/* -----------------------------------------------------------------------
 *
 *   neon.uc - RAID-6 syndrome calculation using ARM NEON instructions
 *
 *   Copyright (C) 2012 Rob Herring
 *   Copyright (C) 2015 Linaro Ltd. <ard.biesheuvel@linaro.org>
 *
 *   Based on altivec.uc:
 *     Copyright 2002-2004 H. Peter Anvin - All Rights Reserved
 *
 *   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, Inc., 53 Temple Place Ste 330,
 *   Boston MA 02111-1307, USA; either version 2 of the License, or
 *   (at your option) any later version; incorporated herein by reference.
 *
 * ----------------------------------------------------------------------- */

/*
 * neon$#.c
 *
 * $#-way unrolled NEON intrinsics math RAID-6 instruction set
 *
 * This file is postprocessed using unroll.awk
 */

#include <arm_neon.h>

typedef uint8x16_t unative_t;

#define NBYTES(x) ((unative_t){x,x,x,x, x,x,x,x, x,x,x,x, x,x,x,x})
#define NSIZE	sizeof(unative_t)

/*
 * The SHLBYTE() operation shifts each byte left by 1, *not*
 * rolling over into the next byte
 */
static inline unative_t SHLBYTE(unative_t v)
{
	return vshlq_n_u8(v, 1);
}

/*
 * The MASK() operation returns 0xFF in any byte for which the high
 * bit is 1, 0x00 for any byte for which the high bit is 0.
 */
static inline unative_t MASK(unative_t v)
{
	const uint8x16_t temp = NBYTES(0);
	return (unative_t)vcltq_s8((int8x16_t)v, (int8x16_t)temp);
}

void raid6_neon$#_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs)
{
	uint8_t **dptr = (uint8_t **)ptrs;
	uint8_t *p, *q;
	int d, z, z0;

	register unative_t wd$$, wq$$, wp$$, w1$$, w2$$;
	const unative_t x1d = NBYTES(0x1d);

	z0 = disks - 3;		/* Highest data disk */
	p = dptr[z0+1];		/* XOR parity */
	q = dptr[z0+2];		/* RS syndrome */

	for ( d = 0 ; d < bytes ; d += NSIZE*$# ) {
		wq$$ = wp$$ = vld1q_u8(&dptr[z0][d+$$*NSIZE]);
		for ( z = z0-1 ; z >= 0 ; z-- ) {
			wd$$ = vld1q_u8(&dptr[z][d+$$*NSIZE]);
			wp$$ = veorq_u8(wp$$, wd$$);
			w2$$ = MASK(wq$$);
			w1$$ = SHLBYTE(wq$$);

			w2$$ = vandq_u8(w2$$, x1d);
			w1$$ = veorq_u8(w1$$, w2$$);
			wq$$ = veorq_u8(w1$$, wd$$);
		}
		vst1q_u8(&p[d+NSIZE*$$], wp$$);
		vst1q_u8(&q[d+NSIZE*$$], wq$$);
	}
}

void raid6_neon$#_xor_syndrome_real(int disks, int start, int stop,
				    unsigned long bytes, void **ptrs)
{
	uint8_t **dptr = (uint8_t **)ptrs;
	uint8_t *p, *q;
	int d, z, z0;

	register unative_t wd$$, wq$$, wp$$, w1$$, w2$$;
	const unative_t x1d = NBYTES(0x1d);

	z0 = stop;		/* P/Q right side optimization */
	p = dptr[disks-2];	/* XOR parity */
	q = dptr[disks-1];	/* RS syndrome */

	for ( d = 0 ; d < bytes ; d += NSIZE*$# ) {
		wq$$ = vld1q_u8(&dptr[z0][d+$$*NSIZE]);
		wp$$ = veorq_u8(vld1q_u8(&p[d+$$*NSIZE]), wq$$);

		/* P/Q data pages */
		for ( z = z0-1 ; z >= start ; z-- ) {
			wd$$ = vld1q_u8(&dptr[z][d+$$*NSIZE]);
			wp$$ = veorq_u8(wp$$, wd$$);
			w2$$ = MASK(wq$$);
			w1$$ = SHLBYTE(wq$$);

			w2$$ = vandq_u8(w2$$, x1d);
			w1$$ = veorq_u8(w1$$, w2$$);
			wq$$ = veorq_u8(w1$$, wd$$);
		}
		/* P/Q left side optimization */
		for ( z = start-1 ; z >= 0 ; z-- ) {
			w2$$ = MASK(wq$$);
			w1$$ = SHLBYTE(wq$$);

			w2$$ = vandq_u8(w2$$, x1d);
			wq$$ = veorq_u8(w1$$, w2$$);
		}
		w1$$ = vld1q_u8(&q[d+NSIZE*$$]);
		wq$$ = veorq_u8(wq$$, w1$$);

