Merge branch 'bitmap-for-next' of https://github.com/norov/linux.git

47 files changed, 1096 insertions, 802 deletions

diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst
index f5b2f92822c8..1ebcc6c3fafe 100644
--- a/Documentation/core-api/mm-api.rst
+++ b/Documentation/core-api/mm-api.rst
@@ -22,16 +22,16 @@ Memory Allocation Controls
 .. kernel-doc:: include/linux/gfp.h
    :internal:
 
-.. kernel-doc:: include/linux/gfp.h
+.. kernel-doc:: include/linux/gfp_types.h
    :doc: Page mobility and placement hints
 
-.. kernel-doc:: include/linux/gfp.h
+.. kernel-doc:: include/linux/gfp_types.h
    :doc: Watermark modifiers
 
-.. kernel-doc:: include/linux/gfp.h
+.. kernel-doc:: include/linux/gfp_types.h
    :doc: Reclaim modifiers
 
-.. kernel-doc:: include/linux/gfp.h
+.. kernel-doc:: include/linux/gfp_types.h
    :doc: Useful GFP flag combinations
 
 The Slab Cache
diff --git a/MAINTAINERS b/MAINTAINERS
index c5ea1aa99b96..0389400aa37c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3613,7 +3613,6 @@ F:	lib/bitmap.c
 F:	lib/cpumask.c
 F:	lib/find_bit.c
 F:	lib/find_bit_benchmark.c
-F:	lib/nodemask.c
 F:	lib/test_bitmap.c
 F:	tools/include/linux/bitmap.h
 F:	tools/include/linux/find.h
@@ -13146,6 +13145,7 @@ W:	http://www.linux-mm.org
 T:	git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
 T:	quilt git://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new
 F:	include/linux/gfp.h
+F:	include/linux/gfp_types.h
 F:	include/linux/memory_hotplug.h
 F:	include/linux/mm.h
 F:	include/linux/mmzone.h
diff --git a/arch/alpha/include/asm/bitops.h b/arch/alpha/include/asm/bitops.h
index e1d8483a45f2..492c7713ddae 100644
--- a/arch/alpha/include/asm/bitops.h
+++ b/arch/alpha/include/asm/bitops.h
@@ -46,8 +46,8 @@ set_bit(unsigned long nr, volatile void * addr)
 /*
  * WARNING: non atomic version.
  */
-static inline void
-__set_bit(unsigned long nr, volatile void * addr)
+static __always_inline void
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	int *m = ((int *) addr) + (nr >> 5);
 
@@ -82,8 +82,8 @@ clear_bit_unlock(unsigned long nr, volatile void * addr)
 /*
  * WARNING: non atomic version.
  */
-static __inline__ void
-__clear_bit(unsigned long nr, volatile void * addr)
+static __always_inline void
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	int *m = ((int *) addr) + (nr >> 5);
 
@@ -94,7 +94,7 @@ static inline void
 __clear_bit_unlock(unsigned long nr, volatile void * addr)
 {
 	smp_mb();
-	__clear_bit(nr, addr);
+	arch___clear_bit(nr, addr);
 }
 
 static inline void
@@ -118,8 +118,8 @@ change_bit(unsigned long nr, volatile void * addr)
 /*
  * WARNING: non atomic version.
  */
-static __inline__ void
-__change_bit(unsigned long nr, volatile void * addr)
+static __always_inline void
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	int *m = ((int *) addr) + (nr >> 5);
 
@@ -186,8 +186,8 @@ test_and_set_bit_lock(unsigned long nr, volatile void *addr)
 /*
  * WARNING: non atomic version.
  */
-static inline int
-__test_and_set_bit(unsigned long nr, volatile void * addr)
+static __always_inline bool
+arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	unsigned long mask = 1 << (nr & 0x1f);
 	int *m = ((int *) addr) + (nr >> 5);
@@ -230,8 +230,8 @@ test_and_clear_bit(unsigned long nr, volatile void * addr)
 /*
  * WARNING: non atomic version.
  */
-static inline int
-__test_and_clear_bit(unsigned long nr, volatile void * addr)
+static __always_inline bool
+arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	unsigned long mask = 1 << (nr & 0x1f);
 	int *m = ((int *) addr) + (nr >> 5);
@@ -272,8 +272,8 @@ test_and_change_bit(unsigned long nr, volatile void * addr)
 /*
  * WARNING: non atomic version.
  */
-static __inline__ int
-__test_and_change_bit(unsigned long nr, volatile void * addr)
+static __always_inline bool
+arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	unsigned long mask = 1 << (nr & 0x1f);
 	int *m = ((int *) addr) + (nr >> 5);
@@ -283,8 +283,8 @@ __test_and_change_bit(unsigned long nr, volatile void * addr)
 	return (old & mask) != 0;
 }
 
-static inline int
-test_bit(int nr, const volatile void * addr)
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
 {
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
@@ -450,6 +450,8 @@ sched_find_first_bit(const unsigned long b[2])
 	return __ffs(tmp) + ofs;
 }
 
+#include <asm-generic/bitops/non-instrumented-non-atomic.h>
+
 #include <asm-generic/bitops/le.h>
 
 #include <asm-generic/bitops/ext2-atomic-setbit.h>
diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
index 8e94fe7ab5eb..714440fa2fc6 100644
--- a/arch/arm/include/asm/bitops.h
+++ b/arch/arm/include/asm/bitops.h
@@ -160,18 +160,20 @@ extern int _test_and_change_bit(int nr, volatile unsigned long * p);
 /*
  * Little endian assembly bitops.  nr = 0 -> byte 0 bit 0.
  */
-extern int _find_first_zero_bit_le(const unsigned long *p, unsigned size);
-extern int _find_next_zero_bit_le(const unsigned long *p, int size, int offset);
-extern int _find_first_bit_le(const unsigned long *p, unsigned size);
-extern int _find_next_bit_le(const unsigned long *p, int size, int offset);
+unsigned long _find_first_zero_bit_le(const unsigned long *p, unsigned long size);
+unsigned long _find_next_zero_bit_le(const unsigned long *p,
+				     unsigned long size, unsigned long offset);
+unsigned long _find_first_bit_le(const unsigned long *p, unsigned long size);
+unsigned long _find_next_bit_le(const unsigned long *p, unsigned long size, unsigned long offset);
 
 /*
  * Big endian assembly bitops.  nr = 0 -> byte 3 bit 0.
  */
-extern int _find_first_zero_bit_be(const unsigned long *p, unsigned size);
-extern int _find_next_zero_bit_be(const unsigned long *p, int size, int offset);
-extern int _find_first_bit_be(const unsigned long *p, unsigned size);
-extern int _find_next_bit_be(const unsigned long *p, int size, int offset);
+unsigned long _find_first_zero_bit_be(const unsigned long *p, unsigned long size);
+unsigned long _find_next_zero_bit_be(const unsigned long *p,
+				     unsigned long size, unsigned long offset);
+unsigned long _find_first_bit_be(const unsigned long *p, unsigned long size);
+unsigned long _find_next_bit_be(const unsigned long *p, unsigned long size, unsigned long offset);
 
 #ifndef CONFIG_SMP
 /*
diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h
index 75d6ba3643b8..da500471ac73 100644
--- a/arch/hexagon/include/asm/bitops.h
+++ b/arch/hexagon/include/asm/bitops.h
@@ -127,38 +127,45 @@ static inline void change_bit(int nr, volatile void *addr)
  * be atomic, particularly for things like slab_lock and slab_unlock.
  *
  */
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	test_and_clear_bit(nr, addr);
 }
 
-static inline void __set_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	test_and_set_bit(nr, addr);
 }
 
-static inline void __change_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	test_and_change_bit(nr, addr);
 }
 
 /*  Apparently, at least some of these are allowed to be non-atomic  */
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	return test_and_clear_bit(nr, addr);
 }
 
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	return test_and_set_bit(nr, addr);
 }
 
-static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	return test_and_change_bit(nr, addr);
 }
 
-static inline int __test_bit(int nr, const volatile unsigned long *addr)
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
 {
 	int retval;
 
@@ -172,8 +179,6 @@ static inline int __test_bit(int nr, const volatile unsigned long *addr)
 	return retval;
 }
 
-#define test_bit(nr, addr) __test_bit(nr, addr)
-
 /*
  * ffz - find first zero in word.
  * @word: The word to search
@@ -271,6 +276,7 @@ static inline unsigned long __fls(unsigned long word)
 }
 
 #include <asm-generic/bitops/lock.h>
+#include <asm-generic/bitops/non-instrumented-non-atomic.h>
 
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
diff --git a/arch/ia64/include/asm/bitops.h b/arch/ia64/include/asm/bitops.h
index 577be93c0818..9f62af7fd7c4 100644
--- a/arch/ia64/include/asm/bitops.h
+++ b/arch/ia64/include/asm/bitops.h
@@ -53,7 +53,7 @@ set_bit (int nr, volatile void *addr)
 }
 
 /**
- * __set_bit - Set a bit in memory
+ * arch___set_bit - Set a bit in memory
  * @nr: the bit to set
  * @addr: the address to start counting from
  *
@@ -61,8 +61,8 @@ set_bit (int nr, volatile void *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static __inline__ void
-__set_bit (int nr, volatile void *addr)
+static __always_inline void
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	*((__u32 *) addr + (nr >> 5)) |= (1 << (nr & 31));
 }
@@ -135,7 +135,7 @@ __clear_bit_unlock(int nr, void *addr)
 }
 
 /**
- * __clear_bit - Clears a bit in memory (non-atomic version)
+ * arch___clear_bit - Clears a bit in memory (non-atomic version)
  * @nr: the bit to clear
  * @addr: the address to start counting from
  *
@@ -143,8 +143,8 @@ __clear_bit_unlock(int nr, void *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static __inline__ void
-__clear_bit (int nr, volatile void *addr)
+static __always_inline void
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	*((__u32 *) addr + (nr >> 5)) &= ~(1 << (nr & 31));
 }
@@ -175,7 +175,7 @@ change_bit (int nr, volatile void *addr)
 }
 
 /**
- * __change_bit - Toggle a bit in memory
+ * arch___change_bit - Toggle a bit in memory
  * @nr: the bit to toggle
  * @addr: the address to start counting from
  *
@@ -183,8 +183,8 @@ change_bit (int nr, volatile void *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static __inline__ void
-__change_bit (int nr, volatile void *addr)
+static __always_inline void
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	*((__u32 *) addr + (nr >> 5)) ^= (1 << (nr & 31));
 }
@@ -224,7 +224,7 @@ test_and_set_bit (int nr, volatile void *addr)
 #define test_and_set_bit_lock test_and_set_bit
 
