Merge tag 'bitmap-6.1-rc1' of https://github.com/norov/linux

Pull bitmap updates from Yury Norov:

 - Fix unsigned comparison to -1 in CPUMAP_FILE_MAX_BYTES (Phil Auld)

 - cleanup nr_cpu_ids vs nr_cpumask_bits mess (me)

   This series cleans that mess and adds new config FORCE_NR_CPUS that
   allows to optimize cpumask subsystem if the number of CPUs is known
   at compile-time.

 - optimize find_bit() functions (me)

   Reworks find_bit() functions based on new FIND_{FIRST,NEXT}_BIT()
   macros.

 - add find_nth_bit() (me)

   Adds find_nth_bit(), which is ~70 times faster than bitcounting with
   for_each() loop:

	for_each_set_bit(bit, mask, size)
		if (n-- == 0)
			return bit;

   Also adds bitmap_weight_and() to let people replace this pattern:

	tmp = bitmap_alloc(nbits);
	bitmap_and(tmp, map1, map2, nbits);
	weight = bitmap_weight(tmp, nbits);
	bitmap_free(tmp);

   with a single bitmap_weight_and() call.

 - repair cpumask_check() (me)

   After switching cpumask to use nr_cpu_ids, cpumask_check() started
   generating many false-positive warnings. This series fixes it.

 - Add for_each_cpu_andnot() and for_each_cpu_andnot() (Valentin
   Schneider)

   Extends the API with one more function and applies it in sched/core.

* tag 'bitmap-6.1-rc1' of https://github.com/norov/linux: (28 commits)
  sched/core: Merge cpumask_andnot()+for_each_cpu() into for_each_cpu_andnot()
  lib/test_cpumask: Add for_each_cpu_and(not) tests
  cpumask: Introduce for_each_cpu_andnot()
  lib/find_bit: Introduce find_next_andnot_bit()
  cpumask: fix checking valid cpu range
  lib/bitmap: add tests for for_each() loops
  lib/find: optimize for_each() macros
  lib/bitmap: introduce for_each_set_bit_wrap() macro
  lib/find_bit: add find_next{,_and}_bit_wrap
  cpumask: switch for_each_cpu{,_not} to use for_each_bit()
  net: fix cpu_max_bits_warn() usage in netif_attrmask_next{,_and}
  cpumask: add cpumask_nth_{,and,andnot}
  lib/bitmap: remove bitmap_ord_to_pos
  lib/bitmap: add tests for find_nth_bit()
  lib: add find_nth{,_and,_andnot}_bit()
  lib/bitmap: add bitmap_weight_and()
  lib/bitmap: don't call __bitmap_weight() in kernel code
  tools: sync find_bit() implementation
  lib/find_bit: optimize find_next_bit() functions
  lib/find_bit: create find_first_zero_bit_le()
  ...

6 files changed, 402 insertions, 85 deletions

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index f65410a49fda..7d6d73b78147 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -51,6 +51,7 @@ struct device;
  *  bitmap_empty(src, nbits)                    Are all bits zero in *src?
  *  bitmap_full(src, nbits)                     Are all bits set in *src?
  *  bitmap_weight(src, nbits)                   Hamming Weight: number set bits
+ *  bitmap_weight_and(src1, src2, nbits)        Hamming Weight of and'ed bitmap
  *  bitmap_set(dst, pos, nbits)                 Set specified bit area
  *  bitmap_clear(dst, pos, nbits)               Clear specified bit area
  *  bitmap_find_next_zero_area(buf, len, pos, n, mask)  Find bit free area
@@ -164,6 +165,8 @@ bool __bitmap_intersects(const unsigned long *bitmap1,
 bool __bitmap_subset(const unsigned long *bitmap1,
 		     const unsigned long *bitmap2, unsigned int nbits);
 unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
+unsigned int __bitmap_weight_and(const unsigned long *bitmap1,
+				 const unsigned long *bitmap2, unsigned int nbits);
 void __bitmap_set(unsigned long *map, unsigned int start, int len);
 void __bitmap_clear(unsigned long *map, unsigned int start, int len);
 
