Merge tag 'bitmap-6.0-rc1' of https://github.com/norov/linux

Pull bitmap updates from Yury Norov:

 - fix the duplicated comments on bitmap_to_arr64() (Qu Wenruo)

 - optimize out non-atomic bitops on compile-time constants (Alexander
   Lobakin)

 - cleanup bitmap-related headers (Yury Norov)

 - x86/olpc: fix 'logical not is only applied to the left hand side'
   (Alexander Lobakin)

 - lib/nodemask: inline wrappers around bitmap (Yury Norov)

* tag 'bitmap-6.0-rc1' of https://github.com/norov/linux: (26 commits)
  lib/nodemask: inline next_node_in() and node_random()
  powerpc: drop dependency on <asm/machdep.h> in archrandom.h
  x86/olpc: fix 'logical not is only applied to the left hand side'
  lib/cpumask: move some one-line wrappers to header file
  headers/deps: mm: align MANITAINERS and Docs with new gfp.h structure
  headers/deps: mm: Split <linux/gfp_types.h> out of <linux/gfp.h>
  headers/deps: mm: Optimize <linux/gfp.h> header dependencies
  lib/cpumask: move trivial wrappers around find_bit to the header
  lib/cpumask: change return types to unsigned where appropriate
  cpumask: change return types to bool where appropriate
  lib/bitmap: change type of bitmap_weight to unsigned long
  lib/bitmap: change return types to bool where appropriate
  arm: align find_bit declarations with generic kernel
  iommu/vt-d: avoid invalid memory access via node_online(NUMA_NO_NODE)
  lib/test_bitmap: test the tail after bitmap_to_arr64()
  lib/bitmap: fix off-by-one in bitmap_to_arr64()
  lib: test_bitmap: add compile-time optimization/evaluations assertions
  bitmap: don't assume compiler evaluates small mem*() builtins calls
  net/ice: fix initializing the bitmap in the switch code
  bitops: let optimize out non-atomic bitops on compile-time constants
  ...

10 files changed, 753 insertions, 509 deletions

diff --git a/include/asm-generic/bitops/generic-non-atomic.h b/include/asm-generic/bitops/generic-non-atomic.h
new file mode 100644
index 000000000000..3d5ebd24652b
--- /dev/null
+++ b/include/asm-generic/bitops/generic-non-atomic.h
@@ -0,0 +1,161 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H
+#define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H
+
+#include <linux/bits.h>
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+/*
+ * Generic definitions for bit operations, should not be used in regular code
+ * directly.
+ */
+
+/**
+ * generic___set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static __always_inline void
+generic___set_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p  |= mask;
+}
+
+static __always_inline void
+generic___clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p &= ~mask;
+}
+
+/**
+ * generic___change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static __always_inline void
+generic___change_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p ^= mask;
+}
+
+/**
+ * generic___test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static __always_inline bool
+generic___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old | mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * generic___test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static __always_inline bool
+generic___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old & ~mask;
+	return (old & mask) != 0;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static __always_inline bool
+generic___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old ^ mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * generic_test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+generic_test_bit(unsigned long nr, const volatile unsigned long *addr)
+{
+	/*
+	 * Unlike the bitops with the '__' prefix above, this one *is* atomic,
+	 * so `volatile` must always stay here with no cast-aways. See
+	 * `Documentation/atomic_bitops.txt` for the details.
+	 */
+	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+/*
+ * const_*() definitions provide good compile-time optimizations when
+ * the passed arguments can be resolved at compile time.
+ */
+#define const___set_bit			generic___set_bit
+#define const___clear_bit		generic___clear_bit
+#define const___change_bit		generic___change_bit
+#define const___test_and_set_bit	generic___test_and_set_bit
+#define const___test_and_clear_bit	generic___test_and_clear_bit
+#define const___test_and_change_bit	generic___test_and_change_bit
+
+/**
+ * const_test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ *
+ * A version of generic_test_bit() which discards the `volatile` qualifier to
+ * allow a compiler to optimize code harder. Non-atomic and to be called only
+ * for testing compile-time constants, e.g. by the corresponding macros, not
+ * directly from "regular" code.
+ */
+static __always_inline bool
+const_test_bit(unsigned long nr, const volatile unsigned long *addr)
+{
+	const unsigned long *p = (const unsigned long *)addr + BIT_WORD(nr);
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long val = *p;
+
+	return !!(val & mask);
+}
+
+#endif /* __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H */
diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h
index 7ab1ecc37782..988a3bbfba34 100644
--- a/include/asm-generic/bitops/instrumented-non-atomic.h
+++ b/include/asm-generic/bitops/instrumented-non-atomic.h
@@ -14,7 +14,7 @@
 #include <linux/instrumented.h>
 
