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
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
|
/*
* Atomic helper templates
* Included from tcg-runtime.c and cputlb.c.
*
* Copyright (c) 2016 Red Hat, Inc
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, see <http://www.gnu.org/licenses/>.
*/
#include "qemu/plugin.h"
#if DATA_SIZE == 16
# define SUFFIX o
# define DATA_TYPE Int128
# define BSWAP bswap128
# define SHIFT 4
#elif DATA_SIZE == 8
# define SUFFIX q
# define DATA_TYPE aligned_uint64_t
# define SDATA_TYPE aligned_int64_t
# define BSWAP bswap64
# define SHIFT 3
#elif DATA_SIZE == 4
# define SUFFIX l
# define DATA_TYPE uint32_t
# define SDATA_TYPE int32_t
# define BSWAP bswap32
# define SHIFT 2
#elif DATA_SIZE == 2
# define SUFFIX w
# define DATA_TYPE uint16_t
# define SDATA_TYPE int16_t
# define BSWAP bswap16
# define SHIFT 1
#elif DATA_SIZE == 1
# define SUFFIX b
# define DATA_TYPE uint8_t
# define SDATA_TYPE int8_t
# define BSWAP
# define SHIFT 0
#else
# error unsupported data size
#endif
#if DATA_SIZE >= 4
# define ABI_TYPE DATA_TYPE
#else
# define ABI_TYPE uint32_t
#endif
/* Define host-endian atomic operations. Note that END is used within
the ATOMIC_NAME macro, and redefined below. */
#if DATA_SIZE == 1
# define END
#elif HOST_BIG_ENDIAN
# define END _be
#else
# define END _le
#endif
ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, abi_ptr addr,
ABI_TYPE cmpv, ABI_TYPE newv,
MemOpIdx oi, uintptr_t retaddr)
{
DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr);
DATA_TYPE ret;
#if DATA_SIZE == 16
ret = atomic16_cmpxchg(haddr, cmpv, newv);
#else
ret = qatomic_cmpxchg__nocheck(haddr, cmpv, newv);
#endif
ATOMIC_MMU_CLEANUP;
atomic_trace_rmw_post(env, addr, oi);
return ret;
}
#if DATA_SIZE < 16
ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, abi_ptr addr, ABI_TYPE val,
MemOpIdx oi, uintptr_t retaddr)
{
DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr);
DATA_TYPE ret;
ret = qatomic_xchg__nocheck(haddr, val);
ATOMIC_MMU_CLEANUP;
atomic_trace_rmw_post(env, addr, oi);
return ret;
}
#define GEN_ATOMIC_HELPER(X) \
ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, abi_ptr addr, \
ABI_TYPE val, MemOpIdx oi, uintptr_t retaddr) \
{ \
DATA_TYPE *haddr, ret; \
haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr); \
ret = qatomic_##X(haddr, val); \
ATOMIC_MMU_CLEANUP; \
atomic_trace_rmw_post(env, addr, oi); \
return ret; \
}
GEN_ATOMIC_HELPER(fetch_add)
GEN_ATOMIC_HELPER(fetch_and)
GEN_ATOMIC_HELPER(fetch_or)
GEN_ATOMIC_HELPER(fetch_xor)
GEN_ATOMIC_HELPER(add_fetch)
GEN_ATOMIC_HELPER(and_fetch)
GEN_ATOMIC_HELPER(or_fetch)
GEN_ATOMIC_HELPER(xor_fetch)
#undef GEN_ATOMIC_HELPER
/*
* These helpers are, as a whole, full barriers. Within the helper,
* the leading barrier is explicit and the trailing barrier is within
* cmpxchg primitive.
*
* Trace this load + RMW loop as a single RMW op. This way, regardless
* of CF_PARALLEL's value, we'll trace just a read and a write.
