5ff1c53 100644
--- a/drivers/virt/acrn/ioreq.c
+++ b/drivers/virt/acrn/ioreq.c
@@ -246,8 +246,7 @@ void acrn_ioreq_request_clear(struct acrn_vm *vm)
 	spin_lock_bh(&vm->ioreq_clients_lock);
 	client = vm->default_client;
 	if (client) {
-		vcpu = find_next_bit(client->ioreqs_map,
-				     ACRN_IO_REQUEST_MAX, 0);
+		vcpu = find_first_bit(client->ioreqs_map, ACRN_IO_REQUEST_MAX);
 		while (vcpu < ACRN_IO_REQUEST_MAX) {
 			acrn_ioreq_complete_request(client, vcpu, NULL);
 			vcpu = find_next_bit(client->ioreqs_map,
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 575d3dc..1dabc82 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -2555,8 +2555,8 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 	secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint);
 	if (secno >= MAIN_SECS(sbi)) {
 		if (dir == ALLOC_RIGHT) {
-			secno = find_next_zero_bit(free_i->free_secmap,
-							MAIN_SECS(sbi), 0);
+			secno = find_first_zero_bit(free_i->free_secmap,
+							MAIN_SECS(sbi));
 			f2fs_bug_on(sbi, secno >= MAIN_SECS(sbi));
 		} else {
 			go_left = 1;
@@ -2571,8 +2571,8 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 			left_start--;
 			continue;
 		}
-		left_start = find_next_zero_bit(free_i->free_secmap,
-							MAIN_SECS(sbi), 0);
+		left_start = find_first_zero_bit(free_i->free_secmap,
+							MAIN_SECS(sbi));
 		f2fs_bug_on(sbi, left_start >= MAIN_SECS(sbi));
 		break;
 	}
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index f89ffcb..a17be16 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -379,7 +379,7 @@ static void o2hb_nego_timeout(struct work_struct *work)
 
 	o2hb_fill_node_map(live_node_bitmap, sizeof(live_node_bitmap));
 	/* lowest node as master node to make negotiate decision. */
-	master_node = find_next_bit(live_node_bitmap, O2NM_MAX_NODES, 0);
+	master_node = find_first_bit(live_node_bitmap, O2NM_MAX_NODES);
 
 	if (master_node == o2nm_this_node()) {
 		if (!test_bit(master_node, reg->hr_nego_node_bitmap)) {
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 9f90fc9..c4eccd4 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1045,7 +1045,7 @@ static int dlm_send_regions(struct dlm_ctxt *dlm, unsigned long *node_map)
 	int status, ret = 0, i;
 	char *p;
 
-	if (find_next_bit(node_map, O2NM_MAX_NODES, 0) >= O2NM_MAX_NODES)
+	if (find_first_bit(node_map, O2NM_MAX_NODES) >= O2NM_MAX_NODES)
 		goto bail;
 
 	qr = kzalloc(sizeof(struct dlm_query_region), GFP_KERNEL);
@@ -1217,7 +1217,7 @@ static int dlm_send_nodeinfo(struct dlm_ctxt *dlm, unsigned long *node_map)
 	struct o2nm_node *node;
 	int ret = 0, status, count, i;
 
-	if (find_next_bit(node_map, O2NM_MAX_NODES, 0) >= O2NM_MAX_NODES)
+	if (find_first_bit(node_map, O2NM_MAX_NODES) >= O2NM_MAX_NODES)
 		goto bail;
 
 	qn = kzalloc(sizeof(struct dlm_query_nodeinfo), GFP_KERNEL);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 9b88219..227da5b 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -861,7 +861,7 @@ struct dlm_lock_resource * dlm_get_lock_resource(struct dlm_ctxt *dlm,
 		 * to see if there are any nodes that still need to be
 		 * considered.  these will not appear in the mle nodemap
 		 * but they might own this lockres.  wait on them. */
-		bit = find_next_bit(dlm->recovery_map, O2NM_MAX_NODES, 0);
+		bit = find_first_bit(dlm->recovery_map, O2NM_MAX_NODES);
 		if (bit < O2NM_MAX_NODES) {
 			mlog(0, "%s: res %.*s, At least one node (%d) "
 			     "to recover before lock mastery can begin\n",
@@ -912,7 +912,7 @@ struct dlm_lock_resource * dlm_get_lock_resource(struct dlm_ctxt *dlm,
 		dlm_wait_for_recovery(dlm);
 