 /**
- * __test_and_set_bit - Set a bit and return its old value
+ * arch___test_and_set_bit - Set a bit and return its old value
  * @nr: Bit to set
  * @addr: Address to count from
  *
@@ -232,8 +232,8 @@ test_and_set_bit (int nr, volatile void *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static __inline__ int
-__test_and_set_bit (int nr, volatile void *addr)
+static __always_inline bool
+arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	__u32 *p = (__u32 *) addr + (nr >> 5);
 	__u32 m = 1 << (nr & 31);
@@ -269,7 +269,7 @@ test_and_clear_bit (int nr, volatile void *addr)
 }
 
 /**
- * __test_and_clear_bit - Clear a bit and return its old value
+ * arch___test_and_clear_bit - Clear a bit and return its old value
  * @nr: Bit to clear
  * @addr: Address to count from
  *
@@ -277,8 +277,8 @@ test_and_clear_bit (int nr, volatile void *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static __inline__ int
-__test_and_clear_bit(int nr, volatile void * addr)
+static __always_inline bool
+arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	__u32 *p = (__u32 *) addr + (nr >> 5);
 	__u32 m = 1 << (nr & 31);
@@ -314,14 +314,14 @@ test_and_change_bit (int nr, volatile void *addr)
 }
 
 /**
- * __test_and_change_bit - Change a bit and return its old value
+ * arch___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 and can be reordered.
  */
-static __inline__ int
-__test_and_change_bit (int nr, void *addr)
+static __always_inline bool
+arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	__u32 old, bit = (1 << (nr & 31));
 	__u32 *m = (__u32 *) addr + (nr >> 5);
@@ -331,8 +331,8 @@ __test_and_change_bit (int nr, void *addr)
 	return (old & bit) != 0;
 }
 
-static __inline__ int
-test_bit (int nr, const volatile void *addr)
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
 {
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
@@ -443,6 +443,8 @@ static __inline__ unsigned long __arch_hweight64(unsigned long x)
 
 #ifdef __KERNEL__
 
+#include <asm-generic/bitops/non-instrumented-non-atomic.h>
+
 #include <asm-generic/bitops/le.h>
 
 #include <asm-generic/bitops/ext2-atomic-setbit.h>
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index 7cbce290f4e5..757c2f6d8d4b 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -538,7 +538,7 @@ ia64_get_irr(unsigned int vector)
 {
 	unsigned int reg = vector / 64;
 	unsigned int bit = vector % 64;
-	u64 irr;
+	unsigned long irr;
 
 	switch (reg) {
 	case 0: irr = ia64_getreg(_IA64_REG_CR_IRR0); break;
diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h
index 87c2cd66a9ce..470aed978590 100644
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -65,8 +65,11 @@ static inline void bfset_mem_set_bit(int nr, volatile unsigned long *vaddr)
 				bfset_mem_set_bit(nr, vaddr))
 #endif
 
-#define __set_bit(nr, vaddr)	set_bit(nr, vaddr)
-
+static __always_inline void
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	set_bit(nr, addr);
+}
 
 static inline void bclr_reg_clear_bit(int nr, volatile unsigned long *vaddr)
 {
@@ -105,8 +108,11 @@ static inline void bfclr_mem_clear_bit(int nr, volatile unsigned long *vaddr)
 				bfclr_mem_clear_bit(nr, vaddr))
 #endif
 
-#define __clear_bit(nr, vaddr)	clear_bit(nr, vaddr)
-
+static __always_inline void
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	clear_bit(nr, addr);
+}
 
 static inline void bchg_reg_change_bit(int nr, volatile unsigned long *vaddr)
 {
@@ -145,14 +151,17 @@ static inline void bfchg_mem_change_bit(int nr, volatile unsigned long *vaddr)
 				bfchg_mem_change_bit(nr, vaddr))
 #endif
 
-#define __change_bit(nr, vaddr)	change_bit(nr, vaddr)
-
-
-static inline int test_bit(int nr, const volatile unsigned long *vaddr)
+static __always_inline void
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
+	change_bit(nr, addr);
 }
 
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
+{
+	return (addr[nr >> 5] & (1UL << (nr & 31))) != 0;
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
@@ -201,8 +210,11 @@ static inline int bfset_mem_test_and_set_bit(int nr,
 					bfset_mem_test_and_set_bit(nr, vaddr))
 #endif
 
-#define __test_and_set_bit(nr, vaddr)	test_and_set_bit(nr, vaddr)
-
+static __always_inline bool
+arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	return test_and_set_bit(nr, addr);
+}
 
 static inline int bclr_reg_test_and_clear_bit(int nr,
 					      volatile unsigned long *vaddr)
@@ -251,8 +263,11 @@ static inline int bfclr_mem_test_and_clear_bit(int nr,
 					bfclr_mem_test_and_clear_bit(nr, vaddr))
 #endif
 
-#define __test_and_clear_bit(nr, vaddr)	test_and_clear_bit(nr, vaddr)
-
+static __always_inline bool
+arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	return test_and_clear_bit(nr, addr);
+}
 
 static inline int bchg_reg_test_and_change_bit(int nr,
 					       volatile unsigned long *vaddr)
@@ -301,8 +316,11 @@ static inline int bfchg_mem_test_and_change_bit(int nr,
 					bfchg_mem_test_and_change_bit(nr, vaddr))
 #endif
 
-#define __test_and_change_bit(nr, vaddr) test_and_change_bit(nr, vaddr)
-
+static __always_inline bool
+arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	return test_and_change_bit(nr, addr);
+}
 
 /*
  *	The true 68020 and more advanced processors support the "bfffo"
@@ -522,6 +540,7 @@ static inline unsigned long __fls(unsigned long x)
 #define clear_bit_unlock	clear_bit
 #define __clear_bit_unlock	clear_bit_unlock
 
+#include <asm-generic/bitops/non-instrumented-non-atomic.h>
 #include <asm-generic/bitops/ext2-atomic.h>
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h
index 564859e6a807..5e46d6ce7d68 100644
--- a/arch/powerpc/include/asm/archrandom.h
+++ b/arch/powerpc/include/asm/archrandom.h
@@ -9,12 +9,7 @@ static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t
 	return 0;
 }
 
-static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs)
-{
-	if (max_longs && ppc_md.get_random_seed && ppc_md.get_random_seed(v))
-		return 1;
-	return 0;
-}
+size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs);
 
 #ifdef CONFIG_PPC_POWERNV
 int pnv_get_random_long(unsigned long *v);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 1a02629ec70b..3b1cf9ca4814 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -171,6 +171,18 @@ EXPORT_SYMBOL_GPL(machine_power_off);
 void (*pm_power_off)(void);
 EXPORT_SYMBOL_GPL(pm_power_off);
 
+#ifdef CONFIG_ARCH_RANDOM
+bool __must_check arch_get_random_seed_long(unsigned long *v)
+{
+	if (ppc_md.get_random_seed)
+		return ppc_md.get_random_seed(v);
+
+	return false;
+}
+EXPORT_SYMBOL(arch_get_random_seed_long);
+
+#endif
+
 void machine_halt(void)
 {
 	machine_shutdown();
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 191dc7898b0f..9a7d15da966e 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -113,75 +113,76 @@ static inline bool arch_test_and_change_bit(unsigned long nr,
 	return old & mask;
 }
 
-static inline void arch___set_bit(unsigned long nr, volatile unsigned long *ptr)
+static __always_inline void
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *addr = __bitops_word(nr, ptr);
+	unsigned long *p = __bitops_word(nr, addr);
 	unsigned long mask = __bitops_mask(nr);
 
-	*addr |= mask;
+	*p |= mask;
 }
 
-static inline void arch___clear_bit(unsigned long nr,
-				    volatile unsigned long *ptr)
+static __always_inline void
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *addr = __bitops_word(nr, ptr);
+	unsigned long *p = __bitops_word(nr, addr);
 	unsigned long mask = __bitops_mask(nr);
 
-	*addr &= ~mask;
+	*p &= ~mask;
 }
 
-static inline void arch___change_bit(unsigned long nr,
-				     volatile unsigned long *ptr)
+static __always_inline void
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *addr = __bitops_word(nr, ptr);
+	unsigned long *p = __bitops_word(nr, addr);
 	unsigned long mask = __bitops_mask(nr);
 
-	*addr ^= mask;
+	*p ^= mask;
 }
 
-static inline bool arch___test_and_set_bit(unsigned long nr,
-					   volatile unsigned long *ptr)
+static __always_inline bool
+arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *addr = __bitops_word(nr, ptr);
+	unsigned long *p = __bitops_word(nr, addr);
 	unsigned long mask = __bitops_mask(nr);
 	unsigned long old;
 
-	old = *addr;
-	*addr |= mask;
+	old = *p;
+	*p |= mask;
 	return old & mask;
 }
 
-static inline bool arch___test_and_clear_bit(unsigned long nr,
-					     volatile unsigned long *ptr)
+static __always_inline bool
+arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *addr = __bitops_word(nr, ptr);
+	unsigned long *p = __bitops_word(nr, addr);
 	unsigned long mask = __bitops_mask(nr);
 	unsigned long old;
 
-	old = *addr;
-	*addr &= ~mask;
+	old = *p;
+	*p &= ~mask;
 	return old & mask;
 }
 
-static inline bool arch___test_and_change_bit(unsigned long nr,
-					      volatile unsigned long *ptr)
+static __always_inline bool
+arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *addr = __bitops_word(nr, ptr);
+	unsigned long *p = __bitops_word(nr, addr);
 	unsigned long mask = __bitops_mask(nr);
 	unsigned long old;
 
-	old = *addr;
-	*addr ^= mask;
+	old = *p;
+	*p ^= mask;
 	return old & mask;
 }
 
-static inline bool arch_test_bit(unsigned long nr,
-				 const volatile unsigned long *ptr)
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
 {
-	const volatile unsigned long *addr = __bitops_word(nr, ptr);
+	const volatile unsigned long *p = __bitops_word(nr, addr);
 	unsigned long mask = __bitops_mask(nr);
 
-	return *addr & mask;
+	return *p & mask;
 }
 
 static inline bool arch_test_and_set_bit_lock(unsigned long nr,
diff --git a/arch/sh/include/asm/bitops-op32.h b/arch/sh/include/asm/bitops-op32.h
index cfe5465acce7..565a85d8b7fb 100644
--- a/arch/sh/include/asm/bitops-op32.h
+++ b/arch/sh/include/asm/bitops-op32.h
@@ -2,6 +2,8 @@
 #ifndef __ASM_SH_BITOPS_OP32_H
 #define __ASM_SH_BITOPS_OP32_H
 
+#include <linux/bits.h>
+
 /*
  * The bit modifying instructions on SH-2A are only capable of working
  * with a 3-bit immediate, which signifies the shift position for the bit
@@ -16,7 +18,8 @@
 #define BYTE_OFFSET(nr)		((nr) % BITS_PER_BYTE)
 #endif
 
