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
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
|
/* Linux-specific atomic operations for PA Linux.
Copyright (C) 2008 Free Software Foundation, Inc.
Based on code contributed by CodeSourcery for ARM EABI Linux.
Modifications for PA Linux by Helge Deller <deller@gmx.de>
This file is part of GCC.
GCC is free software; you can redistribute it and/or modify it under
the terms of the GNU General Public License as published by the Free
Software Foundation; either version 2, or (at your option) any later
version.
In addition to the permissions in the GNU General Public License, the
Free Software Foundation gives you unlimited permission to link the
compiled version of this file into combinations with other programs,
and to distribute those combinations without any restriction coming
from the use of this file. (The General Public License restrictions
do apply in other respects; for example, they cover modification of
the file, and distribution when not linked into a combine
executable.)
GCC 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 General Public License
for more details.
You should have received a copy of the GNU General Public License
along with GCC; see the file COPYING. If not, write to the Free
Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA
02110-1301, USA. */
/* FIXME: work around build failure for hppa64-linux-gnu target. */
#ifndef _LP64
#include <errno.h>
#else
#define EFAULT 14
#define EBUSY 16
#define ENOSYS 251
#endif
/* All PA-RISC implementations supported by linux have strongly
ordered loads and stores. Only cache flushes and purges can be
delayed. The data cache implementations are all globally
coherent. Thus, there is no need to synchonize memory accesses.
GCC automatically issues a asm memory barrier when it encounters
a __sync_synchronize builtin. Thus, we do not need to define this
builtin.
We implement byte, short and int versions of each atomic operation
using the kernel helper defined below. There is no support for
64-bit operations yet. */
/* A privileged instruction to crash a userspace program with SIGILL. */
#define ABORT_INSTRUCTION asm ("iitlbp %r0,(%sr0, %r0)")
/* Determine kernel LWS function call (0=32-bit, 1=64-bit userspace). */
#define LWS_CAS (sizeof(unsigned long) == 4 ? 0 : 1)
/* Kernel helper for compare-and-exchange a 32-bit value. */
static inline long
__kernel_cmpxchg (int oldval, int newval, int *mem)
{
register unsigned long lws_mem asm("r26") = (unsigned long) (mem);
register long lws_ret asm("r28");
register long lws_errno asm("r21");
register int lws_old asm("r25") = oldval;
register int lws_new asm("r24") = newval;
asm volatile ( "ble 0xb0(%%sr2, %%r0) \n\t"
"ldi %5, %%r20 \n\t"
: "=r" (lws_ret), "=r" (lws_errno), "=r" (lws_mem),
"=r" (lws_old), "=r" (lws_new)
: "i" (LWS_CAS), "2" (lws_mem), "3" (lws_old), "4" (lws_new)
: "r1", "r20", "r22", "r23", "r29", "r31", "memory"
);
