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
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
|
/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Copyright (C) 2013-2014, 2020 Synopsys, Inc. All rights reserved.
*/
#ifndef __ASM_ARC_IO_H
#define __ASM_ARC_IO_H
#include <linux/types.h>
#include <asm/byteorder.h>
#ifdef __ARCHS__
/*
* ARCv2 based HS38 cores are in-order issue, but still weakly ordered
* due to micro-arch buffering/queuing of load/store, cache hit vs. miss ...
*
* Explicit barrier provided by DMB instruction
* - Operand supports fine grained load/store/load+store semantics
* - Ensures that selected memory operation issued before it will complete
* before any subsequent memory operation of same type
* - DMB guarantees SMP as well as local barrier semantics
* (asm-generic/barrier.h ensures sane smp_*mb if not defined here, i.e.
* UP: barrier(), SMP: smp_*mb == *mb)
* - DSYNC provides DMB+completion_of_cache_bpu_maintenance_ops hence not needed
* in the general case. Plus it only provides full barrier.
*/
#define mb() asm volatile("dmb 3\n" : : : "memory")
#define rmb() asm volatile("dmb 1\n" : : : "memory")
#define wmb() asm volatile("dmb 2\n" : : : "memory")
#else
/*
* ARCompact based cores (ARC700) only have SYNC instruction which is super
* heavy weight as it flushes the pipeline as well.
* There are no real SMP implementations of such cores.
*/
#define mb() asm volatile("sync\n" : : : "memory")
#endif
#ifdef __ARCHS__
#define __iormb() rmb()
#define __iowmb() wmb()
#else
#define __iormb() asm volatile("" : : : "memory")
#define __iowmb() asm volatile("" : : : "memory")
#endif
static inline void sync(void)
{
/* Not yet implemented */
}
/*
* We must use 'volatile' in C-version read/write IO accessors implementation
* to avoid merging several reads (writes) into one read (write), or optimizing
* them out by compiler.
*/
#define __arch_getb(a) (*(volatile u8 *)(a))
#define __arch_getw(a) (*(volatile u16 *)(a))
#define __arch_getl(a) (*(volatile u32 *)(a))
#define __arch_getq(a) (*(volatile u64 *)(a))
#define __arch_putb(v, a) (*(volatile u8 *)(a) = (v))
#define __arch_putw(v, a) (*(volatile u16 *)(a) = (v))
#define __arch_putl(v, a) (*(volatile u32 *)(a) = (v))
#define __arch_putq(v, a) (*(volatile u64 *)(a) = (v))
#define __raw_writeb(v, a) __arch_putb(v, a)
#define __raw_writew(v, a) __arch_putw(v, a)
#define __raw_writel(v, a) __arch_putl(v, a)
#define __raw_writeq(v, a) __arch_putq(v, a)
#define __raw_readb(a) __arch_getb(a)
#define __raw_readw(a) __arch_getw(a)
#define __raw_readl(a) __arch_getl(a)
#define __raw_readq(a) __arch_getq(a)
static inline void __raw_writesb(unsigned long addr, const void *data,
int bytelen)
{
u8 *buf = (uint8_t *)data;
while (bytelen--)
__arch_putb(*buf++, addr);
}
static inline void __raw_writesw(unsigned long addr, const void *data,
int wordlen)
{
u16 *buf = (uint16_t *)data;
while (wordlen--)
__arch_putw(*buf++, addr);
}
static inline void __raw_writesl(unsigned long addr, const void *data,
int longlen)
{
u32 *buf = (uint32_t *)data;
while (longlen--)
__arch_putl(*buf++, addr);
}
static inline void __raw_readsb(unsigned long addr, void *data, int bytelen)
{
u8 *buf = (uint8_t *)data;
while (bytelen--)
*buf++ = __arch_getb(addr);
}
static inline void __raw_readsw(unsigned long addr, void *data, int wordlen)
{
u16 *buf = (uint16_t *)data;
while (wordlen--)
*buf++ = __arch_getw(addr);
}
static inline void __raw_readsl(unsigned long addr, void *data, int longlen)
{
u32 *buf = (uint32_t *)data;
while (longlen--)
*buf++ = __arch_getl(addr);
}
/*
* Relaxed I/O memory access primitives. These follow the Device memory
* ordering rules but do not guarantee any ordering relative to Normal memory
* accesses.