-static inline void __set_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
 		__asm__ __volatile__ (
@@ -33,7 +36,8 @@ static inline void __set_bit(int nr, volatile unsigned long *addr)
 	}
 }
 
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
 		__asm__ __volatile__ (
@@ -52,7 +56,7 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr)
 }
 
 /**
- * __change_bit - Toggle a bit in memory
+ * arch___change_bit - Toggle a bit in memory
  * @nr: the bit to change
  * @addr: the address to start counting from
  *
@@ -60,7 +64,8 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __change_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
 		__asm__ __volatile__ (
@@ -79,7 +84,7 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
 }
 
 /**
- * __test_and_set_bit - Set a bit and return its old value
+ * arch___test_and_set_bit - Set a bit and return its old value
  * @nr: Bit to set
  * @addr: Address to count from
  *
@@ -87,7 +92,8 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___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);
@@ -98,7 +104,7 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
 }
 
 /**
- * __test_and_clear_bit - Clear a bit and return its old value
+ * arch___test_and_clear_bit - Clear a bit and return its old value
  * @nr: Bit to clear
  * @addr: Address to count from
  *
@@ -106,7 +112,8 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___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);
@@ -117,8 +124,8 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
 }
 
 /* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr,
-					    volatile unsigned long *addr)
+static __always_inline bool
+arch___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);
@@ -129,13 +136,16 @@ static inline int __test_and_change_bit(int nr,
 }
 
 /**
- * test_bit - Determine whether a bit is set
+ * arch_test_bit - Determine whether a bit is set
  * @nr: bit number to test
  * @addr: Address to start counting from
  */
-static inline int test_bit(int nr, const volatile unsigned long *addr)
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
 {
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+#include <asm-generic/bitops/non-instrumented-non-atomic.h>
+
 #endif /* __ASM_SH_BITOPS_OP32_H */
diff --git a/arch/sparc/include/asm/bitops_32.h b/arch/sparc/include/asm/bitops_32.h
index 889afa9f990f..3448c191b484 100644
--- a/arch/sparc/include/asm/bitops_32.h
+++ b/arch/sparc/include/asm/bitops_32.h
@@ -19,9 +19,9 @@
 #error only <linux/bitops.h> can be included directly
 #endif
 
-unsigned long ___set_bit(unsigned long *addr, unsigned long mask);
-unsigned long ___clear_bit(unsigned long *addr, unsigned long mask);
-unsigned long ___change_bit(unsigned long *addr, unsigned long mask);
+unsigned long sp32___set_bit(unsigned long *addr, unsigned long mask);
+unsigned long sp32___clear_bit(unsigned long *addr, unsigned long mask);
+unsigned long sp32___change_bit(unsigned long *addr, unsigned long mask);
 
 /*
  * Set bit 'nr' in 32-bit quantity at address 'addr' where bit '0'
@@ -36,7 +36,7 @@ static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *add
 	ADDR = ((unsigned long *) addr) + (nr >> 5);
 	mask = 1 << (nr & 31);
 
-	return ___set_bit(ADDR, mask) != 0;
+	return sp32___set_bit(ADDR, mask) != 0;
 }
 
 static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
@@ -46,7 +46,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 	ADDR = ((unsigned long *) addr) + (nr >> 5);
 	mask = 1 << (nr & 31);
 
-	(void) ___set_bit(ADDR, mask);
+	(void) sp32___set_bit(ADDR, mask);
 }
 
 static inline int test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
@@ -56,7 +56,7 @@ static inline int test_and_clear_bit(unsigned long nr, volatile unsigned long *a
 	ADDR = ((unsigned long *) addr) + (nr >> 5);
 	mask = 1 << (nr & 31);
 
-	return ___clear_bit(ADDR, mask) != 0;
+	return sp32___clear_bit(ADDR, mask) != 0;
 }
 
 static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
@@ -66,7 +66,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 	ADDR = ((unsigned long *) addr) + (nr >> 5);
 	mask = 1 << (nr & 31);
 
-	(void) ___clear_bit(ADDR, mask);
+	(void) sp32___clear_bit(ADDR, mask);
 }
 
 static inline int test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
@@ -76,7 +76,7 @@ static inline int test_and_change_bit(unsigned long nr, volatile unsigned long *
 	ADDR = ((unsigned long *) addr) + (nr >> 5);
 	mask = 1 << (nr & 31);
 
-	return ___change_bit(ADDR, mask) != 0;
+	return sp32___change_bit(ADDR, mask) != 0;
 }
 
 static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
@@ -86,7 +86,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 	ADDR = ((unsigned long *) addr) + (nr >> 5);
 	mask = 1 << (nr & 31);
 
-	(void) ___change_bit(ADDR, mask);
+	(void) sp32___change_bit(ADDR, mask);
 }
 
 #include <asm-generic/bitops/non-atomic.h>
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index 8b81d0f00c97..cf80d1ae352b 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -120,7 +120,7 @@ void arch_atomic_set(atomic_t *v, int i)
 }
 EXPORT_SYMBOL(arch_atomic_set);
 
-unsigned long ___set_bit(unsigned long *addr, unsigned long mask)
+unsigned long sp32___set_bit(unsigned long *addr, unsigned long mask)
 {
 	unsigned long old, flags;
 
@@ -131,9 +131,9 @@ unsigned long ___set_bit(unsigned long *addr, unsigned long mask)
 
 	return old & mask;
 }
-EXPORT_SYMBOL(___set_bit);
+EXPORT_SYMBOL(sp32___set_bit);
 
-unsigned long ___clear_bit(unsigned long *addr, unsigned long mask)
+unsigned long sp32___clear_bit(unsigned long *addr, unsigned long mask)
 {
 	unsigned long old, flags;
 
@@ -144,9 +144,9 @@ unsigned long ___clear_bit(unsigned long *addr, unsigned long mask)
 
 	return old & mask;
 }
-EXPORT_SYMBOL(___clear_bit);
+EXPORT_SYMBOL(sp32___clear_bit);
 
-unsigned long ___change_bit(unsigned long *addr, unsigned long mask)
+unsigned long sp32___change_bit(unsigned long *addr, unsigned long mask)
 {
 	unsigned long old, flags;
 
@@ -157,7 +157,7 @@ unsigned long ___change_bit(unsigned long *addr, unsigned long mask)
 
 	return old & mask;
 }
-EXPORT_SYMBOL(___change_bit);
+EXPORT_SYMBOL(sp32___change_bit);
 
 unsigned long __cmpxchg_u32(volatile u32 *ptr, u32 old, u32 new)
 {
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index a288ecd230ab..973c6bd17f98 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -63,7 +63,7 @@ arch_set_bit(long nr, volatile unsigned long *addr)
 }
 
 static __always_inline void
-arch___set_bit(long nr, volatile unsigned long *addr)
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
@@ -89,7 +89,7 @@ arch_clear_bit_unlock(long nr, volatile unsigned long *addr)
 }
 
 static __always_inline void
-arch___clear_bit(long nr, volatile unsigned long *addr)
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
@@ -114,7 +114,7 @@ arch___clear_bit_unlock(long nr, volatile unsigned long *addr)
 }
 
 static __always_inline void
-arch___change_bit(long nr, volatile unsigned long *addr)
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
@@ -145,7 +145,7 @@ arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr)
 }
 
 static __always_inline bool
-arch___test_and_set_bit(long nr, volatile unsigned long *addr)
+arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	bool oldbit;
 
@@ -171,7 +171,7 @@ arch_test_and_clear_bit(long nr, volatile unsigned long *addr)
  * this without also updating arch/x86/kernel/kvm.c
  */
 static __always_inline bool
-arch___test_and_clear_bit(long nr, volatile unsigned long *addr)
+arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	bool oldbit;
 
@@ -183,7 +183,7 @@ arch___test_and_clear_bit(long nr, volatile unsigned long *addr)
 }
 
 static __always_inline bool
-arch___test_and_change_bit(long nr, volatile unsigned long *addr)
+arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	bool oldbit;
 
@@ -219,10 +219,12 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l
 	return oldbit;
 }
 
-#define arch_test_bit(nr, addr)			\
-	(__builtin_constant_p((nr))		\
-	 ? constant_test_bit((nr), (addr))	\
-	 : variable_test_bit((nr), (addr)))
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
 
 /**
  * __ffs - find first set bit in word
diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c
index f03a6883dcc6..89f25af4b3c3 100644
--- a/arch/x86/platform/olpc/olpc-xo1-sci.c
+++ b/arch/x86/platform/olpc/olpc-xo1-sci.c
@@ -80,7 +80,7 @@ static void send_ebook_state(void)
 		return;
 	}
 
-	if (!!test_bit(SW_TABLET_MODE, ebook_switch_idev->sw) == state)
+	if (test_bit(SW_TABLET_MODE, ebook_switch_idev->sw) == !!state)
 		return; /* Nothing new to report. */
 
 	input_report_switch(ebook_switch_idev, SW_TABLET_MODE, state);
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index 2f0d2c68c93c..07cb48db76ba 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -4997,7 +4997,7 @@ static int setup_resources(struct udma_dev *ud)
 	switch (ud->match_data->type) {
 	case DMA_TYPE_UDMA:
 		dev_info(dev,
-			 "Channels: %d (tchan: %u, rchan: %u, gp-rflow: %u)\n",
+			 "Channels: %d (tchan: %lu, rchan: %lu, gp-rflow: %lu)\n",
 			 ch_count,
 			 ud->tchan_cnt - bitmap_weight(ud->tchan_map,
 						       ud->tchan_cnt),
@@ -5008,7 +5008,7 @@ static int setup_resources(struct udma_dev *ud)
 		break;
 	case DMA_TYPE_BCDMA:
 		dev_info(dev,
-			 "Channels: %d (bchan: %u, tchan: %u, rchan: %u)\n",
+			 "Channels: %d (bchan: %lu, tchan: %lu, rchan: %lu)\n",
 			 ch_count,
 			 ud->bchan_cnt - bitmap_weight(ud->bchan_map,
 						       ud->bchan_cnt),
@@ -5019,7 +5019,7 @@ static int setup_resources(struct udma_dev *ud)
 		break;
 	case DMA_TYPE_PKTDMA:
 		dev_info(dev,
-			 "Channels: %d (tchan: %u, rchan: %u)\n",
+			 "Channels: %d (tchan: %lu, rchan: %lu)\n",
 			 ch_count,
 			 ud->tchan_cnt - bitmap_weight(ud->tchan_map,
 						       ud->tchan_cnt),
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 222d3d7ea076..0bb2442149ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -222,7 +222,7 @@ void amdgpu_gfx_compute_queue_acquire(struct amdgpu_device *adev)
 			set_bit(i, adev->gfx.mec.queue_bitmap);
 	}
 