if (__builtin_expect (lws_errno == -EFAULT || lws_errno == -ENOSYS, 0))
ABORT_INSTRUCTION;
/* If the kernel LWS call succeeded (lws_errno == 0), lws_ret contains
the old value from memory. If this value is equal to OLDVAL, the
new value was written to memory. If not, return -EBUSY. */
if (!lws_errno && lws_ret != oldval)
lws_errno = -EBUSY;
return lws_errno;
}
#define HIDDEN __attribute__ ((visibility ("hidden")))
/* Big endian masks */
#define INVERT_MASK_1 24
#define INVERT_MASK_2 16
#define MASK_1 0xffu
#define MASK_2 0xffffu
#define FETCH_AND_OP_WORD(OP, PFX_OP, INF_OP) \
int HIDDEN \
__sync_fetch_and_##OP##_4 (int *ptr, int val) \
{ \
int failure, tmp; \
\
do { \
tmp = *ptr; \
failure = __kernel_cmpxchg (tmp, PFX_OP tmp INF_OP val, ptr); \
} while (failure != 0); \
\
return tmp; \
}
FETCH_AND_OP_WORD (add, , +)
FETCH_AND_OP_WORD (sub, , -)
FETCH_AND_OP_WORD (or, , |)
FETCH_AND_OP_WORD (and, , &)
FETCH_AND_OP_WORD (xor, , ^)
FETCH_AND_OP_WORD (nand, ~, &)
#define NAME_oldval(OP, WIDTH) __sync_fetch_and_##OP##_##WIDTH
#define NAME_newval(OP, WIDTH) __sync_##OP##_and_fetch_##WIDTH
/* Implement both __sync_<op>_and_fetch and __sync_fetch_and_<op> for
subword-sized quantities. */
#define SUBWORD_SYNC_OP(OP, PFX_OP, INF_OP, TYPE, WIDTH, RETURN) \
TYPE HIDDEN \
NAME##_##RETURN (OP, WIDTH) (TYPE *ptr, TYPE val) \
{ \
int *wordptr = (int *) ((unsigned long) ptr & ~3); \
unsigned int mask, shift, oldval, newval; \
int failure; \
\
shift = (((unsigned long) ptr & 3) << 3) ^ INVERT_MASK_##WIDTH; \
mask = MASK_##WIDTH << shift; \
\
do { \
oldval = *wordptr; \
newval = ((PFX_OP ((oldval & mask) >> shift) \
INF_OP (unsigned int) val) << shift) & mask; \
newval |= oldval & ~mask; \
failure = __kernel_cmpxchg (oldval, newval, wordptr); \
} while (failure != 0); \
\
return (RETURN & mask) >> shift; \
}
SUBWORD_SYNC_OP (add, , +, short, 2, oldval)
SUBWORD_SYNC_OP (sub, , -, short, 2, oldval)
SUBWORD_SYNC_OP (or, , |, short, 2, oldval)
SUBWORD_SYNC_OP (and, , &, short, 2, oldval)
SUBWORD_SYNC_OP (xor, , ^, short, 2, oldval)
SUBWORD_SYNC_OP (nand, ~, &, short, 2, oldval)
SUBWORD_SYNC_OP (add, , +, char, 1, oldval)
SUBWORD_SYNC_OP (sub, , -, char, 1, oldval)
SUBWORD_SYNC_OP (or, , |, char, 1, oldval)
SUBWORD_SYNC_OP (and, , &, char, 1, oldval)
SUBWORD_SYNC_OP (xor, , ^, char, 1, oldval)
SUBWORD_SYNC_OP (nand, ~, &, char, 1, oldval)
#define OP_AND_FETCH_WORD(OP, PFX_OP, INF_OP) \
int HIDDEN \
__sync_##OP##_and_fetch_4 (int *ptr, int val) \
{ \
int tmp, failure; \
\
do { \
tmp = *ptr; \
failure = __kernel_cmpxchg (tmp, PFX_OP tmp INF_OP val, ptr); \
} while (failure != 0); \
\
return PFX_OP tmp INF_OP val; \
}
OP_AND_FETCH_WORD (add, , +)
OP_AND_FETCH_WORD (sub, , -)
OP_AND_FETCH_WORD (or, , |)
OP_AND_FETCH_WORD (and, , &)
OP_AND_FETCH_WORD (xor, , ^)
OP_AND_FETCH_WORD (nand, ~, &)
SUBWORD_SYNC_OP (add, , +, short, 2, newval)
SUBWORD_SYNC_OP (sub, , -, short, 2, newval)
SUBWORD_SYNC_OP (or, , |, short, 2, newval)
