/*
 * Copyright (C) 2013 ARM Ltd.
 * Copyright (C) 2013 Linaro.
 *
 * This code is based on glibc cortex strings work originally authored by Linaro
 * and re-licensed under GPLv2 for the Linux kernel. The original code can
 * be found @
 *
 * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
 * files/head:/src/aarch64/
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

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

/*
 * compare two strings
 *
 * Parameters:
 *  x0 - const string 1 pointer
 *  x1 - const string 2 pointer
 *  x2 - the maximal length to be compared
 * Returns:
 *  x0 - an integer less than, equal to, or greater than zero if s1 is found,
 *     respectively, to be less than, to match, or be greater than s2.
 */

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

/* Parameters and result.  */
src1		.req	x0
src2		.req	x1
limit		.req	x2
result		.req	x0

/* Internal variables.  */
data1		.req	x3
data1w		.req	w3
data2		.req	x4
data2w		.req	w4
has_nul		.req	x5
diff		.req	x6
syndrome	.req	x7
tmp1		.req	x8
tmp2		.req	x9
tmp3		.req	x10
zeroones	.req	x11
pos		.req	x12
limit_wd	.req	x13
mask		.req	x14
endloop		.req	x15

ENTRY(strncmp)
	cbz	limit, .Lret0
	eor	tmp1, src1, src2
	mov	zeroones, #REP8_01
	tst	tmp1, #7
	b.ne	.Lmisaligned8
	ands	tmp1, src1, #7
	b.ne	.Lmutual_align
	/* Calculate the number of full and partial words -1.  */
	/*
	* when limit is mulitply of 8, if not sub 1,
	* the judgement of last dword will wrong.
	*/
	sub	limit_wd, limit, #1 /* limit != 0, so no underflow.  */
	lsr	limit_wd, limit_wd, #3  /* Convert to Dwords.  */

	/*
	* 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.
	*/
.Lloop_aligned:
	ldr	data1, [src1], #8
	ldr	data2, [src2], #8
.Lstart_realigned:
	subs	limit_wd, limit_wd, #1
	sub	tmp1, data1, zeroones
	orr	tmp2, data1, #REP8_7f
	eor	diff, data1, data2  /* Non-zero if differences found.  */
	csinv	endloop, diff, xzr, pl  /* Last Dword or differences.*/
	bics	has_nul, tmp1, tmp2 /* Non-zero if NUL terminator.  */
	ccmp	endloop, #0, #0, eq
	b.eq	.Lloop_aligned

	/*Not reached the limit, must have found the end or a diff.  */
	tbz	limit_wd, #63, .Lnot_limit

	/* Limit % 8 == 0 => all bytes significant.  */
	ands	limit, limit, #7
	b.eq	.Lnot_limit

	lsl	limit, limit, #3    /* Bits -> bytes.  */
	mov	mask, #~0
CPU_BE( lsr	mask, mask, limit )
CPU_LE( lsl	mask, mask, limit )
	bic	data1, data1, mask
	bic	data2, data2, mask

	/* Make sure that the NUL byte is marked in the syndrome.  */
	orr	has_nul, has_nul, mask

.Lnot_limit:
	orr	syndrome, diff, has_nul
	b	.Lcal_cmpresult

.Lmutual_align:
	/*
	* Sources are mutually aligned, but are not currently at an
	* alignment boundary.  Round down the addresses and then mask off
	* the bytes that precede the start point.
	* We also need to adjust the limit calculations, but without
	* overflowing if the limit is near ULONG_MAX.
	*/
	bic	src1, src1, #7
	bic	src2, src2, #7
	ldr	data1, [src1], #8
	neg	tmp3, tmp1, lsl #3  /* 64 - bits(bytes beyond align). */
	ldr	data2, [src2], #8
	mov	tmp2, #~0
	sub	limit_wd, limit, #1 /* limit != 0, so no underflow.  */
	/* Big-endian.  Early bytes are at MSB.  */
CPU_BE( lsl	tmp2, tmp2, tmp3 )	/* Shift (tmp1 & 63).  */
	/* Little-endian.  Early bytes are at LSB.  */
CPU_LE( lsr	tmp2, tmp2, tmp3 )	/* Shift (tmp1 & 63).  */

	and	tmp3, limit_wd, #7
	lsr	limit_wd, limit_wd, #3
	/* Adjust the limit. Only low 3 bits used, so overflow irrelevant.*/
	add	limit, limit, tmp1
	add	tmp3, tmp3, tmp1
	orr	data1, data1, tmp2
	orr	data2, data2, tmp2
	add	limit_wd, limit_wd, tmp3, lsr #3
	b	.Lstart_realigned

/*when src1 offset is not equal to src2 offset...*/
.Lmisaligned8:
	cmp	limit, #8
	b.lo	.Ltiny8proc /*limit < 8... */
	/*
	* Get the align offset length to compare per byte first.
	* After this process, one string's address will be aligned.*/
	and	tmp1, src1, #7
	neg	tmp1, tmp1
	add	tmp1, tmp1, #8
	and	tmp2, src2, #7
	neg	tmp2, tmp2
	add	tmp2, tmp2, #8
	subs	tmp3, tmp1, tmp2
	csel	pos, tmp1, tmp2, hi /*Choose the maximum. */
	/*
	* Here, limit is not less than 8, so directly run .Ltinycmp
	* without checking the limit.*/
	sub	limit, limit, pos
.Ltinycmp:
	ldrb	data1w, [src1], #1
	ldrb	data2w, [src2], #1
	subs	pos, pos, #1
	ccmp	data1w, #1, #0, ne  /* NZCV = 0b0000.  */
	ccmp	data1w, data2w, #0, cs  /* NZCV = 0b0000.  */
	b.eq	.Ltinycmp
	cbnz	pos, 1f /*find the null or unequal...*/
	cmp	data1w, #1
	ccmp	data1w, data2w, #0, cs
	b.eq	.Lstart_align /*the last bytes are equal....*/
1:
	sub	result, data1, data2
	ret

