Release 4.14 arch/x86/include/asm/xor_32.h
#ifndef _ASM_X86_XOR_32_H
#define _ASM_X86_XOR_32_H
/*
* Optimized RAID-5 checksumming functions for MMX.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2, or (at your option)
* any later version.
*
* You should have received a copy of the GNU General Public License
* (for example /usr/src/linux/COPYING); if not, write to the Free
* Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
/*
* High-speed RAID5 checksumming functions utilizing MMX instructions.
* Copyright (C) 1998 Ingo Molnar.
*/
#define LD(x, y) " movq 8*("#x")(%1), %%mm"#y" ;\n"
#define ST(x, y) " movq %%mm"#y", 8*("#x")(%1) ;\n"
#define XO1(x, y) " pxor 8*("#x")(%2), %%mm"#y" ;\n"
#define XO2(x, y) " pxor 8*("#x")(%3), %%mm"#y" ;\n"
#define XO3(x, y) " pxor 8*("#x")(%4), %%mm"#y" ;\n"
#define XO4(x, y) " pxor 8*("#x")(%5), %%mm"#y" ;\n"
#include <asm/fpu/api.h>
static void
xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
{
unsigned long lines = bytes >> 7;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
LD(i, 0) \
LD(i + 1, 1) \
LD(i + 2, 2) \
LD(i + 3, 3) \
XO1(i, 0) \
ST(i, 0) \
XO1(i+1, 1) \
ST(i+1, 1) \
XO1(i + 2, 2) \
ST(i + 2, 2) \
XO1(i + 3, 3) \
ST(i + 3, 3)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" addl $128, %1 ;\n"
" addl $128, %2 ;\n"
" decl %0 ;\n"
" jnz 1b ;\n"
: "+r" (lines),
"+r" (p1), "+r" (p2)
:
: "memory");
kernel_fpu_end();
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Linus Torvalds (pre-git) | 41 | 83.67% | 1 | 33.33% |
| Joe Perches | 4 | 8.16% | 1 | 33.33% |
| Linus Torvalds | 4 | 8.16% | 1 | 33.33% |
| Total | 49 | 100.00% | 3 | 100.00% |
static void
xor_pII_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3)
{
unsigned long lines = bytes >> 7;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
LD(i, 0) \
LD(i + 1, 1) \
LD(i + 2, 2) \
LD(i + 3, 3) \
XO1(i, 0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
XO2(i, 0) \
ST(i, 0) \
XO2(i + 1, 1) \
ST(i + 1, 1) \
XO2(i + 2, 2) \
ST(i + 2, 2) \
XO2(i + 3, 3) \
ST(i + 3, 3)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" addl $128, %1 ;\n"
" addl $128, %2 ;\n"
" addl $128, %3 ;\n"
" decl %0 ;\n"
" jnz 1b ;\n"
: "+r" (lines),
"+r" (p1), "+r" (p2), "+r" (p3)
:
: "memory");
kernel_fpu_end();
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Linus Torvalds (pre-git) | 46 | 85.19% | 1 | 25.00% |
| Linus Torvalds | 4 | 7.41% | 1 | 25.00% |
| Joe Perches | 3 | 5.56% | 1 | 25.00% |
| Andi Kleen | 1 | 1.85% | 1 | 25.00% |
| Total | 54 | 100.00% | 4 | 100.00% |
static void
xor_pII_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4)
{
unsigned long lines = bytes >> 7;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
LD(i, 0) \
LD(i + 1, 1) \
LD(i + 2, 2) \
LD(i + 3, 3) \
XO1(i, 0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
XO2(i, 0) \
XO2(i + 1, 1) \
XO2(i + 2, 2) \
XO2(i + 3, 3) \