 		spin_lock(&dlm->spinlock);
-		bit = find_next_bit(dlm->recovery_map, O2NM_MAX_NODES, 0);
+		bit = find_first_bit(dlm->recovery_map, O2NM_MAX_NODES);
 		if (bit < O2NM_MAX_NODES) {
 			mlog(0, "%s: res %.*s, At least one node (%d) "
 			     "to recover before lock mastery can begin\n",
@@ -1079,7 +1079,7 @@ static int dlm_wait_for_lock_mastery(struct dlm_ctxt *dlm,
 		sleep = 1;
 		/* have all nodes responded? */
 		if (voting_done && !*blocked) {
-			bit = find_next_bit(mle->maybe_map, O2NM_MAX_NODES, 0);
+			bit = find_first_bit(mle->maybe_map, O2NM_MAX_NODES);
 			if (dlm->node_num <= bit) {
 				/* my node number is lowest.
 			 	 * now tell other nodes that I am
@@ -1234,8 +1234,8 @@ static int dlm_restart_lock_mastery(struct dlm_ctxt *dlm,
 		} else {
 			mlog(ML_ERROR, "node down! %d\n", node);
 			if (blocked) {
-				int lowest = find_next_bit(mle->maybe_map,
-						       O2NM_MAX_NODES, 0);
+				int lowest = find_first_bit(mle->maybe_map,
+						       O2NM_MAX_NODES);
 
 				/* act like it was never there */
 				clear_bit(node, mle->maybe_map);
@@ -1795,7 +1795,7 @@ int dlm_assert_master_handler(struct o2net_msg *msg, u32 len, void *data,
 		     "MLE for it! (%.*s)\n", assert->node_idx,
 		     namelen, name);
 	} else {
-		int bit = find_next_bit (mle->maybe_map, O2NM_MAX_NODES, 0);
+		int bit = find_first_bit(mle->maybe_map, O2NM_MAX_NODES);
 		if (bit >= O2NM_MAX_NODES) {
 			/* not necessarily an error, though less likely.
 			 * could be master just re-asserting. */
@@ -2521,7 +2521,7 @@ static int dlm_is_lockres_migratable(struct dlm_ctxt *dlm,
 	}
 
 	if (!nonlocal) {
-		node_ref = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
+		node_ref = find_first_bit(res->refmap, O2NM_MAX_NODES);
 		if (node_ref >= O2NM_MAX_NODES)
 			return 0;
 	}
@@ -3303,7 +3303,7 @@ static void dlm_clean_block_mle(struct dlm_ctxt *dlm,
 	BUG_ON(mle->type != DLM_MLE_BLOCK);
 
 	spin_lock(&mle->spinlock);
-	bit = find_next_bit(mle->maybe_map, O2NM_MAX_NODES, 0);
+	bit = find_first_bit(mle->maybe_map, O2NM_MAX_NODES);
 	if (bit != dead_node) {
 		mlog(0, "mle found, but dead node %u would not have been "
 		     "master\n", dead_node);
@@ -3542,7 +3542,7 @@ void dlm_force_free_mles(struct dlm_ctxt *dlm)
 	spin_lock(&dlm->master_lock);
 
 	BUG_ON(dlm->dlm_state != DLM_CTXT_LEAVING);
-	BUG_ON((find_next_bit(dlm->domain_map, O2NM_MAX_NODES, 0) < O2NM_MAX_NODES));
+	BUG_ON((find_first_bit(dlm->domain_map, O2NM_MAX_NODES) < O2NM_MAX_NODES));
 
 	for (i = 0; i < DLM_HASH_BUCKETS; i++) {
 		bucket = dlm_master_hash(dlm, i);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 5cd5f75..52ad342 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -451,7 +451,7 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm)
 	if (dlm->reco.dead_node == O2NM_INVALID_NODE_NUM) {
 		int bit;
 
-		bit = find_next_bit (dlm->recovery_map, O2NM_MAX_NODES, 0);
+		bit = find_first_bit(dlm->recovery_map, O2NM_MAX_NODES);
 		if (bit >= O2NM_MAX_NODES || bit < 0)
 			dlm_set_reco_dead_node(dlm, O2NM_INVALID_NODE_NUM);
 		else
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index c350bd4..eedf07c 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -92,7 +92,7 @@ int __dlm_lockres_unused(struct dlm_lock_resource *res)
 		return 0;
 