.Lstart_align:
	lsr	limit_wd, limit, #3
	cbz	limit_wd, .Lremain8
	/*process more leading bytes to make str1 aligned...*/
	ands	xzr, src1, #7
	b.eq	.Lrecal_offset
	add	src1, src1, tmp3	/*tmp3 is positive in this branch.*/
	add	src2, src2, tmp3
	ldr	data1, [src1], #8
	ldr	data2, [src2], #8

	sub	limit, limit, tmp3
	lsr	limit_wd, limit, #3
	subs	limit_wd, limit_wd, #1

	sub	tmp1, data1, zeroones
	orr	tmp2, data1, #REP8_7f
	eor	diff, data1, data2  /* Non-zero if differences found.  */
	csinv	endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/
	bics	has_nul, tmp1, tmp2
	ccmp	endloop, #0, #0, eq /*has_null is ZERO: no null byte*/
	b.ne	.Lunequal_proc
	/*How far is the current str2 from the alignment boundary...*/
	and	tmp3, tmp3, #7
.Lrecal_offset:
	neg	pos, tmp3
.Lloopcmp_proc:
	/*
	* Divide the eight bytes into two parts. First,backwards the src2
	* to an alignment boundary,load eight bytes from the SRC2 alignment
	* boundary,then compare with the relative bytes from SRC1.
	* If all 8 bytes are equal,then start the second part's comparison.
	* Otherwise finish the comparison.
	* This special handle can garantee all the accesses are in the
	* thread/task space in avoid to overrange access.
	*/
	ldr	data1, [src1,pos]
	ldr	data2, [src2,pos]
	sub	tmp1, data1, zeroones
	orr	tmp2, data1, #REP8_7f
	bics	has_nul, tmp1, tmp2 /* Non-zero if NUL terminator.  */
	eor	diff, data1, data2  /* Non-zero if differences found.  */
	csinv	endloop, diff, xzr, eq
	cbnz	endloop, .Lunequal_proc

	/*The second part process*/
	ldr	data1, [src1], #8
	ldr	data2, [src2], #8
	subs	limit_wd, limit_wd, #1
	sub	tmp1, data1, zeroones
	orr	tmp2, data1, #REP8_7f
	eor	diff, data1, data2  /* Non-zero if differences found.  */
	csinv	endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/
	bics	has_nul, tmp1, tmp2
	ccmp	endloop, #0, #0, eq /*has_null is ZERO: no null byte*/
	b.eq	.Lloopcmp_proc

.Lunequal_proc:
	orr	syndrome, diff, has_nul
	cbz	syndrome, .Lremain8
.Lcal_cmpresult:
	/*
	* reversed the byte-order as big-endian,then CLZ can find the most
	* significant zero bits.
	*/
CPU_LE( rev	syndrome, syndrome )
CPU_LE( rev	data1, data1 )
CPU_LE( rev	data2, data2 )
	/*
	* For big-endian we cannot use the trick with the syndrome value
	* as carry-propagation can corrupt the upper bits if the trailing
	* bytes in the string contain 0x01.
	* However, if there is no NUL byte in the dword, we can generate
	* the result directly.  We can't just subtract the bytes as the
	* MSB might be significant.
	*/
CPU_BE( cbnz	has_nul, 1f )
CPU_BE( cmp	data1, data2 )
CPU_BE( cset	result, ne )
CPU_BE( cneg	result, result, lo )
CPU_BE( ret )
CPU_BE( 1: )
	/* Re-compute the NUL-byte detection, using a byte-reversed value.*/
CPU_BE( rev	tmp3, data1 )
CPU_BE( sub	tmp1, tmp3, zeroones )
CPU_BE( orr	tmp2, tmp3, #REP8_7f )
CPU_BE( bic	has_nul, tmp1, tmp2 )
CPU_BE( rev	has_nul, has_nul )
CPU_BE( orr	syndrome, diff, has_nul )
	/*
	* The MS-non-zero bit of the syndrome marks either the first bit
	* that is different, or the top bit of the first zero byte.
	* Shifting left now will bring the critical information into the
	* top bits.
	*/
	clz	pos, syndrome
	lsl	data1, data1, pos
	lsl	data2, data2, pos
	/*
	* But we need to zero-extend (char is unsigned) the value and then
	* perform a signed 32-bit subtraction.
	*/
	lsr	data1, data1, #56
	sub	result, data1, data2, lsr #56
	ret

.Lremain8:
	/* Limit % 8 == 0 => all bytes significant.  */
	ands	limit, limit, #7
	b.eq	.Lret0
.Ltiny8proc:
	ldrb	data1w, [src1], #1
	ldrb	data2w, [src2], #1
	subs	limit, limit, #1

	ccmp	data1w, #1, #0, ne  /* NZCV = 0b0000.  */
	ccmp	data1w, data2w, #0, cs  /* NZCV = 0b0000.  */
	b.eq	.Ltiny8proc
	sub	result, data1, data2
	ret

.Lret0:
	mov	result, #0
	ret
ENDPROC(strncmp)