Merge tag 'bitmap-for-6.12' of https://github.com/norov/linux

Pull bitmap updates from Yury Norov:

 - switch all bitmamp APIs from inline to __always_inline (Brian Norris)

   The __always_inline series improves on code generation, and now with
   the latest compiler versions is required to avoid compilation
   warnings. It spent enough in my backlog, and I'm thankful to Brian
   Norris for taking over and moving it forward.

 - introduce GENMASK_U128() macro (Anshuman Khandual)

   GENMASK_U128() is a prerequisite needed for arm64 development

* tag 'bitmap-for-6.12' of https://github.com/norov/linux:
  lib/test_bits.c: Add tests for GENMASK_U128()
  uapi: Define GENMASK_U128
  nodemask: Switch from inline to __always_inline
  cpumask: Switch from inline to __always_inline
  bitmap: Switch from inline to __always_inline
  find: Switch from inline to __always_inline

8 files changed, 325 insertions, 232 deletions

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index d3b66d77df7a..262b6596eca5 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -203,12 +203,12 @@ unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
  * the bit offset of all zero areas this function finds is multiples of that
  * power of 2. A @align_mask of 0 means no alignment is required.
  */
-static inline unsigned long
-bitmap_find_next_zero_area(unsigned long *map,
-			   unsigned long size,
-			   unsigned long start,
-			   unsigned int nr,
-			   unsigned long align_mask)
+static __always_inline
+unsigned long bitmap_find_next_zero_area(unsigned long *map,
+					 unsigned long size,
+					 unsigned long start,
+					 unsigned int nr,
+					 unsigned long align_mask)
 {
 	return bitmap_find_next_zero_area_off(map, size, start, nr,
 					      align_mask, 0);
@@ -228,7 +228,7 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig,
 
 #define bitmap_size(nbits)	(ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE)
 
-static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
+static __always_inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 {
 	unsigned int len = bitmap_size(nbits);
 
@@ -238,7 +238,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 		memset(dst, 0, len);
 }
 
-static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
+static __always_inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 {
 	unsigned int len = bitmap_size(nbits);
 
@@ -248,8 +248,8 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 		memset(dst, 0xff, len);
 }
 
-static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
-			unsigned int nbits)
+static __always_inline
+void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits)
 {
 	unsigned int len = bitmap_size(nbits);
 
@@ -262,8 +262,8 @@ static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
 /*
  * Copy bitmap and clear tail bits in last word.
  */
-static inline void bitmap_copy_clear_tail(unsigned long *dst,
-		const unsigned long *src, unsigned int nbits)
+static __always_inline
+void bitmap_copy_clear_tail(unsigned long *dst, const unsigned long *src, unsigned int nbits)
 {
 	bitmap_copy(dst, src, nbits);
 	if (nbits % BITS_PER_LONG)
@@ -318,16 +318,18 @@ 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 bool bitmap_and(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static __always_inline
+bool bitmap_and(unsigned long *dst, const unsigned long *src1,
+		const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0;
 	return __bitmap_and(dst, src1, src2, nbits);
 }
 
-static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static __always_inline
+void bitmap_or(unsigned long *dst, const unsigned long *src1,
+	       const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = *src1 | *src2;
@@ -335,8 +337,9 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
 		__bitmap_or(dst, src1, src2, nbits);
 }
 
-static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static __always_inline
+void bitmap_xor(unsigned long *dst, const unsigned long *src1,
+		const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = *src1 ^ *src2;
@@ -344,16 +347,17 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
 		__bitmap_xor(dst, src1, src2, nbits);
 }
 
-static inline bool bitmap_andnot(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static __always_inline
+bool bitmap_andnot(unsigned long *dst, const unsigned long *src1,
+		   const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return (*dst = *src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
 	return __bitmap_andnot(dst, src1, src2, nbits);
 }
 
