arm64: lib: Implement optimized memmove routine

This patch, based on Linaro's Cortex Strings library, improves
the performance of the assembly optimized memmove() function.
Signed-off-by: Zhichang Yuan <zhichang.yuan@linaro.org>
Signed-off-by: Deepak Saxena <dsaxena@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/lib/memmove.S

 /*
  * 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
@@ -16,6 +24,7 @@
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <asm/cache.h>
 
 /*
  * Move a buffer from src to test (alignment handled by the hardware).
@@ -28,30 +37,161 @@
  * Returns:
  *	x0 - dest
  */
+dstin	.req	x0
+src	.req	x1
+count	.req	x2
+tmp1	.req	x3
+tmp1w	.req	w3
+tmp2	.req	x4
+tmp2w	.req	w4
+tmp3	.req	x5
+tmp3w	.req	w5
+dst	.req	x6
+
+A_l	.req	x7
+A_h	.req	x8
+B_l	.req	x9
+B_h	.req	x10
+C_l	.req	x11
+C_h	.req	x12
+D_l	.req	x13
+D_h	.req	x14
+
 ENTRY(memmove)
-	cmp	x0, x1
-	b.ls	memcpy
-	add	x4, x0, x2
-	add	x1, x1, x2
-	subs	x2, x2, #8
-	b.mi	2f
-1:	ldr	x3, [x1, #-8]!
-	subs	x2, x2, #8
-	str	x3, [x4, #-8]!
-	b.pl	1b
-2:	adds	x2, x2, #4
-	b.mi	3f
-	ldr	w3, [x1, #-4]!
-	sub	x2, x2, #4
-	str	w3, [x4, #-4]!
-3:	adds	x2, x2, #2
-	b.mi	4f
-	ldrh	w3, [x1, #-2]!
-	sub	x2, x2, #2
-	strh	w3, [x4, #-2]!
-4:	adds	x2, x2, #1
-	b.mi	5f
-	ldrb	w3, [x1, #-1]
-	strb	w3, [x4, #-1]
-5:	ret
+	cmp	dstin, src
+	b.lo	memcpy
+	add	tmp1, src, count
+	cmp	dstin, tmp1
+	b.hs	memcpy		/* No overlap.  */
+
+	add	dst, dstin, count
+	add	src, src, count
+	cmp	count, #16
+	b.lo	.Ltail15  /*probably non-alignment accesses.*/
+
+	ands	tmp2, src, #15     /* Bytes to reach alignment.  */
+	b.eq	.LSrcAligned
+	sub	count, count, tmp2
+	/*
+	* process the aligned offset length to make the src aligned firstly.
+	* those extra instructions' cost is acceptable. It also make the
+	* coming accesses are based on aligned address.
+	*/
+	tbz	tmp2, #0, 1f
+	ldrb	tmp1w, [src, #-1]!
+	strb	tmp1w, [dst, #-1]!
+1:
+	tbz	tmp2, #1, 2f
+	ldrh	tmp1w, [src, #-2]!
+	strh	tmp1w, [dst, #-2]!
+2:
+	tbz	tmp2, #2, 3f
+	ldr	tmp1w, [src, #-4]!
+	str	tmp1w, [dst, #-4]!
+3:
+	tbz	tmp2, #3, .LSrcAligned
+	ldr	tmp1, [src, #-8]!
+	str	tmp1, [dst, #-8]!
+
+.LSrcAligned:
+	cmp	count, #64
+	b.ge	.Lcpy_over64
+
+	/*
+	* Deal with small copies quickly by dropping straight into the
+	* exit block.
+	*/
+.Ltail63:
+	/*
+	* Copy up to 48 bytes of data. At this point we only need the
+	* bottom 6 bits of count to be accurate.
+	*/
+	ands	tmp1, count, #0x30
+	b.eq	.Ltail15
+	cmp	tmp1w, #0x20
+	b.eq	1f
+	b.lt	2f
+	ldp	A_l, A_h, [src, #-16]!
+	stp	A_l, A_h, [dst, #-16]!
+1:
+	ldp	A_l, A_h, [src, #-16]!
+	stp	A_l, A_h, [dst, #-16]!
+2:
+	ldp	A_l, A_h, [src, #-16]!
+	stp	A_l, A_h, [dst, #-16]!
+
+.Ltail15:
+	tbz	count, #3, 1f
+	ldr	tmp1, [src, #-8]!
+	str	tmp1, [dst, #-8]!
+1:
+	tbz	count, #2, 2f
+	ldr	tmp1w, [src, #-4]!
+	str	tmp1w, [dst, #-4]!
+2:
+	tbz	count, #1, 3f
+	ldrh	tmp1w, [src, #-2]!
+	strh	tmp1w, [dst, #-2]!
+3:
+	tbz	count, #0, .Lexitfunc
+	ldrb	tmp1w, [src, #-1]
+	strb	tmp1w, [dst, #-1]
+
+.Lexitfunc:
+	ret
+
+.Lcpy_over64:
+	subs	count, count, #128
+	b.ge	.Lcpy_body_large
+	/*
+	* Less than 128 bytes to copy, so handle 64 bytes here and then jump
+	* to the tail.
+	*/
+	ldp	A_l, A_h, [src, #-16]
+	stp	A_l, A_h, [dst, #-16]
+	ldp	B_l, B_h, [src, #-32]
+	ldp	C_l, C_h, [src, #-48]
+	stp	B_l, B_h, [dst, #-32]
+	stp	C_l, C_h, [dst, #-48]
+	ldp	D_l, D_h, [src, #-64]!
+	stp	D_l, D_h, [dst, #-64]!
+
+	tst	count, #0x3f
+	b.ne	.Ltail63
+	ret
+
+	/*
+	* Critical loop. Start at a new cache line boundary. Assuming
+	* 64 bytes per line this ensures the entire loop is in one line.
+	*/
+	.p2align	L1_CACHE_SHIFT
+.Lcpy_body_large:
+	/* pre-load 64 bytes data. */
+	ldp	A_l, A_h, [src, #-16]
+	ldp	B_l, B_h, [src, #-32]
+	ldp	C_l, C_h, [src, #-48]
+	ldp	D_l, D_h, [src, #-64]!
+1:
+	/*
+	* interlace the load of next 64 bytes data block with store of the last
+	* loaded 64 bytes data.
+	*/
+	stp	A_l, A_h, [dst, #-16]
+	ldp	A_l, A_h, [src, #-16]
+	stp	B_l, B_h, [dst, #-32]
+	ldp	B_l, B_h, [src, #-32]
+	stp	C_l, C_h, [dst, #-48]
+	ldp	C_l, C_h, [src, #-48]
+	stp	D_l, D_h, [dst, #-64]!
+	ldp	D_l, D_h, [src, #-64]!
+	subs	count, count, #64
+	b.ge	1b
+	stp	A_l, A_h, [dst, #-16]
+	stp	B_l, B_h, [dst, #-32]
+	stp	C_l, C_h, [dst, #-48]
+	stp	D_l, D_h, [dst, #-64]!
+
+	tst	count, #0x3f
+	b.ne	.Ltail63
+	ret
 ENDPROC(memmove)