[PATCH 3/3] x86: drop LOCK from XCHG when optimizing

[Jan Beulich]

Like with segment overrides on LEA, optimize away such a redundant
instruction prefix.

--- a/gas/config/tc-i386.c
+++ b/gas/config/tc-i386.c
@@ -5179,14 +5179,20 @@ md_assemble (char *line)
 
   /* Check for lock without a lockable instruction.  Destination operand
      must be memory unless it is xchg (0x86).  */
-  if (i.prefix[LOCK_PREFIX]
-      && (i.tm.opcode_modifier.prefixok < PrefixLock
+  if (i.prefix[LOCK_PREFIX])
+    {
+      if (i.tm.opcode_modifier.prefixok < PrefixLock
 	  || i.mem_operands == 0
 	  || (i.tm.base_opcode != 0x86
-	      && !(i.flags[i.operands - 1] & Operand_Mem))))
-    {
-      as_bad (_("expecting lockable instruction after `lock'"));
-      return;
+	      && !(i.flags[i.operands - 1] & Operand_Mem)))
+	{
+	  as_bad (_("expecting lockable instruction after `lock'"));
+	  return;
+	}
+
+      /* Zap the redundant prefix from XCHG when optimizing.  */
+      if (i.tm.base_opcode == 0x86 && optimize && !i.no_optimize)
+	i.prefix[LOCK_PREFIX] = 0;
     }
 
   if (is_any_vex_encoding (&i.tm)
--- a/gas/testsuite/gas/i386/optimize-2.d
+++ b/gas/testsuite/gas/i386/optimize-2.d
@@ -22,6 +22,8 @@ Disassembly of section .text:
  +[a-f0-9]+:	08 e4                	or     %ah,%ah
  +[a-f0-9]+:	66 09 ed             	or     %bp,%bp
  +[a-f0-9]+:	09 f6                	or     %esi,%esi
+ +[a-f0-9]+:	87 0a                	xchg   %ecx,\(%edx\)
+ +[a-f0-9]+:	87 11                	xchg   %edx,\(%ecx\)
  +[a-f0-9]+:	c5 f1 55 e9          	vandnpd %xmm1,%xmm1,%xmm5
  +[a-f0-9]+:	c5 f9 6f d1          	vmovdqa %xmm1,%xmm2
  +[a-f0-9]+:	c5 f9 6f d1          	vmovdqa %xmm1,%xmm2
--- a/gas/testsuite/gas/i386/optimize-2.s
+++ b/gas/testsuite/gas/i386/optimize-2.s
@@ -20,6 +20,9 @@ _start:
 	or	%bp, %bp
 	or	%esi, %esi
 
+	lock xchg %ecx, (%edx)
+	lock xchg (%ecx), %edx
+
 	vandnpd	%zmm1, %zmm1, %zmm5
 
 	vmovdqa32	%xmm1, %xmm2
--- a/gas/testsuite/gas/i386/optimize-2b.d
+++ b/gas/testsuite/gas/i386/optimize-2b.d
@@ -23,6 +23,8 @@ Disassembly of section .text:
  +[a-f0-9]+:	84 e4                	test   %ah,%ah
  +[a-f0-9]+:	66 85 ed             	test   %bp,%bp
  +[a-f0-9]+:	85 f6                	test   %esi,%esi
+ +[a-f0-9]+:	87 0a                	xchg   %ecx,\(%edx\)
+ +[a-f0-9]+:	87 11                	xchg   %edx,\(%ecx\)
  +[a-f0-9]+:	c5 f1 55 e9          	vandnpd %xmm1,%xmm1,%xmm5
  +[a-f0-9]+:	c5 f9 6f d1          	vmovdqa %xmm1,%xmm2
  +[a-f0-9]+:	c5 f9 6f d1          	vmovdqa %xmm1,%xmm2
--- a/gas/testsuite/gas/i386/optimize-3.d
+++ b/gas/testsuite/gas/i386/optimize-3.d
@@ -9,6 +9,8 @@ Disassembly of section .text:
 
 0+ <_start>:
  +[a-f0-9]+:	a9 7f 00 00 00       	test   \$0x7f,%eax
+ +[a-f0-9]+:	f0 87 0a             	lock xchg %ecx,\(%edx\)
+ +[a-f0-9]+:	f0 87 11             	lock xchg %edx,\(%ecx\)
  +[a-f0-9]+:	62 f1 7d 28 6f d1    	vmovdqa32 %ymm1,%ymm2
  +[a-f0-9]+:	62 f1 fd 28 6f d1    	vmovdqa64 %ymm1,%ymm2
  +[a-f0-9]+:	62 f1 7f 08 6f d1    	vmovdqu8 %xmm1,%xmm2
--- a/gas/testsuite/gas/i386/optimize-3.s
+++ b/gas/testsuite/gas/i386/optimize-3.s
@@ -5,6 +5,9 @@
 _start:
 	{nooptimize} testl $0x7f, %eax
 
+	{nooptimize} lock xchg	%ecx, (%edx)
+	{nooptimize} lock xchg	(%ecx), %edx
+
 	{nooptimize} vmovdqa32	%ymm1, %ymm2
 	{nooptimize} vmovdqa64	%ymm1, %ymm2
 	{nooptimize} vmovdqu8	%xmm1, %xmm2