// SPDX-License-Identifier: GPL-2.0-or-later
#include <linux/prefetch.h>
#include "xor_impl.h"

static void
xor_32regs_p_2(unsigned long bytes, unsigned long * __restrict p1,
	       const unsigned long * __restrict p2)
{
	long lines = bytes / (sizeof (long)) / 8 - 1;

	prefetchw(p1);
	prefetch(p2);

	do {
		register long d0, d1, d2, d3, d4, d5, d6, d7;

		prefetchw(p1+8);
		prefetch(p2+8);
 once_more:
		d0 = p1[0];	/* Pull the stuff into registers	*/
		d1 = p1[1];	/*  ... in bursts, if possible.		*/
		d2 = p1[2];
		d3 = p1[3];
		d4 = p1[4];
		d5 = p1[5];
		d6 = p1[6];
		d7 = p1[7];
		d0 ^= p2[0];
		d1 ^= p2[1];
		d2 ^= p2[2];
		d3 ^= p2[3];
		d4 ^= p2[4];
		d5 ^= p2[5];
		d6 ^= p2[6];
		d7 ^= p2[7];
		p1[0] = d0;	/* Store the result (in bursts)		*/
		p1[1] = d1;
		p1[2] = d2;
		p1[3] = d3;
		p1[4] = d4;
		p1[5] = d5;
		p1[6] = d6;
		p1[7] = d7;
		p1 += 8;
		p2 += 8;
	} while (--lines > 0);
	if (lines == 0)
		goto once_more;
}

static void
xor_32regs_p_3(unsigned long bytes, unsigned long * __restrict p1,
	       const unsigned long * __restrict p2,
	       const unsigned long * __restrict p3)
{
	long lines = bytes / (sizeof (long)) / 8 - 1;

	prefetchw(p1);
	prefetch(p2);
	prefetch(p3);

	do {
		register long d0, d1, d2, d3, d4, d5, d6, d7;

		prefetchw(p1+8);
		prefetch(p2+8);
		prefetch(p3+8);
 once_more:
		d0 = p1[0];	/* Pull the stuff into registers	*/
		d1 = p1[1];	/*  ... in bursts, if possible.		*/
		d2 = p1[2];
		d3 = p1[3];
		d4 = p1[4];
		d5 = p1[5];
		d6 = p1[6];
		d7 = p1[7];
		d0 ^= p2[0];
		d1 ^= p2[1];
		d2 ^= p2[2];
		d3 ^= p2[3];
		d4 ^= p2[4];
		d5 ^= p2[5];
		d6 ^= p2[6];
		d7 ^= p2[7];
		d0 ^= p3[0];
		d1 ^= p3[1];
		d2 ^= p3[2];
		d3 ^= p3[3];
		d4 ^= p3[4];
		d5 ^= p3[5];
		d6 ^= p3[6];
		d7 ^= p3[7];
		p1[0] = d0;	/* Store the result (in bursts)		*/
		p1[1] = d1;
		p1[2] = d2;
		p1[3] = d3;
		p1[4] = d4;
		p1[5] = d5;
		p1[6] = d6;
		p1[7] = d7;
		p1 += 8;
		p2 += 8;
		p3 += 8;
	} while (--lines > 0);
	if (lines == 0)
		goto once_more;
}

static void
xor_32regs_p_4(unsigned long bytes, unsigned long * __restrict p1,
	       const unsigned long * __restrict p2,
	       const unsigned long * __restrict p3,
	       const unsigned long * __restrict p4)
{
	long lines = bytes / (sizeof (long)) / 8 - 1;

	prefetchw(p1);
	prefetch(p2);
	prefetch(p3);
	prefetch(p4);

	do {
		register long d0, d1, d2, d3, d4, d5, d6, d7;

