linux/arch/arc/lib/memcpy-700.S

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

#include <linux/linkage.h>

ENTRY_CFI(memcpy)
	or	r3,r0,r1
	asl_s	r3,r3,30
	mov_s	r5,r0
	brls.d	r2,r3,.Lcopy_bytewise
	sub.f	r3,r2,1
	ld_s	r12,[r1,0]
	asr.f	lp_count,r3,3
	bbit0.d	r3,2,.Lnox4
	bmsk_s	r2,r2,1
	st.ab	r12,[r5,4]
	ld.a	r12,[r1,4]
.Lnox4:
	lppnz	.Lendloop
	ld_s	r3,[r1,4]
	st.ab	r12,[r5,4]
	ld.a	r12,[r1,8]
	st.ab	r3,[r5,4]
.Lendloop:
	breq	r2,0,.Last_store
	ld	r3,[r5,0]
#ifdef __LITTLE_ENDIAN__
	add3	r2,-1,r2
	; uses long immediate
	xor_s	r12,r12,r3
	bmsk	r12,r12,r2
    xor_s	r12,r12,r3
#else /* BIG ENDIAN */
	sub3	r2,31,r2
	; uses long immediate
        xor_s	r3,r3,r12
        bmsk	r3,r3,r2
        xor_s	r12,r12,r3
#endif /* ENDIAN */
.Last_store:
	j_s.d	[blink]
	st	r12,[r5,0]

	.balign	4
.Lcopy_bytewise:
	jcs	[blink]
	ldb_s	r12,[r1,0]
	lsr.f	lp_count,r3
	bhs_s	.Lnox1
	stb.ab	r12,[r5,1]
	ldb.a	r12,[r1,1]
.Lnox1:
	lppnz	.Lendbloop
	ldb_s	r3,[r1,1]
	stb.ab	r12,[r5,1]
	ldb.a	r12,[r1,2]
	stb.ab	r3,[r5,1]
.Lendbloop:
	j_s.d	[blink]
	stb	r12,[r5,0]
END_CFI(memcpy)
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 500 Based on 2 normalized pattern(s): 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 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 # extracted by the scancode license scanner the SPDX license identifier GPL-2.0-only has been chosen to replace the boilerplate/reference in 4122 file(s). Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Enrico Weigelt <info@metux.net> Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Allison Randal <allison@lohutok.net> Cc: linux-spdx@vger.kernel.org Link: https://lkml.kernel.org/r/20190604081206.933168790@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 2019-06-04 08:11:33 +00:00			`/* SPDX-License-Identifier: GPL-2.0-only */`
ARC: String library Hand optimised asm code for ARC700 pipeline. Originally written/optimized by Joern Rennecke Signed-off-by: Vineet Gupta <vgupta@synopsys.com> Cc: Joern Rennecke <joern.rennecke@embecosm.com> 2013-01-18 09:42:18 +00:00			`/*`
			`* Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)`
			`*/`