 /**
- * __set_bit - Set a bit in memory
+ * ___set_bit - Set a bit in memory
  * @nr: the bit to set
  * @addr: the address to start counting from
  *
@@ -22,14 +22,15 @@
  * region of memory concurrently, the effect may be that only one operation
  * succeeds.
  */
-static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
+static __always_inline void
+___set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	instrument_write(addr + BIT_WORD(nr), sizeof(long));
 	arch___set_bit(nr, addr);
 }
 
 /**
- * __clear_bit - Clears a bit in memory
+ * ___clear_bit - Clears a bit in memory
  * @nr: the bit to clear
  * @addr: the address to start counting from
  *
@@ -37,14 +38,15 @@ static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
  * region of memory concurrently, the effect may be that only one operation
  * succeeds.
  */
-static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline void
+___clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	instrument_write(addr + BIT_WORD(nr), sizeof(long));
 	arch___clear_bit(nr, addr);
 }
 
 /**
- * __change_bit - Toggle a bit in memory
+ * ___change_bit - Toggle a bit in memory
  * @nr: the bit to change
  * @addr: the address to start counting from
  *
@@ -52,7 +54,8 @@ static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
  * region of memory concurrently, the effect may be that only one operation
  * succeeds.
  */
-static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void
+___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	instrument_write(addr + BIT_WORD(nr), sizeof(long));
 	arch___change_bit(nr, addr);
@@ -83,53 +86,57 @@ static __always_inline void __instrument_read_write_bitop(long nr, volatile unsi
 }
 
 /**
- * __test_and_set_bit - Set a bit and return its old value
+ * ___test_and_set_bit - Set a bit and return its old value
  * @nr: Bit to set
  * @addr: Address to count from
  *
  * This operation is non-atomic. If two instances of this operation race, one
  * can appear to succeed but actually fail.
  */
-static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_set_bit(nr, addr);
 }
 
 /**
- * __test_and_clear_bit - Clear a bit and return its old value
+ * ___test_and_clear_bit - Clear a bit and return its old value
  * @nr: Bit to clear
  * @addr: Address to count from
  *
  * This operation is non-atomic. If two instances of this operation race, one
  * can appear to succeed but actually fail.
  */
-static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_clear_bit(nr, addr);
 }
 
 /**
- * __test_and_change_bit - Change a bit and return its old value
+ * ___test_and_change_bit - Change a bit and return its old value
  * @nr: Bit to change
  * @addr: Address to count from
  *
  * This operation is non-atomic. If two instances of this operation race, one
  * can appear to succeed but actually fail.
  */
-static __always_inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_change_bit(nr, addr);
 }
 
 /**
- * test_bit - Determine whether a bit is set
+ * _test_bit - Determine whether a bit is set
  * @nr: bit number to test
  * @addr: Address to start counting from
  */
-static __always_inline bool test_bit(long nr, const volatile unsigned long *addr)
+static __always_inline bool
+_test_bit(unsigned long nr, const volatile unsigned long *addr)
 {
 	instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long));
 	return arch_test_bit(nr, addr);
diff --git a/include/asm-generic/bitops/non-atomic.h b/include/asm-generic/bitops/non-atomic.h
index 078cc68be2f1..5c37ced343ae 100644
--- a/include/asm-generic/bitops/non-atomic.h
+++ b/include/asm-generic/bitops/non-atomic.h
@@ -2,121 +2,18 @@
 #ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
-#include <asm/types.h>
+#include <asm-generic/bitops/generic-non-atomic.h>
 
-/**
- * arch___set_bit - Set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * Unlike set_bit(), this function is non-atomic and may be reordered.
- * If it's called on the same region of memory simultaneously, the effect
- * may be that only one operation succeeds.
- */
-static __always_inline void
-arch___set_bit(unsigned int nr, volatile unsigned long *addr)
-{
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+#define arch___set_bit generic___set_bit
+#define arch___clear_bit generic___clear_bit
+#define arch___change_bit generic___change_bit
 
-	*p  |= mask;
-}
-#define __set_bit arch___set_bit
+#define arch___test_and_set_bit generic___test_and_set_bit
+#define arch___test_and_clear_bit generic___test_and_clear_bit
+#define arch___test_and_change_bit generic___test_and_change_bit
 
