x86: Force inlining of atomic ops

With both gcc 4.7.2 and 4.9.2, sometimes gcc mysteriously
doesn't inline very small functions we expect to be inlined:

$ nm --size-sort vmlinux | grep -iF ' t ' | uniq -c | grep -v '^
*1 ' | sort -rn     473 000000000000000b t spin_unlock_irqrestore
    449 000000000000005f t rcu_read_unlock
    355 0000000000000009 t atomic_inc                <== THIS
    353 000000000000006e t rcu_read_lock
    350 0000000000000075 t rcu_read_lock_sched_held
    291 000000000000000b t spin_unlock
    266 0000000000000019 t arch_local_irq_restore
    215 000000000000000b t spin_lock
    180 0000000000000011 t kzalloc
    165 0000000000000012 t list_add_tail
    161 0000000000000019 t arch_local_save_flags
    153 0000000000000016 t test_and_set_bit
    134 000000000000000b t spin_unlock_irq
    134 0000000000000009 t atomic_dec                <== THIS
    130 000000000000000b t spin_unlock_bh
    122 0000000000000010 t brelse
    120 0000000000000016 t test_and_clear_bit
    120 000000000000000b t spin_lock_irq
    119 000000000000001e t get_dma_ops
    117 0000000000000053 t cpumask_next
    116 0000000000000036 t kref_get
    114 000000000000001a t schedule_work
    106 000000000000000b t spin_lock_bh
    103 0000000000000019 t arch_local_irq_disable
...

Note sizes of marked functions. They are merely 9 bytes long!
Selecting function with 'atomic' in their names:

    355 0000000000000009 t atomic_inc
    134 0000000000000009 t atomic_dec
     98 0000000000000014 t atomic_dec_and_test
     31 000000000000000e t atomic_add_return
     27 000000000000000a t atomic64_inc
     26 000000000000002f t kmap_atomic
     24 0000000000000009 t atomic_add
     12 0000000000000009 t atomic_sub
     10 0000000000000021 t __atomic_add_unless
     10 000000000000000a t atomic64_add
      5 000000000000001f t __atomic_add_unless.constprop.7
      5 000000000000000a t atomic64_dec
      4 000000000000001f t __atomic_add_unless.constprop.18
      4 000000000000001f t __atomic_add_unless.constprop.12
      4 000000000000001f t __atomic_add_unless.constprop.10
      3 000000000000001f t __atomic_add_unless.constprop.13
      3 0000000000000011 t atomic64_add_return
      2 000000000000001f t __atomic_add_unless.constprop.9
      2 000000000000001f t __atomic_add_unless.constprop.8
      2 000000000000001f t __atomic_add_unless.constprop.6
      2 000000000000001f t __atomic_add_unless.constprop.5
      2 000000000000001f t __atomic_add_unless.constprop.3
      2 000000000000001f t __atomic_add_unless.constprop.22
      2 000000000000001f t __atomic_add_unless.constprop.14
      2 000000000000001f t __atomic_add_unless.constprop.11
      2 000000000000001e t atomic_dec_if_positive
      2 0000000000000014 t atomic_inc_and_test
      2 0000000000000011 t atomic_add_return.constprop.4
      2 0000000000000011 t atomic_add_return.constprop.17
      2 0000000000000011 t atomic_add_return.constprop.16
      2 000000000000000d t atomic_inc.constprop.4
      2 000000000000000c t atomic_cmpxchg

This patch fixes this for x86 atomic ops via
s/inline/__always_inline/. This decreases allyesconfig kernel by
about 25k:

    text     data      bss       dec     hex filename
82399481 22255416 20627456 125282353 777a831 vmlinux.before
82375570 22255544 20627456 125258570 7774b4a vmlinux

Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Drewry <wad@chromium.org>
Link: http://lkml.kernel.org/r/1431080762-17797-1-git-send-email-dvlasenk@redhat.com
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 75a9ee8..e916895 100644 (file)
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -22,7 +22,7 @@
  *
  * Atomically reads the value of @v.
  */
-static inline int atomic_read(const atomic_t *v)
+static __always_inline int atomic_read(const atomic_t *v)
 {
        return ACCESS_ONCE((v)->counter);
 }
@@ -34,7 +34,7 @@ static inline int atomic_read(const atomic_t *v)
  *
  * Atomically sets the value of @v to @i.
  */
-static inline void atomic_set(atomic_t *v, int i)
+static __always_inline void atomic_set(atomic_t *v, int i)
 {
        v->counter = i;
 }
@@ -126,7 +126,7 @@ static __always_inline int atomic_dec_and_test(atomic_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic_inc_and_test(atomic_t *v)
+static __always_inline int atomic_inc_and_test(atomic_t *v)
 {
        GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
 }
@@ -140,7 +140,7 @@ static inline int atomic_inc_and_test(atomic_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline int atomic_add_negative(int i, atomic_t *v)
+static __always_inline int atomic_add_negative(int i, atomic_t *v)
 {
        GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s");
 }
@@ -164,7 +164,7 @@ static __always_inline int atomic_add_return(int i, atomic_t *v)
  *
  * Atomically subtracts @i from @v and returns @v - @i
  */
-static inline int atomic_sub_return(int i, atomic_t *v)
+static __always_inline int atomic_sub_return(int i, atomic_t *v)
 {
        return atomic_add_return(-i, v);
 }
@@ -172,7 +172,7 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 #define atomic_inc_return(v)  (atomic_add_return(1, v))
 #define atomic_dec_return(v)  (atomic_sub_return(1, v))
 
-static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
        return cmpxchg(&v->counter, old, new);
 }
@@ -213,7 +213,7 @@ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
  * Atomically adds 1 to @v
  * Returns the new value of @u
  */
-static inline short int atomic_inc_short(short int *v)
+static __always_inline short int atomic_inc_short(short int *v)
 {
        asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
        return *v;