Commit ce9119ad authored Dec 09, 2009 by H. Peter Anvin

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>

parent f839bbc5

arch/x86/kernel/entry_32.S

+3 −3

Original line number	Diff line number	Diff line
		@@ -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) \