XO3(i, 0) \
ST(i, 0) \
XO3(i + 1, 1) \
ST(i + 1, 1) \
XO3(i + 2, 2) \
ST(i + 2, 2) \
XO3(i + 3, 3) \
ST(i + 3, 3)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" addl $128, %1 ;\n"
" addl $128, %2 ;\n"
" addl $128, %3 ;\n"
" addl $128, %4 ;\n"
" decl %0 ;\n"
" jnz 1b ;\n"
: "+r" (lines),
"+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
:
: "memory");
kernel_fpu_end();
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Linus Torvalds (pre-git) | 51 | 86.44% | 1 | 25.00% |
| Linus Torvalds | 4 | 6.78% | 1 | 25.00% |
| Joe Perches | 3 | 5.08% | 1 | 25.00% |
| Andi Kleen | 1 | 1.69% | 1 | 25.00% |
| Total | 59 | 100.00% | 4 | 100.00% |
static void
xor_pII_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4, unsigned long *p5)
{
unsigned long lines = bytes >> 7;
kernel_fpu_begin();
/* Make sure GCC forgets anything it knows about p4 or p5,
such that it won't pass to the asm volatile below a
register that is shared with any other variable. That's
because we modify p4 and p5 there, but we can't mark them
as read/write, otherwise we'd overflow the 10-asm-operands
limit of GCC < 3.1. */
asm("" : "+r" (p4), "+r" (p5));
asm volatile(
#undef BLOCK
#define BLOCK(i) \
LD(i, 0) \
LD(i + 1, 1) \
LD(i + 2, 2) \
LD(i + 3, 3) \
XO1(i, 0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
XO2(i, 0) \
XO2(i + 1, 1) \
XO2(i + 2, 2) \
XO2(i + 3, 3) \
XO3(i, 0) \
XO3(i + 1, 1) \
XO3(i + 2, 2) \
XO3(i + 3, 3) \
XO4(i, 0) \
ST(i, 0) \
XO4(i + 1, 1) \
ST(i + 1, 1) \
XO4(i + 2, 2) \
ST(i + 2, 2) \
XO4(i + 3, 3) \
ST(i + 3, 3)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" addl $128, %1 ;\n"
" addl $128, %2 ;\n"
" addl $128, %3 ;\n"
" addl $128, %4 ;\n"
" addl $128, %5 ;\n"
" decl %0 ;\n"
" jnz 1b ;\n"
: "+r" (lines),
"+r" (p1), "+r" (p2), "+r" (p3)
: "r" (p4), "r" (p5)
: "memory");
/* p4 and p5 were modified, and now the variables are dead.
Clobber them just to be sure nobody does something stupid
like assuming they have some legal value. */
asm("" : "=r" (p4), "=r" (p5));
kernel_fpu_end();
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Linus Torvalds (pre-git) | 55 | 80.88% | 1 | 25.00% |
| Joe Perches | 6 | 8.82% | 1 | 25.00% |
| Linus Torvalds | 4 | 5.88% | 1 | 25.00% |
| Alexandre Oliva | 3 | 4.41% | 1 | 25.00% |
| Total | 68 | 100.00% | 4 | 100.00% |
#undef LD
#undef XO1
#undef XO2
#undef XO3
#undef XO4
#undef ST
#undef BLOCK
static void
xor_p5_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
{
unsigned long lines = bytes >> 6;
kernel_fpu_begin();
asm volatile(
" .align 32 ;\n"
" 1: ;\n"
" movq (%1), %%mm0 ;\n"
" movq 8(%1), %%mm1 ;\n"
" pxor (%2), %%mm0 ;\n"
" movq 16(%1), %%mm2 ;\n"
" movq %%mm0, (%1) ;\n"
" pxor 8(%2), %%mm1 ;\n"
" movq 24(%1), %%mm3 ;\n"
" movq %%mm1, 8(%1) ;\n"
" pxor 16(%2), %%mm2 ;\n"
" movq 32(%1), %%mm4 ;\n"
" movq %%mm2, 16(%1) ;\n"
" pxor 24(%2), %%mm3 ;\n"
" movq 40(%1), %%mm5 ;\n"