-static inline void bitmap_complement(unsigned long *dst, const unsigned long *src,
-			unsigned int nbits)
+static __always_inline
+void bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = ~(*src);
@@ -368,8 +372,8 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr
 #endif
 #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1)
 
-static inline bool bitmap_equal(const unsigned long *src1,
-				const unsigned long *src2, unsigned int nbits)
+static __always_inline
+bool bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
@@ -388,10 +392,9 @@ static inline bool bitmap_equal(const unsigned long *src1,
  *
  * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise
  */
-static inline bool bitmap_or_equal(const unsigned long *src1,
-				   const unsigned long *src2,
-				   const unsigned long *src3,
-				   unsigned int nbits)
+static __always_inline
+bool bitmap_or_equal(const unsigned long *src1, const unsigned long *src2,
+		     const unsigned long *src3, unsigned int nbits)
 {
 	if (!small_const_nbits(nbits))
 		return __bitmap_or_equal(src1, src2, src3, nbits);
@@ -399,9 +402,8 @@ static inline bool bitmap_or_equal(const unsigned long *src1,
 	return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits));
 }
 
-static inline bool bitmap_intersects(const unsigned long *src1,
-				     const unsigned long *src2,
-				     unsigned int nbits)
+static __always_inline
+bool bitmap_intersects(const unsigned long *src1, const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
@@ -409,8 +411,8 @@ static inline bool bitmap_intersects(const unsigned long *src1,
 		return __bitmap_intersects(src1, src2, nbits);
 }
 
-static inline bool bitmap_subset(const unsigned long *src1,
-				 const unsigned long *src2, unsigned int nbits)
+static __always_inline
+bool bitmap_subset(const unsigned long *src1, const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits));
@@ -418,7 +420,8 @@ static inline bool bitmap_subset(const unsigned long *src1,
 		return __bitmap_subset(src1, src2, nbits);
 }
 
-static inline bool bitmap_empty(const unsigned long *src, unsigned nbits)
+static __always_inline
+bool bitmap_empty(const unsigned long *src, unsigned nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
@@ -426,7 +429,8 @@ static inline bool bitmap_empty(const unsigned long *src, unsigned nbits)
 	return find_first_bit(src, nbits) == nbits;
 }
 
-static inline bool bitmap_full(const unsigned long *src, unsigned int nbits)
+static __always_inline
+bool bitmap_full(const unsigned long *src, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
@@ -460,8 +464,8 @@ unsigned long bitmap_weight_andnot(const unsigned long *src1,
 	return __bitmap_weight_andnot(src1, src2, nbits);
 }
 
-static __always_inline void bitmap_set(unsigned long *map, unsigned int start,
-		unsigned int nbits)
+static __always_inline
+void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits)
 {
 	if (__builtin_constant_p(nbits) && nbits == 1)
 		__set_bit(start, map);
@@ -476,8 +480,8 @@ static __always_inline void bitmap_set(unsigned long *map, unsigned int start,
 		__bitmap_set(map, start, nbits);
 }
 
-static __always_inline void bitmap_clear(unsigned long *map, unsigned int start,
-		unsigned int nbits)
+static __always_inline
+void bitmap_clear(unsigned long *map, unsigned int start, unsigned int nbits)
 {
 	if (__builtin_constant_p(nbits) && nbits == 1)
 		__clear_bit(start, map);
@@ -492,8 +496,9 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start,
 		__bitmap_clear(map, start, nbits);
 }
 
-static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src,
-				unsigned int shift, unsigned int nbits)
+static __always_inline
+void bitmap_shift_right(unsigned long *dst, const unsigned long *src,
+			unsigned int shift, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift;
@@ -501,8 +506,9 @@ static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *s
 		__bitmap_shift_right(dst, src, shift, nbits);
 }
 
-static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *src,
-				unsigned int shift, unsigned int nbits)
+static __always_inline
+void bitmap_shift_left(unsigned long *dst, const unsigned long *src,
+		       unsigned int shift, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits);
@@ -510,11 +516,12 @@ static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *sr
 		__bitmap_shift_left(dst, src, shift, nbits);
 }
 