@@ -222,7 +225,6 @@ void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int n
 #else
 #define bitmap_copy_le bitmap_copy
 #endif
-unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits);
 int bitmap_print_to_pagebuf(bool list, char *buf,
 				   const unsigned long *maskp, int nmaskbits);
 
@@ -439,6 +441,15 @@ unsigned int bitmap_weight(const unsigned long *src, unsigned int nbits)
 	return __bitmap_weight(src, nbits);
 }
 
+static __always_inline
+unsigned long bitmap_weight_and(const unsigned long *src1,
+				const unsigned long *src2, unsigned int nbits)
+{
+	if (small_const_nbits(nbits))
+		return hweight_long(*src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits));
+	return __bitmap_weight_and(src1, src2, nbits);
+}
+
 static __always_inline void bitmap_set(unsigned long *map, unsigned int start,
 		unsigned int nbits)
 {
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 3b89c64bcfd8..d7dd83fafeba 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -248,6 +248,25 @@ static inline unsigned long __ffs64(u64 word)
 }
 
 /**
+ * fns - find N'th set bit in a word
+ * @word: The word to search
+ * @n: Bit to find
+ */
+static inline unsigned long fns(unsigned long word, unsigned int n)
+{
+	unsigned int bit;
+
+	while (word) {
+		bit = __ffs(word);
+		if (n-- == 0)
+			return bit;
+		__clear_bit(bit, &word);
+	}
+
+	return BITS_PER_LONG;
+}
+
+/**
  * assign_bit - Assign value to a bit in memory
  * @nr: the bit to set
  * @addr: the address to start counting from
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index e8ad12b5b9d2..2f065ad97541 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -35,19 +35,23 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
  */
 #define cpumask_pr_args(maskp)		nr_cpu_ids, cpumask_bits(maskp)
 
-#if NR_CPUS == 1
-#define nr_cpu_ids		1U
+#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS)
+#define nr_cpu_ids ((unsigned int)NR_CPUS)
 #else
 extern unsigned int nr_cpu_ids;
 #endif
 
-#ifdef CONFIG_CPUMASK_OFFSTACK
-/* Assuming NR_CPUS is huge, a runtime limit is more efficient.  Also,
- * not all bits may be allocated. */
-#define nr_cpumask_bits	nr_cpu_ids
+static inline void set_nr_cpu_ids(unsigned int nr)
+{
+#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS)
+	WARN_ON(nr != nr_cpu_ids);
 #else
-#define nr_cpumask_bits	((unsigned int)NR_CPUS)
+	nr_cpu_ids = nr;
 #endif
+}
+
+/* Deprecated. Always use nr_cpu_ids. */
+#define nr_cpumask_bits	nr_cpu_ids
 
 /*
  * The following particular system cpumasks and operations manage
@@ -67,10 +71,6 @@ extern unsigned int nr_cpu_ids;
  *  cpu_online_mask is the dynamic subset of cpu_present_mask,
  *  indicating those CPUs available for scheduling.
  *
- *  If HOTPLUG is enabled, then cpu_possible_mask is forced to have
- *  all NR_CPUS bits set, otherwise it is just the set of CPUs that
- *  ACPI reports present at boot.
- *
  *  If HOTPLUG is enabled, then cpu_present_mask varies dynamically,
  *  depending on what ACPI reports as currently plugged in, otherwise
  *  cpu_present_mask is just a copy of cpu_possible_mask.
@@ -174,9 +174,8 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp)
 static inline
 unsigned int cpumask_next(int n, const struct cpumask *srcp)
 {
-	/* -1 is a legal arg here. */
-	if (n != -1)
-		cpumask_check(n);
+	/* n is a prior cpu */
+	cpumask_check(n + 1);
 	return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1);
 }
 
@@ -189,9 +188,8 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp)
  */
 static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 {
-	/* -1 is a legal arg here. */
-	if (n != -1)
-		cpumask_check(n);
+	/* n is a prior cpu */
+	cpumask_check(n + 1);
 	return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1);
 }
 