		prefetchw(p1+8);
		prefetch(p2+8);
		prefetch(p3+8);
		prefetch(p4+8);
 once_more:
		d0 = p1[0];	/* Pull the stuff into registers	*/
		d1 = p1[1];	/*  ... in bursts, if possible.		*/
		d2 = p1[2];
		d3 = p1[3];
		d4 = p1[4];
		d5 = p1[5];
		d6 = p1[6];
		d7 = p1[7];
		d0 ^= p2[0];
		d1 ^= p2[1];
		d2 ^= p2[2];
		d3 ^= p2[3];
		d4 ^= p2[4];
		d5 ^= p2[5];
		d6 ^= p2[6];
		d7 ^= p2[7];
		d0 ^= p3[0];
		d1 ^= p3[1];
		d2 ^= p3[2];
		d3 ^= p3[3];
		d4 ^= p3[4];
		d5 ^= p3[5];
		d6 ^= p3[6];
		d7 ^= p3[7];
		d0 ^= p4[0];
		d1 ^= p4[1];
		d2 ^= p4[2];
		d3 ^= p4[3];
		d4 ^= p4[4];
		d5 ^= p4[5];
		d6 ^= p4[6];
		d7 ^= p4[7];
		p1[0] = d0;	/* Store the result (in bursts)		*/
		p1[1] = d1;
		p1[2] = d2;
		p1[3] = d3;
		p1[4] = d4;
		p1[5] = d5;
		p1[6] = d6;
		p1[7] = d7;
		p1 += 8;
		p2 += 8;
		p3 += 8;
		p4 += 8;
	} while (--lines > 0);
	if (lines == 0)
		goto once_more;
}

static void
xor_32regs_p_5(unsigned long bytes, unsigned long * __restrict p1,
	       const unsigned long * __restrict p2,
	       const unsigned long * __restrict p3,
	       const unsigned long * __restrict p4,
	       const unsigned long * __restrict p5)
{
	long lines = bytes / (sizeof (long)) / 8 - 1;

	prefetchw(p1);
	prefetch(p2);
	prefetch(p3);
	prefetch(p4);
	prefetch(p5);

	do {
		register long d0, d1, d2, d3, d4, d5, d6, d7;

		prefetchw(p1+8);
		prefetch(p2+8);
		prefetch(p3+8);
		prefetch(p4+8);
		prefetch(p5+8);
 once_more:
		d0 = p1[0];	/* Pull the stuff into registers	*/
		d1 = p1[1];	/*  ... in bursts, if possible.		*/
		d2 = p1[2];
		d3 = p1[3];
		d4 = p1[4];
		d5 = p1[5];
		d6 = p1[6];
		d7 = p1[7];
		d0 ^= p2[0];
		d1 ^= p2[1];
		d2 ^= p2[2];
		d3 ^= p2[3];
		d4 ^= p2[4];
		d5 ^= p2[5];
		d6 ^= p2[6];
		d7 ^= p2[7];
		d0 ^= p3[0];
		d1 ^= p3[1];
		d2 ^= p3[2];
		d3 ^= p3[3];
		d4 ^= p3[4];
		d5 ^= p3[5];
		d6 ^= p3[6];
		d7 ^= p3[7];
		d0 ^= p4[0];
		d1 ^= p4[1];
		d2 ^= p4[2];
		d3 ^= p4[3];
		d4 ^= p4[4];
		d5 ^= p4[5];
		d6 ^= p4[6];
		d7 ^= p4[7];
		d0 ^= p5[0];
		d1 ^= p5[1];
		d2 ^= p5[2];
		d3 ^= p5[3];
		d4 ^= p5[4];
		d5 ^= p5[5];
		d6 ^= p5[6];
		d7 ^= p5[7];
		p1[0] = d0;	/* Store the result (in bursts)		*/
		p1[1] = d1;
		p1[2] = d2;
		p1[3] = d3;
		p1[4] = d4;
		p1[5] = d5;
		p1[6] = d6;
		p1[7] = d7;
		p1 += 8;
		p2 += 8;
		p3 += 8;
		p4 += 8;
		p5 += 8;
	} while (--lines > 0);
	if (lines == 0)
		goto once_more;
}

DO_XOR_BLOCKS(32regs_p, xor_32regs_p_2, xor_32regs_p_3, xor_32regs_p_4,
		xor_32regs_p_5);

struct xor_block_template xor_block_32regs_p = {
	.name		= "32regs_prefetch",
	.xor_gen	= xor_gen_32regs_p,
};