" movq %%mm3, 24(%1) ;\n"
" pxor 32(%2), %%mm4 ;\n"
" movq 48(%1), %%mm6 ;\n"
" movq %%mm4, 32(%1) ;\n"
" pxor 40(%2), %%mm5 ;\n"
" movq 56(%1), %%mm7 ;\n"
" movq %%mm5, 40(%1) ;\n"
" pxor 48(%2), %%mm6 ;\n"
" pxor 56(%2), %%mm7 ;\n"
" movq %%mm6, 48(%1) ;\n"
" movq %%mm7, 56(%1) ;\n"
" addl $64, %1 ;\n"
" addl $64, %2 ;\n"
" decl %0 ;\n"
" jnz 1b ;\n"
: "+r" (lines),
"+r" (p1), "+r" (p2)
:
: "memory");
kernel_fpu_end();
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Linus Torvalds (pre-git) | 30 | 81.08% | 1 | 33.33% |
| Linus Torvalds | 4 | 10.81% | 1 | 33.33% |
| Joe Perches | 3 | 8.11% | 1 | 33.33% |
| Total | 37 | 100.00% | 3 | 100.00% |
static void
xor_p5_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3)
{
unsigned long lines = bytes >> 6;
kernel_fpu_begin();
asm volatile(
" .align 32,0x90 ;\n"
" 1: ;\n"
" movq (%1), %%mm0 ;\n"
" movq 8(%1), %%mm1 ;\n"
" pxor (%2), %%mm0 ;\n"
" movq 16(%1), %%mm2 ;\n"
" pxor 8(%2), %%mm1 ;\n"
" pxor (%3), %%mm0 ;\n"
" pxor 16(%2), %%mm2 ;\n"
" movq %%mm0, (%1) ;\n"
" pxor 8(%3), %%mm1 ;\n"
" pxor 16(%3), %%mm2 ;\n"
" movq 24(%1), %%mm3 ;\n"
" movq %%mm1, 8(%1) ;\n"
" movq 32(%1), %%mm4 ;\n"
" movq 40(%1), %%mm5 ;\n"
" pxor 24(%2), %%mm3 ;\n"
" movq %%mm2, 16(%1) ;\n"
" pxor 32(%2), %%mm4 ;\n"
" pxor 24(%3), %%mm3 ;\n"
" pxor 40(%2), %%mm5 ;\n"
" movq %%mm3, 24(%1) ;\n"
" pxor 32(%3), %%mm4 ;\n"
" pxor 40(%3), %%mm5 ;\n"
" movq 48(%1), %%mm6 ;\n"
" movq %%mm4, 32(%1) ;\n"
" movq 56(%1), %%mm7 ;\n"
" pxor 48(%2), %%mm6 ;\n"
" movq %%mm5, 40(%1) ;\n"
" pxor 56(%2), %%mm7 ;\n"
" pxor 48(%3), %%mm6 ;\n"
" pxor 56(%3), %%mm7 ;\n"
" movq %%mm6, 48(%1) ;\n"
" movq %%mm7, 56(%1) ;\n"
" addl $64, %1 ;\n"
" addl $64, %2 ;\n"
" addl $64, %3 ;\n"
" decl %0 ;\n"
" jnz 1b ;\n"
: "+r" (lines),
"+r" (p1), "+r" (p2), "+r" (p3)
:
: "memory" );
kernel_fpu_end();
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Linus Torvalds (pre-git) | 35 | 83.33% | 1 | 33.33% |
| Linus Torvalds | 4 | 9.52% | 1 | 33.33% |
| Joe Perches | 3 | 7.14% | 1 | 33.33% |
| Total | 42 | 100.00% | 3 | 100.00% |
static void
xor_p5_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4)
{
unsigned long lines = bytes >> 6;
kernel_fpu_begin();
asm volatile(
" .align 32,0x90 ;\n"
" 1: ;\n"
" movq (%1), %%mm0 ;\n"
" movq 8(%1), %%mm1 ;\n"
" pxor (%2), %%mm0 ;\n"
" movq 16(%1), %%mm2 ;\n"
" pxor 8(%2), %%mm1 ;\n"
" pxor (%3), %%mm0 ;\n"
" pxor 16(%2), %%mm2 ;\n"
" pxor 8(%3), %%mm1 ;\n"
" pxor (%4), %%mm0 ;\n"
" movq 24(%1), %%mm3 ;\n"
" pxor 16(%3), %%mm2 ;\n"
" pxor 8(%4), %%mm1 ;\n"
" movq %%mm0, (%1) ;\n"
" movq 32(%1), %%mm4 ;\n"
" pxor 24(%2), %%mm3 ;\n"
" pxor 16(%4), %%mm2 ;\n"
" movq %%mm1, 8(%1) ;\n"
" movq 40(%1), %%mm5 ;\n"
" pxor 32(%2), %%mm4 ;\n"
" pxor 24(%3), %%mm3 ;\n"
" movq %%mm2, 16(%1) ;\n"
" pxor 40(%2), %%mm5 ;\n"
" pxor 32(%3), %%mm4 ;\n"
" pxor 24(%4), %%mm3 ;\n"
" movq %%mm3, 24(%1) ;\n"