-static inline void bitmap_replace(unsigned long *dst,
-				  const unsigned long *old,
-				  const unsigned long *new,
-				  const unsigned long *mask,
-				  unsigned int nbits)
+static __always_inline
+void bitmap_replace(unsigned long *dst,
+		    const unsigned long *old,
+		    const unsigned long *new,
+		    const unsigned long *mask,
+		    unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = (*old & ~(*mask)) | (*new & *mask);
@@ -557,8 +564,9 @@ static inline void bitmap_replace(unsigned long *dst,
  * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation.
  * See bitmap_scatter() for details related to this relationship.
  */
-static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src,
-				  const unsigned long *mask, unsigned int nbits)
+static __always_inline
+void bitmap_scatter(unsigned long *dst, const unsigned long *src,
+		    const unsigned long *mask, unsigned int nbits)
 {
 	unsigned int n = 0;
 	unsigned int bit;
@@ -611,8 +619,9 @@ static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src,
  * bitmap_scatter(res, src, mask, n) and a call to
  * bitmap_scatter(res, result, mask, n) will lead to the same res value.
  */
-static inline void bitmap_gather(unsigned long *dst, const unsigned long *src,
-				 const unsigned long *mask, unsigned int nbits)
+static __always_inline
+void bitmap_gather(unsigned long *dst, const unsigned long *src,
+		   const unsigned long *mask, unsigned int nbits)
 {
 	unsigned int n = 0;
 	unsigned int bit;
@@ -623,9 +632,9 @@ static inline void bitmap_gather(unsigned long *dst, const unsigned long *src,
 		__assign_bit(n++, dst, test_bit(bit, src));
 }
 
-static inline void bitmap_next_set_region(unsigned long *bitmap,
-					  unsigned int *rs, unsigned int *re,
-					  unsigned int end)
+static __always_inline
+void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs,
+			    unsigned int *re, unsigned int end)
 {
 	*rs = find_next_bit(bitmap, end, *rs);
 	*re = find_next_zero_bit(bitmap, end, *rs + 1);
@@ -640,7 +649,8 @@ static inline void bitmap_next_set_region(unsigned long *bitmap,
  * This is the complement to __bitmap_find_free_region() and releases
  * the found region (by clearing it in the bitmap).
  */
-static inline void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order)
+static __always_inline
+void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order)
 {
 	bitmap_clear(bitmap, pos, BIT(order));
 }
@@ -656,7 +666,8 @@ static inline void bitmap_release_region(unsigned long *bitmap, unsigned int pos
  * Returns: 0 on success, or %-EBUSY if specified region wasn't
  * free (not all bits were zero).
  */
-static inline int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order)
+static __always_inline
+int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order)
 {
 	unsigned int len = BIT(order);
 
@@ -680,7 +691,8 @@ static inline int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos
  * Returns: the bit offset in bitmap of the allocated region,
  * or -errno on failure.
  */
-static inline int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order)
+static __always_inline
+int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order)
 {
 	unsigned int pos, end;		/* scans bitmap by regions of size order */
 
