d/freebsd-nq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

amd64: tidy up kernel memmove, take 2

Browse Source 
There is no need to use %rax for temporary values and avoiding doing
so shortens the func.
Handle the explicit 'check for tail' depessimisization for backwards copying.

This reduces the diff against userspace.

Tested with the glibc test suite.

Approved by:	re (kib)
This commit is contained in:
Mateusz Guzik 2018-09-17 15:51:49 +00:00
parent 23ec0d58bf
commit d6943c5804
1 changed files with 15 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
sys/amd64/amd64/support.S
View File

@ -108,40 +108,40 @@ END(sse2_pagezero)
*/
ENTRY(memmove_std)
PUSH_FRAME_POINTER
movq %rdi,%r9
movq %rdi,%rax
movq %rdx,%rcx
movq %rdi,%rax
subq %rsi,%rax
cmpq %rcx,%rax /* overlapping && src < dst? */
jb 1f
movq %rdi,%r8
subq %rsi,%r8
cmpq %rcx,%r8 /* overlapping && src < dst? */
jb 2f
shrq $3,%rcx /* copy by 64-bit words */
rep
movsq
movq %rdx,%rcx
andq $7,%rcx /* any bytes left? */
jne 2f
movq %r9,%rax
jne 1f
POP_FRAME_POINTER
ret
2:
1:
rep
movsb
movq %r9,%rax
POP_FRAME_POINTER
ret
/* ALIGN_TEXT */
1:
2:
addq %rcx,%rdi /* copy backwards */
addq %rcx,%rsi
decq %rdi
decq %rsi
andq $7,%rcx /* any fractional bytes? */
std
andq $7,%rcx /* any fractional bytes? */
je 3f
rep
movsb
3:
movq %rdx,%rcx /* copy remainder by 32-bit words */
shrq $3,%rcx
subq $7,%rsi
@ -149,24 +149,22 @@ ENTRY(memmove_std)
rep
movsq
cld
movq %r9,%rax
POP_FRAME_POINTER
ret
END(memmove_std)
ENTRY(memmove_erms)
PUSH_FRAME_POINTER
movq %rdi,%r9
movq %rdi,%rax
movq %rdx,%rcx
movq %rdi,%rax
subq %rsi,%rax
cmpq %rcx,%rax /* overlapping && src < dst? */
movq %rdi,%r8
subq %rsi,%r8
cmpq %rcx,%r8 /* overlapping && src < dst? */
jb 1f
rep
movsb
movq %r9,%rax
POP_FRAME_POINTER
ret
@ -179,7 +177,6 @@ ENTRY(memmove_erms)
rep
movsb
cld
movq %r9,%rax
POP_FRAME_POINTER
ret
END(memmove_erms)