ARC: switch to generic ENTRY/END assembler annotations With commit 9df62f054406 "arch: use ASM_NL instead of ';'" the generic macros can handle the arch specific newline quirk. Hence we can get rid of ARC asm macros and use the "C" style macros. Signed-off-by: Vineet Gupta <vgupta@synopsys.com> 2014-02-07 08:17:43 +00:00			`#include <linux/linkage.h>`
ARC: String library Hand optimised asm code for ARC700 pipeline. Originally written/optimized by Joern Rennecke Signed-off-by: Vineet Gupta <vgupta@synopsys.com> Cc: Joern Rennecke <joern.rennecke@embecosm.com> 2013-01-18 09:42:18 +00:00
ARC: dw2 unwind: enable cfi pseudo ops in string lib This uses a new set of annoations viz. ENTRY_CFI/END_CFI to enabel cfi ops generation. Note that we didn't change the normal ENTRY/EXIT as we don't actually want unwind info in the trap/exception/interrutp handlers which use these, as unwinder then gets confused (it keeps recursing vs. stopping). Semantically these are leaf routines and unwinding should stop when it hits those routines. Before ------ 28.52% 1.19% 9929 hackbench libuClibc-1.0.17.so [.] __write_nocancel \| ---__write_nocancel \|--8.95%--EV_Trap \| --8.25%--sys_write \| \|--3.93%--sock_write_iter ... \|--2.62%--memset <==== [LEAF entry as no unwind info] ^^^^^^ After ----- 29.46% 1.24% 13622 hackbench libuClibc-1.0.17.so [.] __write_nocancel \| ---__write_nocancel \|--9.31%--EV_Trap \| --8.62%--sys_write \| \|--4.17%--sock_write_iter ... \|--6.19%--sys_write \| --6.19%--sock_write_iter \| unix_stream_sendmsg \| \|--1.62%--sock_alloc_send_pskb \| \|--0.89%--sock_def_readable \| \|--0.88%--_raw_spin_unlock_irqrestore \| \|--0.69%--memset \| \| ^^^^^^ <==== [now in proper callframe] \| \| \| --0.52%--skb_copy_datagram_from_iter Signed-off-by: Vineet Gupta <vgupta@synopsys.com> 2016-09-19 23:42:25 +00:00			`ENTRY_CFI(memcpy)`
ARC: String library Hand optimised asm code for ARC700 pipeline. Originally written/optimized by Joern Rennecke Signed-off-by: Vineet Gupta <vgupta@synopsys.com> Cc: Joern Rennecke <joern.rennecke@embecosm.com> 2013-01-18 09:42:18 +00:00			`or r3,r0,r1`
			`asl_s r3,r3,30`
			`mov_s r5,r0`
			`brls.d r2,r3,.Lcopy_bytewise`
			`sub.f r3,r2,1`
			`ld_s r12,[r1,0]`
			`asr.f lp_count,r3,3`
			`bbit0.d r3,2,.Lnox4`
			`bmsk_s r2,r2,1`
			`st.ab r12,[r5,4]`
			`ld.a r12,[r1,4]`
			`.Lnox4:`
			`lppnz .Lendloop`
			`ld_s r3,[r1,4]`
			`st.ab r12,[r5,4]`
			`ld.a r12,[r1,8]`
			`st.ab r3,[r5,4]`
			`.Lendloop:`
			`breq r2,0,.Last_store`
			`ld r3,[r5,0]`
			`#ifdef __LITTLE_ENDIAN__`
			`add3 r2,-1,r2`
			`; uses long immediate`
			`xor_s r12,r12,r3`
			`bmsk r12,r12,r2`
			`xor_s r12,r12,r3`
			`#else /* BIG ENDIAN */`
			`sub3 r2,31,r2`
			`; uses long immediate`
			`xor_s r3,r3,r12`
			`bmsk r3,r3,r2`
			`xor_s r12,r12,r3`
			`#endif /* ENDIAN */`
			`.Last_store:`
			`j_s.d [blink]`
			`st r12,[r5,0]`

			`.balign 4`
			`.Lcopy_bytewise:`
			`jcs [blink]`
			`ldb_s r12,[r1,0]`
			`lsr.f lp_count,r3`
			`bhs_s .Lnox1`
			`stb.ab r12,[r5,1]`
			`ldb.a r12,[r1,1]`
			`.Lnox1:`
			`lppnz .Lendbloop`
			`ldb_s r3,[r1,1]`
			`stb.ab r12,[r5,1]`
			`ldb.a r12,[r1,2]`
			`stb.ab r3,[r5,1]`
			`.Lendbloop:`
			`j_s.d [blink]`
			`stb r12,[r5,0]`
ARC: dw2 unwind: enable cfi pseudo ops in string lib This uses a new set of annoations viz. ENTRY_CFI/END_CFI to enabel cfi ops generation. Note that we didn't change the normal ENTRY/EXIT as we don't actually want unwind info in the trap/exception/interrutp handlers which use these, as unwinder then gets confused (it keeps recursing vs. stopping). Semantically these are leaf routines and unwinding should stop when it hits those routines. Before ------ 28.52% 1.19% 9929 hackbench libuClibc-1.0.17.so [.] __write_nocancel \| ---__write_nocancel \|--8.95%--EV_Trap \| --8.25%--sys_write \| \|--3.93%--sock_write_iter ... \|--2.62%--memset <==== [LEAF entry as no unwind info] ^^^^^^ After ----- 29.46% 1.24% 13622 hackbench libuClibc-1.0.17.so [.] __write_nocancel \| ---__write_nocancel \|--9.31%--EV_Trap \| --8.62%--sys_write \| \|--4.17%--sock_write_iter ... \|--6.19%--sys_write \| --6.19%--sock_write_iter \| unix_stream_sendmsg \| \|--1.62%--sock_alloc_send_pskb \| \|--0.89%--sock_def_readable \| \|--0.88%--_raw_spin_unlock_irqrestore \| \|--0.69%--memset \| \| ^^^^^^ <==== [now in proper callframe] \| \| \| --0.52%--skb_copy_datagram_from_iter Signed-off-by: Vineet Gupta <vgupta@synopsys.com> 2016-09-19 23:42:25 +00:00			`END_CFI(memcpy)`