openkylin
/
linux
mirror of https://gitee.com/openkylin/linux.git
9
0
Fork 0
Code Issues Projects Releases Wiki Activity
linux/arch/x86/lib/memset_64.S

134 lines
2.3 KiB
ArmAsm
Raw Normal View History

Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Copyright 2002 Andi Kleen, SuSE Labs */
[PATCH] annotate arch/x86_64/lib/*.S Add unwind annotations to arch/x86_64/lib/*.S, and also use the macros provided by linux/linkage.h where-ever possible. Some of the alternative instructions handling needed to be adjusted so that the replacement code would also have valid unwind information. Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andi Kleen <ak@suse.de>
2006-09-26 16:52:32 +08:00
#include <linux/linkage.h>
#include <asm/dwarf2.h>
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/*
* ISO C memset - set a memory block to a byte value.
*
* rdi destination
* rsi value (char)
* rdx count (bytes)
*
* rax original destination
*/
[PATCH] annotate arch/x86_64/lib/*.S Add unwind annotations to arch/x86_64/lib/*.S, and also use the macros provided by linux/linkage.h where-ever possible. Some of the alternative instructions handling needed to be adjusted so that the replacement code would also have valid unwind information. Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andi Kleen <ak@suse.de>
2006-09-26 16:52:32 +08:00
ALIGN
memset_c:
CFI_STARTPROC
movq %rdi,%r9
movl %edx,%r8d
andl $7,%r8d
movl %edx,%ecx
shrl $3,%ecx
/* expand byte value */
movzbl %sil,%esi
movabs $0x0101010101010101,%rax
mulq %rsi /* with rax, clobbers rdx */
rep stosq
movl %r8d,%ecx
rep stosb
movq %r9,%rax
ret
CFI_ENDPROC
ENDPROC(memset_c)
ENTRY(memset)
ENTRY(__memset)
CFI_STARTPROC
[PATCH] x86_64: Undo the earlier changes to remove unrolled copy/memset functions They cause quite bad performance regressions on Netburst This is temporary until we can get new optimized functions for these CPUs. This undoes changes that were done in 2.6.15 and in 2.6.16-rc1, essentially bringing the code back to 2.6.14 level. Only change is I renamed the X86_FEATURE_K8_C flag to X86_FEATURE_REP_GOOD and fixed the check for the flag and also fixed some comments. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-02-04 04:51:02 +08:00
movq %rdi,%r10
movq %rdx,%r11
/* expand byte value */
movzbl %sil,%ecx
movabs $0x0101010101010101,%rax
mul %rcx /* with rax, clobbers rdx */
/* align dst */
movl %edi,%r9d
andl $7,%r9d
jnz .Lbad_alignment
[PATCH] annotate arch/x86_64/lib/*.S Add unwind annotations to arch/x86_64/lib/*.S, and also use the macros provided by linux/linkage.h where-ever possible. Some of the alternative instructions handling needed to be adjusted so that the replacement code would also have valid unwind information. Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andi Kleen <ak@suse.de>
2006-09-26 16:52:32 +08:00
CFI_REMEMBER_STATE
[PATCH] x86_64: Undo the earlier changes to remove unrolled copy/memset functions They cause quite bad performance regressions on Netburst This is temporary until we can get new optimized functions for these CPUs. This undoes changes that were done in 2.6.15 and in 2.6.16-rc1, essentially bringing the code back to 2.6.14 level. Only change is I renamed the X86_FEATURE_K8_C flag to X86_FEATURE_REP_GOOD and fixed the check for the flag and also fixed some comments. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-02-04 04:51:02 +08:00
.Lafter_bad_alignment:
movl %r11d,%ecx
shrl $6,%ecx
jz .Lhandle_tail
.p2align 4
.Lloop_64:
decl %ecx
movq %rax,(%rdi)
movq %rax,8(%rdi)
movq %rax,16(%rdi)
movq %rax,24(%rdi)
movq %rax,32(%rdi)
movq %rax,40(%rdi)
movq %rax,48(%rdi)
movq %rax,56(%rdi)
leaq 64(%rdi),%rdi
jnz .Lloop_64
/* Handle tail in loops. The loops should be faster than hard
to predict jump tables. */
.p2align 4
.Lhandle_tail:
movl %r11d,%ecx
andl $63&(~7),%ecx
jz .Lhandle_7
shrl $3,%ecx
.p2align 4
.Lloop_8:
decl %ecx
movq %rax,(%rdi)
leaq 8(%rdi),%rdi
jnz .Lloop_8
.Lhandle_7:
movl %r11d,%ecx
andl $7,%ecx
jz .Lende
.p2align 4
.Lloop_1:
decl %ecx
movb %al,(%rdi)
leaq 1(%rdi),%rdi
jnz .Lloop_1
.Lende:
movq %r10,%rax
ret