@@ -231,9 +229,8 @@ static inline
 unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
 		     const struct cpumask *src2p)
 {
-	/* -1 is a legal arg here. */
-	if (n != -1)
-		cpumask_check(n);
+	/* n is a prior cpu */
+	cpumask_check(n + 1);
 	return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p),
 		nr_cpumask_bits, n + 1);
 }
@@ -246,9 +243,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
  * After the loop, cpu is >= nr_cpu_ids.
  */
 #define for_each_cpu(cpu, mask)				\
-	for ((cpu) = -1;				\
-		(cpu) = cpumask_next((cpu), (mask)),	\
-		(cpu) < nr_cpu_ids;)
+	for_each_set_bit(cpu, cpumask_bits(mask), nr_cpumask_bits)
 
 /**
  * for_each_cpu_not - iterate over every cpu in a complemented mask
@@ -258,17 +253,15 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
  * After the loop, cpu is >= nr_cpu_ids.
  */
 #define for_each_cpu_not(cpu, mask)				\
-	for ((cpu) = -1;					\
-		(cpu) = cpumask_next_zero((cpu), (mask)),	\
-		(cpu) < nr_cpu_ids;)
+	for_each_clear_bit(cpu, cpumask_bits(mask), nr_cpumask_bits)
 
 #if NR_CPUS == 1
 static inline
 unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
 {
 	cpumask_check(start);
-	if (n != -1)
-		cpumask_check(n);
+	/* n is a prior cpu */
+	cpumask_check(n + 1);
 
 	/*
 	 * Return the first available CPU when wrapping, or when starting before cpu0,
@@ -293,10 +286,8 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta
  *
  * After the loop, cpu is >= nr_cpu_ids.
  */
-#define for_each_cpu_wrap(cpu, mask, start)					\
-	for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false);	\
-	     (cpu) < nr_cpumask_bits;						\
-	     (cpu) = cpumask_next_wrap((cpu), (mask), (start), true))
+#define for_each_cpu_wrap(cpu, mask, start)				\
+	for_each_set_bit_wrap(cpu, cpumask_bits(mask), nr_cpumask_bits, start)
 
 /**
  * for_each_cpu_and - iterate over every cpu in both masks
@@ -313,9 +304,25 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta
  * After the loop, cpu is >= nr_cpu_ids.
  */
 #define for_each_cpu_and(cpu, mask1, mask2)				\
-	for ((cpu) = -1;						\
-		(cpu) = cpumask_next_and((cpu), (mask1), (mask2)),	\
-		(cpu) < nr_cpu_ids;)
+	for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits)
+
+/**
+ * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding
+ *			 those present in another.
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask1: the first cpumask pointer
+ * @mask2: the second cpumask pointer
+ *
+ * This saves a temporary CPU mask in many places.  It is equivalent to:
+ *	struct cpumask tmp;
+ *	cpumask_andnot(&tmp, &mask1, &mask2);
+ *	for_each_cpu(cpu, &tmp)
+ *		...
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu_andnot(cpu, mask1, mask2)				\
+	for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits)
 
 /**
  * cpumask_any_but - return a "random" in a cpumask, but not this one.
@@ -337,6 +344,50 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 	return i;
 }
 
+/**
+ * cpumask_nth - get the first cpu in a cpumask
+ * @srcp: the cpumask pointer
+ * @cpu: the N'th cpu to find, starting from 0
+ *
+ * Returns >= nr_cpu_ids if such cpu doesn't exist.
+ */
+static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp)
+{
+	return find_nth_bit(cpumask_bits(srcp), nr_cpumask_bits, cpumask_check(cpu));
+}
+
+/**
+ * cpumask_nth_and - get the first cpu in 2 cpumasks
+ * @srcp1: the cpumask pointer
+ * @srcp2: the cpumask pointer
+ * @cpu: the N'th cpu to find, starting from 0
+ *
+ * Returns >= nr_cpu_ids if such cpu doesn't exist.
+ */
+static inline
+unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1,
+							const struct cpumask *srcp2)
+{
+	return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2),
+				nr_cpumask_bits, cpumask_check(cpu));
+}
+
+/**
+ * cpumask_nth_andnot - get the first cpu set in 1st cpumask, and clear in 2nd.
+ * @srcp1: the cpumask pointer
+ * @srcp2: the cpumask pointer
+ * @cpu: the N'th cpu to find, starting from 0
+ *
+ * Returns >= nr_cpu_ids if such cpu doesn't exist.
+ */
+static inline
+unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1,
+							const struct cpumask *srcp2)
+{
+	return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2),
+				nr_cpumask_bits, cpumask_check(cpu));
+}
+
 #define CPU_BITS_NONE						\
 {								\
 	[0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL			\
@@ -587,6 +638,17 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp)
 }
 