SUBWORD_SYNC_OP (and, , &, short, 2, newval)
SUBWORD_SYNC_OP (xor, , ^, short, 2, newval)
SUBWORD_SYNC_OP (nand, ~, &, short, 2, newval)
SUBWORD_SYNC_OP (add, , +, char, 1, newval)
SUBWORD_SYNC_OP (sub, , -, char, 1, newval)
SUBWORD_SYNC_OP (or, , |, char, 1, newval)
SUBWORD_SYNC_OP (and, , &, char, 1, newval)
SUBWORD_SYNC_OP (xor, , ^, char, 1, newval)
SUBWORD_SYNC_OP (nand, ~, &, char, 1, newval)
int HIDDEN
__sync_val_compare_and_swap_4 (int *ptr, int oldval, int newval)
{
int actual_oldval, fail;
while (1)
{
actual_oldval = *ptr;
if (oldval != actual_oldval)
return actual_oldval;
fail = __kernel_cmpxchg (actual_oldval, newval, ptr);
if (!fail)
return oldval;
}
}
#define SUBWORD_VAL_CAS(TYPE, WIDTH) \
TYPE HIDDEN \
__sync_val_compare_and_swap_##WIDTH (TYPE *ptr, TYPE oldval, \
TYPE newval) \
{ \
int *wordptr = (int *)((unsigned long) ptr & ~3), fail; \
unsigned int mask, shift, actual_oldval, actual_newval; \
\
shift = (((unsigned long) ptr & 3) << 3) ^ INVERT_MASK_##WIDTH; \
mask = MASK_##WIDTH << shift; \
\
while (1) \
{ \
actual_oldval = *wordptr; \
\
if (((actual_oldval & mask) >> shift) != (unsigned int) oldval) \
return (actual_oldval & mask) >> shift; \
\
actual_newval = (actual_oldval & ~mask) \
| (((unsigned int) newval << shift) & mask); \
\
fail = __kernel_cmpxchg (actual_oldval, actual_newval, \
wordptr); \
\
if (!fail) \
return oldval; \
} \
}
SUBWORD_VAL_CAS (short, 2)
SUBWORD_VAL_CAS (char, 1)
typedef unsigned char bool;
bool HIDDEN
__sync_bool_compare_and_swap_4 (int *ptr, int oldval, int newval)
{
int failure = __kernel_cmpxchg (oldval, newval, ptr);
return (failure == 0);
}
#define SUBWORD_BOOL_CAS(TYPE, WIDTH) \
bool HIDDEN \
__sync_bool_compare_and_swap_##WIDTH (TYPE *ptr, TYPE oldval, \
TYPE newval) \
{ \
TYPE actual_oldval \
= __sync_val_compare_and_swap_##WIDTH (ptr, oldval, newval); \
return (oldval == actual_oldval); \
}
SUBWORD_BOOL_CAS (short, 2)
SUBWORD_BOOL_CAS (char, 1)
int HIDDEN
__sync_lock_test_and_set_4 (int *ptr, int val)
{
int failure, oldval;
do {
oldval = *ptr;
failure = __kernel_cmpxchg (oldval, val, ptr);
} while (failure != 0);
return oldval;
}
#define SUBWORD_TEST_AND_SET(TYPE, WIDTH) \
TYPE HIDDEN \
__sync_lock_test_and_set_##WIDTH (TYPE *ptr, TYPE val) \
{ \
int failure; \
unsigned int oldval, newval, shift, mask; \
int *wordptr = (int *) ((unsigned long) ptr & ~3); \
\
shift = (((unsigned long) ptr & 3) << 3) ^ INVERT_MASK_##WIDTH; \
mask = MASK_##WIDTH << shift; \
\
do { \
oldval = *wordptr; \
newval = (oldval & ~mask) \
| (((unsigned int) val << shift) & mask); \
failure = __kernel_cmpxchg (oldval, newval, wordptr); \
} while (failure != 0); \
\
return (oldval & mask) >> shift; \
}
SUBWORD_TEST_AND_SET (short, 2)
SUBWORD_TEST_AND_SET (char, 1)
#define SYNC_LOCK_RELEASE(TYPE, WIDTH) \
void HIDDEN \
__sync_lock_release_##WIDTH (TYPE *ptr) \
{ \
*ptr = 0; \
}
SYNC_LOCK_RELEASE (int, 4)
SYNC_LOCK_RELEASE (short, 2)
SYNC_LOCK_RELEASE (char, 1)
|