@@ -734,7 +746,7 @@ static inline int bitmap_find_free_region(unsigned long *bitmap, unsigned int bi
  * That is ``(u32 *)(&val)[0]`` gets the upper 32 bits,
  * but we expect the lower 32-bits of u64.
  */
-static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
+static __always_inline void bitmap_from_u64(unsigned long *dst, u64 mask)
 {
 	bitmap_from_arr64(dst, &mask, 64);
 }
@@ -749,9 +761,8 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
  * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return
  * value is undefined.
  */
-static inline unsigned long bitmap_read(const unsigned long *map,
-					unsigned long start,
-					unsigned long nbits)
+static __always_inline
+unsigned long bitmap_read(const unsigned long *map, unsigned long start, unsigned long nbits)
 {
 	size_t index = BIT_WORD(start);
 	unsigned long offset = start % BITS_PER_LONG;
@@ -784,8 +795,9 @@ static inline unsigned long bitmap_read(const unsigned long *map,
  *
  * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed.
  */
-static inline void bitmap_write(unsigned long *map, unsigned long value,
-				unsigned long start, unsigned long nbits)
+static __always_inline
+void bitmap_write(unsigned long *map, unsigned long value,
+		  unsigned long start, unsigned long nbits)
 {
 	size_t index;
 	unsigned long offset;
diff --git a/include/linux/bits.h b/include/linux/bits.h
index 0eb24d21aac2..60044b608817 100644
--- a/include/linux/bits.h
+++ b/include/linux/bits.h
@@ -36,4 +36,19 @@
 #define GENMASK_ULL(h, l) \
 	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
 
+#if !defined(__ASSEMBLY__)
+/*
+ * Missing asm support
+ *
+ * __GENMASK_U128() depends on _BIT128() which would not work
+ * in the asm code, as it shifts an 'unsigned __init128' data
+ * type instead of direct representation of 128 bit constants
+ * such as long and unsigned long. The fundamental problem is
+ * that a 128 bit constant will get silently truncated by the
+ * gcc compiler.
+ */
+#define GENMASK_U128(h, l) \
+	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l))
+#endif
+
 #endif	/* __LINUX_BITS_H */
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 53158de44b83..9278a50d514f 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -30,7 +30,7 @@
 extern unsigned int nr_cpu_ids;
 #endif
 
-static inline void set_nr_cpu_ids(unsigned int nr)
+static __always_inline void set_nr_cpu_ids(unsigned int nr)
 {
 #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS)
 	WARN_ON(nr != nr_cpu_ids);
@@ -149,7 +149,7 @@ static __always_inline unsigned int cpumask_check(unsigned int cpu)
  *
  * Return: >= nr_cpu_ids if no cpus set.
  */
-static inline unsigned int cpumask_first(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_first(const struct cpumask *srcp)
 {
 	return find_first_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -160,7 +160,7 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp)
  *
  * Return: >= nr_cpu_ids if all cpus are set.
  */
-static inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
 {
 	return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -172,7 +172,7 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
  *
  * Return: >= nr_cpu_ids if no cpus set in both.  See also cpumask_next_and().
  */
-static inline
+static __always_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), small_cpumask_bits);
@@ -186,7 +186,7 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask
  *
  * Return: >= nr_cpu_ids if no cpus set in all.
  */
-static inline
+static __always_inline
 unsigned int cpumask_first_and_and(const struct cpumask *srcp1,
 				   const struct cpumask *srcp2,
 				   const struct cpumask *srcp3)
@@ -201,7 +201,7 @@ unsigned int cpumask_first_and_and(const struct cpumask *srcp1,
  *
  * Return:	>= nr_cpumask_bits if no CPUs set.
  */
-static inline unsigned int cpumask_last(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_last(const struct cpumask *srcp)
 {
 	return find_last_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -213,7 +213,7 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp)
  *
  * Return: >= nr_cpu_ids if no further cpus set.
  */
-static inline
+static __always_inline
 unsigned int cpumask_next(int n, const struct cpumask *srcp)
 {
 	/* -1 is a legal arg here. */
@@ -229,7 +229,8 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp)
  *
  * Return: >= nr_cpu_ids if no further cpus unset.
  */
-static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
+static __always_inline
+unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 {
 	/* -1 is a legal arg here. */
 	if (n != -1)
@@ -239,18 +240,21 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 
 #if NR_CPUS == 1
 /* Uniprocessor: there is only one valid CPU */
-static inline unsigned int cpumask_local_spread(unsigned int i, int node)
+static __always_inline
+unsigned int cpumask_local_spread(unsigned int i, int node)
 {
 	return 0;
 }
 
