i586 strcpy.S used a clever trick with LEA to implement jump table:
/* ECX has the last 2 bits of the address of source - 1. */
andl $3, %ecx
call 2f
2: popl %edx
/* 0xb is the distance between 2: and 1:. */
leal 0xb(%edx,%ecx,8), %ecx
jmp *%ecx
.align 8
1: /* ECX == 0 */
orb (%esi), %al
jz L(end)
stosb
xorl %eax, %eax
incl %esi
/* ECX == 1 */
orb (%esi), %al
jz L(end)
stosb
xorl %eax, %eax
incl %esi
/* ECX == 2 */
orb (%esi), %al
jz L(end)
stosb
xorl %eax, %eax
incl %esi
/* ECX == 3 */
L(1): movl (%esi), %ecx
leal 4(%esi),%esi
This fails if there are instruction length changes before L(1):. This
patch replaces it with conditional branches:
cmpb $2, %cl
je L(Src2)
ja L(Src3)
cmpb $1, %cl
je L(Src1)
L(Src0):
which have similar performance and work with any instruction lengths.
Tested on i586 and i686 with and without --disable-multi-arch.
[BZ #22353]
* sysdeps/i386/i586/strcpy.S (STRCPY): Use conditional branches.
(1): Renamed to ...
(L(Src0)): This.
(L(Src1)): New.
(L(Src2)): Likewise.
(L(1)): Renamed to ...
(L(Src3)): This.
+2017-10-30 H.J. Lu <hongjiu.lu@intel.com>
+
+ [BZ #22353]
+ * sysdeps/i386/i586/strcpy.S (STRCPY): Use conditional branches.
+ (1): Renamed to ...
+ (L(Src0)): This.
+ (L(Src1)): New.
+ (L(Src2)): Likewise.
+ (L(1)): Renamed to ...
+ (L(Src3)): This.
+
2017-10-30 Joseph Myers <joseph@codesourcery.com>
* math/math.h [__HAVE_FLOAT16 && __USE_GNU] (M_Ef16): New macro.
cfi_rel_offset (ebx, 0)
andl $3, %ecx
-#ifdef PIC
- call 2f
- cfi_adjust_cfa_offset (4)
-2: popl %edx
- cfi_adjust_cfa_offset (-4)
- /* 0xb is the distance between 2: and 1: but we avoid writing
- 1f-2b because the assembler generates worse code. */
- leal 0xb(%edx,%ecx,8), %ecx
-#else
- leal 1f(,%ecx,8), %ecx
-#endif
-
- jmp *%ecx
+ cmpb $2, %cl
+ je L(Src2)
+ ja L(Src3)
+ cmpb $1, %cl
+ je L(Src1)
- .align 8
-1:
+L(Src0):
orb (%esi), %al
jz L(end)
stosb
xorl %eax, %eax
incl %esi
+L(Src1):
orb (%esi), %al
jz L(end)
stosb
xorl %eax, %eax
incl %esi
+L(Src2):
orb (%esi), %al
jz L(end)
stosb
xorl %eax, %eax
incl %esi
-L(1): movl (%esi), %ecx
+L(Src3):
+ movl (%esi), %ecx
leal 4(%esi),%esi
subl %ecx, %eax
movl %edx, (%edi)
leal 4(%edi),%edi
- jmp L(1)
+ jmp L(Src3)
L(3): movl %ecx, %edx