[PATCH v2 5/9] atomic,x86: Implement atomic_dec_and_test_overflow()

[Peter Zijlstra <peterz@infradead.org>]

Provide a better implementation of atomic_{dec,dec_and_test}_overflow() by
making use of the atomic-op condition codes.

This further improves the fast path code:

    a980:       b8 ff ff ff ff          mov    $0xffffffff,%eax
    a985:       f0 0f c1 07             lock xadd %eax,(%rdi)
    a989:       83 e8 01                sub    $0x1,%eax
    a98c:       78 20                   js     a9ae <ring_buffer_put+0x2e>
    a98e:       74 01                   je     a991 <ring_buffer_put+0x11>
    a990:       c3                      ret

to:

    a950:       f0 ff 0f                lock decl (%rdi)
    a953:       7c 20                   jl     a975 <ring_buffer_put+0x25>
    a955:       74 01                   je     a958 <ring_buffer_put+0x8>
    a957:       c3                      ret

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/include/asm/atomic.h |   23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -263,6 +263,29 @@ static __always_inline int arch_atomic_f
 }
 #define arch_atomic_fetch_xor arch_atomic_fetch_xor
 
+#define arch_atomic_dec_overflow(_v, _label)				\
+	asm_volatile_goto(LOCK_PREFIX "decl %[var]\n\t"			\
+			  "jle %l1"					\
+			  : : [var] "m" ((_v)->counter)			\
+			  : "memory"					\
+			  : _label)
+
+#define arch_atomic_dec_and_test_overflow(_v, _label)			\
+({									\
+	__label__ __zero;						\
+	__label__ __out;						\
+	bool __ret = false;						\
+	asm_volatile_goto(LOCK_PREFIX "decl %[var]\n\t"			\
+			  "jl %l2\n\t"					\
+			  "je %l[__zero]"				\
+			  : : [var] "m" ((_v)->counter)			\
+			  : "memory"					\
+			  : __zero, _label);				\
+	goto __out;							\
+__zero:	__ret = true;							\
+__out:	__ret;								\
+})
+
 #ifdef CONFIG_X86_32
 # include <asm/atomic64_32.h>
 #else