[linux-2.6-block.git] / arch / arc / lib / strcpy-700.S

/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
 */

/* If dst and src are 4 byte aligned, copy 8 bytes at a time.
   If the src is 4, but not 8 byte aligned, we first read 4 bytes to get
   it 8 byte aligned.  Thus, we can do a little read-ahead, without
   dereferencing a cache line that we should not touch.
   Note that short and long instructions have been scheduled to avoid
   branch stalls.
   The beq_s to r3z could be made unaligned & long to avoid a stall
   there, but the it is not likely to be taken often, and it
   would also be likey to cost an unaligned mispredict at the next call.  */

#include <linux/linkage.h>

ENTRY_CFI(strcpy)
	or	r2,r0,r1
	bmsk_s	r2,r2,1
	brne.d	r2,0,charloop
	mov_s	r10,r0
	ld_s	r3,[r1,0]
	mov	r8,0x01010101
	bbit0.d	r1,2,loop_start
	ror	r12,r8
	sub	r2,r3,r8
	bic_s	r2,r2,r3
	tst_s	r2,r12
	bne	r3z
	mov_s	r4,r3
	.balign 4
loop:
	ld.a	r3,[r1,4]
	st.ab	r4,[r10,4]
loop_start:
	ld.a	r4,[r1,4]
	sub	r2,r3,r8
	bic_s	r2,r2,r3
	tst_s	r2,r12
	bne_s	r3z
	st.ab	r3,[r10,4]
	sub	r2,r4,r8
	bic	r2,r2,r4
	tst	r2,r12
	beq	loop
	mov_s	r3,r4
#ifdef __LITTLE_ENDIAN__
r3z:	bmsk.f	r1,r3,7
	lsr_s	r3,r3,8
#else
r3z:	lsr.f	r1,r3,24
	asl_s	r3,r3,8
#endif
	bne.d	r3z
	stb.ab	r1,[r10,1]
	j_s	[blink]

	.balign	4
charloop:
	ldb.ab	r3,[r1,1]


	brne.d	r3,0,charloop
	stb.ab	r3,[r10,1]
	j	[blink]
END_CFI(strcpy)
Commit	Line	Data
d2912cb1	1	/* SPDX-License-Identifier: GPL-2.0-only */
5210d1e6 VG	2	/*
5210d1e6 VG	3	* Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
5210d1e6 VG	4	*/
	5
	6	/* If dst and src are 4 byte aligned, copy 8 bytes at a time.
	7	If the src is 4, but not 8 byte aligned, we first read 4 bytes to get
	8	it 8 byte aligned. Thus, we can do a little read-ahead, without
	9	dereferencing a cache line that we should not touch.
	10	Note that short and long instructions have been scheduled to avoid
	11	branch stalls.
	12	The beq_s to r3z could be made unaligned & long to avoid a stall
	13	there, but the it is not likely to be taken often, and it
	14	would also be likey to cost an unaligned mispredict at the next call. */
	15
ec7ac6af	16	#include <linux/linkage.h>
5210d1e6	17
86effd0d	18	ENTRY_CFI(strcpy)
5210d1e6 VG	19	or r2,r0,r1
	20	bmsk_s r2,r2,1
	21	brne.d r2,0,charloop
	22	mov_s r10,r0
	23	ld_s r3,[r1,0]
	24	mov r8,0x01010101
	25	bbit0.d r1,2,loop_start
	26	ror r12,r8
	27	sub r2,r3,r8
	28	bic_s r2,r2,r3
	29	tst_s r2,r12
	30	bne r3z
	31	mov_s r4,r3
	32	.balign 4
	33	loop:
	34	ld.a r3,[r1,4]
	35	st.ab r4,[r10,4]
	36	loop_start:
	37	ld.a r4,[r1,4]
	38	sub r2,r3,r8
	39	bic_s r2,r2,r3
	40	tst_s r2,r12
	41	bne_s r3z
	42	st.ab r3,[r10,4]
	43	sub r2,r4,r8
	44	bic r2,r2,r4
	45	tst r2,r12
	46	beq loop
	47	mov_s r3,r4
	48	#ifdef __LITTLE_ENDIAN__
	49	r3z: bmsk.f r1,r3,7
	50	lsr_s r3,r3,8
	51	#else
	52	r3z: lsr.f r1,r3,24
	53	asl_s r3,r3,8
	54	#endif
	55	bne.d r3z
	56	stb.ab r1,[r10,1]
	57	j_s [blink]
	58
	59	.balign 4
	60	charloop:
	61	ldb.ab r3,[r1,1]
	62
	63
	64	brne.d r3,0,charloop
	65	stb.ab r3,[r10,1]
	66	j [blink]
86effd0d	67	END_CFI(strcpy)