" movq 56(%1), %%mm7 ;\n"
" movq 48(%1), %%mm6 ;\n"
" pxor 40(%3), %%mm5 ;\n"
" pxor 32(%4), %%mm4 ;\n"
" pxor 48(%2), %%mm6 ;\n"
" movq %%mm4, 32(%1) ;\n"
" pxor 56(%2), %%mm7 ;\n"
" pxor 40(%4), %%mm5 ;\n"
" pxor 48(%3), %%mm6 ;\n"
" pxor 56(%3), %%mm7 ;\n"
" movq %%mm5, 40(%1) ;\n"
" pxor 48(%4), %%mm6 ;\n"
" pxor 56(%4), %%mm7 ;\n"
" movq %%mm6, 48(%1) ;\n"
" movq %%mm7, 56(%1) ;\n"
" addl $64, %1 ;\n"
" addl $64, %2 ;\n"
" addl $64, %3 ;\n"
" addl $64, %4 ;\n"
" decl %0 ;\n"
" jnz 1b ;\n"
: "+r" (lines),
"+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
:
: "memory");
kernel_fpu_end();
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Linus Torvalds (pre-git) | 40 | 85.11% | 1 | 33.33% |
| Linus Torvalds | 4 | 8.51% | 1 | 33.33% |
| Joe Perches | 3 | 6.38% | 1 | 33.33% |
| Total | 47 | 100.00% | 3 | 100.00% |
static void
xor_p5_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4, unsigned long *p5)
{
unsigned long lines = bytes >> 6;
kernel_fpu_begin();
/* Make sure GCC forgets anything it knows about p4 or p5,
such that it won't pass to the asm volatile below a
register that is shared with any other variable. That's
because we modify p4 and p5 there, but we can't mark them
as read/write, otherwise we'd overflow the 10-asm-operands
limit of GCC < 3.1. */
asm("" : "+r" (p4), "+r" (p5));
asm volatile(
" .align 32,0x90 ;\n"
" 1: ;\n"
" movq (%1), %%mm0 ;\n"
" movq 8(%1), %%mm1 ;\n"
" pxor (%2), %%mm0 ;\n"
" pxor 8(%2), %%mm1 ;\n"
" movq 16(%1), %%mm2 ;\n"
" pxor (%3), %%mm0 ;\n"
" pxor 8(%3), %%mm1 ;\n"
" pxor 16(%2), %%mm2 ;\n"
" pxor (%4), %%mm0 ;\n"
" pxor 8(%4), %%mm1 ;\n"
" pxor 16(%3), %%mm2 ;\n"
" movq 24(%1), %%mm3 ;\n"
" pxor (%5), %%mm0 ;\n"
" pxor 8(%5), %%mm1 ;\n"
" movq %%mm0, (%1) ;\n"
" pxor 16(%4), %%mm2 ;\n"
" pxor 24(%2), %%mm3 ;\n"
" movq %%mm1, 8(%1) ;\n"
" pxor 16(%5), %%mm2 ;\n"
" pxor 24(%3), %%mm3 ;\n"
" movq 32(%1), %%mm4 ;\n"
" movq %%mm2, 16(%1) ;\n"
" pxor 24(%4), %%mm3 ;\n"
" pxor 32(%2), %%mm4 ;\n"
" movq 40(%1), %%mm5 ;\n"
" pxor 24(%5), %%mm3 ;\n"
" pxor 32(%3), %%mm4 ;\n"
" pxor 40(%2), %%mm5 ;\n"
" movq %%mm3, 24(%1) ;\n"
" pxor 32(%4), %%mm4 ;\n"
" pxor 40(%3), %%mm5 ;\n"
" movq 48(%1), %%mm6 ;\n"
" movq 56(%1), %%mm7 ;\n"
" pxor 32(%5), %%mm4 ;\n"
" pxor 40(%4), %%mm5 ;\n"
" pxor 48(%2), %%mm6 ;\n"
" pxor 56(%2), %%mm7 ;\n"
" movq %%mm4, 32(%1) ;\n"
" pxor 48(%3), %%mm6 ;\n"
" pxor 56(%3), %%mm7 ;\n"
" pxor 40(%5), %%mm5 ;\n"
" pxor 48(%4), %%mm6 ;\n"
" pxor 56(%4), %%mm7 ;\n"
" movq %%mm5, 40(%1) ;\n"
" pxor 48(%5), %%mm6 ;\n"
" pxor 56(%5), %%mm7 ;\n"
" movq %%mm6, 48(%1) ;\n"
" movq %%mm7, 56(%1) ;\n"
" addl $64, %1 ;\n"
" addl $64, %2 ;\n"
" addl $64, %3 ;\n"
" addl $64, %4 ;\n"
" addl $64, %5 ;\n"
" decl %0 ;\n"
" jnz 1b ;\n"
: "+r" (lines),
"+r" (p1), "+r" (p2), "+r" (p3)
: "r" (p4), "r" (p5)
: "memory");
/* p4 and p5 were modified, and now the variables are dead.