*/
#define GEN_ATOMIC_HELPER_FN(X, FN, XDATA_TYPE, RET) \
ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, abi_ptr addr, \
ABI_TYPE xval, MemOpIdx oi, uintptr_t retaddr) \
{ \
XDATA_TYPE *haddr, cmp, old, new, val = xval; \
haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr); \
smp_mb(); \
cmp = qatomic_read__nocheck(haddr); \
do { \
old = cmp; new = FN(old, val); \
cmp = qatomic_cmpxchg__nocheck(haddr, old, new); \
} while (cmp != old); \
ATOMIC_MMU_CLEANUP; \
atomic_trace_rmw_post(env, addr, oi); \
return RET; \
}
GEN_ATOMIC_HELPER_FN(fetch_smin, MIN, SDATA_TYPE, old)
GEN_ATOMIC_HELPER_FN(fetch_umin, MIN, DATA_TYPE, old)
GEN_ATOMIC_HELPER_FN(fetch_smax, MAX, SDATA_TYPE, old)
GEN_ATOMIC_HELPER_FN(fetch_umax, MAX, DATA_TYPE, old)
GEN_ATOMIC_HELPER_FN(smin_fetch, MIN, SDATA_TYPE, new)
GEN_ATOMIC_HELPER_FN(umin_fetch, MIN, DATA_TYPE, new)
GEN_ATOMIC_HELPER_FN(smax_fetch, MAX, SDATA_TYPE, new)
GEN_ATOMIC_HELPER_FN(umax_fetch, MAX, DATA_TYPE, new)
#undef GEN_ATOMIC_HELPER_FN
#endif /* DATA SIZE < 16 */
#undef END
#if DATA_SIZE > 1
/* Define reverse-host-endian atomic operations. Note that END is used
within the ATOMIC_NAME macro. */
#if HOST_BIG_ENDIAN
# define END _le
#else
# define END _be
#endif
ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, abi_ptr addr,
ABI_TYPE cmpv, ABI_TYPE newv,
MemOpIdx oi, uintptr_t retaddr)
{
DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr);
DATA_TYPE ret;
#if DATA_SIZE == 16
ret = atomic16_cmpxchg(haddr, BSWAP(cmpv), BSWAP(newv));
#else
ret = qatomic_cmpxchg__nocheck(haddr, BSWAP(cmpv), BSWAP(newv));
#endif
ATOMIC_MMU_CLEANUP;
atomic_trace_rmw_post(env, addr, oi);
return BSWAP(ret);
}
#if DATA_SIZE < 16
ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, abi_ptr addr, ABI_TYPE val,
MemOpIdx oi, uintptr_t retaddr)
{
DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr);
ABI_TYPE ret;
ret = qatomic_xchg__nocheck(haddr, BSWAP(val));
ATOMIC_MMU_CLEANUP;
atomic_trace_rmw_post(env, addr, oi);
return BSWAP(ret);
}
#define GEN_ATOMIC_HELPER(X) \
ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, abi_ptr addr, \
ABI_TYPE val, MemOpIdx oi, uintptr_t retaddr) \
{ \
DATA_TYPE *haddr, ret; \
haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr); \
ret = qatomic_##X(haddr, BSWAP(val)); \
ATOMIC_MMU_CLEANUP; \
atomic_trace_rmw_post(env, addr, oi); \
return BSWAP(ret); \
}
GEN_ATOMIC_HELPER(fetch_and)
GEN_ATOMIC_HELPER(fetch_or)
GEN_ATOMIC_HELPER(fetch_xor)
GEN_ATOMIC_HELPER(and_fetch)
GEN_ATOMIC_HELPER(or_fetch)
GEN_ATOMIC_HELPER(xor_fetch)
#undef GEN_ATOMIC_HELPER
/* These helpers are, as a whole, full barriers. Within the helper,
* the leading barrier is explicit and the trailing barrier is within
* cmpxchg primitive.
*
* Trace this load + RMW loop as a single RMW op. This way, regardless
* of CF_PARALLEL's value, we'll trace just a read and a write.
*/
#define GEN_ATOMIC_HELPER_FN(X, FN, XDATA_TYPE, RET) \
ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, abi_ptr addr, \
ABI_TYPE xval, MemOpIdx oi, uintptr_t retaddr) \
{ \
XDATA_TYPE *haddr, ldo, ldn, old, new, val = xval; \
haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr); \
smp_mb(); \
ldn = qatomic_read__nocheck(haddr); \
do { \
ldo = ldn; old = BSWAP(ldo); new = FN(old, val); \
ldn = qatomic_cmpxchg__nocheck(haddr, ldo, BSWAP(new)); \
} while (ldo != ldn); \
ATOMIC_MMU_CLEANUP; \
atomic_trace_rmw_post(env, addr, oi); \
return RET; \
}
GEN_ATOMIC_HELPER_FN(fetch_smin, MIN, SDATA_TYPE, old)
GEN_ATOMIC_HELPER_FN(fetch_umin, MIN, DATA_TYPE, old)
GEN_ATOMIC_HELPER_FN(fetch_smax, MAX, SDATA_TYPE, old)
GEN_ATOMIC_HELPER_FN(fetch_umax, MAX, DATA_TYPE, old)
GEN_ATOMIC_HELPER_FN(smin_fetch, MIN, SDATA_TYPE, new)
GEN_ATOMIC_HELPER_FN(umin_fetch, MIN, DATA_TYPE, new)
GEN_ATOMIC_HELPER_FN(smax_fetch, MAX, SDATA_TYPE, new)
GEN_ATOMIC_HELPER_FN(umax_fetch, MAX, DATA_TYPE, new)
/* Note that for addition, we need to use a separate cmpxchg loop instead
of bswaps for the reverse-host-endian helpers. */
#define ADD(X, Y) (X + Y)
GEN_ATOMIC_HELPER_FN(fetch_add, ADD, DATA_TYPE, old)
GEN_ATOMIC_HELPER_FN(add_fetch, ADD, DATA_TYPE, new)
#undef ADD
#undef GEN_ATOMIC_HELPER_FN
#endif /* DATA_SIZE < 16 */
#undef END
#endif /* DATA_SIZE > 1 */
#undef BSWAP
#undef ABI_TYPE
#undef DATA_TYPE
#undef SDATA_TYPE
#undef SUFFIX
#undef DATA_SIZE
#undef SHIFT
|
