[LLVMdev] [PATCH] x86/asm: avoid mnemonics without type suffix

[Ramkumar Ramachandra]

1c54d77 (x86: partial unification of asm-x86/bitops.h, 2008-01-30)
changed a bunch of btrl/btsl instructions to btr/bts, with the following
justification:

  The inline assembly for the bit operations has been changed to remove
  explicit sizing hints on the instructions, so the assembler will pick
  the appropriate instruction forms depending on the architecture and
  the context.

Unfortunately, GNU as does no such thing, and the AT&T syntax manual
[1] contains no references to any such inference.  As evidenced by the
following experiment, gas always disambiguates btr/bts to btrl/btsl.
Feed the following input to gas:

  btrl	$1, 0
  btr	$1, 0
  btsl	$1, 0
  bts	$1, 0

Check that btr matches btrl, and bts matches btsl in both cases:

  $ as --32 -a in.s
  $ as --64 -a in.s

To avoid giving readers the illusion of such an inference, and for
clarity, change btr/bts back to btrl/btsl.  Also, llvm-mc refuses to
disambiguate btr/bts automatically.

[1]: http://docs.oracle.com/cd/E19253-01/817-5477/817-5477.pdf

Cc: Jeremy Fitzhardinge <jeremy at goop.org>
Cc: Andi Kleen <ak at linux.intel.com>
Cc: Linus Torvalds <torvalds at linux-foundation.org>
Cc: Ingo Molnar <mingo at kernel.org>
Cc: Thomas Gleixner <tglx at linutronix.de>
Cc: Eli Friedman <eli.friedman at gmail.com>
Cc: Jim Grosbach <grosbach at apple.com>
Cc: Stephen Checkoway <s at pahtak.org>
Cc: LLVMdev <llvmdev at cs.uiuc.edu>
Signed-off-by: Ramkumar Ramachandra <artagnon at gmail.com>
---
 We discussed this pretty extensively on LLVMDev, but I'm still not
 sure that I haven't missed something.

 arch/x86/include/asm/bitops.h | 16 ++++++++--------
 arch/x86/include/asm/percpu.h |  2 +-
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 6dfd019..6ed3d1e 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -67,7 +67,7 @@ set_bit(unsigned int nr, volatile unsigned long *addr)
 			: "iq" ((u8)CONST_MASK(nr))
 			: "memory");
 	} else {
-		asm volatile(LOCK_PREFIX "bts %1,%0"
+		asm volatile(LOCK_PREFIX "btsl %1,%0"
 			: BITOP_ADDR(addr) : "Ir" (nr) : "memory");
 	}
 }
@@ -83,7 +83,7 @@ set_bit(unsigned int nr, volatile unsigned long *addr)
  */
 static inline void __set_bit(int nr, volatile unsigned long *addr)
 {
-	asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
+	asm volatile("btsl %1,%0" : ADDR : "Ir" (nr) : "memory");
 }
 
 /**
@@ -104,7 +104,7 @@ clear_bit(int nr, volatile unsigned long *addr)
 			: CONST_MASK_ADDR(nr, addr)
 			: "iq" ((u8)~CONST_MASK(nr)));
 	} else {
-		asm volatile(LOCK_PREFIX "btr %1,%0"
+		asm volatile(LOCK_PREFIX "btrl %1,%0"
 			: BITOP_ADDR(addr)
 			: "Ir" (nr));
 	}
@@ -126,7 +126,7 @@ static inline void clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
 
 static inline void __clear_bit(int nr, volatile unsigned long *addr)
 {
-	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
+	asm volatile("btrl %1,%0" : ADDR : "Ir" (nr));
 }
 
 /*
@@ -198,7 +198,7 @@ static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
-	asm volatile(LOCK_PREFIX "bts %2,%1\n\t"
+	asm volatile(LOCK_PREFIX "btsl %2,%1\n\t"
 		     "sbb %0,%0" : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
 
 	return oldbit;
@@ -230,7 +230,7 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
-	asm("bts %2,%1\n\t"
+	asm("btsl %2,%1\n\t"
 	    "sbb %0,%0"
 	    : "=r" (oldbit), ADDR
 	    : "Ir" (nr));
@@ -249,7 +249,7 @@ static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
-	asm volatile(LOCK_PREFIX "btr %2,%1\n\t"
+	asm volatile(LOCK_PREFIX "btrl %2,%1\n\t"
 		     "sbb %0,%0"
 		     : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
 
@@ -276,7 +276,7 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
-	asm volatile("btr %2,%1\n\t"
+	asm volatile("btrl %2,%1\n\t"
 		     "sbb %0,%0"
 		     : "=r" (oldbit), ADDR
 		     : "Ir" (nr));
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 0da5200..fda54c9 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -490,7 +490,7 @@ do {									\
 #define x86_test_and_clear_bit_percpu(bit, var)				\
 ({									\
 	int old__;							\
-	asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0"		\
+	asm volatile("btrl %2,"__percpu_arg(1)"\n\tsbbl %0,%0"		\
 		     : "=r" (old__), "+m" (var)				\
 		     : "dIr" (bit));					\
 	old__;								\
-- 
1.8.3.2.736.g869de25