 /**
+ * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2)
+ * @srcp1: the cpumask to count bits (< nr_cpu_ids) in.
+ * @srcp2: the cpumask to count bits (< nr_cpu_ids) in.
+ */
+static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1,
+						const struct cpumask *srcp2)
+{
+	return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), nr_cpumask_bits);
+}
+
+/**
  * cpumask_shift_right - *dstp = *srcp >> n
  * @dstp: the cpumask result
  * @srcp: the input to shift
diff --git a/include/linux/find.h b/include/linux/find.h
index 424ef67d4a42..ccaf61a0f5fd 100644
--- a/include/linux/find.h
+++ b/include/linux/find.h
@@ -8,15 +8,33 @@
 
 #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);
+unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits,
+				unsigned long start);
+unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2,
+					unsigned long nbits, unsigned long start);
+unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
+					unsigned long nbits, unsigned long start);
+unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits,
+					 unsigned long start);
 extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size);
+unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n);
+unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2,
+				unsigned long size, unsigned long n);
+unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
+					unsigned long size, unsigned long n);
 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);
 
+#ifdef __BIG_ENDIAN
+unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size);
+unsigned long _find_next_zero_bit_le(const  unsigned long *addr, unsigned
+					long size, unsigned long offset);
+unsigned long _find_next_bit_le(const unsigned long *addr, unsigned
+				long size, unsigned long offset);
+#endif
+
 #ifndef find_next_bit
 /**
  * find_next_bit - find the next set bit in a memory region
@@ -41,7 +59,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
 		return val ? __ffs(val) : size;
 	}
 
-	return _find_next_bit(addr, NULL, size, offset, 0UL, 0);
+	return _find_next_bit(addr, size, offset);
 }
 #endif
 
@@ -71,7 +89,38 @@ unsigned long find_next_and_bit(const unsigned long *addr1,
 		return val ? __ffs(val) : size;
 	}
 
-	return _find_next_bit(addr1, addr2, size, offset, 0UL, 0);
+	return _find_next_and_bit(addr1, addr2, size, offset);
+}
+#endif
+
+#ifndef find_next_andnot_bit
+/**
+ * find_next_andnot_bit - find the next set bit in *addr1 excluding all the bits
+ *                        in *addr2
+ * @addr1: The first address to base the search on
+ * @addr2: The second address to base the search on
+ * @size: The bitmap size in bits
+ * @offset: The bitnumber to start searching at
+ *
+ * Returns the bit number for the next set bit
+ * If no bits are set, returns @size.
+ */
+static inline
+unsigned long find_next_andnot_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_andnot_bit(addr1, addr2, size, offset);
 }
 #endif
 
@@ -99,7 +148,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
 		return val == ~0UL ? size : ffz(val);
 	}
 
-	return _find_next_bit(addr, NULL, size, offset, ~0UL, 0);
+	return _find_next_zero_bit(addr, size, offset);
 }
 #endif
 
@@ -125,6 +174,87 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
 }
 #endif
 