-static __always_inline void
-arch___clear_bit(unsigned int nr, volatile unsigned long *addr)
-{
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+#define arch_test_bit generic_test_bit
 
-	*p &= ~mask;
-}
-#define __clear_bit arch___clear_bit
-
-/**
- * arch___change_bit - Toggle a bit in memory
- * @nr: the bit to change
- * @addr: the address to start counting from
- *
- * Unlike change_bit(), this function is non-atomic and may be reordered.
- * If it's called on the same region of memory simultaneously, the effect
- * may be that only one operation succeeds.
- */
-static __always_inline
-void arch___change_bit(unsigned int nr, volatile unsigned long *addr)
-{
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-
-	*p ^= mask;
-}
-#define __change_bit arch___change_bit
-
-/**
- * arch___test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail.  You must protect multiple accesses with a lock.
- */
-static __always_inline int
-arch___test_and_set_bit(unsigned int nr, volatile unsigned long *addr)
-{
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old = *p;
-
-	*p = old | mask;
-	return (old & mask) != 0;
-}
-#define __test_and_set_bit arch___test_and_set_bit
-
-/**
- * arch___test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail.  You must protect multiple accesses with a lock.
- */
-static __always_inline int
-arch___test_and_clear_bit(unsigned int nr, volatile unsigned long *addr)
-{
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old = *p;
-
-	*p = old & ~mask;
-	return (old & mask) != 0;
-}
-#define __test_and_clear_bit arch___test_and_clear_bit
-
-/* WARNING: non atomic and it can be reordered! */
-static __always_inline int
-arch___test_and_change_bit(unsigned int nr, volatile unsigned long *addr)
-{
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old = *p;
-
-	*p = old ^ mask;
-	return (old & mask) != 0;
-}
-#define __test_and_change_bit arch___test_and_change_bit
-
-/**
- * arch_test_bit - Determine whether a bit is set
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static __always_inline int
-arch_test_bit(unsigned int nr, const volatile unsigned long *addr)
-{
-	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
-}
-#define test_bit arch_test_bit
+#include <asm-generic/bitops/non-instrumented-non-atomic.h>
 
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
diff --git a/include/asm-generic/bitops/non-instrumented-non-atomic.h b/include/asm-generic/bitops/non-instrumented-non-atomic.h
new file mode 100644
index 000000000000..bdb9b1ffaee9
--- /dev/null
+++ b/include/asm-generic/bitops/non-instrumented-non-atomic.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H
+#define __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H
+
+#define ___set_bit		arch___set_bit
+#define ___clear_bit		arch___clear_bit
+#define ___change_bit		arch___change_bit
+
+#define ___test_and_set_bit	arch___test_and_set_bit
+#define ___test_and_clear_bit	arch___test_and_clear_bit
+#define ___test_and_change_bit	arch___test_and_change_bit
+
+#define _test_bit		arch_test_bit
+
+#endif /* __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H */
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 2e6cd5681040..f65410a49fda 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -71,9 +71,9 @@ struct device;
  *  bitmap_release_region(bitmap, pos, order)   Free specified bit region
  *  bitmap_allocate_region(bitmap, pos, order)  Allocate specified bit region
  *  bitmap_from_arr32(dst, buf, nbits)          Copy nbits from u32[] buf to dst
+ *  bitmap_from_arr64(dst, buf, nbits)          Copy nbits from u64[] buf to dst
  *  bitmap_to_arr32(buf, src, nbits)            Copy nbits from buf to u32[] dst
  *  bitmap_to_arr64(buf, src, nbits)            Copy nbits from buf to u64[] dst
- *  bitmap_to_arr64(buf, src, nbits)            Copy nbits from buf to u64[] dst
  *  bitmap_get_value8(map, start)               Get 8bit value from map at start
  *  bitmap_set_value8(map, value, start)        Set 8bit value to map at start
  *
@@ -148,13 +148,13 @@ void __bitmap_shift_left(unsigned long *dst, const unsigned long *src,
 			 unsigned int shift, unsigned int nbits);
 void bitmap_cut(unsigned long *dst, const unsigned long *src,
 		unsigned int first, unsigned int cut, unsigned int nbits);
-int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, unsigned int nbits);
 void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, unsigned int nbits);
 void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
 		  const unsigned long *bitmap2, unsigned int nbits);
-int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
+bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
 		    const unsigned long *bitmap2, unsigned int nbits);
 void __bitmap_replace(unsigned long *dst,
 		      const unsigned long *old, const unsigned long *new,
@@ -163,7 +163,7 @@ bool __bitmap_intersects(const unsigned long *bitmap1,
 			 const unsigned long *bitmap2, unsigned int nbits);
 bool __bitmap_subset(const unsigned long *bitmap1,
 		     const unsigned long *bitmap2, unsigned int nbits);
-int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
+unsigned int __bitmap_weight(const unsigned long *bitmap, 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);
 
