1/*
2 * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu>
3 * Copyright (C) 2008-2009 PetaLogix
4 * Copyright (C) 2007 John Williams
5 *
6 * Reasonably optimised generic C-code for memcpy on Microblaze
7 * This is generic C code to do efficient, alignment-aware memmove.
8 *
9 * It is based on demo code originally Copyright 2001 by Intel Corp, taken from
10 * http://www.embedded.com/showArticle.jhtml?articleID=19205567
11 *
12 * Attempts were made, unsuccessfully, to contact the original
13 * author of this code (Michael Morrow, Intel).  Below is the original
14 * copyright notice.
15 *
16 * This software has been developed by Intel Corporation.
17 * Intel specifically disclaims all warranties, express or
18 * implied, and all liability, including consequential and
19 * other indirect damages, for the use of this program, including
20 * liability for infringement of any proprietary rights,
21 * and including the warranties of merchantability and fitness
22 * for a particular purpose. Intel does not assume any
23 * responsibility for and errors which may appear in this program
24 * not any responsibility to update it.
25 */
26
27#include <linux/export.h>
28#include <linux/types.h>
29#include <linux/stddef.h>
30#include <linux/compiler.h>
31#include <linux/string.h>
32
33#ifdef CONFIG_OPT_LIB_FUNCTION
34void *memmove(void *v_dst, const void *v_src, __kernel_size_t c)
35{
36	const char *src = v_src;
37	char *dst = v_dst;
38	const uint32_t *i_src;
39	uint32_t *i_dst;
40
41	if (!c)
42		return v_dst;
43
44	/* Use memcpy when source is higher than dest */
45	if (v_dst <= v_src)
46		return memcpy(v_dst, v_src, c);
47
48	/* The following code tries to optimize the copy by using unsigned
49	 * alignment. This will work fine if both source and destination are
50	 * aligned on the same boundary. However, if they are aligned on
51	 * different boundaries shifts will be necessary. This might result in
52	 * bad performance on MicroBlaze systems without a barrel shifter.
53	 */
54	/* FIXME this part needs more test */
55	/* Do a descending copy - this is a bit trickier! */
56	dst += c;
57	src += c;
58
59	if (c >= 4) {
60		unsigned  value, buf_hold;
61
62		/* Align the destination to a word boundary. */
63		/* This is done in an endian independent manner. */
64
65		switch ((unsigned long)dst & 3) {
66		case 3:
67			*--dst = *--src;
68			--c;
69			fallthrough;
70		case 2:
71			*--dst = *--src;
72			--c;
73			fallthrough;
74		case 1:
75			*--dst = *--src;
76			--c;
77		}
78
79		i_dst = (void *)dst;
80		/* Choose a copy scheme based on the source */
81		/* alignment relative to destination. */
82		switch ((unsigned long)src & 3) {
83		case 0x0:	/* Both byte offsets are aligned */
84
85			i_src  = (const void *)src;
86
87			for (; c >= 4; c -= 4)
88				*--i_dst = *--i_src;
89
90			src  = (const void *)i_src;
91			break;
92		case 0x1:	/* Unaligned - Off by 1 */
93			/* Word align the source */
94			i_src = (const void *) (((unsigned)src + 4) & ~3);
95#ifndef __MICROBLAZEEL__
96			/* Load the holding buffer */
97			buf_hold = *--i_src >> 24;
98
99			for (; c >= 4; c -= 4) {
100				value = *--i_src;
101				*--i_dst = buf_hold << 8 | value;
102				buf_hold = value >> 24;
103			}
104#else
105			/* Load the holding buffer */
106			buf_hold = (*--i_src & 0xFF) << 24;
107
108			for (; c >= 4; c -= 4) {
109				value = *--i_src;
110				*--i_dst = buf_hold |
111						((value & 0xFFFFFF00) >> 8);
112				buf_hold = (value  & 0xFF) << 24;
113			}
114#endif
115			/* Realign the source */
116			src = (const void *)i_src;
117			src += 1;
118			break;
119		case 0x2:	/* Unaligned - Off by 2 */
120			/* Word align the source */
121			i_src = (const void *) (((unsigned)src + 4) & ~3);
122#ifndef __MICROBLAZEEL__
123			/* Load the holding buffer */
124			buf_hold = *--i_src >> 16;
125
126			for (; c >= 4; c -= 4) {
127				value = *--i_src;
128				*--i_dst = buf_hold << 16 | value;
129				buf_hold = value >> 16;
130			}
131#else
132			/* Load the holding buffer */
133			buf_hold = (*--i_src & 0xFFFF) << 16;
134
135			for (; c >= 4; c -= 4) {
136				value = *--i_src;
137				*--i_dst = buf_hold |
138						((value & 0xFFFF0000) >> 16);
139				buf_hold = (value & 0xFFFF) << 16;
140			}
141#endif
142			/* Realign the source */
143			src = (const void *)i_src;
144			src += 2;
145			break;
146		case 0x3:	/* Unaligned - Off by 3 */
147			/* Word align the source */
148			i_src = (const void *) (((unsigned)src + 4) & ~3);
149#ifndef __MICROBLAZEEL__
150			/* Load the holding buffer */
151			buf_hold = *--i_src >> 8;
152
153			for (; c >= 4; c -= 4) {
154				value = *--i_src;
155				*--i_dst = buf_hold << 24 | value;
156				buf_hold = value >> 8;
157			}
158#else
159			/* Load the holding buffer */
160			buf_hold = (*--i_src & 0xFFFFFF) << 8;
161
162			for (; c >= 4; c -= 4) {
163				value = *--i_src;
164				*--i_dst = buf_hold |
165						((value & 0xFF000000) >> 24);
166				buf_hold = (value & 0xFFFFFF) << 8;
167			}
168#endif
169			/* Realign the source */
170			src = (const void *)i_src;
171			src += 3;
172			break;
173		}
174		dst = (void *)i_dst;
175	}
176
177	/* simple fast copy, ... unless a cache boundary is crossed */
178	/* Finish off any remaining bytes */
179	switch (c) {
180	case 4:
181		*--dst = *--src;
182		fallthrough;
183	case 3:
184		*--dst = *--src;
185		fallthrough;
186	case 2:
187		*--dst = *--src;
188		fallthrough;
189	case 1:
190		*--dst = *--src;
191	}
192	return v_dst;
193}
194EXPORT_SYMBOL(memmove);
195#endif /* CONFIG_OPT_LIB_FUNCTION */
196