-	dev_dbg(adev->dev, "mec queue bitmap weight=%d\n", bitmap_weight(adev->gfx.mec.queue_bitmap, AMDGPU_MAX_COMPUTE_QUEUES));
+	dev_dbg(adev->dev, "mec queue bitmap weight=%ld\n", bitmap_weight(adev->gfx.mec.queue_bitmap, AMDGPU_MAX_COMPUTE_QUEUES));
 }
 
 void amdgpu_gfx_graphics_queue_acquire(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 589af257edeb..c5f39abc3851 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -378,7 +378,7 @@ static void print_power_domains(struct i915_power_domains *power_domains,
 						     power_domains);
 	enum intel_display_power_domain domain;
 
-	drm_dbg(&i915->drm, "%s (%d):\n", prefix, bitmap_weight(mask->bits, POWER_DOMAIN_NUM));
+	drm_dbg(&i915->drm, "%s (%ld):\n", prefix, bitmap_weight(mask->bits, POWER_DOMAIN_NUM));
 	for_each_power_domain(domain, mask)
 		drm_dbg(&i915->drm, "%s use_count %d\n",
 			intel_display_power_domain_str(domain),
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index c6d3050604c8..79fa564785b6 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -865,10 +865,10 @@ void intel_sseu_print_ss_info(const char *type,
 	int s;
 
 	if (sseu->has_xehp_dss) {
-		seq_printf(m, "  %s Geometry DSS: %u\n", type,
+		seq_printf(m, "  %s Geometry DSS: %lu\n", type,
 			   bitmap_weight(sseu->geometry_subslice_mask.xehp,
 					 XEHP_BITMAP_BITS(sseu->geometry_subslice_mask)));
-		seq_printf(m, "  %s Compute DSS: %u\n", type,
+		seq_printf(m, "  %s Compute DSS: %lu\n", type,
 			   bitmap_weight(sseu->compute_subslice_mask.xehp,
 					 XEHP_BITMAP_BITS(sseu->compute_subslice_mask)));
 	} else {
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
index 56a3063545ec..3d35b3982a60 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
@@ -363,7 +363,7 @@ void mdp5_smp_dump(struct mdp5_smp *smp, struct drm_printer *p)
 	}
 
 	drm_printf(p, "TOTAL:\t%d\t(of %d)\n", total, smp->blk_cnt);
-	drm_printf(p, "AVAIL:\t%d\n", smp->blk_cnt -
+	drm_printf(p, "AVAIL:\t%ld\n", smp->blk_cnt -
 			bitmap_weight(state->state, smp->blk_cnt));
 
 	if (drm_can_sleep())
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 6327b34f5aa7..5a8f780e7ffd 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -494,7 +494,7 @@ static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
 		if (drhd->reg_base_addr == rhsa->base_address) {
 			int node = pxm_to_node(rhsa->proximity_domain);
 
-			if (!node_online(node))
+			if (node != NUMA_NO_NODE && !node_online(node))
 				node = NUMA_NO_NODE;
 			drhd->iommu->node = node;
 			return 0;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 7cca030a508e..7d538e753b2c 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3805,7 +3805,7 @@ static ssize_t domains_used_show(struct device *dev,
 				 struct device_attribute *attr, char *buf)
 {
 	struct intel_iommu *iommu = dev_to_intel_iommu(dev);
-	return sprintf(buf, "%d\n", bitmap_weight(iommu->domain_ids,
+	return sprintf(buf, "%ld\n", bitmap_weight(iommu->domain_ids,
 						  cap_ndoms(iommu->cap)));
 }
 static DEVICE_ATTR_RO(domains_used);
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index fce204693dbb..262e553e3b58 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -4971,7 +4971,7 @@ ice_find_free_recp_res_idx(struct ice_hw *hw, const unsigned long *profiles,
 	bitmap_zero(recipes, ICE_MAX_NUM_RECIPES);
 	bitmap_zero(used_idx, ICE_MAX_FV_WORDS);
 
-	bitmap_set(possible_idx, 0, ICE_MAX_FV_WORDS);
+	bitmap_fill(possible_idx, ICE_MAX_FV_WORDS);
 
 	/* For each profile we are going to associate the recipe with, add the
 	 * recipes that are associated with that profile. This will give us
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
index 594029007f85..c62a234eb2fc 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
@@ -451,7 +451,7 @@ static int rvu_npc_exact_alloc_mem_table_entry(struct rvu *rvu, u8 *way,
 	}
 	mutex_unlock(&table->lock);
 
-	dev_dbg(rvu->dev, "%s: No space in 4 way exact way, weight=%u\n", __func__,
+	dev_dbg(rvu->dev, "%s: No space in 4 way exact way, weight=%lu\n", __func__,
 		bitmap_weight(table->mem_table.bmap, table->mem_table.depth));
 	return -ENOSPC;
 }
@@ -489,7 +489,7 @@ static bool rvu_npc_exact_alloc_id(struct rvu *rvu, u32 *seq_id)
 	idx = find_first_zero_bit(table->id_bmap, table->tot_ids);
 	if (idx == table->tot_ids) {
 		mutex_unlock(&table->lock);
-		dev_err(rvu->dev, "%s: No space in id bitmap (%d)\n",
+		dev_err(rvu->dev, "%s: No space in id bitmap (%lu)\n",
 			__func__, bitmap_weight(table->id_bmap, table->tot_ids));
 
 		return false;
@@ -522,7 +522,7 @@ static int rvu_npc_exact_alloc_cam_table_entry(struct rvu *rvu, int *index)
 	idx = find_first_zero_bit(table->cam_table.bmap, table->cam_table.depth);
 	if (idx == table->cam_table.depth) {
 		mutex_unlock(&table->lock);
-		dev_info(rvu->dev, "%s: No space in exact cam table, weight=%u\n", __func__,
+		dev_info(rvu->dev, "%s: No space in exact cam table, weight=%lu\n", __func__,
 			 bitmap_weight(table->cam_table.bmap, table->cam_table.depth));
 		return -ENOSPC;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 42c96c9d7fb1..af054a3808ca 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -463,7 +463,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 
 		field = min(
 			bitmap_weight(actv_ports.ports, dev->caps.num_ports),
-			dev->caps.num_ports);
+			(unsigned long)dev->caps.num_ports);
 		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_NUM_PORTS_OFFSET);
 
 		size = dev->caps.function_caps; /* set PF behaviours */
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
index b3ed65e5c4da..d32056c4ee1d 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
@@ -296,7 +296,7 @@ static ssize_t read_file_slot(struct file *file, char __user *user_buf,
 	spin_lock_bh(&priv->tx.tx_lock);
 	len = scnprintf(buf, sizeof(buf),
 			"TX slot bitmap : %*pb\n"
-			"Used slots     : %d\n",
+			"Used slots     : %ld\n",
 			MAX_TX_BUF_NUM, priv->tx.tx_slot,
 			bitmap_weight(priv->tx.tx_slot, MAX_TX_BUF_NUM));
 	spin_unlock_bh(&priv->tx.tx_lock);
diff --git a/drivers/net/wireless/ath/carl9170/debug.c b/drivers/net/wireless/ath/carl9170/debug.c
index bb40889d7c72..7e88882b87d9 100644
--- a/drivers/net/wireless/ath/carl9170/debug.c
+++ b/drivers/net/wireless/ath/carl9170/debug.c
@@ -221,7 +221,7 @@ static char *carl9170_debugfs_mem_usage_read(struct ar9170 *ar, char *buf,
 	ADD(buf, *len, bufsize, "jar: [%*pb]\n",
 	    ar->fw.mem_blocks, ar->mem_bitmap);
 
-	ADD(buf, *len, bufsize, "cookies: used:%3d / total:%3d, allocs:%d\n",
+	ADD(buf, *len, bufsize, "cookies: used:%3ld / total:%3d, allocs:%d\n",
 	    bitmap_weight(ar->mem_bitmap, ar->fw.mem_blocks),
 	    ar->fw.mem_blocks, atomic_read(&ar->mem_allocs));
 
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..035d4ac66641 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 long __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 long 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 4592d0845941..57c8496d28b2 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;
@@ -176,12 +178,12 @@ static inline unsigned int cpumask_local_spread(unsigned int i, int node)
 	return 0;
 }
 
-static inline int cpumask_any_and_distribute(const struct cpumask *src1p,
+static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
 					     const struct cpumask *src2p) {
 	return cpumask_first_and(src1p, src2p);
 }
 
-static inline int cpumask_any_distribute(const struct cpumask *srcp)
+static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp)
 {
 	return cpumask_first(srcp);
 }
@@ -241,7 +243,21 @@ 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
@@ -258,12 +274,29 @@ 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);
+/**
+ * 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);
+}
+
 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);
 
 /**
  * for_each_cpu - iterate over every cpu in a mask
@@ -289,7 +322,7 @@ int cpumask_any_distribute(const struct cpumask *srcp);
 		(cpu) = cpumask_next_zero((cpu), (mask)),	\
 		(cpu) < nr_cpu_ids;)
 
-extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
+unsigned int 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
@@ -324,6 +357,26 @@ extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool
 	for ((cpu) = -1;						\
 		(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;
+}
 #endif /* SMP */
 
 #define CPU_BITS_NONE						\
@@ -372,9 +425,9 @@ 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)));
 }
@@ -384,11 +437,11 @@ 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));
 }
@@ -398,11 +451,11 @@ 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));
 }
@@ -431,9 +484,9 @@ 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)
 {
@@ -474,9 +527,9 @@ 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)
 {
@@ -539,9 +592,9 @@ 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),
@@ -743,9 +796,35 @@ 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);
+}
+
 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);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 0ace7759acd2..f314be58fa77 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -2,357 +2,13 @@
 #ifndef __LINUX_GFP_H
 #define __LINUX_GFP_H
 
-#include <linux/mmdebug.h>
+#include <linux/gfp_types.h>
+
 #include <linux/mmzone.h>
-#include <linux/stddef.h>
-#include <linux/linkage.h>
 #include <linux/topology.h>
 
-/* The typedef is in types.h but we want the documentation here */
-#if 0
-/**
- * typedef gfp_t - Memory allocation flags.
- *
- * GFP flags are commonly used throughout Linux to indicate how memory
- * should be allocated.  The GFP acronym stands for get_free_pages(),
- * the underlying memory allocation function.  Not every GFP flag is
- * supported by every function which may allocate memory.  Most users
- * will want to use a plain ``GFP_KERNEL``.
- */
-typedef unsigned int __bitwise gfp_t;
-#endif
-
 struct vm_area_struct;
 