Clobber them just to be sure nobody does something stupid
like assuming they have some legal value. */
asm("" : "=r" (p4), "=r" (p5));
kernel_fpu_end();
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Linus Torvalds (pre-git) | 45 | 80.36% | 1 | 25.00% |
| Joe Perches | 5 | 8.93% | 1 | 25.00% |
| Linus Torvalds | 4 | 7.14% | 1 | 25.00% |
| Alexandre Oliva | 2 | 3.57% | 1 | 25.00% |
| Total | 56 | 100.00% | 4 | 100.00% |
static struct xor_block_template xor_block_pII_mmx = {
.name = "pII_mmx",
.do_2 = xor_pII_mmx_2,
.do_3 = xor_pII_mmx_3,
.do_4 = xor_pII_mmx_4,
.do_5 = xor_pII_mmx_5,
};
static struct xor_block_template xor_block_p5_mmx = {
.name = "p5_mmx",
.do_2 = xor_p5_mmx_2,
.do_3 = xor_p5_mmx_3,
.do_4 = xor_p5_mmx_4,
.do_5 = xor_p5_mmx_5,
};
static struct xor_block_template xor_block_pIII_sse = {
.name = "pIII_sse",
.do_2 = xor_sse_2,
.do_3 = xor_sse_3,
.do_4 = xor_sse_4,
.do_5 = xor_sse_5,
};
/* Also try the AVX routines */
#include <asm/xor_avx.h>
/* Also try the generic routines. */
#include <asm-generic/xor.h>
/* We force the use of the SSE xor block because it can write around L2.
We may also be able to load into the L1 only depending on how the cpu
deals with a load to a line that is being prefetched. */
#undef XOR_TRY_TEMPLATES
#define XOR_TRY_TEMPLATES \
do { \
AVX_XOR_SPEED; \
if (boot_cpu_has(X86_FEATURE_XMM)) { \
xor_speed(&xor_block_pIII_sse); \
xor_speed(&xor_block_sse_pf64); \
} else if (boot_cpu_has(X86_FEATURE_MMX)) { \
xor_speed(&xor_block_pII_mmx); \
xor_speed(&xor_block_p5_mmx); \
} else { \
xor_speed(&xor_block_8regs); \
xor_speed(&xor_block_8regs_p); \
xor_speed(&xor_block_32regs); \
xor_speed(&xor_block_32regs_p); \
} \
} while (0)
#endif /* _ASM_X86_XOR_32_H */
Overall Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Linus Torvalds (pre-git) | 496 | 80.78% | 1 | 6.67% |
| Linus Torvalds | 32 | 5.21% | 1 | 6.67% |
| Art Haas | 30 | 4.89% | 1 | 6.67% |
| Joe Perches | 30 | 4.89% | 1 | 6.67% |
| Vegard Nossum | 6 | 0.98% | 1 | 6.67% |
| Alexandre Oliva | 5 | 0.81% | 1 | 6.67% |
| Jim Kukunas | 3 | 0.49% | 1 | 6.67% |
| H. Peter Anvin | 3 | 0.49% | 1 | 6.67% |
| Andi Kleen | 2 | 0.33% | 1 | 6.67% |
| Jan Beulich | 2 | 0.33% | 2 | 13.33% |
| Neil Brown | 2 | 0.33% | 1 | 6.67% |
| David Howells | 1 | 0.16% | 1 | 6.67% |
| Borislav Petkov | 1 | 0.16% | 1 | 6.67% |
| Ingo Molnar | 1 | 0.16% | 1 | 6.67% |
| Total | 614 | 100.00% | 15 | 100.00% |
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.