-static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
-						      const struct cpumask *src2p)
+static __always_inline
+unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
+					const struct cpumask *src2p)
 {
 	return cpumask_first_and(src1p, src2p);
 }
 
-static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp)
+static __always_inline
+unsigned int cpumask_any_distribute(const struct cpumask *srcp)
 {
 	return cpumask_first(srcp);
 }
@@ -269,9 +273,9 @@ unsigned int cpumask_any_distribute(const struct cpumask *srcp);
  *
  * Return: >= nr_cpu_ids if no further cpus set in both.
  */
-static inline
+static __always_inline
 unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
-		     const struct cpumask *src2p)
+			      const struct cpumask *src2p)
 {
 	/* -1 is a legal arg here. */
 	if (n != -1)
@@ -291,7 +295,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
 	for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits)
 
 #if NR_CPUS == 1
-static inline
+static __always_inline
 unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
 {
 	cpumask_check(start);
@@ -394,7 +398,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta
  * Often used to find any cpu but smp_processor_id() in a mask.
  * Return: >= nr_cpu_ids if no cpus set.
  */
-static inline
+static __always_inline
 unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 {
 	unsigned int i;
@@ -414,7 +418,7 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
  *
  * Returns >= nr_cpu_ids if no cpus set.
  */
-static inline
+static __always_inline
 unsigned int cpumask_any_and_but(const struct cpumask *mask1,
 				 const struct cpumask *mask2,
 				 unsigned int cpu)
@@ -436,7 +440,8 @@ unsigned int cpumask_any_and_but(const struct cpumask *mask1,
  *
  * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
-static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp)
+static __always_inline
+unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp)
 {
 	return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu));
 }
@@ -449,7 +454,7 @@ static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *s
  *
  * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
-static inline
+static __always_inline
 unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1,
 							const struct cpumask *srcp2)
 {
@@ -465,7 +470,7 @@ unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1,
  *
  * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
-static inline
+static __always_inline
 unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1,
 							const struct cpumask *srcp2)
 {
@@ -508,12 +513,14 @@ unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp
  * @cpu: cpu number (< nr_cpu_ids)
  * @dstp: the cpumask pointer
  */
-static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+static __always_inline
+void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 {
 	set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
-static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+static __always_inline
+void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 {
 	__set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
@@ -557,7 +564,8 @@ static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp,
  *
  * Return: true if @cpu is set in @cpumask, else returns false
  */
-static __always_inline bool 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)));
 }
@@ -571,7 +579,8 @@ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpum
  *
  * Return: true if @cpu is set in old bitmap of @cpumask, else returns false
  */
-static __always_inline bool 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));
 }
@@ -585,7 +594,8 @@ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cp
  *
  * Return: true if @cpu is set in old bitmap of @cpumask, else returns false
  */
-static __always_inline bool 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));
 }
@@ -594,7 +604,7 @@ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *
  * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask
  * @dstp: the cpumask pointer
  */
-static inline void cpumask_setall(struct cpumask *dstp)
+static __always_inline void cpumask_setall(struct cpumask *dstp)
 {
 	if (small_const_nbits(small_cpumask_bits)) {
 		cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits);
@@ -607,7 +617,7 @@ static inline void cpumask_setall(struct cpumask *dstp)
  * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask
  * @dstp: the cpumask pointer
  */
-static inline void cpumask_clear(struct cpumask *dstp)
+static __always_inline void cpumask_clear(struct cpumask *dstp)
 {
 	bitmap_zero(cpumask_bits(dstp), large_cpumask_bits);
 }
@@ -620,9 +630,9 @@ static inline void cpumask_clear(struct cpumask *dstp)
