x86/asm: Always inline atomics

During some code analysis I realized that atomic_add(), atomic_sub()
and friends are not necessarily inlined AND that each function
is defined multiple times:

	atomic_inc:          544 duplicates
	atomic_dec:          215 duplicates
	atomic_dec_and_test: 107 duplicates
	atomic64_inc:         38 duplicates
	[...]

Each definition is exact equally, e.g.:

	ffffffff813171b8 <atomic_add>:
	55         push   %rbp
	48 89 e5   mov    %rsp,%rbp
	f0 01 3e   lock add %edi,(%rsi)
	5d         pop    %rbp
	c3         retq

In turn each definition has one or more callsites (sure):

	ffffffff81317c78: e8 3b f5 ff ff  callq  ffffffff813171b8 <atomic_add> [...]
	ffffffff8131a062: e8 51 d1 ff ff  callq  ffffffff813171b8 <atomic_add> [...]
	ffffffff8131a190: e8 23 d0 ff ff  callq  ffffffff813171b8 <atomic_add> [...]

The other way around would be to remove the static linkage - but
I prefer an enforced inlining here.

	Before:
	  text     data	  bss      dec       hex     filename
	  81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig

	After:
	  text     data     bss      dec       hex     filename
	  81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined

Yes, the inlining here makes the kernel even smaller! ;)

Linus further observed:

	"I have this memory of having seen that before - the size
	 heuristics for gcc getting confused by inlining.
	 [...]

	 It might be a good idea to mark things that are basically just
	 wrappers around a single (or a couple of) asm instruction to be
	 always_inline."

Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 5e5cd123fdfbc2b0fe90cabc5d27948d3ded267a..75a9ee8529f3828e24f292305b4d81fe5524b8ce 100644 (file)
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -46,7 +46,7 @@ static inline void atomic_set(atomic_t *v, int i)
  *
  * Atomically adds @i to @v.
  */
-static inline void atomic_add(int i, atomic_t *v)
+static __always_inline void atomic_add(int i, atomic_t *v)
 {
        asm volatile(LOCK_PREFIX "addl %1,%0"
                     : "+m" (v->counter)
@@ -60,7 +60,7 @@ static inline void atomic_add(int i, atomic_t *v)
  *
  * Atomically subtracts @i from @v.
  */
-static inline void atomic_sub(int i, atomic_t *v)
+static __always_inline void atomic_sub(int i, atomic_t *v)
 {
        asm volatile(LOCK_PREFIX "subl %1,%0"
                     : "+m" (v->counter)
@@ -76,7 +76,7 @@ static inline void atomic_sub(int i, atomic_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic_sub_and_test(int i, atomic_t *v)
+static __always_inline int atomic_sub_and_test(int i, atomic_t *v)
 {
        GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e");
 }
@@ -87,7 +87,7 @@ static inline int atomic_sub_and_test(int i, atomic_t *v)
  *
  * Atomically increments @v by 1.
  */
-static inline void atomic_inc(atomic_t *v)
+static __always_inline void atomic_inc(atomic_t *v)
 {
        asm volatile(LOCK_PREFIX "incl %0"
                     : "+m" (v->counter));
@@ -99,7 +99,7 @@ static inline void atomic_inc(atomic_t *v)
  *
  * Atomically decrements @v by 1.
  */
-static inline void atomic_dec(atomic_t *v)
+static __always_inline void atomic_dec(atomic_t *v)
 {
        asm volatile(LOCK_PREFIX "decl %0"
                     : "+m" (v->counter));
@@ -113,7 +113,7 @@ static inline void atomic_dec(atomic_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static inline int atomic_dec_and_test(atomic_t *v)
+static __always_inline int atomic_dec_and_test(atomic_t *v)
 {
        GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
 }
@@ -152,7 +152,7 @@ static inline int atomic_add_negative(int i, atomic_t *v)
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static inline int atomic_add_return(int i, atomic_t *v)
+static __always_inline int atomic_add_return(int i, atomic_t *v)
 {
        return i + xadd(&v->counter, i);
 }
@@ -191,7 +191,7 @@ static inline int atomic_xchg(atomic_t *v, int new)
  * Atomically adds @a to @v, so long as @v was not already @u.
  * Returns the old value of @v.
  */
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
        int c, old;
        c = atomic_read(v);

diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index f8d273e18516dedf885bbafb16224c189913e14f..b965f9e03f2a04b2291fc0b62d537b6d9416bdaf 100644 (file)
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -40,7 +40,7 @@ static inline void atomic64_set(atomic64_t *v, long i)
  *
  * Atomically adds @i to @v.
  */
-static inline void atomic64_add(long i, atomic64_t *v)
+static __always_inline void atomic64_add(long i, atomic64_t *v)
 {
        asm volatile(LOCK_PREFIX "addq %1,%0"
                     : "=m" (v->counter)
@@ -81,7 +81,7 @@ static inline int atomic64_sub_and_test(long i, atomic64_t *v)
  *
  * Atomically increments @v by 1.
  */
-static inline void atomic64_inc(atomic64_t *v)
+static __always_inline void atomic64_inc(atomic64_t *v)
 {
        asm volatile(LOCK_PREFIX "incq %0"
                     : "=m" (v->counter)
@@ -94,7 +94,7 @@ static inline void atomic64_inc(atomic64_t *v)
  *
  * Atomically decrements @v by 1.
  */
-static inline void atomic64_dec(atomic64_t *v)
+static __always_inline void atomic64_dec(atomic64_t *v)
 {
        asm volatile(LOCK_PREFIX "decq %0"
                     : "=m" (v->counter)
@@ -148,7 +148,7 @@ static inline int atomic64_add_negative(long i, atomic64_t *v)
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static inline long atomic64_add_return(long i, atomic64_t *v)
+static __always_inline long atomic64_add_return(long i, atomic64_t *v)
 {
        return i + xadd(&v->counter, i);
 }