+/**
+ * find_nth_bit - find N'th set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum number of bits to search
+ * @n: The number of set bit, which position is needed, counting from 0
+ *
+ * The following is semantically equivalent:
+ *	 idx = find_nth_bit(addr, size, 0);
+ *	 idx = find_first_bit(addr, size);
+ *
+ * Returns the bit number of the N'th set bit.
+ * If no such, returns @size.
+ */
+static inline
+unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n)
+{
+	if (n >= size)
+		return size;
+
+	if (small_const_nbits(size)) {
+		unsigned long val =  *addr & GENMASK(size - 1, 0);
+
+		return val ? fns(val, n) : size;
+	}
+
+	return __find_nth_bit(addr, size, n);
+}
+
+/**
+ * find_nth_and_bit - find N'th set bit in 2 memory regions
+ * @addr1: The 1st address to start the search at
+ * @addr2: The 2nd address to start the search at
+ * @size: The maximum number of bits to search
+ * @n: The number of set bit, which position is needed, counting from 0
+ *
+ * Returns the bit number of the N'th set bit.
+ * If no such, returns @size.
+ */
+static inline
+unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2,
+				unsigned long size, unsigned long n)
+{
+	if (n >= size)
+		return size;
+
+	if (small_const_nbits(size)) {
+		unsigned long val =  *addr1 & *addr2 & GENMASK(size - 1, 0);
+
+		return val ? fns(val, n) : size;
+	}
+
+	return __find_nth_and_bit(addr1, addr2, size, n);
+}
+
+/**
+ * find_nth_andnot_bit - find N'th set bit in 2 memory regions,
+ *			 flipping bits in 2nd region
+ * @addr1: The 1st address to start the search at
+ * @addr2: The 2nd address to start the search at
+ * @size: The maximum number of bits to search
+ * @n: The number of set bit, which position is needed, counting from 0
+ *
+ * Returns the bit number of the N'th set bit.
+ * If no such, returns @size.
+ */
+static inline
+unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
+				unsigned long size, unsigned long n)
+{
+	if (n >= size)
+		return size;
+
+	if (small_const_nbits(size)) {
+		unsigned long val =  *addr1 & (~*addr2) & GENMASK(size - 1, 0);
+
+		return val ? fns(val, n) : size;
+	}
+
+	return __find_nth_andnot_bit(addr1, addr2, size, n);
+}
+
 #ifndef find_first_and_bit
 /**
  * find_first_and_bit - find the first set bit in both memory regions
@@ -194,6 +324,78 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
 #endif
 
 /**
+ * find_next_and_bit_wrap - 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
+ * @size: The bitmap size in bits
+ * @offset: The bitnumber to start searching at
+ *
+ * Returns the bit number for the next set bit, or first set bit up to @offset
+ * If no bits are set, returns @size.
+ */
+static inline
+unsigned long find_next_and_bit_wrap(const unsigned long *addr1,
+					const unsigned long *addr2,
+					unsigned long size, unsigned long offset)
+{
+	unsigned long bit = find_next_and_bit(addr1, addr2, size, offset);
+
+	if (bit < size)
+		return bit;
+
+	bit = find_first_and_bit(addr1, addr2, offset);
+	return bit < offset ? bit : size;
+}
+
+/**
+ * find_next_bit_wrap - find the next set bit in both memory regions
+ * @addr: The first address to base the search on
+ * @size: The bitmap size in bits
+ * @offset: The bitnumber to start searching at
+ *
+ * Returns the bit number for the next set bit, or first set bit up to @offset
+ * If no bits are set, returns @size.
+ */
+static inline
+unsigned long find_next_bit_wrap(const unsigned long *addr,
+					unsigned long size, unsigned long offset)
+{
+	unsigned long bit = find_next_bit(addr, size, offset);
+
+	if (bit < size)
+		return bit;
+
+	bit = find_first_bit(addr, offset);
+	return bit < offset ? bit : size;
+}
+
+/*
+ * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing
+ * before using it alone.
+ */
+static inline
+unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size,
+				 unsigned long start, unsigned long n)
+{
+	unsigned long bit;
+
+	/* If not wrapped around */
+	if (n > start) {
+		/* and have a bit, just return it. */
+		bit = find_next_bit(bitmap, size, n);
+		if (bit < size)
+			return bit;
+
+		/* Otherwise, wrap around and ... */
+		n = 0;
+	}
+
+	/* Search the other part. */
+	bit = find_next_bit(bitmap, start, n);
+	return bit < start ? bit : size;
+}
+
+/**
  * 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
@@ -247,7 +449,21 @@ unsigned long find_next_zero_bit_le(const void *addr, unsigned
 		return val == ~0UL ? size : ffz(val);
 	}
 
-	return _find_next_bit(addr, NULL, size, offset, ~0UL, 1);
+	return _find_next_zero_bit_le(addr, size, offset);
+}
+#endif
+
+#ifndef find_first_zero_bit_le
+static inline
+unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val = swab(*(const unsigned long *)addr) | ~GENMASK(size - 1, 0);
+
+		return val == ~0UL ? size : ffz(val);
+	}
+
+	return _find_first_zero_bit_le(addr, size);
 }
 #endif
 
