x86-32: Avoid pipeline serialization in PTREGSCALL1 and 2

In the PTREGSCALL1 and 2 macros, we can trivially avoid an unnecessary
pipeline serialization, so do so.

In PTREGSCALLS3 this is much less clear-cut since we have to push a
new value to the stack.  Leave it alone for now assuming it is as good
as it is going to be; may want to check on Atom or another in-order
x86 to see if we can do better.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Cc: Brian Gerst <brgerst@gmail.com>
LKML-Reference: <1260403316-5679-2-git-send-email-brgerst@gmail.com>

arch/x86/kernel/entry_32.S

@@ -735,15 +735,15 @@ ptregs_##name: \
 	ALIGN; \
 ptregs_##name: \
 	leal 4(%esp),%edx; \
-	movl PT_EBX(%edx),%eax; \
+	movl (PT_EBX+4)(%esp),%eax; \
 	jmp sys_##name;
 
 #define PTREGSCALL2(name) \
 	ALIGN; \
 ptregs_##name: \
 	leal 4(%esp),%ecx; \
-	movl PT_ECX(%ecx),%edx; \
-	movl PT_EBX(%ecx),%eax; \
+	movl (PT_ECX+4)(%esp),%edx; \
+	movl (PT_EBX+4)(%esp),%eax; \
 	jmp sys_##name;
 
 #define PTREGSCALL3(name) \