*/
#define readb_relaxed(c) ({ u8 __r = __raw_readb(c); __r; })
#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16) \
__raw_readw(c)); __r; })
#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32) \
__raw_readl(c)); __r; })
#define readq_relaxed(c) ({ u64 __r = le64_to_cpu((__force __le64) \
__raw_readq(c)); __r; })
#define writeb_relaxed(v, c) ((void)__raw_writeb((v), (c)))
#define writew_relaxed(v, c) ((void)__raw_writew((__force u16) \
cpu_to_le16(v), (c)))
#define writel_relaxed(v, c) ((void)__raw_writel((__force u32) \
cpu_to_le32(v), (c)))
#define writeq_relaxed(v, c) ((void)__raw_writeq((__force u64) \
cpu_to_le64(v), (c)))
/*
* MMIO can also get buffered/optimized in micro-arch, so barriers needed
* Based on ARM model for the typical use case
*
* <ST [DMA buffer]>
* <writel MMIO "go" reg>
* or:
* <readl MMIO "status" reg>
* <LD [DMA buffer]>
*
* http://lkml.kernel.org/r/20150622133656.GG1583@arm.com
*/
#define readb(c) ({ u8 __v = readb_relaxed(c); __iormb(); __v; })
#define readw(c) ({ u16 __v = readw_relaxed(c); __iormb(); __v; })
#define readl(c) ({ u32 __v = readl_relaxed(c); __iormb(); __v; })
#define readq(c) ({ u64 __v = readq_relaxed(c); __iormb(); __v; })
#define writeb(v, c) ({ __iowmb(); writeb_relaxed(v, c); })
#define writew(v, c) ({ __iowmb(); writew_relaxed(v, c); })
#define writel(v, c) ({ __iowmb(); writel_relaxed(v, c); })
#define writeq(v, c) ({ __iowmb(); writeq_relaxed(v, c); })
#define out_arch(type, endian, a, v) __raw_write##type(cpu_to_##endian(v), a)
#define in_arch(type, endian, a) endian##_to_cpu(__raw_read##type(a))
#define out_le32(a, v) out_arch(l, le32, a, v)
#define out_le16(a, v) out_arch(w, le16, a, v)
#define in_le32(a) in_arch(l, le32, a)
#define in_le16(a) in_arch(w, le16, a)
#define out_be32(a, v) out_arch(l, be32, a, v)
#define out_be16(a, v) out_arch(w, be16, a, v)
#define in_be32(a) in_arch(l, be32, a)
#define in_be16(a) in_arch(w, be16, a)
#define out_8(a, v) __raw_writeb(v, a)
#define in_8(a) __raw_readb(a)
/*
* Clear and set bits in one shot. These macros can be used to clear and
* set multiple bits in a register using a single call. These macros can
* also be used to set a multiple-bit bit pattern using a mask, by
* specifying the mask in the 'clear' parameter and the new bit pattern
* in the 'set' parameter.
*/
#define clrbits(type, addr, clear) \
out_##type((addr), in_##type(addr) & ~(clear))
#define setbits(type, addr, set) \
out_##type((addr), in_##type(addr) | (set))
#define clrsetbits(type, addr, clear, set) \
out_##type((addr), (in_##type(addr) & ~(clear)) | (set))
#define clrbits_be32(addr, clear) clrbits(be32, addr, clear)
#define setbits_be32(addr, set) setbits(be32, addr, set)
#define clrsetbits_be32(addr, clear, set) clrsetbits(be32, addr, clear, set)
#define clrbits_le32(addr, clear) clrbits(le32, addr, clear)
#define setbits_le32(addr, set) setbits(le32, addr, set)
#define clrsetbits_le32(addr, clear, set) clrsetbits(le32, addr, clear, set)
#define clrbits_be16(addr, clear) clrbits(be16, addr, clear)
#define setbits_be16(addr, set) setbits(be16, addr, set)
#define clrsetbits_be16(addr, clear, set) clrsetbits(be16, addr, clear, set)
#define clrbits_le16(addr, clear) clrbits(le16, addr, clear)
#define setbits_le16(addr, set) setbits(le16, addr, set)
#define clrsetbits_le16(addr, clear, set) clrsetbits(le16, addr, clear, set)
#define clrbits_8(addr, clear) clrbits(8, addr, clear)
#define setbits_8(addr, set) setbits(8, addr, set)
#define clrsetbits_8(addr, clear, set) clrsetbits(8, addr, clear, set)
#include <asm-generic/io.h>
#endif /* __ASM_ARC_IO_H */
|