[PATCH] annotate arch/x86_64/lib/*.S Add unwind annotations to arch/x86_64/lib/*.S, and also use the macros provided by linux/linkage.h where-ever possible. Some of the alternative instructions handling needed to be adjusted so that the replacement code would also have valid unwind information. Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andi Kleen <ak@suse.de>
2006-09-26 16:52:32 +08:00
CFI_RESTORE_STATE
[PATCH] x86_64: Undo the earlier changes to remove unrolled copy/memset functions They cause quite bad performance regressions on Netburst This is temporary until we can get new optimized functions for these CPUs. This undoes changes that were done in 2.6.15 and in 2.6.16-rc1, essentially bringing the code back to 2.6.14 level. Only change is I renamed the X86_FEATURE_K8_C flag to X86_FEATURE_REP_GOOD and fixed the check for the flag and also fixed some comments. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-02-04 04:51:02 +08:00
.Lbad_alignment:
cmpq $7,%r11
jbe .Lhandle_7
movq %rax,(%rdi) /* unaligned store */
movq $8,%r8
subq %r9,%r8
addq %r8,%rdi
subq %r8,%r11
jmp .Lafter_bad_alignment
[PATCH] annotate arch/x86_64/lib/*.S Add unwind annotations to arch/x86_64/lib/*.S, and also use the macros provided by linux/linkage.h where-ever possible. Some of the alternative instructions handling needed to be adjusted so that the replacement code would also have valid unwind information. Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andi Kleen <ak@suse.de>
2006-09-26 16:52:32 +08:00
.Lfinal:
CFI_ENDPROC
ENDPROC(memset)
ENDPROC(__memset)
[PATCH] x86_64: Undo the earlier changes to remove unrolled copy/memset functions They cause quite bad performance regressions on Netburst This is temporary until we can get new optimized functions for these CPUs. This undoes changes that were done in 2.6.15 and in 2.6.16-rc1, essentially bringing the code back to 2.6.14 level. Only change is I renamed the X86_FEATURE_K8_C flag to X86_FEATURE_REP_GOOD and fixed the check for the flag and also fixed some comments. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-02-04 04:51:02 +08:00
/* Some CPUs run faster using the string instructions.
It is also a lot simpler. Use this when possible */
#include <asm/cpufeature.h>
[PATCH] annotate arch/x86_64/lib/*.S Add unwind annotations to arch/x86_64/lib/*.S, and also use the macros provided by linux/linkage.h where-ever possible. Some of the alternative instructions handling needed to be adjusted so that the replacement code would also have valid unwind information. Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andi Kleen <ak@suse.de>
2006-09-26 16:52:32 +08:00
.section .altinstr_replacement,"ax"
1: .byte 0xeb /* jmp <disp8> */
.byte (memset_c - memset) - (2f - 1b) /* offset */
2:
.previous
[PATCH] x86_64: Undo the earlier changes to remove unrolled copy/memset functions They cause quite bad performance regressions on Netburst This is temporary until we can get new optimized functions for these CPUs. This undoes changes that were done in 2.6.15 and in 2.6.16-rc1, essentially bringing the code back to 2.6.14 level. Only change is I renamed the X86_FEATURE_K8_C flag to X86_FEATURE_REP_GOOD and fixed the check for the flag and also fixed some comments. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-02-04 04:51:02 +08:00
.section .altinstructions,"a"
.align 8
[PATCH] annotate arch/x86_64/lib/*.S Add unwind annotations to arch/x86_64/lib/*.S, and also use the macros provided by linux/linkage.h where-ever possible. Some of the alternative instructions handling needed to be adjusted so that the replacement code would also have valid unwind information. Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andi Kleen <ak@suse.de>
2006-09-26 16:52:32 +08:00
.quad memset
.quad 1b
.byte X86_FEATURE_REP_GOOD
.byte .Lfinal - memset
.byte 2b - 1b
[PATCH] x86_64: Undo the earlier changes to remove unrolled copy/memset functions They cause quite bad performance regressions on Netburst This is temporary until we can get new optimized functions for these CPUs. This undoes changes that were done in 2.6.15 and in 2.6.16-rc1, essentially bringing the code back to 2.6.14 level. Only change is I renamed the X86_FEATURE_K8_C flag to X86_FEATURE_REP_GOOD and fixed the check for the flag and also fixed some comments. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-02-04 04:51:02 +08:00
.previous