asm-generic/bitops: Always inline all bit manipulation helpers

Make it consistent with the atomic/atomic-instrumented.h helpers.

And defconfig size is actually going down!

     text    data     bss     dec     hex filename
  22352096        8213152 1917164 32482412        1efa46c vmlinux.x86-64.defconfig.before
  22350551        8213184 1917164 32480899        1ef9e83 vmlinux.x86-64.defconfig.after
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Marco Elver <elver@google.com>
Link: https://lore.kernel.org/r/20220113155357.4706-2-bp@alien8.de

include/asm-generic/bitops/instrumented-atomic.h

@@ -23,7 +23,7 @@
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void set_bit(long nr, volatile unsigned long *addr)
+static __always_inline void set_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
 	arch_set_bit(nr, addr);
@@ -36,7 +36,7 @@ static inline void set_bit(long nr, volatile unsigned long *addr)
  *
  * This is a relaxed atomic operation (no implied memory barriers).
  */
-static inline void clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline void clear_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
 	arch_clear_bit(nr, addr);
@@ -52,7 +52,7 @@ static inline void clear_bit(long nr, volatile unsigned long *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void change_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
 	arch_change_bit(nr, addr);
@@ -65,7 +65,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr)
  *
  * This is an atomic fully-ordered operation (implied full memory barrier).
  */
-static inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
@@ -79,7 +79,7 @@ static inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
  *
  * This is an atomic fully-ordered operation (implied full memory barrier).
  */
-static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
@@ -93,7 +93,7 @@ static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
  *
  * This is an atomic fully-ordered operation (implied full memory barrier).
  */
-static inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));

include/asm-generic/bitops/instrumented-non-atomic.h

@@ -22,7 +22,7 @@
  * region of memory concurrently, the effect may be that only one operation
  * succeeds.
  */
-static inline void __set_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_write(addr + BIT_WORD(nr), sizeof(long));
 	arch___set_bit(nr, addr);
@@ -37,7 +37,7 @@ static inline void __set_bit(long nr, volatile unsigned long *addr)
  * region of memory concurrently, the effect may be that only one operation
  * succeeds.
  */
-static inline void __clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_write(addr + BIT_WORD(nr), sizeof(long));
 	arch___clear_bit(nr, addr);
@@ -52,13 +52,13 @@ static inline void __clear_bit(long nr, volatile unsigned long *addr)
  * region of memory concurrently, the effect may be that only one operation
  * succeeds.
  */
-static inline void __change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_write(addr + BIT_WORD(nr), sizeof(long));
 	arch___change_bit(nr, addr);
 }
 
-static inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr)
+static __always_inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr)
 {
 	if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) {
 		/*
@@ -90,7 +90,7 @@ static inline void __instrument_read_write_bitop(long nr, volatile unsigned long
  * This operation is non-atomic. If two instances of this operation race, one
  * can appear to succeed but actually fail.
  */
-static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_set_bit(nr, addr);
@@ -104,7 +104,7 @@ static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
  * This operation is non-atomic. If two instances of this operation race, one
  * can appear to succeed but actually fail.
  */
-static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_clear_bit(nr, addr);
@@ -118,7 +118,7 @@ static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
  * This operation is non-atomic. If two instances of this operation race, one
  * can appear to succeed but actually fail.
  */
-static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_change_bit(nr, addr);
@@ -129,7 +129,7 @@ static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
  * @nr: bit number to test
  * @addr: Address to start counting from
  */
-static inline bool test_bit(long nr, const volatile unsigned long *addr)
+static __always_inline bool test_bit(long nr, const volatile unsigned long *addr)
 {
 	instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long));
 	return arch_test_bit(nr, addr);