Messages in this thread Patch in this message | | | Date | Thu, 10 Dec 2009 00:47:12 GMT | From | "tip-bot for H. Peter Anvin" <> | Subject | [tip:x86/asm] x86-32: Avoid pipeline serialization in PTREGSCALL1 and 2 |
| |
Commit-ID: ce9119ad90b1caba550447bfcc0a21850558ca49 Gitweb: http://git.kernel.org/tip/ce9119ad90b1caba550447bfcc0a21850558ca49 Author: H. Peter Anvin <hpa@zytor.com> AuthorDate: Wed, 9 Dec 2009 16:33:44 -0800 Committer: H. Peter Anvin <hpa@zytor.com> CommitDate: Wed, 9 Dec 2009 16:33:44 -0800
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 | 6 +++--- 1 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 6492555..cb12b9b 100644 --- a/arch/x86/kernel/entry_32.S +++ b/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) \
| |