  *
  * Return: false if *@dstp is empty, else returns true
  */
-static inline bool cpumask_and(struct cpumask *dstp,
-			       const struct cpumask *src1p,
-			       const struct cpumask *src2p)
+static __always_inline
+bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p,
+		 const struct cpumask *src2p)
 {
 	return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p),
 				       cpumask_bits(src2p), small_cpumask_bits);
@@ -634,8 +644,9 @@ static inline bool cpumask_and(struct cpumask *dstp,
  * @src1p: the first input
  * @src2p: the second input
  */
-static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p,
-			      const struct cpumask *src2p)
+static __always_inline
+void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p,
+		const struct cpumask *src2p)
 {
 	bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p),
 				      cpumask_bits(src2p), small_cpumask_bits);
@@ -647,9 +658,9 @@ static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p,
  * @src1p: the first input
  * @src2p: the second input
  */
-static inline void cpumask_xor(struct cpumask *dstp,
-			       const struct cpumask *src1p,
-			       const struct cpumask *src2p)
+static __always_inline
+void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p,
+		 const struct cpumask *src2p)
 {
 	bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p),
 				       cpumask_bits(src2p), small_cpumask_bits);
@@ -663,9 +674,9 @@ static inline void cpumask_xor(struct cpumask *dstp,
  *
  * Return: false if *@dstp is empty, else returns true
  */
-static inline bool cpumask_andnot(struct cpumask *dstp,
-				  const struct cpumask *src1p,
-				  const struct cpumask *src2p)
+static __always_inline
+bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p,
+		    const struct cpumask *src2p)
 {
 	return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p),
 					  cpumask_bits(src2p), small_cpumask_bits);
@@ -678,8 +689,8 @@ static inline bool cpumask_andnot(struct cpumask *dstp,
  *
  * Return: true if the cpumasks are equal, false if not
  */
-static inline bool cpumask_equal(const struct cpumask *src1p,
-				const struct cpumask *src2p)
+static __always_inline
+bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p)
 {
 	return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p),
 						 small_cpumask_bits);
@@ -694,9 +705,9 @@ static inline bool cpumask_equal(const struct cpumask *src1p,
  * Return: true if first cpumask ORed with second cpumask == third cpumask,
  *	   otherwise false
  */
-static inline bool cpumask_or_equal(const struct cpumask *src1p,
-				    const struct cpumask *src2p,
-				    const struct cpumask *src3p)
+static __always_inline
+bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p,
+		      const struct cpumask *src3p)
 {
 	return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p),
 			       cpumask_bits(src3p), small_cpumask_bits);
@@ -710,8 +721,8 @@ static inline bool cpumask_or_equal(const struct cpumask *src1p,
  * Return: true if first cpumask ANDed with second cpumask is non-empty,
  *	   otherwise false
  */
-static inline bool cpumask_intersects(const struct cpumask *src1p,
-				     const struct cpumask *src2p)
+static __always_inline
+bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p)
 {
 	return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p),
 						      small_cpumask_bits);
@@ -724,8 +735,8 @@ static inline bool cpumask_intersects(const struct cpumask *src1p,
  *
  * Return: true if *@src1p is a subset of *@src2p, else returns false
  */
-static inline bool cpumask_subset(const struct cpumask *src1p,
-				 const struct cpumask *src2p)
+static __always_inline
+bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p)
 {
 	return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p),
 						  small_cpumask_bits);
@@ -737,7 +748,7 @@ static inline bool cpumask_subset(const struct cpumask *src1p,
  *
  * Return: true if srcp is empty (has no bits set), else false
  */
-static inline bool cpumask_empty(const struct cpumask *srcp)
+static __always_inline bool cpumask_empty(const struct cpumask *srcp)
 {
 	return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -748,7 +759,7 @@ static inline bool cpumask_empty(const struct cpumask *srcp)
  *
  * Return: true if srcp is full (has all bits set), else false
  */
-static inline bool cpumask_full(const struct cpumask *srcp)
+static __always_inline bool cpumask_full(const struct cpumask *srcp)
 {
 	return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits);
 }
@@ -759,7 +770,7 @@ static inline bool cpumask_full(const struct cpumask *srcp)
  *
  * Return: count of bits set in *srcp
  */
-static inline unsigned int cpumask_weight(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp)