		vst1q_u8(&p[d+NSIZE*$$], wp$$);
		vst1q_u8(&q[d+NSIZE*$$], wq$$);
	}
}
iv class='content'><div class='cgit-panel'><b>diff options</b><form method='get'><input type='hidden' name='id' value='6ea17ed15d9a343c2d17d76b99501fcad204f309'/><table><tr><td colspan='2'/></tr><tr><td class='label'>context:</td><td class='ctrl'><select name='context' onchange='this.form.submit();'><option value='1'>1</option><option value='2'>2</option><option value='3' selected='selected'>3</option><option value='4'>4</option><option value='5'>5</option><option value='6'>6</option><option value='7'>7</option><option value='8'>8</option><option value='9'>9</option><option value='10'>10</option><option value='15'>15</option><option value='20'>20</option><option value='25'>25</option><option value='30'>30</option><option value='35'>35</option><option value='40'>40</option></select></td></tr><tr><td class='label'>space:</td><td class='ctrl'><select name='ignorews' onchange='this.form.submit();'><option value='0' selected='selected'>include</option><option value='1'>ignore</option></select></td></tr><tr><td class='label'>mode:</td><td class='ctrl'><select name='dt' onchange='this.form.submit();'><option value='0' selected='selected'>unified</option><option value='1'>ssdiff</option><option value='2'>stat only</option></select></td></tr><tr><td/><td class='ctrl'><noscript><input type='submit' value='reload'/></noscript></td></tr></table></form></div><table summary='commit info' class='commit-info'>
<tr><th>author</th><td>Linus Torvalds &lt;torvalds@linux-foundation.org&gt;</td><td class='right'>2017-01-08 11:22:00 -0800</td></tr>
<tr><th>committer</th><td>Linus Torvalds &lt;torvalds@linux-foundation.org&gt;</td><td class='right'>2017-01-08 11:22:00 -0800</td></tr>
<tr><th>commit</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/commit/include/dt-bindings/power/r8a7795-sysc.h?id=6ea17ed15d9a343c2d17d76b99501fcad204f309'>6ea17ed15d9a343c2d17d76b99501fcad204f309</a> (<a href='/cgit.cgi/linux/net-next.git/patch/include/dt-bindings/power/r8a7795-sysc.h?id=6ea17ed15d9a343c2d17d76b99501fcad204f309'>patch</a>)</td></tr>
<tr><th>tree</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/tree/?id=6ea17ed15d9a343c2d17d76b99501fcad204f309'>17a8ce6b61906d57a79e20639bc6330d0b805cc6</a> /<a href='/cgit.cgi/linux/net-next.git/tree/include/dt-bindings/power/r8a7795-sysc.h?id=6ea17ed15d9a343c2d17d76b99501fcad204f309'>include/dt-bindings/power/r8a7795-sysc.h</a></td></tr>
<tr><th>parent</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/commit/include/dt-bindings/power/r8a7795-sysc.h?id=ea07b862ac8ef9b8c8358517d2e39f847dda6659'>ea07b862ac8ef9b8c8358517d2e39f847dda6659</a> (<a href='/cgit.cgi/linux/net-next.git/diff/include/dt-bindings/power/r8a7795-sysc.h?id=6ea17ed15d9a343c2d17d76b99501fcad204f309&amp;id2=ea07b862ac8ef9b8c8358517d2e39f847dda6659'>diff</a>)</td></tr><tr><th>parent</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/commit/include/dt-bindings/power/r8a7795-sysc.h?id=01d0f715869161dc70e2bf66fcdf6533a6a782cd'>01d0f715869161dc70e2bf66fcdf6533a6a782cd</a> (<a href='/cgit.cgi/linux/net-next.git/diff/include/dt-bindings/power/r8a7795-sysc.h?id=6ea17ed15d9a343c2d17d76b99501fcad204f309&amp;id2=01d0f715869161dc70e2bf66fcdf6533a6a782cd'>diff</a>)</td></tr></table>
<div class='commit-subject'>Merge tag 'staging-4.10-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging</div><div class='commit-msg'>Pull staging/IIO fixes from Greg KH:
 "Here are some staging and IIO driver fixes for 4.10-rc3.

  Most of these are minor IIO fixes of reported issues, along with one
  network driver fix to resolve an issue. And a MAINTAINERS update with
  a new mailing list. All of these, except the MAINTAINERS file update,
  have been in linux-next with no reported issues (the MAINTAINERS patch
  happened on Friday...)"

* tag 'staging-4.10-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging:
  MAINTAINERS: add greybus subsystem mailing list
  staging: octeon: Call SET_NETDEV_DEV()
  iio: accel: st_accel: fix LIS3LV02 reading and scaling
  iio: common: st_sensors: fix channel data parsing
  iio: max44000: correct value in illuminance_integration_time_available
  iio: adc: TI_AM335X_ADC should depend on HAS_DMA
  iio: bmi160: Fix time needed to sleep after command execution
  iio: 104-quad-8: Fix active level mismatch for the preset enable option
  iio: 104-quad-8: Fix off-by-one errors when addressing IOR
  iio: 104-quad-8: Fix index control configuration
</div><div class='diffstat-header'><a href='/cgit.cgi/linux/net-next.git/diff/?id=6ea17ed15d9a343c2d17d76b99501fcad204f309'>Diffstat</a> (limited to 'include/dt-bindings/power/r8a7795-sysc.h')</div><table summary='diffstat' class='diffstat'>