JFIF$        dd7 

Viewing File: /usr/src/kernels/5.14.0-503.33.1.el9_5.x86_64/arch/x86/include/asm/xor_avx.h

/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef _ASM_X86_XOR_AVX_H
#define _ASM_X86_XOR_AVX_H

/*
 * Optimized RAID-5 checksumming functions for AVX
 *
 * Copyright (C) 2012 Intel Corporation
 * Author: Jim Kukunas <james.t.kukunas@linux.intel.com>
 *
 * Based on Ingo Molnar and Zach Brown's respective MMX and SSE routines
 */

#include <linux/compiler.h>
#include <asm/fpu/api.h>

#define BLOCK4(i) \
		BLOCK(32 * i, 0) \
		BLOCK(32 * (i + 1), 1) \
		BLOCK(32 * (i + 2), 2) \
		BLOCK(32 * (i + 3), 3)

#define BLOCK16() \
		BLOCK4(0) \
		BLOCK4(4) \
		BLOCK4(8) \
		BLOCK4(12)

static void xor_avx_2(unsigned long bytes, unsigned long * __restrict p0,
		      const unsigned long * __restrict p1)
{
	unsigned long lines = bytes >> 9;

	kernel_fpu_begin();

	while (lines--) {
#undef BLOCK
#define BLOCK(i, reg) \
do { \
	asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p1[i / sizeof(*p1)])); \
	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm"  #reg : : \
		"m" (p0[i / sizeof(*p0)])); \
	asm volatile("vmovdqa %%ymm" #reg ", %0" : \
		"=m" (p0[i / sizeof(*p0)])); \
} while (0);

		BLOCK16()

		p0 = (unsigned long *)((uintptr_t)p0 + 512);
		p1 = (unsigned long *)((uintptr_t)p1 + 512);
	}

	kernel_fpu_end();
}

static void xor_avx_3(unsigned long bytes, unsigned long * __restrict p0,
		      const unsigned long * __restrict p1,
		      const unsigned long * __restrict p2)
{
	unsigned long lines = bytes >> 9;

	kernel_fpu_begin();

	while (lines--) {
#undef BLOCK
#define BLOCK(i, reg) \
do { \
	asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p2[i / sizeof(*p2)])); \
	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
		"m" (p1[i / sizeof(*p1)])); \
	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
		"m" (p0[i / sizeof(*p0)])); \
	asm volatile("vmovdqa %%ymm" #reg ", %0" : \
		"=m" (p0[i / sizeof(*p0)])); \
} while (0);

		BLOCK16()

		p0 = (unsigned long *)((uintptr_t)p0 + 512);
		p1 = (unsigned long *)((uintptr_t)p1 + 512);
		p2 = (unsigned long *)((uintptr_t)p2 + 512);
	}

	kernel_fpu_end();
}

static void xor_avx_4(unsigned long bytes, unsigned long * __restrict p0,
		      const unsigned long * __restrict p1,
		      const unsigned long * __restrict p2,
		      const unsigned long * __restrict p3)
{
	unsigned long lines = bytes >> 9;

	kernel_fpu_begin();

	while (lines--) {
#undef BLOCK
#define BLOCK(i, reg) \
do { \
	asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p3[i / sizeof(*p3)])); \
	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
		"m" (p2[i / sizeof(*p2)])); \
	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
		"m" (p1[i / sizeof(*p1)])); \
	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
		"m" (p0[i / sizeof(*p0)])); \
	asm volatile("vmovdqa %%ymm" #reg ", %0" : \
		"=m" (p0[i / sizeof(*p0)])); \
} while (0);

		BLOCK16();

		p0 = (unsigned long *)((uintptr_t)p0 + 512);
		p1 = (unsigned long *)((uintptr_t)p1 + 512);
		p2 = (unsigned long *)((uintptr_t)p2 + 512);
		p3 = (unsigned long *)((uintptr_t)p3 + 512);
	}

	kernel_fpu_end();
}

static void xor_avx_5(unsigned long bytes, unsigned long * __restrict p0,
	     const unsigned long * __restrict p1,
	     const unsigned long * __restrict p2,
	     const unsigned long * __restrict p3,
	     const unsigned long * __restrict p4)
{
	unsigned long lines = bytes >> 9;

	kernel_fpu_begin();

	while (lines--) {
#undef BLOCK
#define BLOCK(i, reg) \
do { \
	asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p4[i / sizeof(*p4)])); \
	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
		"m" (p3[i / sizeof(*p3)])); \
	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
		"m" (p2[i / sizeof(*p2)])); \
	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
		"m" (p1[i / sizeof(*p1)])); \
	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
		"m" (p0[i / sizeof(*p0)])); \
	asm volatile("vmovdqa %%ymm" #reg ", %0" : \
		"=m" (p0[i / sizeof(*p0)])); \
} while (0);