 {
 	return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -771,8 +782,8 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp)
  *
  * Return: count of bits set in both *srcp1 and *srcp2
  */
-static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1,
-						const struct cpumask *srcp2)
+static __always_inline
+unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2)
 {
 	return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
 }
@@ -784,8 +795,9 @@ static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1,
  *
  * Return: count of bits set in both *srcp1 and *srcp2
  */
-static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1,
-						const struct cpumask *srcp2)
+static __always_inline
+unsigned int cpumask_weight_andnot(const struct cpumask *srcp1,
+				   const struct cpumask *srcp2)
 {
 	return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
 }
@@ -796,8 +808,8 @@ static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1,
  * @srcp: the input to shift
  * @n: the number of bits to shift by
  */
-static inline void cpumask_shift_right(struct cpumask *dstp,
-				       const struct cpumask *srcp, int n)
+static __always_inline
+void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n)
 {
 	bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n,
 					       small_cpumask_bits);
@@ -809,8 +821,8 @@ static inline void cpumask_shift_right(struct cpumask *dstp,
  * @srcp: the input to shift
  * @n: the number of bits to shift by
  */
-static inline void cpumask_shift_left(struct cpumask *dstp,
-				      const struct cpumask *srcp, int n)
+static __always_inline
+void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n)
 {
 	bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n,
 					      nr_cpumask_bits);
@@ -821,8 +833,8 @@ static inline void cpumask_shift_left(struct cpumask *dstp,
  * @dstp: the result
  * @srcp: the input cpumask
  */
-static inline void cpumask_copy(struct cpumask *dstp,
-				const struct cpumask *srcp)
+static __always_inline
+void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp)
 {
 	bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits);
 }
@@ -858,8 +870,8 @@ static inline void cpumask_copy(struct cpumask *dstp,
  *
  * Return: -errno, or 0 for success.
  */
-static inline int cpumask_parse_user(const char __user *buf, int len,
-				     struct cpumask *dstp)
+static __always_inline
+int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp)
 {
 	return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
 }
@@ -872,8 +884,8 @@ static inline int cpumask_parse_user(const char __user *buf, int len,
  *
  * Return: -errno, or 0 for success.
  */
-static inline int cpumask_parselist_user(const char __user *buf, int len,
-				     struct cpumask *dstp)
+static __always_inline
+int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp)
 {
 	return bitmap_parselist_user(buf, len, cpumask_bits(dstp),
 				     nr_cpumask_bits);
@@ -886,7 +898,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len,
  *
  * Return: -errno, or 0 for success.
  */
-static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
+static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp)
 {
 	return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits);
 }
@@ -898,7 +910,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
  *
  * Return: -errno, or 0 for success.
  */
-static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
+static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp)
 {
 	return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits);
 }
@@ -908,7 +920,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
  *
  * Return: size to allocate for a &struct cpumask in bytes
  */
-static inline unsigned int cpumask_size(void)
+static __always_inline unsigned int cpumask_size(void)
 {
 	return bitmap_size(large_cpumask_bits);
 }
@@ -920,7 +932,7 @@ static inline unsigned int cpumask_size(void)
 
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
 
-static inline
+static __always_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);
@@ -938,13 +950,13 @@ bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
  *
  * Return: %true if allocation succeeded, %false if not
  */
-static inline
+static __always_inline
 bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE);
 }
 
-static inline
+static __always_inline
 bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	return alloc_cpumask_var(mask, flags | __GFP_ZERO);
@@ -954,7 +966,7 @@ void alloc_bootmem_cpumask_var(cpumask_var_t *mask);
 void free_cpumask_var(cpumask_var_t mask);
 void free_bootmem_cpumask_var(cpumask_var_t mask);
 
-static inline bool cpumask_available(cpumask_var_t mask)
+static __always_inline bool cpu