-/*
- * In case of changes, please don't forget to update
- * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c
- */
-
-/* Plain integer GFP bitmasks. Do not use this directly. */
-#define ___GFP_DMA		0x01u
-#define ___GFP_HIGHMEM		0x02u
-#define ___GFP_DMA32		0x04u
-#define ___GFP_MOVABLE		0x08u
-#define ___GFP_RECLAIMABLE	0x10u
-#define ___GFP_HIGH		0x20u
-#define ___GFP_IO		0x40u
-#define ___GFP_FS		0x80u
-#define ___GFP_ZERO		0x100u
-#define ___GFP_ATOMIC		0x200u
-#define ___GFP_DIRECT_RECLAIM	0x400u
-#define ___GFP_KSWAPD_RECLAIM	0x800u
-#define ___GFP_WRITE		0x1000u
-#define ___GFP_NOWARN		0x2000u
-#define ___GFP_RETRY_MAYFAIL	0x4000u
-#define ___GFP_NOFAIL		0x8000u
-#define ___GFP_NORETRY		0x10000u
-#define ___GFP_MEMALLOC		0x20000u
-#define ___GFP_COMP		0x40000u
-#define ___GFP_NOMEMALLOC	0x80000u
-#define ___GFP_HARDWALL		0x100000u
-#define ___GFP_THISNODE		0x200000u
-#define ___GFP_ACCOUNT		0x400000u
-#define ___GFP_ZEROTAGS		0x800000u
-#ifdef CONFIG_KASAN_HW_TAGS
-#define ___GFP_SKIP_ZERO		0x1000000u
-#define ___GFP_SKIP_KASAN_UNPOISON	0x2000000u
-#define ___GFP_SKIP_KASAN_POISON	0x4000000u
-#else
-#define ___GFP_SKIP_ZERO		0
-#define ___GFP_SKIP_KASAN_UNPOISON	0
-#define ___GFP_SKIP_KASAN_POISON	0
-#endif
-#ifdef CONFIG_LOCKDEP
-#define ___GFP_NOLOCKDEP	0x8000000u
-#else
-#define ___GFP_NOLOCKDEP	0
-#endif
-/* If the above are modified, __GFP_BITS_SHIFT may need updating */
-
-/*
- * Physical address zone modifiers (see linux/mmzone.h - low four bits)
- *
- * Do not put any conditional on these. If necessary modify the definitions
- * without the underscores and use them consistently. The definitions here may
- * be used in bit comparisons.
- */
-#define __GFP_DMA	((__force gfp_t)___GFP_DMA)
-#define __GFP_HIGHMEM	((__force gfp_t)___GFP_HIGHMEM)
-#define __GFP_DMA32	((__force gfp_t)___GFP_DMA32)
-#define __GFP_MOVABLE	((__force gfp_t)___GFP_MOVABLE)  /* ZONE_MOVABLE allowed */
-#define GFP_ZONEMASK	(__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)
-
-/**
- * DOC: Page mobility and placement hints
- *
- * Page mobility and placement hints
- * ---------------------------------
- *
- * These flags provide hints about how mobile the page is. Pages with similar
- * mobility are placed within the same pageblocks to minimise problems due
- * to external fragmentation.
- *
- * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be
- * moved by page migration during memory compaction or can be reclaimed.
- *
- * %__GFP_RECLAIMABLE is used for slab allocations that specify
- * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers.
- *
- * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible,
- * these pages will be spread between local zones to avoid all the dirty
- * pages being in one zone (fair zone allocation policy).
- *
- * %__GFP_HARDWALL enforces the cpuset memory allocation policy.
- *
- * %__GFP_THISNODE forces the allocation to be satisfied from the requested
- * node with no fallbacks or placement policy enforcements.
- *
- * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
- */
-#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
-#define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)
-#define __GFP_HARDWALL   ((__force gfp_t)___GFP_HARDWALL)
-#define __GFP_THISNODE	((__force gfp_t)___GFP_THISNODE)
-#define __GFP_ACCOUNT	((__force gfp_t)___GFP_ACCOUNT)
-
-/**
- * DOC: Watermark modifiers
- *
- * Watermark modifiers -- controls access to emergency reserves
- * ------------------------------------------------------------
- *
- * %__GFP_HIGH indicates that the caller is high-priority and that granting
- * the request is necessary before the system can make forward progress.
- * For example, creating an IO context to clean pages.
- *
- * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is
- * high priority. Users are typically interrupt handlers. This may be
- * used in conjunction with %__GFP_HIGH
- *
- * %__GFP_MEMALLOC allows access to all memory. This should only be used when
- * the caller guarantees the allocation will allow more memory to be freed
- * very shortly e.g. process exiting or swapping. Users either should
- * be the MM or co-ordinating closely with the VM (e.g. swap over NFS).
- * Users of this flag have to be extremely careful to not deplete the reserve
- * completely and implement a throttling mechanism which controls the
- * consumption of the reserve based on the amount of freed memory.
- * Usage of a pre-allocated pool (e.g. mempool) should be always considered
- * before using this flag.
- *
- * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves.
- * This takes precedence over the %__GFP_MEMALLOC flag if both are set.
- */
-#define __GFP_ATOMIC	((__force gfp_t)___GFP_ATOMIC)
-#define __GFP_HIGH	((__force gfp_t)___GFP_HIGH)
-#define __GFP_MEMALLOC	((__force gfp_t)___GFP_MEMALLOC)
-#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC)
-
-/**
- * DOC: Reclaim modifiers
- *
- * Reclaim modifiers
- * -----------------
- * Please note that all the following flags are only applicable to sleepable
- * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them).
- *
- * %__GFP_IO can start physical IO.
- *
- * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the
- * allocator recursing into the filesystem which might already be holding
- * locks.
- *
- * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim.
- * This flag can be cleared to avoid unnecessary delays when a fallback
- * option is available.
- *
- * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when
- * the low watermark is reached and have it reclaim pages until the high
- * watermark is reached. A caller may wish to clear this flag when fallback
- * options are available and the reclaim is likely to disrupt the system. The
- * canonical example is THP allocation where a fallback is cheap but
- * reclaim/compaction may cause indirect stalls.
- *
- * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
- *
- * The default allocator behavior depends on the request size. We have a concept
- * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER).
- * !costly allocations are too essential to fail so they are implicitly
- * non-failing by default (with some exceptions like OOM victims might fail so
- * the caller still has to check for failures) while costly requests try to be
- * not disruptive and back off even without invoking the OOM killer.
- * The following three modifiers might be used to override some of these
- * implicit rules
- *
- * %__GFP_NORETRY: The VM implementation will try only very lightweight
- * memory direct reclaim to get some memory under memory pressure (thus
- * it can sleep). It will avoid disruptive actions like OOM killer. The
- * caller must handle the failure which is quite likely to happen under
- * heavy memory pressure. The flag is suitable when failure can easily be
- * handled at small cost, such as reduced throughput
- *
- * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim
- * procedures that have previously failed if there is some indication
- * that progress has been made else where.  It can wait for other
- * tasks to attempt high level approaches to freeing memory such as
- * compaction (which removes fragmentation) and page-out.
- * There is still a definite limit to the number of retries, but it is
- * a larger limit than with %__GFP_NORETRY.
- * Allocations with this flag may fail, but only when there is
- * genuinely little unused memory. While these allocations do not
- * directly trigger the OOM killer, their failure indicates that
- * the system is likely to need to use the OOM killer soon.  The
- * caller must handle failure, but can reasonably do so by failing
- * a higher-level request, or completing it only in a much less
- * efficient manner.
- * If the allocation does fail, and the caller is in a position to
- * free some non-essential memory, doing so could benefit the system
- * as a whole.
- *
- * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
- * cannot handle allocation failures. The allocation could block
- * indefinitely but will never return with failure. Testing for
- * failure is pointless.
- * New users should be evaluated carefully (and the flag should be
- * used only when there is no reasonable failure policy) but it is
- * definitely preferable to use the flag rather than opencode endless
- * loop around allocator.
- * Using this flag for costly allocations is _highly_ discouraged.
- */
-#define __GFP_IO	((__force gfp_t)___GFP_IO)
-#define __GFP_FS	((__force gfp_t)___GFP_FS)
-#define __GFP_DIRECT_RECLAIM	((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */
-#define __GFP_KSWAPD_RECLAIM	((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */
-#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
-#define __GFP_RETRY_MAYFAIL	((__force gfp_t)___GFP_RETRY_MAYFAIL)
-#define __GFP_NOFAIL	((__force gfp_t)___GFP_NOFAIL)
-#define __GFP_NORETRY	((__force gfp_t)___GFP_NORETRY)
-
-/**
- * DOC: Action modifiers
- *
- * Action modifiers
- * ----------------
- *
- * %__GFP_NOWARN suppresses allocation failure reports.
- *
- * %__GFP_COMP address compound page metadata.
- *
- * %__GFP_ZERO returns a zeroed page on success.
- *
- * %__GFP_ZEROTAGS zeroes memory tags at allocation time if the memory itself
- * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that
- * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting
- * memory tags at the same time as zeroing memory has minimal additional
- * performace impact.
- *
- * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation.
- * Only effective in HW_TAGS mode.
- *
- * %__GFP_SKIP_KASAN_POISON makes KASAN skip poisoning on page deallocation.
- * Typically, used for userspace pages. Only effective in HW_TAGS mode.
- */
-#define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)
-#define __GFP_COMP	((__force gfp_t)___GFP_COMP)
-#define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)
-#define __GFP_ZEROTAGS	((__force gfp_t)___GFP_ZEROTAGS)
-#define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO)
-#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON)
-#define __GFP_SKIP_KASAN_POISON   ((__force gfp_t)___GFP_SKIP_KASAN_POISON)
-
-/* Disable lockdep for GFP context tracking */
-#define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
-
-/* Room for N __GFP_FOO bits */
-#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP))
-#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
-
-/**
- * DOC: Useful GFP flag combinations
- *
- * Useful GFP flag combinations
- * ----------------------------
- *
- * Useful GFP flag combinations that are commonly used. It is recommended
- * that subsystems start with one of these combinations and then set/clear
- * %__GFP_FOO flags as necessary.
- *
- * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower
- * watermark is applied to allow access to "atomic reserves".
- * The current implementation doesn't support NMI and few other strict
- * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT.
- *
- * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires
- * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim.
- *
- * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is
- * accounted to kmemcg.
- *
- * %GFP_NOWAIT is for kernel allocations that should not stall for direct
- * reclaim, start physical IO or use any filesystem callback.
- *
- * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages
- * that do not require the starting of any physical IO.
- * Please try to avoid using this flag directly and instead use
- * memalloc_noio_{save,restore} to mark the whole scope which cannot
- * perform any IO with a short explanation why. All allocation requests
- * will inherit GFP_NOIO implicitly.
- *
- * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces.
- * Please try to avoid using this flag directly and instead use
- * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't
- * recurse into the FS layer with a short explanation why. All allocation
- * requests will inherit GFP_NOFS implicitly.
- *
- * %GFP_USER is for userspace allocations that also need to be directly
- * accessibly by the kernel or hardware. It is typically used by hardware
- * for buffers that are mapped to userspace (e.g. graphics) that hardware
- * still must DMA to. cpuset limits are enforced for these allocations.
- *
- * %GFP_DMA exists for historical reasons and should be avoided where possible.
- * The flags indicates that the caller requires that the lowest zone be
- * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but
- * it would require careful auditing as some users really require it and
- * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the
- * lowest zone as a type of emergency reserve.
- *
- * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit
- * address. Note that kmalloc(..., GFP_DMA32) does not return DMA32 memory
- * because the DMA32 kmalloc cache array is not implemented.
- * (Reason: there is no such user in kernel).
- *
- * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace,
- * do not need to be directly accessible by the kernel but that cannot
- * move once in use. An example may be a hardware allocation that maps
- * data directly into userspace but has no addressing limitations.
- *
- * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not
- * need direct access to but can use kmap() when access is required. They
- * are expected to be movable via page reclaim or page migration. Typically,
- * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE.
- *
- * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They
- * are compound allocations that will generally fail quickly if memory is not
- * available and will not wake kswapd/kcompactd on failure. The _LIGHT
- * version does not attempt reclaim/compaction at all and is by default used
- * in page fault path, while the non-light is used by khugepaged.
- */
-#define GFP_ATOMIC	(__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
-#define GFP_KERNEL	(__GFP_RECLAIM | __GFP_IO | __GFP_FS)
-#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT)
-#define GFP_NOWAIT	(__GFP_KSWAPD_RECLAIM)
-#define GFP_NOIO	(__GFP_RECLAIM)
-#define GFP_NOFS	(__GFP_RECLAIM | __GFP_IO)
-#define GFP_USER	(__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
-#define GFP_DMA		__GFP_DMA
-#define GFP_DMA32	__GFP_DMA32
-#define GFP_HIGHUSER	(GFP_USER | __GFP_HIGHMEM)
-#define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE | \
-			 __GFP_SKIP_KASAN_POISON | __GFP_SKIP_KASAN_UNPOISON)
-#define GFP_TRANSHUGE_LIGHT	((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
-			 __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM)
-#define GFP_TRANSHUGE	(GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM)
-
 /* Convert GFP flags to their corresponding migrate type */
 #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
 #define GFP_MOVABLE_SHIFT 3
diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h
new file mode 100644
index 000000000000..d88c46ca82e1
--- /dev/null
+++ b/include/linux/gfp_types.h
@@ -0,0 +1,348 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_GFP_TYPES_H
+#define __LINUX_GFP_TYPES_H
+
+/* The typedef is in types.h but we want the documentation here */
+#if 0
+/**
+ * typedef gfp_t - Memory allocation flags.
+ *
+ * GFP flags are commonly used throughout Linux to indicate how memory