		BLOCK16()

		p0 = (unsigned long *)((uintptr_t)p0 + 512);
		p1 = (unsigned long *)((uintptr_t)p1 + 512);
		p2 = (unsigned long *)((uintptr_t)p2 + 512);
		p3 = (unsigned long *)((uintptr_t)p3 + 512);
		p4 = (unsigned long *)((uintptr_t)p4 + 512);
	}

	kernel_fpu_end();
}

static struct xor_block_template xor_block_avx = {
	.name = "avx",
	.do_2 = xor_avx_2,
	.do_3 = xor_avx_3,
	.do_4 = xor_avx_4,
	.do_5 = xor_avx_5,
};

#define AVX_XOR_SPEED \
do { \
	if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE)) \
		xor_speed(&xor_block_avx); \
} while (0)

#define AVX_SELECT(FASTEST) \
	(boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE) ? &xor_block_avx : FASTEST)

#endif
Back to Directory  nL+D550H?Mx ,D"v]qv;6*Zqn)ZP0!1 A "#a$2Qr D8 a Ri[f\mIykIw0cuFcRı?lO7к_f˓[C$殷WF<_W ԣsKcëIzyQy/_LKℂ;C",pFA:/]=H  ~,ls/9ć:[=/#f;)x{ٛEQ )~ =𘙲r*2~ a _V=' kumFD}KYYC)({ *g&f`툪ry`=^cJ.I](*`wq1dđ#̩͑0;H]u搂@:~וKL Nsh}OIR*8:2 !lDJVo(3=M(zȰ+i*NAr6KnSl)!JJӁ* %݉?|D}d5:eP0R;{$X'xF@.ÊB {,WJuQɲRI;9QE琯62fT.DUJ;*cP A\ILNj!J۱+O\͔]ޒS߼Jȧc%ANolՎprULZԛerE2=XDXgVQeӓk yP7U*omQIs,K`)6\G3t?pgjrmۛجwluGtfh9uyP0D;Uڽ"OXlif$)&|ML0Zrm1[HXPlPR0'G=i2N+0e2]]9VTPO׮7h(F*癈'=QVZDF,d߬~TX G[`le69CR(!S2!P <0x<!1AQ "Raq02Br#SCTb ?Ζ"]mH5WR7k.ۛ!}Q~+yԏz|@T20S~Kek *zFf^2X*(@8r?CIuI|֓>^ExLgNUY+{.RѪ τV׸YTD I62'8Y27'\TP.6d&˦@Vqi|8-OΕ]ʔ U=TL8=;6c| !qfF3aů&~$l}'NWUs$Uk^SV:U# 6w++s&r+nڐ{@29 gL u"TÙM=6(^"7r}=6YݾlCuhquympǦ GjhsǜNlɻ}o7#S6aw4!OSrD57%|?x>L |/nD6?/8w#[)L7+6〼T ATg!%5MmZ/c-{1_Je"|^$'O&ޱմTrb$w)R$& N1EtdU3Uȉ1pM"N*(DNyd96.(jQ)X 5cQɎMyW?Q*!R>6=7)Xj5`J]e8%t!+'!1Q5 !1 AQaqё#2"0BRb?Gt^## .llQT $v,,m㵜5ubV =sY+@d{N! dnO<.-B;_wJt6;QJd.Qc%p{ 1,sNDdFHI0ГoXшe黅XۢF:)[FGXƹ/w_cMeD,ʡcc.WDtA$j@:) -# u c1<@ۗ9F)KJ-hpP]_x[qBlbpʖw q"LFGdƶ*s+ډ_Zc"?%t[IP 6J]#=ɺVvvCGsGh1 >)6|ey?Lӣm,4GWUi`]uJVoVDG< SB6ϏQ@ TiUlyOU0kfV~~}SZ@*WUUi##; s/[=!7}"WN]'(L! ~y5g9T̅JkbM' +s:S +B)v@Mj e Cf jE 0Y\QnzG1д~Wo{T9?`Rmyhsy3!HAD]mc1~2LSu7xT;j$`}4->L#vzŏILS ֭T{rjGKC;bpU=-`BsK.SFw4Mq]ZdHS0)tLg