 	/* Another node has this resource with this node as the master */
-	bit = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
+	bit = find_first_bit(res->refmap, O2NM_MAX_NODES);
 	if (bit < O2NM_MAX_NODES)
 		return 0;
 
diff --git a/include/asm-generic/bitops.h b/include/asm-generic/bitops.h
index df9b5bc..a47b8a7 100644
--- a/include/asm-generic/bitops.h
+++ b/include/asm-generic/bitops.h
@@ -20,7 +20,6 @@
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
-#include <asm-generic/bitops/find.h>
 
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
diff --git a/include/asm-generic/bitops/le.h b/include/asm-generic/bitops/le.h
index 5a28629..d51beff 100644
--- a/include/asm-generic/bitops/le.h
+++ b/include/asm-generic/bitops/le.h
@@ -2,83 +2,19 @@
 #ifndef _ASM_GENERIC_BITOPS_LE_H_
 #define _ASM_GENERIC_BITOPS_LE_H_
 
-#include <asm-generic/bitops/find.h>
 #include <asm/types.h>
 #include <asm/byteorder.h>
-#include <linux/swab.h>
 
 #if defined(__LITTLE_ENDIAN)
 
 #define BITOP_LE_SWIZZLE	0
 
-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)
 
 #define BITOP_LE_SWIZZLE	((BITS_PER_LONG-1) & ~0x7)
 
-#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 <asm/byteorder.h>"
-#endif
 
 static inline int test_bit_le(int nr, const void *addr)
 {
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index a241dcf..7dba084 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -6,6 +6,7 @@
 
 #include <linux/align.h>
 #include <linux/bitops.h>
+#include <linux/find.h>
 #include <linux/limits.h>
 #include <linux/string.h>
 #include <linux/types.h>
@@ -54,12 +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
@@ -466,14 +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)
@@ -482,25 +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/bitops.h b/include/linux/bitops.h
index 5e62e23..7aaed50 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -32,40 +32,6 @@ extern unsigned long __sw_hweight64(__u64 w);
  */
 #include <asm/bitops.h>
 
-#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/cpumask.h b/include/linux/cpumask.h
index 1e7399f..64dae70 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -123,6 +123,17 @@ 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)
+{
+	return 0;
+}
+
 static inline unsigned int cpumask_last(const struct cpumask *srcp)
 {
 	return 0;
@@ -167,7 +178,7 @@ 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)
@@ -196,6 +207,30 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp)
 }
 
 /**
+ * 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
+ * @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
  *
@@ -586,15 +621,6 @@ 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
  * @mask2: the second input cpumask
diff --git a/include/linux/find.h b/include/linux/find.h
new file mode 100644
index 0000000..5bb6db2
--- /dev/null
+++ b/include/linux/find.h
@@ -0,0 +1,372 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_FIND_H_
+#define __LINUX_FIND_H_
+
+#ifndef __LINUX_BITMAP_H
+#error only <linux/bitmap.h> can be included directly
+#endif
+
+#include <linux/bitops.h>
+
+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);
+
+#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
+
+#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_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
+ * @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
+
+#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 <asm/byteorder.h>"
+#endif
+
+#define for_each_set_bit(bit, addr, size) \
+	for ((bit) = find_next_bit((addr), (size), 0);		\
+	     (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_next_zero_bit((addr), (size), 0);	\
+	     (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_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
+ * @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_ */
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index b7e52a6..1cf7380 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -285,7 +285,7 @@ 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))
@@ -307,7 +307,7 @@ 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);
 	}
diff --git a/lib/Kconfig b/lib/Kconfig
index 51c368a..c80fde8 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -65,9 +65,6 @@
 config GENERIC_NET_UTILS
 	bool
 
-config GENERIC_FIND_FIRST_BIT
-	bool
-
 source "lib/math/Kconfig"
 
 config NO_GENERIC_PCI_IOPORT_MAP
diff --git a/lib/find_bit.c b/lib/find_bit.c
index 0f8e2e3..1b8e4b2 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 5637c57..db904b5 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);
 
 	/*
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 9a57257..00fc50d 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -251,7 +251,7 @@ void gen_pool_destroy(struct gen_pool *pool)
 		list_del(&chunk->next_chunk);
 
 		end_bit = chunk_size(chunk) >> order;
-		bit = find_next_bit(chunk->bits, end_bit, 0);
+		bit = find_first_bit(chunk->bits, end_bit);
 		BUG_ON(bit < end_bit);
 
 		vfree(chunk);
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index d33fa5a..0c82f07 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -446,6 +446,42 @@ static void __init test_bitmap_parselist(void)
 	}
 }
 
