/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (C) 2013 ARM Ltd.
 * Copyright (C) 2013 Linaro.
 *
 * This code is based on glibc cortex strings work originally authored by Linaro
 * be found @
 *
 * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
 * files/head:/src/aarch64/
 */

#include <linux/linkage.h>
#include <asm/assembler.h>

/*
 * calculate the length of a string
 *
 * Parameters:
 *	x0 - const string pointer
 * Returns:
 *	x0 - the return length of specific string
 */

/* Arguments and results.  */
srcin		.req	x0
len		.req	x0

/* Locals and temporaries.  */
src		.req	x1
data1		.req	x2
data2		.req	x3
data2a		.req	x4
has_nul1	.req	x5
has_nul2	.req	x6
tmp1		.req	x7
tmp2		.req	x8
tmp3		.req	x9
tmp4		.req	x10
zeroones	.req	x11
pos		.req	x12

#define REP8_01 0x0101010101010101
#define REP8_7f 0x7f7f7f7f7f7f7f7f
#define REP8_80 0x8080808080808080

WEAK(strlen)
	mov	zeroones, #REP8_01
	bic	src, srcin, #15
	ands	tmp1, srcin, #15
	b.ne	.Lmisaligned
	/*
	* NUL detection works on the principle that (X - 1) & (~X) & 0x80
	* (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
	* can be done in parallel across the entire word.
	*/
	/*
	* The inner loop deals with two Dwords at a time. This has a
	* slightly higher start-up cost, but we should win quite quickly,
	* especially on cores with a high number of issue slots per
	* cycle, as we get much better parallelism out of the operations.
	*/
.Lloop:
	ldp	data1, data2, [src], #16
.Lrealigned:
	sub	tmp1, data1, zeroones
	orr	tmp2, data1, #REP8_7f
	sub	tmp3, data2, zeroones
	orr	tmp4, data2, #REP8_7f
	bic	has_nul1, tmp1, tmp2
	bics	has_nul2, tmp3, tmp4
	ccmp	has_nul1, #0, #0, eq	/* NZCV = 0000  */
	b.eq	.Lloop

	sub	len, src, srcin
	cbz	has_nul1, .Lnul_in_data2
CPU_BE(	mov	data2, data1 )	/*prepare data to re-calculate the syndrome*/
	sub	len, len, #8
	mov	has_nul2, has_nul1
.Lnul_in_data2:
	/*
	* For big-endian, carry propagation (if the final byte in the
	* string is 0x01) means we cannot use has_nul directly.  The
	* easiest way to get the correct byte is to byte-swap the data
	* and calculate the syndrome a second time.
	*/
CPU_BE( rev	data2, data2 )
CPU_BE( sub	tmp1, data2, zeroones )
CPU_BE( orr	tmp2, data2, #REP8_7f )
CPU_BE( bic	has_nul2, tmp1, tmp2 )

	sub	len, len, #8
	rev	has_nul2, has_nul2
	clz	pos, has_nul2
	add	len, len, pos, lsr #3		/* Bits to bytes.  */
	ret

.Lmisaligned:
	cmp	tmp1, #8
	neg	tmp1, tmp1
	ldp	data1, data2, [src], #16
	lsl	tmp1, tmp1, #3		/* Bytes beyond alignment -> bits.  */
	mov	tmp2, #~0
	/* Big-endian.  Early bytes are at MSB.  */
CPU_BE( lsl	tmp2, tmp2, tmp1 )	/* Shift (tmp1 & 63).  */
	/* Little-endian.  Early bytes are at LSB.  */
CPU_LE( lsr	tmp2, tmp2, tmp1 )	/* Shift (tmp1 & 63).  */

	orr	data1, data1, tmp2
	orr	data2a, data2, tmp2
	csinv	data1, data1, xzr, le
	csel	data2, data2, data2a, le
	b	.Lrealigned
ENDPIPROC(strlen)
EXPORT_SYMBOL_NOKASAN(strlen)