@@ -238,20 +238,32 @@ extern int bitmap_print_list_to_buf(char *buf, const unsigned long *maskp,
 static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 {
 	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
-	memset(dst, 0, len);
+
+	if (small_const_nbits(nbits))
+		*dst = 0;
+	else
+		memset(dst, 0, len);
 }
 
 static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 {
 	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
-	memset(dst, 0xff, len);
+
+	if (small_const_nbits(nbits))
+		*dst = ~0UL;
+	else
+		memset(dst, 0xff, len);
 }
 
 static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
 			unsigned int nbits)
 {
 	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
-	memcpy(dst, src, len);
+
+	if (small_const_nbits(nbits))
+		*dst = *src;
+	else
+		memcpy(dst, src, len);
 }
 
 /*
@@ -303,7 +315,7 @@ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits);
 	bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits))
 #endif
 
-static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
+static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1,
 			const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
@@ -329,7 +341,7 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
 		__bitmap_xor(dst, src1, src2, nbits);
 }
 
-static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1,
+static inline bool bitmap_andnot(unsigned long *dst, const unsigned long *src1,
 			const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
@@ -419,7 +431,8 @@ static inline bool bitmap_full(const unsigned long *src, unsigned int nbits)
 	return find_first_zero_bit(src, nbits) == nbits;
 }
 
-static __always_inline int bitmap_weight(const unsigned long *src, unsigned int nbits)
+static __always_inline
+unsigned int bitmap_weight(const unsigned long *src, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
@@ -431,6 +444,8 @@ static __always_inline void bitmap_set(unsigned long *map, unsigned int start,
 {
 	if (__builtin_constant_p(nbits) && nbits == 1)
 		__set_bit(start, map);
+	else if (small_const_nbits(start + nbits))
+		*map |= GENMASK(start + nbits - 1, start);
 	else if (__builtin_constant_p(start & BITMAP_MEM_MASK) &&
 		 IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) &&
 		 __builtin_constant_p(nbits & BITMAP_MEM_MASK) &&
@@ -445,6 +460,8 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start,
 {
 	if (__builtin_constant_p(nbits) && nbits == 1)
 		__clear_bit(start, map);
+	else if (small_const_nbits(start + nbits))
+		*map &= ~GENMASK(start + nbits - 1, start);
 	else if (__builtin_constant_p(start & BITMAP_MEM_MASK) &&
 		 IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) &&
 		 __builtin_constant_p(nbits & BITMAP_MEM_MASK) &&
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 7aaed501f768..cf9bf65039f2 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -27,11 +27,61 @@ extern unsigned int __sw_hweight32(unsigned int w);
 extern unsigned long __sw_hweight64(__u64 w);
 
 /*
+ * Defined here because those may be needed by architecture-specific static
+ * inlines.
+ */
+
+#include <asm-generic/bitops/generic-non-atomic.h>
+
+/*
+ * Many architecture-specific non-atomic bitops contain inline asm code and due
+ * to that the compiler can't optimize them to compile-time expressions or
+ * constants. In contrary, generic_*() helpers are defined in pure C and
+ * compilers optimize them just well.
+ * Therefore, to make `unsigned long foo = 0; __set_bit(BAR, &foo)` effectively
+ * equal to `unsigned long foo = BIT(BAR)`, pick the generic C alternative when
+ * the arguments can be resolved at compile time. That expression itself is a
+ * constant and doesn't bring any functional changes to the rest of cases.
+ * The casts to `uintptr_t` are needed to mitigate `-Waddress` warnings when
+ * passing a bitmap from .bss or .data (-> `!!addr` is always true).
+ */
+#define bitop(op, nr, addr)						\
+	((__builtin_constant_p(nr) &&					\
+	  __builtin_constant_p((uintptr_t)(addr) != (uintptr_t)NULL) &&	\
+	  (uintptr_t)(addr) != (uintptr_t)NULL &&			\
+	  __builtin_constant_p(*(const unsigned long *)(addr))) ?	\
+	 const##op(nr, addr) : op(nr, addr))
+
+#define __set_bit(nr, addr)		bitop(___set_bit, nr, addr)
+#define __clear_bit(nr, addr)		bitop(___clear_bit, nr, addr)
+#define __change_bit(nr, addr)		bitop(___change_bit, nr, addr)
+#define __test_and_set_bit(nr, addr)	bitop(___test_and_set_bit, nr, addr)
+#define __test_and_clear_bit(nr, addr)	bitop(___test_and_clear_bit, nr, addr)
+#define __test_and_change_bit(nr, addr)	bitop(___test_and_change_bit, nr, addr)
+#define test_bit(nr, addr)		bitop(_test_bit, nr, addr)
+
+/*
  * Include this here because some architectures need generic_ffs/fls in
  * scope
  */
 #include <asm/bitops.h>
 