+static void __init test_bitmap_printlist(void)
+{
+	unsigned long *bmap = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	char *buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	char expected[256];
+	int ret, slen;
+	ktime_t time;
+
+	if (!buf || !bmap)
+		goto out;
+
+	memset(bmap, -1, PAGE_SIZE);
+	slen = snprintf(expected, 256, "0-%ld", PAGE_SIZE * 8 - 1);
+	if (slen < 0)
+		goto out;
+
+	time = ktime_get();
+	ret = bitmap_print_to_pagebuf(true, buf, bmap, PAGE_SIZE * 8);
+	time = ktime_get() - time;
+
+	if (ret != slen + 1) {
+		pr_err("bitmap_print_to_pagebuf: result is %d, expected %d\n", ret, slen);
+		goto out;
+	}
+
+	if (strncmp(buf, expected, slen)) {
+		pr_err("bitmap_print_to_pagebuf: result is %s, expected %s\n", buf, expected);
+		goto out;
+	}
+
+	pr_err("bitmap_print_to_pagebuf: input is '%s', Time: %llu\n", buf, time);
+out:
+	kfree(buf);
+	kfree(bmap);
+}
+
 static const unsigned long parse_test[] __initconst = {
 	BITMAP_FROM_U64(0),
 	BITMAP_FROM_U64(1),
@@ -818,6 +854,7 @@ static void __init selftest(void)
 	test_bitmap_arr32();
 	test_bitmap_parse();
 	test_bitmap_parselist();
+	test_bitmap_printlist();
 	test_mem_optimisations();
 	test_for_each_set_clump8();
 	test_bitmap_cut();
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 53d6081..3b8129d 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1241,20 +1241,13 @@ char *bitmap_list_string(char *buf, char *end, unsigned long *bitmap,
 			 struct printf_spec spec, const char *fmt)
 {
 	int nr_bits = max_t(int, spec.field_width, 0);
-	/* current bit is 'cur', most recently seen range is [rbot, rtop] */
-	int cur, rbot, rtop;
 	bool first = true;
+	int rbot, rtop;
 
 	if (check_pointer(&buf, end, bitmap, spec))
 		return buf;
 
-	rbot = cur = find_first_bit(bitmap, nr_bits);
-	while (cur < nr_bits) {
-		rtop = cur;
-		cur = find_next_bit(bitmap, nr_bits, cur + 1);
-		if (cur < nr_bits && cur <= rtop + 1)
-			continue;
-
+	for_each_set_bitrange(rbot, rtop, bitmap, nr_bits) {
 		if (!first) {
 			if (buf < end)
 				*buf = ',';
@@ -1263,15 +1256,12 @@ char *bitmap_list_string(char *buf, char *end, unsigned long *bitmap,
 		first = false;
 
 		buf = number(buf, end, rbot, default_dec_spec);
-		if (rbot < rtop) {
-			if (buf < end)
-				*buf = '-';
-			buf++;
+		if (rtop == rbot + 1)
+			continue;
 
-			buf = number(buf, end, rtop, default_dec_spec);
-		}
-
-		rbot = cur;
+		if (buf < end)
+			*buf = '-';
+		buf = number(++buf, end, rtop - 1, default_dec_spec);
 	}
 	return buf;
 }
diff --git a/mm/percpu.c b/mm/percpu.c
index a188ac9..ea28db2 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);
 }
 
 /**
@@ -1070,17 +1069,18 @@ static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off,
 static bool pcpu_is_populated(struct pcpu_chunk *chunk, int bit_off, int bits,
 			      int *next_off)
 {
-	unsigned int page_start, page_end, rs, re;
+	unsigned int start, end;
 
-	page_start = PFN_DOWN(bit_off * PCPU_MIN_ALLOC_SIZE);
-	page_end = PFN_UP((bit_off + bits) * PCPU_MIN_ALLOC_SIZE);
+	start = PFN_DOWN(bit_off * PCPU_MIN_ALLOC_SIZE);
+	end = PFN_UP((bit_off + bits) * PCPU_MIN_ALLOC_SIZE);
 
-	rs = page_start;
-	bitmap_next_clear_region(chunk->populated, &rs, &re, page_end);
-	if (rs >= page_end)
+	start = find_next_zero_bit(chunk->populated, end, start);
+	if (start >= end)
 		return true;
 
