x86: Use asm goto to implement better modify_and_test() functions

Linus suggested using asm goto to get rid of the typical SETcc + TEST
instruction pair -- which also clobbers an extra register -- for our
typical modify_and_test() functions.

Because asm goto doesn't allow output fields it has to include an
unconditinal memory clobber when it changes a memory variable to force
a reload.

Luckily all atomic ops already imply a compiler barrier to go along
with their memory barrier semantics.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-0mtn9siwbeo1d33bap1422se@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/atomic.h

@@ -6,6 +6,7 @@
 #include <asm/processor.h>
 #include <asm/alternative.h>
 #include <asm/cmpxchg.h>
+#include <asm/rmwcc.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
@@ -76,12 +77,7 @@ static inline void atomic_sub(int i, atomic_t *v)
  */
 static inline int atomic_sub_and_test(int i, atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "subl %2,%0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, i, "%0", "e");
 }
 
 /**
@@ -118,12 +114,7 @@ static inline void atomic_dec(atomic_t *v)
  */
 static inline int atomic_dec_and_test(atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "decl %0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
 }
 
 /**
@@ -136,12 +127,7 @@ static inline int atomic_dec_and_test(atomic_t *v)
  */
 static inline int atomic_inc_and_test(atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "incl %0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
 }
 
 /**
@@ -155,12 +141,7 @@ static inline int atomic_inc_and_test(atomic_t *v)
  */
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "addl %2,%0; sets %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, i, "%0", "s");
 }
 
 /**

arch/x86/include/asm/atomic64_64.h

@@ -72,12 +72,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
  */
 static inline int atomic64_sub_and_test(long i, atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "subq %2,%0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "er" (i), "m" (v->counter) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, i, "%0", "e");
 }
 
 /**
@@ -116,12 +111,7 @@ static inline void atomic64_dec(atomic64_t *v)
  */
 static inline int atomic64_dec_and_test(atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "decq %0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "m" (v->counter) : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", "e");
 }
 
 /**
@@ -134,12 +124,7 @@ static inline int atomic64_dec_and_test(atomic64_t *v)
  */
 static inline int atomic64_inc_and_test(atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "incq %0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "m" (v->counter) : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", "e");
 }
 
 /**
@@ -153,12 +138,7 @@ static inline int atomic64_inc_and_test(atomic64_t *v)
  */
 static inline int atomic64_add_negative(long i, atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "addq %2,%0; sets %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "er" (i), "m" (v->counter) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, i, "%0", "s");
 }
 
 /**

arch/x86/include/asm/bitops.h

@@ -14,6 +14,7 @@
 
 #include <linux/compiler.h>
 #include <asm/alternative.h>
+#include <asm/rmwcc.h>
 
 #if BITS_PER_LONG == 32
 # define _BITOPS_LONG_SHIFT 5
@@ -204,12 +205,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "bts %2,%1\n\t"
-		     "sbb %0,%0" : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, nr, "%0", "c");
 }
 
 /**
@@ -255,13 +251,7 @@ static inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "btr %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, nr, "%0", "c");
 }
 
 /**
@@ -314,13 +304,7 @@ static inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "btc %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, nr, "%0", "c");
 }
 
 static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr)

arch/x86/include/asm/local.h

@@ -52,12 +52,7 @@ static inline void local_sub(long i, local_t *l)
  */
 static inline int local_sub_and_test(long i, local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_SUB "%2,%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, i, "%0", "e");
 }
 
 /**
@@ -70,12 +65,7 @@ static inline int local_sub_and_test(long i, local_t *l)
  */
 static inline int local_dec_and_test(local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_DEC "%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", "e");
 }
 
 /**
@@ -88,12 +78,7 @@ static inline int local_dec_and_test(local_t *l)
  */
 static inline int local_inc_and_test(local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_INC "%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", "e");
 }
 
 /**
@@ -107,12 +92,7 @@ static inline int local_inc_and_test(local_t *l)
  */
 static inline int local_add_negative(long i, local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_ADD "%2,%0; sets %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, i, "%0", "s");
 }
 
 /**

arch/x86/include/asm/rmwcc.h

@@ -0,0 +1,41 @@
+#ifndef _ASM_X86_RMWcc
+#define _ASM_X86_RMWcc
+
+#ifdef CC_HAVE_ASM_GOTO
+
+#define __GEN_RMWcc(fullop, var, cc, ...)				\
+do {									\
+	asm volatile goto (fullop "; j" cc " %l[cc_label]"		\
+			: : "m" (var), ## __VA_ARGS__ 			\
+			: "memory" : cc_label);				\
+	return 0;							\
+cc_label:								\
+	return 1;							\
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc) 				\
+	__GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, val, arg0, cc)			\
+	__GEN_RMWcc(op " %1, " arg0, var, cc, "er" (val))
+
+#else /* !CC_HAVE_ASM_GOTO */
+
+#define __GEN_RMWcc(fullop, var, cc, ...)				\
+do {									\
+	char c;								\
+	asm volatile (fullop "; set" cc " %1"				\
+			: "+m" (var), "=qm" (c)				\
+			: __VA_ARGS__ : "memory");			\
+	return c != 0;							\
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc)				\
+	__GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, val, arg0, cc)			\
+	__GEN_RMWcc(op " %2, " arg0, var, cc, "er" (val))
+
+#endif /* CC_HAVE_ASM_GOTO */
+
+#endif /* _ASM_X86_RMWcc */