+/* Check that the bitops prototypes are sane */
+#define __check_bitop_pr(name)						\
+	static_assert(__same_type(arch_##name, generic_##name) &&	\
+		      __same_type(const_##name, generic_##name) &&	\
+		      __same_type(_##name, generic_##name))
+
+__check_bitop_pr(__set_bit);
+__check_bitop_pr(__clear_bit);
+__check_bitop_pr(__change_bit);
+__check_bitop_pr(__test_and_set_bit);
+__check_bitop_pr(__test_and_clear_bit);
+__check_bitop_pr(__test_and_change_bit);
+__check_bitop_pr(test_bit);
+
+#undef __check_bitop_pr
+
 static inline int get_bitmask_order(unsigned int count)
 {
 	int order;
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 707387323862..0d435d0edbcb 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -12,6 +12,8 @@
 #include <linux/bitmap.h>
 #include <linux/atomic.h>
 #include <linux/bug.h>
+#include <linux/gfp_types.h>
+#include <linux/numa.h>
 
 /* Don't assign or return these: may not be this big! */
 typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
@@ -162,7 +164,21 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp)
 	return find_last_bit(cpumask_bits(srcp), nr_cpumask_bits);
 }
 
-unsigned int __pure cpumask_next(int n, const struct cpumask *srcp);
+/**
+ * cpumask_next - get the next cpu in a cpumask
+ * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @srcp: the cpumask pointer
+ *
+ * Returns >= nr_cpu_ids if no further cpus set.
+ */
+static inline
+unsigned int cpumask_next(int n, const struct cpumask *srcp)
+{
+	/* -1 is a legal arg here. */
+	if (n != -1)
+		cpumask_check(n);
+	return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1);
+}
 
 /**
  * cpumask_next_zero - get the next unset cpu in a cpumask
@@ -179,9 +195,6 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 	return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1);
 }
 
-int __pure cpumask_next_and(int n, const struct cpumask *, const struct cpumask *);
-int __pure cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
-
 #if NR_CPUS == 1
 /* Uniprocessor: there is only one valid CPU */
 static inline unsigned int cpumask_local_spread(unsigned int i, int node)
@@ -200,12 +213,31 @@ static inline int cpumask_any_distribute(const struct cpumask *srcp)
 }
 #else
 unsigned int cpumask_local_spread(unsigned int i, int node);
-int cpumask_any_and_distribute(const struct cpumask *src1p,
+unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
 			       const struct cpumask *src2p);
-int cpumask_any_distribute(const struct cpumask *srcp);
+unsigned int cpumask_any_distribute(const struct cpumask *srcp);
 #endif /* NR_CPUS */
 
 /**
+ * cpumask_next_and - get the next cpu in *src1p & *src2p
+ * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @src1p: the first cpumask pointer
+ * @src2p: the second cpumask pointer
+ *
+ * Returns >= nr_cpu_ids if no further cpus set in both.
+ */
+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);
+	return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p),
+		nr_cpumask_bits, n + 1);
+}
+
+/**
  * for_each_cpu - iterate over every cpu in a mask
  * @cpu: the (optionally unsigned) integer iterator
  * @mask: the cpumask pointer
@@ -229,7 +261,7 @@ int cpumask_any_distribute(const struct cpumask *srcp);
 		(cpu) = cpumask_next_zero((cpu), (mask)),	\
 		(cpu) < nr_cpu_ids;)
 
-int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
+unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
 
 /**
  * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location
@@ -265,6 +297,26 @@ int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool
 		(cpu) = cpumask_next_and((cpu), (mask1), (mask2)),	\
 		(cpu) < nr_cpu_ids;)
 