-	*next_off = re * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE;
+	end = find_next_bit(chunk->populated, end, start + 1);
+
+	*next_off = end * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE;
 	return false;
 }
 
@@ -1851,13 +1851,12 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 
 	/* 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);
@@ -2013,8 +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);
@@ -2084,8 +2082,7 @@ static void pcpu_balance_populated(void)
 			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);
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 7121ce2..7881441 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -608,7 +608,7 @@ static int clear_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc,
 	bitmap = &ncf->bitmap;
 
 	spin_lock_irqsave(&nc->lock, flags);
-	index = find_next_bit(bitmap, ncf->n_vids, 0);
+	index = find_first_bit(bitmap, ncf->n_vids);
 	if (index >= ncf->n_vids) {
 		spin_unlock_irqrestore(&nc->lock, flags);
 		return -1;
@@ -667,7 +667,7 @@ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc,
 		return -1;
 	}
 
-	index = find_next_zero_bit(bitmap, ncf->n_vids, 0);
+	index = find_first_zero_bit(bitmap, ncf->n_vids);
 	if (index < 0 || index >= ncf->n_vids) {
 		netdev_err(ndp->ndev.dev,
 			   "Channel %u already has all VLAN filters set\n",
diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h
index 5d2ab38..9ab313e 100644
--- a/tools/include/asm-generic/bitops.h
+++ b/tools/include/asm-generic/bitops.h
@@ -18,7 +18,6 @@
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
-#include <asm-generic/bitops/find.h>
 
 #ifndef _TOOLS_LINUX_BITOPS_H_
 #error only <linux/bitops.h> can be included directly
diff --git a/tools/include/asm-generic/bitops/find.h b/tools/include/asm-generic/bitops/find.h
deleted file mode 100644
index 6481fd1..0000000
--- a/tools/include/asm-generic/bitops/find.h
+++ /dev/null
@@ -1,145 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
-#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
-
-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
-
-#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 /* find_first_bit */
-
-#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
-
-#endif /*_TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_ */
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index 95611df..ea97804 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -1,9 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _PERF_BITOPS_H
-#define _PERF_BITOPS_H
+#ifndef _TOOLS_LINUX_BITMAP_H
+#define _TOOLS_LINUX_BITMAP_H
 
 #include <string.h>
 #include <linux/bitops.h>
+#include <linux/find.h>
 #include <stdlib.h>
 #include <linux/kernel.h>
 
@@ -181,4 +182,4 @@ static inline int bitmap_intersects(const unsigned long *src1,
 		return __bitmap_intersects(src1, src2, nbits);
 }
 
-#endif /* _PERF_BITOPS_H */
+#endif /* _TOOLS_LINUX_BITMAP_H */
diff --git a/include/asm-generic/bitops/find.h b/tools/include/linux/find.h
similarity index 82%
rename from include/asm-generic/bitops/find.h
rename to tools/include/linux/find.h
index 0d132ee..47e2bd6 100644
--- a/include/asm-generic/bitops/find.h
+++ b/tools/include/linux/find.h
@@ -1,11 +1,19 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_GENERIC_BITOPS_FIND_H_
-#define _ASM_GENERIC_BITOPS_FIND_H_
+#ifndef _TOOLS_LINUX_FIND_H_
+#define _TOOLS_LINUX_FIND_H_
+
+#ifndef _TOOLS_LINUX_BITMAP_H
+#error tools: only <linux/bitmap.h> can be included directly
+#endif
+
+#include <linux/bitops.h>
 
 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);
 
@@ -95,8 +103,7 @@ 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
  * @addr: The address to start the search at
@@ -116,7 +123,34 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
 
 	return _find_first_bit(addr, 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
  * @addr: The address to start the search at
@@ -136,16 +170,7 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
 
 	return _find_first_zero_bit(addr, size);
 }
-#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
 /**
@@ -185,4 +210,5 @@ extern unsigned long find_next_clump8(unsigned long *clump,
 #define find_first_clump8(clump, bits, size) \
 	find_next_clump8((clump), (bits), (size), 0)
 
-#endif /*_ASM_GENERIC_BITOPS_FIND_H_ */
+
+#endif /*__LINUX_FIND_H_ */
diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c
index 109aa7f..ba4b8d9 100644
--- a/tools/lib/find_bit.c
+++ b/tools/lib/find_bit.c
@@ -96,6 +96,26 @@ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size)
 }
 #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;
+}
+#endif
+
 #ifndef find_first_zero_bit
 /*
  * Find the first cleared bit in a memory region.