Messages in this thread Patch in this message | | | Date | Thu, 26 Nov 2009 09:55:56 GMT | From | tip-bot for Brian Gerst <> | Subject | [tip:x86/asm] x86: Optimize loadsegment() |
| |
Commit-ID: 79b0379cee09b00ef309384aff652e328e438c79 Gitweb: http://git.kernel.org/tip/79b0379cee09b00ef309384aff652e328e438c79 Author: Brian Gerst <brgerst@gmail.com> AuthorDate: Wed, 25 Nov 2009 14:18:26 -0500 Committer: Ingo Molnar <mingo@elte.hu> CommitDate: Thu, 26 Nov 2009 10:33:58 +0100
x86: Optimize loadsegment()
Zero the input register in the exception handler instead of using an extra register to pass in a zero value.
Signed-off-by: Brian Gerst <brgerst@gmail.com> LKML-Reference: <1259176706-5908-1-git-send-email-brgerst@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> --- arch/x86/include/asm/system.h | 15 ++++++++------- 1 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index 1a953e2..537395a 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -156,18 +156,19 @@ extern void native_load_gs_index(unsigned); * segment if something goes wrong.. */ #define loadsegment(seg, value) \ +do { \ + unsigned short __val = value; \ asm volatile("\n" \ "1:\t" \ "movl %k0,%%" #seg "\n" \ - "2:\n" \ ".section .fixup,\"ax\"\n" \ - "3:\t" \ - "movl %k1, %%" #seg "\n\t" \ - "jmp 2b\n" \ + "2:\t" \ + "xorl %k0,%k0\n\t" \ + "jmp 1b\n" \ ".previous\n" \ - _ASM_EXTABLE(1b,3b) \ - : :"r" (value), "r" (0) : "memory") - + _ASM_EXTABLE(1b, 2b) \ + : "+r" (__val) : : "memory"); \ +} while (0) /* * Save a segment register away
| |