+/**
+ * cpumask_any_but - return a "random" in a cpumask, but not this one.
+ * @mask: the cpumask to search
+ * @cpu: the cpu to ignore.
+ *
+ * Often used to find any cpu but smp_processor_id() in a mask.
+ * Returns >= nr_cpu_ids if no cpus set.
+ */
+static inline
+unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
+{
+	unsigned int i;
+
+	cpumask_check(cpu);
+	for_each_cpu(i, mask)
+		if (i != cpu)
+			break;
+	return i;
+}
+
 #define CPU_BITS_NONE						\
 {								\
 	[0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL			\
@@ -311,9 +363,9 @@ static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
  * @cpu: cpu number (< nr_cpu_ids)
  * @cpumask: the cpumask pointer
  *
- * Returns 1 if @cpu is set in @cpumask, else returns 0
+ * Returns true if @cpu is set in @cpumask, else returns false
  */
-static __always_inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
+static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
 {
 	return test_bit(cpumask_check(cpu), cpumask_bits((cpumask)));
 }
@@ -323,11 +375,11 @@ static __always_inline int cpumask_test_cpu(int cpu, const struct cpumask *cpuma
  * @cpu: cpu number (< nr_cpu_ids)
  * @cpumask: the cpumask pointer
  *
- * Returns 1 if @cpu is set in old bitmap of @cpumask, else returns 0
+ * Returns true if @cpu is set in old bitmap of @cpumask, else returns false
  *
  * test_and_set_bit wrapper for cpumasks.
  */
-static __always_inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
+static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
 {
 	return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask));
 }
@@ -337,11 +389,11 @@ static __always_inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpu
  * @cpu: cpu number (< nr_cpu_ids)
  * @cpumask: the cpumask pointer
  *
- * Returns 1 if @cpu is set in old bitmap of @cpumask, else returns 0
+ * Returns true if @cpu is set in old bitmap of @cpumask, else returns false
  *
  * test_and_clear_bit wrapper for cpumasks.
  */
-static __always_inline int cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
+static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
 {
 	return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask));
 }
@@ -370,9 +422,9 @@ static inline void cpumask_clear(struct cpumask *dstp)
  * @src1p: the first input
  * @src2p: the second input
  *
- * If *@dstp is empty, returns 0, else returns 1
+ * If *@dstp is empty, returns false, else returns true
  */
-static inline int cpumask_and(struct cpumask *dstp,
+static inline bool cpumask_and(struct cpumask *dstp,
 			       const struct cpumask *src1p,
 			       const struct cpumask *src2p)
 {
@@ -413,9 +465,9 @@ static inline void cpumask_xor(struct cpumask *dstp,
  * @src1p: the first input
  * @src2p: the second input
  *
- * If *@dstp is empty, returns 0, else returns 1
+ * If *@dstp is empty, returns false, else returns true
  */
-static inline int cpumask_andnot(struct cpumask *dstp,
+static inline bool cpumask_andnot(struct cpumask *dstp,
 				  const struct cpumask *src1p,
 				  const struct cpumask *src2p)
 {
@@ -478,9 +530,9 @@ static inline bool cpumask_intersects(const struct cpumask *src1p,
  * @src1p: the first input
  * @src2p: the second input
  *
- * Returns 1 if *@src1p is a subset of *@src2p, else returns 0
+ * Returns true if *@src1p is a subset of *@src2p, else returns false
  */
-static inline int cpumask_subset(const struct cpumask *src1p,
+static inline bool cpumask_subset(const struct cpumask *src1p,
 				 const struct cpumask *src2p)
 {
 	return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p),
@@ -682,9 +734,35 @@ typedef struct cpumask *cpumask_var_t;
 #define __cpumask_var_read_mostly	__read_mostly
 
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
-bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
-bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
-bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
+
+static inline
+bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
+{
+	return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
+}
+
+/**
+ * alloc_cpumask_var - allocate a struct cpumask
+ * @mask: pointer to cpumask_var_t where the cpumask is returned
+ * @flags: GFP_ flags
+ *
+ * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
+ * a nop returning a constant 1 (in <linux/cpumask.h>).
+ *
+ * See alloc_cpumask_var_node.
+ */
+static inline
+bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+{
+	return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE);
+}
+
+static inline
+bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+{
+	return alloc_cpumask_var(mask, flags | __GFP_ZERO);
+}
+