+ * should be allocated.  The GFP acronym stands for get_free_pages(),
+ * the underlying memory allocation function.  Not every GFP flag is
+ * supported by every function which may allocate memory.  Most users
+ * will want to use a plain ``GFP_KERNEL``.
+ */
+typedef unsigned int __bitwise gfp_t;
+#endif
+
+/*
+ * In case of changes, please don't forget to update
+ * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c
+ */
+
+/* Plain integer GFP bitmasks. Do not use this directly. */
+#define ___GFP_DMA		0x01u
+#define ___GFP_HIGHMEM		0x02u
+#define ___GFP_DMA32		0x04u
+#define ___GFP_MOVABLE		0x08u
+#define ___GFP_RECLAIMABLE	0x10u
+#define ___GFP_HIGH		0x20u
+#define ___GFP_IO		0x40u
+#define ___GFP_FS		0x80u
+#define ___GFP_ZERO		0x100u
+#define ___GFP_ATOMIC		0x200u
+#define ___GFP_DIRECT_RECLAIM	0x400u
+#define ___GFP_KSWAPD_RECLAIM	0x800u
+#define ___GFP_WRITE		0x1000u
+#define ___GFP_NOWARN		0x2000u
+#define ___GFP_RETRY_MAYFAIL	0x4000u
+#define ___GFP_NOFAIL		0x8000u
+#define ___GFP_NORETRY		0x10000u
+#define ___GFP_MEMALLOC		0x20000u
+#define ___GFP_COMP		0x40000u
+#define ___GFP_NOMEMALLOC	0x80000u
+#define ___GFP_HARDWALL		0x100000u
+#define ___GFP_THISNODE		0x200000u
+#define ___GFP_ACCOUNT		0x400000u
+#define ___GFP_ZEROTAGS		0x800000u
+#ifdef CONFIG_KASAN_HW_TAGS
+#define ___GFP_SKIP_ZERO		0x1000000u
+#define ___GFP_SKIP_KASAN_UNPOISON	0x2000000u
+#define ___GFP_SKIP_KASAN_POISON	0x4000000u
+#else
+#define ___GFP_SKIP_ZERO		0
+#define ___GFP_SKIP_KASAN_UNPOISON	0
+#define ___GFP_SKIP_KASAN_POISON	0
+#endif
+#ifdef CONFIG_LOCKDEP
+#define ___GFP_NOLOCKDEP	0x8000000u
+#else
+#define ___GFP_NOLOCKDEP	0
+#endif
+/* If the above are modified, __GFP_BITS_SHIFT may need updating */
+
+/*
+ * Physical address zone modifiers (see linux/mmzone.h - low four bits)
+ *
+ * Do not put any conditional on these. If necessary modify the definitions
+ * without the underscores and use them consistently. The definitions here may
+ * be used in bit comparisons.
+ */
+#define __GFP_DMA	((__force gfp_t)___GFP_DMA)
+#define __GFP_HIGHMEM	((__force gfp_t)___GFP_HIGHMEM)
+#define __GFP_DMA32	((__force gfp_t)___GFP_DMA32)
+#define __GFP_MOVABLE	((__force gfp_t)___GFP_MOVABLE)  /* ZONE_MOVABLE allowed */
+#define GFP_ZONEMASK	(__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)
+
+/**
+ * DOC: Page mobility and placement hints
+ *
+ * Page mobility and placement hints
+ * ---------------------------------
+ *
+ * These flags provide hints about how mobile the page is. Pages with similar
+ * mobility are placed within the same pageblocks to minimise problems due
+ * to external fragmentation.
+ *
+ * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be
+ * moved by page migration during memory compaction or can be reclaimed.
+ *
+ * %__GFP_RECLAIMABLE is used for slab allocations that specify
+ * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers.
+ *
+ * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible,
+ * these pages will be spread between local zones to avoid all the dirty
+ * pages being in one zone (fair zone allocation policy).
+ *
+ * %__GFP_HARDWALL enforces the cpuset memory allocation policy.
+ *
+ * %__GFP_THISNODE forces the allocation to be satisfied from the requested
+ * node with no fallbacks or placement policy enforcements.
+ *
+ * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
+ */
+#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
+#define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)
+#define __GFP_HARDWALL   ((__force gfp_t)___GFP_HARDWALL)
+#define __GFP_THISNODE	((__force gfp_t)___GFP_THISNODE)
+#define __GFP_ACCOUNT	((__force gfp_t)___GFP_ACCOUNT)
+
+/**
+ * DOC: Watermark modifiers
+ *
+ * Watermark modifiers -- controls access to emergency reserves
+ * ------------------------------------------------------------
+ *
+ * %__GFP_HIGH indicates that the caller is high-priority and that granting
+ * the request is necessary before the system can make forward progress.
+ * For example, creating an IO context to clean pages.
+ *
+ * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is
+ * high priority. Users are typically interrupt handlers. This may be
+ * used in conjunction with %__GFP_HIGH
+ *
+ * %__GFP_MEMALLOC allows access to all memory. This should only be used when
+ * the caller guarantees the allocation will allow more memory to be freed
+ * very shortly e.g. process exiting or swapping. Users either should
+ * be the MM or co-ordinating closely with the VM (e.g. swap over NFS).
+ * Users of this flag have to be extremely careful to not deplete the reserve
+ * completely and implement a throttling mechanism which controls the
+ * consumption of the reserve based on the amount of freed memory.
+ * Usage of a pre-allocated pool (e.g. mempool) should be always considered
+ * before using this flag.
+ *
+ * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves.
+ * This takes precedence over the %__GFP_MEMALLOC flag if both are set.
+ */
+#define __GFP_ATOMIC	((__force gfp_t)___GFP_ATOMIC)
+#define __GFP_HIGH	((__force gfp_t)___GFP_HIGH)
+#define __GFP_MEMALLOC	((__force gfp_t)___GFP_MEMALLOC)
+#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC)
+
+/**
+ * DOC: Reclaim modifiers
+ *
+ * Reclaim modifiers
+ * -----------------
+ * Please note that all the following flags are only applicable to sleepable
+ * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them).
+ *
+ * %__GFP_IO can start physical IO.
+ *
+ * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the
+ * allocator recursing into the filesystem which might already be holding
+ * locks.
+ *
+ * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim.
+ * This flag can be cleared to avoid unnecessary delays when a fallback
+ * option is available.
+ *
+ * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when
+ * the low watermark is reached and have it reclaim pages until the high
+ * watermark is reached. A caller may wish to clear this flag when fallback
+ * options are available and the reclaim is likely to disrupt the system. The
+ * canonical example is THP allocation where a fallback is cheap but
+ * reclaim/compaction may cause indirect stalls.
+ *
+ * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
+ *
+ * The default allocator behavior depends on the request size. We have a concept
+ * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER).
+ * !costly allocations are too essential to fail so they are implicitly
+ * non-failing by default (with some exceptions like OOM victims might fail so
+ * the caller still has to check for failures) while costly requests try to be
+ * not disruptive and back off even without invoking the OOM killer.
+ * The following three modifiers might be used to override some of these
+ * implicit rules
+ *
+ * %__GFP_NORETRY: The VM implementation will try only very lightweight
+ * memory direct reclaim to get some memory under memory pressure (thus
+ * it can sleep). It will avoid disruptive actions like OOM killer. The
+ * caller must handle the failure which is quite likely to happen under
+ * heavy memory pressure. The flag is suitable when failure can easily be
+ * handled at small cost, such as reduced throughput
+ *
+ * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim
+ * procedures that have previously failed if there is some indication
+ * that progress has been made else where.  It can wait for other
+ * tasks to attempt high level approaches to freeing memory such as
+ * compaction (which removes fragmentation) and page-out.
+ * There is still a definite limit to the number of retries, but it is
+ * a larger limit than with %__GFP_NORETRY.
+ * Allocations with this flag may fail, but only when there is
+ * genuinely little unused memory. While these allocations do not
+ * directly trigger the OOM killer, their failure indicates that
+ * the system is likely to need to use the OOM killer soon.  The
+ * caller must handle failure, but can reasonably do so by failing
+ * a higher-level request, or completing it only in a much less
+ * efficient manner.
+ * If the allocation does fail, and the caller is in a position to
+ * free some non-essential memory, doing so could benefit the system
+ * as a whole.
+ *
+ * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
+ * cannot handle allocation failures. The allocation could block
+ * indefinitely but will never return with failure. Testing for
+ * failure is pointless.
+ * New users should be evaluated carefully (and the flag should be
+ * used only when there is no reasonable failure policy) but it is
+ * definitely preferable to use the flag rather than opencode endless
+ * loop around allocator.
+ * Using this flag for costly allocations is _highly_ discouraged.
+ */
+#define __GFP_IO	((__force gfp_t)___GFP_IO)
+#define __GFP_FS	((__force gfp_t)___GFP_FS)
+#define __GFP_DIRECT_RECLAIM	((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */
+#define __GFP_KSWAPD_RECLAIM	((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */
+#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
+#define __GFP_RETRY_MAYFAIL	((__force gfp_t)___GFP_RETRY_MAYFAIL)
+#define __GFP_NOFAIL	((__force gfp_t)___GFP_NOFAIL)
+#define __GFP_NORETRY	((__force gfp_t)___GFP_NORETRY)
+
+/**
+ * DOC: Action modifiers
+ *
+ * Action modifiers
+ * ----------------
+ *
+ * %__GFP_NOWARN suppresses allocation failure reports.
+ *
+ * %__GFP_COMP address compound page metadata.
+ *
+ * %__GFP_ZERO returns a zeroed page on success.
+ *
+ * %__GFP_ZEROTAGS zeroes memory tags at allocation time if the memory itself
+ * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that
+ * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting
+ * memory tags at the same time as zeroing memory has minimal additional
+ * performace impact.
+ *
+ * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation.
+ * Only effective in HW_TAGS mode.
+ *
+ * %__GFP_SKIP_KASAN_POISON makes KASAN skip poisoning on page deallocation.
+ * Typically, used for userspace pages. Only effective in HW_TAGS mode.
+ */
+#define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)
+#define __GFP_COMP	((__force gfp_t)___GFP_COMP)
+#define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)
+#define __GFP_ZEROTAGS	((__force gfp_t)___GFP_ZEROTAGS)
+#define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO)
+#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON)
+#define __GFP_SKIP_KASAN_POISON   ((__force gfp_t)___GFP_SKIP_KASAN_POISON)
+
+/* Disable lockdep for GFP context tracking */
+#define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
+
+/* Room for N __GFP_FOO bits */
+#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP))
+#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
+
+/**
+ * DOC: Useful GFP flag combinations
+ *
+ * Useful GFP flag combinations
+ * ----------------------------
+ *
+ * Useful GFP flag combinations that are commonly used. It is recommended
+ * that subsystems start with one of these combinations and then set/clear
+ * %__GFP_FOO flags as necessary.
+ *
+ * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower
+ * watermark is applied to allow access to "atomic reserves".
+ * The current implementation doesn't support NMI and few other strict
+ * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT.
+ *
+ * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires
+ * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim.
+ *
+ * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is
+ * accounted to kmemcg.
+ *
+ * %GFP_NOWAIT is for kernel allocations that should not stall for direct
+ * reclaim, start physical IO or use any filesystem callback.
+ *
+ * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages
+ * that do not require the starting of any physical IO.
+ * Please try to avoid using this flag directly and instead use
+ * memalloc_noio_{save,restore} to mark the whole scope which cannot
+ * perform any IO with a short explanation why. All allocation requests
+ * will inherit GFP_NOIO implicitly.
+ *
+ * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces.
+ * Please try to avoid using this flag directly and instead use
+ * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't
+ * recurse into the FS layer with a short explanation why. All allocation
+ * requests will inherit GFP_NOFS implicitly.
+ *
+ * %GFP_USER is for userspace allocations that also need to be directly
+ * accessibly by the kernel or hardware. It is typically used by hardware
+ * for buffers that are mapped to userspace (e.g. graphics) that hardware
+ * still must DMA to. cpuset limits are enforced for these allocations.
+ *
+ * %GFP_DMA exists for historical reasons and should be avoided where possible.
+ * The flags indicates that the caller requires that the lowest zone be
+ * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but
+ * it would require careful auditing as some users really require it and
+ * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the
+ * lowest zone as a type of emergency reserve.
+ *
+ * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit
+ * address. Note that kmalloc(..., GFP_DMA32) does not return DMA32 memory
+ * because the DMA32 kmalloc cache array is not implemented.
+ * (Reason: there is no such user in kernel).
+ *
+ * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace,
+ * do not need to be directly accessible by the kernel but that cannot
+ * move once in use. An example may be a hardware allocation that maps
+ * data directly into userspace but has no addressing limitations.
+ *
+ * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not
+ * need direct access to but can use kmap() when access is required. They
+ * are expected to be movable via page reclaim or page migration. Typically,
+ * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE.
+ *
+ * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They
+ * are compound allocations that will generally fail quickly if memory is not
+ * available and will not wake kswapd/kcompactd on failure. The _LIGHT
+ * version does not attempt reclaim/compaction at all and is by default used
+ * in page fault path, while the non-light is used by khugepaged.
+ */
+#define GFP_ATOMIC	(__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
+#define GFP_KERNEL	(__GFP_RECLAIM | __GFP_IO | __GFP_FS)
+#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT)
+#define GFP_NOWAIT	(__GFP_KSWAPD_RECLAIM)
+#define GFP_NOIO	(__GFP_RECLAIM)
+#define GFP_NOFS	(__GFP_RECLAIM | __GFP_IO)
+#define GFP_USER	(__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
+#define GFP_DMA		__GFP_DMA
+#define GFP_DMA32	__GFP_DMA32
+#define GFP_HIGHUSER	(GFP_USER | __GFP_HIGHMEM)
+#define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE | \
+			 __GFP_SKIP_KASAN_POISON | __GFP_SKIP_KASAN_UNPOISON)
+#define GFP_TRANSHUGE_LIGHT	((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
+			 __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM)
+#define GFP_TRANSHUGE	(GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM)
+
+#endif /* __LINUX_GFP_TYPES_H */
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 0f233b76c9ce..4b71a96190a8 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -94,6 +94,7 @@
 #include <linux/bitmap.h>
 #include <linux/minmax.h>
 #include <linux/numa.h>
+#include <linux/random.h>
 
 typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;
 extern nodemask_t _unused_nodemask_arg_;
@@ -276,7 +277,14 @@ static inline unsigned int __next_node(int n, const nodemask_t *srcp)
  * the first node in src if needed.  Returns MAX_NUMNODES if src is empty.
  */
 #define next_node_in(n, src) __next_node_in((n), &(src))
-unsigned int __next_node_in(int node, const nodemask_t *srcp);
+static inline unsigned int __next_node_in(int node, const nodemask_t *srcp)
+{
+	unsigned int ret = __next_node(node, srcp);
+
+	if (ret == MAX_NUMNODES)
+		ret = __first_node(srcp);
+	return ret;
+}
 
 static inline void init_nodemask_of_node(nodemask_t *mask, int node)
 {
@@ -493,14 +501,20 @@ static inline int num_node_state(enum node_states state)
 
 #endif
 
+static inline int node_random(const nodemask_t *maskp)
+{
 #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1)
-extern int node_random(const nodemask_t *maskp);
+	int w, bit = NUMA_NO_NODE;
+
+	w = nodes_weight(*maskp);
+	if (w)
+		bit = bitmap_ord_to_pos(maskp->bits,
+			get_random_int() % w, MAX_NUMNODES);
+	return bit;
 #else
-static inline int node_random(const nodemask_t *mask)
-{
 	return 0;
-}
 #endif
+}
 
 #define node_online_map 	node_states[N_ONLINE]
 #define node_possible_map 	node_states[N_POSSIBLE]
diff --git a/lib/Makefile b/lib/Makefile
index 0eb8114600c1..90d02a0986e9 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -33,7 +33,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
-	 nmi_backtrace.o nodemask.o win_minmax.o memcat_p.o \
+	 nmi_backtrace.o win_minmax.o memcat_p.o \
 	 buildid.o
 
 lib-$(CONFIG_PRINTK) += dump_stack.o
diff --git a/lib/bitmap.c b/lib/bitmap.c
index b18e31ea6e66..2b67cd657692 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -237,7 +237,7 @@ void bitmap_cut(unsigned long *dst, const unsigned long *src,
 }
 EXPORT_SYMBOL(bitmap_cut);
 
-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 bits)
 {
 	unsigned int k;
@@ -275,7 +275,7 @@ void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
 }
 EXPORT_SYMBOL(__bitmap_xor);
 
-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 bits)
 {
 	unsigned int k;
@@ -333,10 +333,9 @@ bool __bitmap_subset(const unsigned long *bitmap1,
 }
 EXPORT_SYMBOL(__bitmap_subset);
 
-int __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
+unsigned long __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
 {
-	unsigned int k, lim = bits/BITS_PER_LONG;
-	int w = 0;
+	unsigned long k, w = 0, lim = bits/BITS_PER_LONG;
 
 	for (k = 0; k < lim; k++)
 		w += hweight_long(bitmap[k]);
@@ -1564,7 +1563,7 @@ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits)
 
 	/* Clear tail bits in the last element of array beyond nbits. */
 	if (nbits % 64)
-		buf[-1] &= GENMASK_ULL(nbits % 64, 0);
+		buf[-1] &= GENMASK_ULL((nbits - 1) % 64, 0);
 }
 EXPORT_SYMBOL(bitmap_to_arr64);
 #endif
diff --git a/lib/cpumask.c b/lib/cpumask.c
index a971a82d2f43..f0ae119be8c4 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -8,61 +8,6 @@
 #include <linux/numa.h>
 
 /**
- * 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.
- */
-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);
-}
-EXPORT_SYMBOL(cpumask_next);
-
-/**
- * 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.
- */
-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);
-}
-EXPORT_SYMBOL(cpumask_next_and);
-
-/**
- * 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.
- */
-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;
-}
-EXPORT_SYMBOL(cpumask_any_but);
-
-/**
  * cpumask_next_wrap - helper to implement for_each_cpu_wrap
  * @n: the cpu prior to the place to search
  * @mask: the cpumask pointer
@@ -74,9 +19,9 @@ EXPORT_SYMBOL(cpumask_any_but);
  * Note: the @wrap argument is required for the start condition when
  * we cannot assume @start is set in @mask.
  */
-int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
+unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
 {
-	int next;
+	unsigned int next;
 
 again:
 	next = cpumask_next(n, mask);
@@ -125,34 +70,6 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
 }
 EXPORT_SYMBOL(alloc_cpumask_var_node);
 
-bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
-{
-	return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
-}
-EXPORT_SYMBOL(zalloc_cpumask_var_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.
- */
-bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
-{
-	return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE);
-}
-EXPORT_SYMBOL(alloc_cpumask_var);
-
-bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
-{
-	return alloc_cpumask_var(mask, flags | __GFP_ZERO);
-}
-EXPORT_SYMBOL(zalloc_cpumask_var);
-
 /**
  * alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena.
  * @mask: pointer to cpumask_var_t where the cpumask is returned
@@ -205,7 +122,7 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
  */
 unsigned int cpumask_local_spread(unsigned int i, int node)
 {
-	int cpu;
+	unsigned int cpu;
 
 	/* Wrap: we always want a cpu. */
 	i %= num_online_cpus();
@@ -243,10 +160,10 @@ static DEFINE_PER_CPU(int, distribute_cpu_mask_prev);
  *
  * Returns >= nr_cpu_ids if the intersection is empty.
  */
-int cpumask_any_and_distribute(const struct cpumask *src1p,
+unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
 			       const struct cpumask *src2p)
 {
-	int next, prev;
+	unsigned int next, prev;
 
 	/* NOTE: our first selection will skip 0. */
 	prev = __this_cpu_read(distribute_cpu_mask_prev);
@@ -262,9 +179,9 @@ int cpumask_any_and_distribute(const struct cpumask *src1p,
 }
 EXPORT_SYMBOL(cpumask_any_and_distribute);
 
-int cpumask_any_distribute(const struct cpumask *srcp)
+unsigned int cpumask_any_distribute(const struct cpumask *srcp)
 {
-	int next, prev;
+	unsigned int next, prev;
 
 	/* NOTE: our first selection will skip 0. */
 	prev = __this_cpu_read(distribute_cpu_mask_prev);
diff --git a/lib/nodemask.c b/lib/nodemask.c
index e22647f5181b..b8a433d16b51 100644
--- a/lib/nodemask.c
+++ b/lib/nodemask.c
@@ -3,14 +3,6 @@
 #include <linux/module.h>
 #include <linux/random.h>
 
-unsigned int __next_node_in(int node, const nodemask_t *srcp)
-{
-	unsigned int ret = __next_node(node, srcp);
-
-	if (ret == MAX_NUMNODES)
-		ret = __first_node(srcp);
-	return ret;
-}
 EXPORT_SYMBOL(__next_node_in);
 
 #ifdef CONFIG_NUMA
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index d5923a640457..98754ff9fe68 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -604,6 +604,12 @@ static void __init test_bitmap_arr64(void)
 			pr_err("bitmap_copy_arr64(nbits == %d:"
 				" tail is not safely cleared: %d\n", nbits, next_bit);
 
+		if ((nbits % 64) &&
+		    (arr[(nbits - 1) / 64] & ~GENMASK_ULL((nbits - 1) % 64, 0)))
+			pr_err("bitmap_to_arr64(nbits == %d): tail is not safely cleared: 0x%016llx (must be 0x%016llx)\n",
+			       nbits, arr[(nbits - 1) / 64],
+			       GENMASK_ULL((nbits - 1) % 64, 0));
+
 		if (nbits < EXP1_IN_BITS - 64)
 			expect_eq_uint(arr[DIV_ROUND_UP(nbits, 64)], 0xa5a5a5a5);
 	}
@@ -869,6 +875,67 @@ static void __init test_bitmap_print_buf(void)
 	}
 }
 
+static void __init test_bitmap_const_eval(void)
+{
+	DECLARE_BITMAP(bitmap, BITS_PER_LONG);
+	unsigned long initvar = BIT(2);
+	unsigned long bitopvar = 0;
+	unsigned long var = 0;
+	int res;
+
+	/*
+	 * Compilers must be able to optimize all of those to compile-time
+	 * constants on any supported optimization level (-O2, -Os) and any
+	 * architecture. Otherwise, trigger a build bug.
+	 * The whole function gets optimized out then, there's nothing to do
+	 * in runtime.
+	 */
+
+	/*
+	 * Equals to `unsigned long bitmap[1] = { GENMASK(6, 5), }`.
+	 * Clang on s390 optimizes bitops at compile-time as intended, but at
+	 * the same time stops treating @bitmap and @bitopvar as compile-time
+	 * constants after regular test_bit() is executed, thus triggering the
+	 * build bugs below. So, call const_test_bit() there directly until
+	 * the compiler is fixed.
+	 */
+	bitmap_clear(bitmap, 0, BITS_PER_LONG);
+#if defined(__s390__) && defined(__clang__)
+	if (!const_test_bit(7, bitmap))
+#else
+	if (!test_bit(7, bitmap))
+#endif
+		bitmap_set(bitmap, 5, 2);
+
+	/* Equals to `unsigned long bitopvar = BIT(20)` */
+	__change_bit(31, &bitopvar);
+	bitmap_shift_right(&bitopvar, &bitopvar, 11, BITS_PER_LONG);
+
+	/* Equals to `unsigned long var = BIT(25)` */
+	var |= BIT(25);
+	if (var & BIT(0))
+		var ^= GENMASK(9, 6);
+
+	/* __const_hweight<32|64>(GENMASK(6, 5)) == 2 */
+	res = bitmap_weight(bitmap, 20);
+	BUILD_BUG_ON(!__builtin_constant_p(res));
+	BUILD_BUG_ON(res != 2);
+
+	/* !(BIT(31) & BIT(18)) == 1 */
+	res = !test_bit(18, &bitopvar);
+	BUILD_BUG_ON(!__builtin_constant_p(res));
+	BUILD_BUG_ON(!res);
+
+	/* BIT(2) & GENMASK(14, 8) == 0 */
+	res = initvar & GENMASK(14, 8);
+	BUILD_BUG_ON(!__builtin_constant_p(res));
+	BUILD_BUG_ON(res);
+
+	/* ~BIT(25) */
+	BUILD_BUG_ON(!__builtin_constant_p(~var));
+	BUILD_BUG_ON(~var != ~BIT(25));
+}
+
 static void __init selftest(void)
 {
 	test_zero_clear();
@@ -884,6 +951,7 @@ static void __init selftest(void)
 	test_for_each_set_clump8();
 	test_bitmap_cut();
 	test_bitmap_print_buf();
+	test_bitmap_const_eval();
 }
 
 KSTM_MODULE_LOADERS(test_bitmap);
diff --git a/tools/include/asm-generic/bitops/non-atomic.h b/tools/include/asm-generic/bitops/non-atomic.h
index 7e10c4b50c5d..0c472a833408 100644
--- a/tools/include/asm-generic/bitops/non-atomic.h
+++ b/tools/include/asm-generic/bitops/non-atomic.h
@@ -2,10 +2,10 @@
 #ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
-#include <asm/types.h>
+#include <linux/bits.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
  *
@@ -13,7 +13,8 @@
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __set_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+___set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -21,7 +22,8 @@ static inline void __set_bit(int nr, volatile unsigned long *addr)
 	*p  |= mask;
 }
 
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+___clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -30,7 +32,7 @@ static inline void __clear_bit(int nr, volatile unsigned long *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
  *
@@ -38,7 +40,8 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __change_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -47,7 +50,7 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
 }
 
 /**
- * __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
  *
@@ -55,7 +58,8 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+static __always_inline bool
+___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);
@@ -66,7 +70,7 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *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
  *
@@ -74,7 +78,8 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline bool
+___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);
@@ -85,8 +90,8 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
 }
 
 /* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr,
-					    volatile unsigned long *addr)
+static __always_inline bool
+___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);
@@ -97,11 +102,12 @@ static inline int __test_and_change_bit(int nr,
 }
 
 /**
- * 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 inline int test_bit(int nr, const volatile unsigned long *addr)
+static __always_inline bool
+_test_bit(unsigned long nr, const volatile unsigned long *addr)
 {
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index afdf93bebaaf..ae1852e39142 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -11,10 +11,10 @@
 #define DECLARE_BITMAP(name,bits) \
 	unsigned long name[BITS_TO_LONGS(bits)]
 
-int __bitmap_weight(const unsigned long *bitmap, int bits);
+unsigned long __bitmap_weight(const unsigned long *bitmap, unsigned int bits);
 void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, int bits);
-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 bits);
 bool __bitmap_equal(const unsigned long *bitmap1,
 		    const unsigned long *bitmap2, unsigned int bits);
@@ -45,7 +45,7 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 	dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits);
 }
 
-static inline int bitmap_empty(const unsigned long *src, unsigned nbits)
+static inline bool bitmap_empty(const unsigned long *src, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
@@ -53,7 +53,7 @@ static inline int bitmap_empty(const unsigned long *src, unsigned nbits)
 	return find_first_bit(src, nbits) == nbits;
 }
 
-static inline int bitmap_full(const unsigned long *src, unsigned int nbits)
+static inline bool bitmap_full(const unsigned long *src, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
@@ -61,7 +61,7 @@ static inline int bitmap_full(const unsigned long *src, unsigned int nbits)
 	return find_first_zero_bit(src, nbits) == nbits;
 }
 
-static inline int bitmap_weight(const unsigned long *src, unsigned int nbits)
+static inline unsigned long bitmap_weight(const unsigned long *src, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
@@ -146,7 +146,7 @@ size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits,
  * @src2: operand 2
  * @nbits: size of bitmap
  */
-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))
diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
index 5fca38fe1ba8..f18683b95ea6 100644
--- a/tools/include/linux/bitops.h
+++ b/tools/include/linux/bitops.h
@@ -26,6 +26,22 @@ 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.
+ */
+
+#define bitop(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
  *
diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c
index 354f8cdc0880..e1fafc131a49 100644
--- a/tools/lib/bitmap.c
+++ b/tools/lib/bitmap.c
@@ -5,9 +5,9 @@
  */
 #include <linux/bitmap.h>
 
-int __bitmap_weight(const unsigned long *bitmap, int bits)
+unsigned long __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
 {
-	int k, w = 0, lim = bits/BITS_PER_LONG;
+	unsigned long k, w = 0, lim = bits/BITS_PER_LONG;
 
 	for (k = 0; k < lim; k++)
 		w += hweight_long(bitmap[k]);
@@ -57,7 +57,7 @@ size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits,
 	return ret;
 }
 
-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 bits)
 {
 	unsigned int k;