@@ -266,40 +482,39 @@ unsigned long find_next_bit_le(const void *addr, unsigned
 		return val ? __ffs(val) : size;
 	}
 
-	return _find_next_bit(addr, NULL, size, offset, 0UL, 1);
+	return _find_next_bit_le(addr, size, offset);
 }
 #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))
+	for ((bit) = 0; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++)
+
+#define for_each_and_bit(bit, addr1, addr2, size) \
+	for ((bit) = 0;									\
+	     (bit) = find_next_and_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\
+	     (bit)++)
+
+#define for_each_andnot_bit(bit, addr1, addr2, size) \
+	for ((bit) = 0;									\
+	     (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\
+	     (bit)++)
 
 /* 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))
+	for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++)
 
 #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))
+	for ((bit) = 0;									\
+	     (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size);		\
+	     (bit)++)
 
 /* 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 (; (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); (bit)++)
 
 /**
  * for_each_set_bitrange - iterate over all set bit ranges [b; e)
@@ -309,11 +524,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned
  * @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);	\
+	for ((b) = 0;						\
+	     (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))
+	     (b) = (e) + 1)
 
 /**
  * for_each_set_bitrange_from - iterate over all set bit ranges [b; e)
@@ -323,11 +538,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned
  * @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);	\
+	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))
+	     (b) = (e) + 1)
 
 /**
  * for_each_clear_bitrange - iterate over all unset bit ranges [b; e)
@@ -337,11 +552,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned
  * @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);	\
+	for ((b) = 0;						\
+	     (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))
+	     (b) = (e) + 1)
 
 /**
  * for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e)
@@ -351,11 +566,24 @@ unsigned long find_next_bit_le(const void *addr, unsigned
  * @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);	\
+	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))
+	     (b) = (e) + 1)
+
+/**
+ * for_each_set_bit_wrap - iterate over all set bits starting from @start, and
+ * wrapping around the end of bitmap.
+ * @bit: offset for current iteration
+ * @addr: bitmap address to base the search on
+ * @size: bitmap size in number of bits
+ * @start: Starting bit for bitmap traversing, wrapping around the bitmap end
+ */
+#define for_each_set_bit_wrap(bit, addr, size, start) \
+	for ((bit) = find_next_bit_wrap((addr), (size), (start));		\
+	     (bit) < (size);							\
+	     (bit) = __for_each_wrap((addr), (size), (start), (bit) + 1))
 
 /**
  * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index eddf8ee270e7..a36edb0ec199 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3663,9 +3663,8 @@ static inline bool netif_attr_test_online(unsigned long j,
 static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp,
 					       unsigned int nr_bits)
 {
-	/* -1 is a legal arg here. */
-	if (n != -1)
-		cpu_max_bits_warn(n, nr_bits);
+	/* n is a prior cpu */
+	cpu_max_bits_warn(n + 1, nr_bits);
 
 	if (srcp)
 		return find_next_bit(srcp, nr_bits, n + 1);
@@ -3686,9 +3685,8 @@ static inline int netif_attrmask_next_and(int n, const unsigned long *src1p,
 					  const unsigned long *src2p,
 					  unsigned int nr_bits)
 {
-	/* -1 is a legal arg here. */
-	if (n != -1)
-		cpu_max_bits_warn(n, nr_bits);
+	/* n is a prior cpu */
+	cpu_max_bits_warn(n + 1, nr_bits);
 
 	if (src1p && src2p)
 		return find_next_and_bit(src1p, src2p, nr_bits, n + 1);
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 4b71a96190a8..0c45fb066caa 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -508,8 +508,7 @@ static inline int node_random(const nodemask_t *maskp)
 
 	w = nodes_weight(*maskp);
 	if (w)
-		bit = bitmap_ord_to_pos(maskp->bits,
-			get_random_int() % w, MAX_NUMNODES);
+		bit = find_nth_bit(maskp->bits, MAX_NUMNODES, get_random_int() % w);
 	return bit;
 #else
 	return 0;