aboutsummaryrefslogtreecommitdiffstats
path: root/arch/sh/include/asm/unaligned-sh4a.h
blob: c48a9c3420da0e63888a2d85710db7dc1931b8db (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
#ifndef __ASM_SH_UNALIGNED_SH4A_H
#define __ASM_SH_UNALIGNED_SH4A_H

/*
 * SH-4A has support for unaligned 32-bit loads, and 32-bit loads only.
 * Support for 64-bit accesses are done through shifting and masking
 * relative to the endianness. Unaligned stores are not supported by the
 * instruction encoding, so these continue to use the packed
 * struct.
 *
 * The same note as with the movli.l/movco.l pair applies here, as long
 * as the load is gauranteed to be inlined, nothing else will hook in to
 * r0 and we get the return value for free.
 *
 * NOTE: Due to the fact we require r0 encoding, care should be taken to
 * avoid mixing these heavily with other r0 consumers, such as the atomic
 * ops. Failure to adhere to this can result in the compiler running out
 * of spill registers and blowing up when building at low optimization
 * levels. See http://gcc.gnu.org/bugzilla/show_bug.cgi?id=34777.
 */
#include <linux/unaligned/packed_struct.h>
#include <linux/types.h>
#include <asm/byteorder.h>

static inline u16 sh4a_get_unaligned_cpu16(const u8 *p)
{
#ifdef __LITTLE_ENDIAN
	return p[0] | p[1] << 8;
#else
	return p[0] << 8 | p[1];
#endif
}

static __always_inline u32 sh4a_get_unaligned_cpu32(const u8 *p)
{
	unsigned long unaligned;

	__asm__ __volatile__ (
		"movua.l	@%1, %0\n\t"
		 : "=z" (unaligned)
		 : "r" (p)
	);

	return unaligned;
}

/*
 * Even though movua.l supports auto-increment on the read side, it can
 * only store to r0 due to instruction encoding constraints, so just let
 * the compiler sort it out on its own.
 */
static inline u64 sh4a_get_unaligned_cpu64(const u8 *p)
{
#ifdef __LITTLE_ENDIAN
	return (u64)sh4a_get_unaligned_cpu32(p + 4) << 32 |
		    sh4a_get_unaligned_cpu32(p);
#else
	return (u64)sh4a_get_unaligned_cpu32(p) << 32 |
		    sh4a_get_unaligned_cpu32(p + 4);
#endif
}

static inline u16 get_unaligned_le16(const void *p)
{
	return le16_to_cpu(sh4a_get_unaligned_cpu16(p));
}

static inline u32 get_unaligned_le32(const void *p)
{
	return le32_to_cpu(sh4a_get_unaligned_cpu32(p));
}

static inline u64 get_unaligned_le64(const void *p)
{
	return le64_to_cpu(sh4a_get_unaligned_cpu64(p));
}

static inline u16 get_unaligned_be16(const void *p)
{
	return be16_to_cpu(sh4a_get_unaligned_cpu16(p));
}

static inline u32 get_unaligned_be32(const void *p)
{
	return be32_to_cpu(sh4a_get_unaligned_cpu32(p));
}

static inline u64 get_unaligned_be64(const void *p)
{
	return be64_to_cpu(sh4a_get_unaligned_cpu64(p));
}

static inline void nonnative_put_le16(u16 val, u8 *p)
{
	*p++ = val;
	*p++ = val >> 8;
}

static inline void nonnative_put_le32(u32 val, u8 *p)
{
	nonnative_put_le16(val, p);
	nonnative_put_le16(val >> 16, p + 2);
}

static inline void nonnative_put_le64(u64 val, u8 *p)
{
	nonnative_put_le32(val, p);
	nonnative_put_le32(val >> 32, p + 4);
}

static inline void nonnative_put_be16(u16 val, u8 *p)
{
	*p++ = val >> 8;
	*p++ = val;
}

static inline void nonnative_put_be32(u32 val, u8 *p)
{
	nonnative_put_be16(val >> 16, p);
	nonnative_put_be16(val, p + 2);
}

static inline void nonnative_put_be64(u64 val, u8 *p)
{
	nonnative_put_be32(val >> 32, p);
	nonnative_put_be32(val, p + 4);
}

static inline void put_unaligned_le16(u16 val, void *p)
{
#ifdef __LITTLE_ENDIAN
	__put_unaligned_cpu16(val, p);
#else
	nonnative_put_le16(val, p);
#endif
}

static inline void put_unaligned_le32(u32 val, void *p)
{
#ifdef __LITTLE_ENDIAN
	__put_unaligned_cpu32(val, p);
#else
	nonnative_put_le32(val, p);
#endif
}

static inline void put_unaligned_le64(u64 val, void *p)
{
#ifdef __LITTLE_ENDIAN
	__put_unaligned_cpu64(val, p);
#else
	nonnative_put_le64(val, p);
#endif
}

static inline void put_unaligned_be16(u16 val, void *p)
{
#ifdef __BIG_ENDIAN
	__put_unaligned_cpu16(val, p);
#else
	nonnative_put_be16(val, p);
#endif
}

static inline void put_unaligned_be32(u32 val, void *p)
{
#ifdef __BIG_ENDIAN
	__put_unaligned_cpu32(val, p);
#else
	nonnative_put_be32(val, p);
#endif
}

static inline void put_unaligned_be64(u64 val, void *p)
{
#ifdef __BIG_ENDIAN
	__put_unaligned_cpu64(val, p);
#else
	nonnative_put_be64(val, p);
#endif
}

/*
 * While it's a bit non-obvious, even though the generic le/be wrappers
 * use the __get/put_xxx prefixing, they actually wrap in to the
 * non-prefixed get/put_xxx variants as provided above.
 */
#include <linux/unaligned/generic.h>

#ifdef __LITTLE_ENDIAN
# define get_unaligned __get_unaligned_le
# define put_unaligned __put_unaligned_le
#else
# define get_unaligned __get_unaligned_be
# define put_unaligned __put_unaligned_be
#endif

#endif /* __ASM_SH_UNALIGNED_SH4A_H */