x86, generic: mark complex bitops.h inlines as __always_inline

Impact: reduce kernel image size

Hugh Dickins noticed that older gcc versions when the kernel
is built for code size didn't inline some of the bitops.

Mark all complex x86 bitops that have more than a single
asm statement or two as always inline to avoid this problem.

Probably should be done for other architectures too.

Ingo then found a better fix that only requires
a single line change, but it unfortunately only
works on gcc 4.3.

On older gccs the original patch still makes a ~0.3% defconfig
difference with CONFIG_OPTIMIZE_INLINING=y.

With gcc 4.1 and a defconfig like build:

    6116998 1138540  883788 8139326  7c323e vmlinux-oi-with-patch
    6137043 1138540  883788 8159371  7c808b vmlinux-optimize-inlining

~20k / 0.3% difference.
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

arch/x86/include/asm/bitops.h

@@ -3,6 +3,9 @@
 
 /*
  * Copyright 1992, Linus Torvalds.
+ *
+ * Note: inlines with more than a single statement should be marked
+ * __always_inline to avoid problems with older gcc's inlining heuristics.
  */
 
 #ifndef _LINUX_BITOPS_H
@@ -53,7 +56,8 @@
  * 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(unsigned int nr, volatile unsigned long *addr)
+static __always_inline void
+set_bit(unsigned int nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "orb %1,%0"
@@ -90,7 +94,8 @@ static inline void __set_bit(int nr, volatile unsigned long *addr)
  * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
  * in order to ensure changes are visible on other processors.
  */
-static inline void clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+clear_bit(int nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "andb %1,%0"
@@ -204,7 +209,8 @@ static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
  *
  * This is the same as test_and_set_bit on x86.
  */
-static inline int test_and_set_bit_lock(int nr, volatile unsigned long *addr)
+static __always_inline int
+test_and_set_bit_lock(int nr, volatile unsigned long *addr)
 {
 	return test_and_set_bit(nr, addr);
 }
@@ -300,7 +306,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 	return oldbit;
 }
 
-static inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
+static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
 {
 	return ((1UL << (nr % BITS_PER_LONG)) &
 		(((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;

include/asm-generic/bitops/__ffs.h

@@ -9,7 +9,7 @@
  *
  * Undefined if no bit exists, so code should check against 0 first.
  */
-static inline unsigned long __ffs(unsigned long word)
+static __always_inline unsigned long __ffs(unsigned long word)
 {
 	int num = 0;
 

include/asm-generic/bitops/__fls.h

@@ -9,7 +9,7 @@
  *
  * Undefined if no set bit exists, so code should check against 0 first.
  */
-static inline unsigned long __fls(unsigned long word)
+static __always_inline unsigned long __fls(unsigned long word)
 {
 	int num = BITS_PER_LONG - 1;
 

include/asm-generic/bitops/fls.h

@@ -9,7 +9,7 @@
  * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
  */
 
-static inline int fls(int x)
+static __always_inline int fls(int x)
 {
 	int r = 32;
 

include/asm-generic/bitops/fls64.h

@@ -15,7 +15,7 @@
  * at position 64.
  */
 #if BITS_PER_LONG == 32
-static inline int fls64(__u64 x)
+static __always_inline int fls64(__u64 x)
 {
 	__u32 h = x >> 32;
 	if (h)
@@ -23,7 +23,7 @@ static inline int fls64(__u64 x)
 	return fls(x);
 }
 #elif BITS_PER_LONG == 64
-static inline int fls64(__u64 x)
+static __always_inline int fls64(__u64 x)
 {
 	if (x == 0)
 		return 0;