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

4 files changed, 409 insertions, 77 deletions

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index a241dcf50f39..7dba0847510c 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 5e62e2383b7f..7aaed501f768 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -32,40 +32,6 @@ extern unsigned long __sw_hweight64(__u64 w);
  */
 #include <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 1e7399fc69c0..64dae70d31f5 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 000000000000..5bb6db213bcb
--- /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_ */