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
|
/* SPDX-License-Identifier: GPL-2.0-or-later */
#ifndef _ASM_POWERPC_SIMPLE_SPINLOCK_H
#define _ASM_POWERPC_SIMPLE_SPINLOCK_H
/*
* Simple spin lock operations.
*
* Copyright (C) 2001-2004 Paul Mackerras <paulus@au.ibm.com>, IBM
* Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
* Copyright (C) 2002 Dave Engebretsen <engebret@us.ibm.com>, IBM
* Rework to support virtual processors
*
* Type of int is used as a full 64b word is not necessary.
*
* (the type definitions are in asm/simple_spinlock_types.h)
*/
#include <linux/irqflags.h>
#include <linux/kcsan-checks.h>
#include <asm/paravirt.h>
#include <asm/paca.h>
#include <asm/synch.h>
#include <asm/ppc-opcode.h>
#ifdef CONFIG_PPC64
/* use 0x800000yy when locked, where yy == CPU number */
#ifdef __BIG_ENDIAN__
#define LOCK_TOKEN (*(u32 *)(&get_paca()->lock_token))
#else
#define LOCK_TOKEN (*(u32 *)(&get_paca()->paca_index))
#endif
#else
#define LOCK_TOKEN 1
#endif
static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
{
return lock.slock == 0;
}
static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
return !arch_spin_value_unlocked(READ_ONCE(*lock));
}
/*
* This returns the old value in the lock, so we succeeded
* in getting the lock if the return value is 0.
*/
static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock)
{
unsigned long tmp, token;
unsigned int eh = IS_ENABLED(CONFIG_PPC64);
token = LOCK_TOKEN;
__asm__ __volatile__(
"1: lwarx %0,0,%2,%[eh]\n\
cmpwi 0,%0,0\n\
bne- 2f\n\
stwcx. %1,0,%2\n\
bne- 1b\n"
PPC_ACQUIRE_BARRIER
"2:"
: "=&r" (tmp)
: "r" (token), "r" (&lock->slock), [eh] "n" (eh)
: "cr0", "memory");
return tmp;
}
static inline int arch_spin_trylock(arch_spinlock_t *lock)
{
return __arch_spin_trylock(lock) == 0;
}
/*
* On a system with shared processors (that is, where a physical
* processor is multiplexed between several virtual processors),
* there is no point spinning on a lock if the holder of the lock
* isn't currently scheduled on a physical processor. Instead
* we detect this situation and ask the hypervisor to give the
* rest of our timeslice to the lock holder.
*
* So that we can tell which virtual processor is holding a lock,
* we put 0x80000000 | smp_processor_id() in the lock when it is
* held. Conveniently, we have a word in the paca that holds this
* value.
*/
#if defined(CONFIG_PPC_SPLPAR)
/* We only yield to the hypervisor if we are in shared processor mode */
void splpar_spin_yield(arch_spinlock_t *lock);
void splpar_rw_yield(arch_rwlock_t *lock);
#else /* SPLPAR */
static inline void splpar_spin_yield(arch_spinlock_t *lock) {}
static inline void splpar_rw_yield(arch_rwlock_t *lock) {}
#endif
static inline void spin_yield(arch_spinlock_t *lock)
{
if (is_shared_processor())
splpar_spin_yield(lock);
else
barrier();
}
static inline void rw_yield(arch_rwlock_t *lock)
{
if (is_shared_processor())
splpar_rw_yield(lock);
else
barrier();
}
static inline void arch_spin_lock(arch_spinlock_t *lock)
{
while (1) {
if (likely(__arch_spin_trylock(lock) == 0))
break;
do {
HMT_low();
if (is_shared_processor())
splpar_spin_yield(lock);
} while (unlikely(lock->slock != 0));
HMT_medium();
}
}
static inline void arch_spin_unlock(arch_spinlock_t *lock)
{
kcsan_mb();
__asm__ __volatile__("# arch_spin_unlock\n\t"
PPC_RELEASE_BARRIER: : :"memory");
lock->slock = 0;
}
/*
* Read-write spinlocks, allowing multiple readers
* but only one writer.
*
* NOTE! it is quite common to have readers in interrupts
* but no interrupt writers. For those circumstances we
* can "mix" irq-safe locks - any writer needs to get a
* irq-safe write-lock, but readers can get non-irqsafe
* read-locks.
*/
#ifdef CONFIG_PPC64
#define __DO_SIGN_EXTEND "extsw %0,%0\n"
#define WRLOCK_TOKEN LOCK_TOKEN /* it's negative */
#else
#define __DO_SIGN_EXTEND
#define WRLOCK_TOKEN (-1)
#endif
/*
* This returns the old value in the lock + 1,
* so we got a read lock if the return value is > 0.
*/
static inline long __arch_read_trylock(arch_rwlock_t *rw)
{
long tmp;
unsigned int eh = IS_ENABLED(CONFIG_PPC64);
__asm__ __volatile__(
"1: lwarx %0,0,%1,%[eh]\n"
__DO_SIGN_EXTEND
" addic. %0,%0,1\n\
ble- 2f\n"
" stwcx. %0,0,%1\n\
bne- 1b\n"
PPC_ACQUIRE_BARRIER
"2:" : "=&r" (tmp)
: "r" (&rw->lock), [eh] "n" (eh)
: "cr0", "xer", "memory");
return tmp;
}
/*
* This returns the old value in the lock,
* so we got the write lock if the return value is 0.
*/
static inline long __arch_write_trylock(arch_rwlock_t *rw)
{
long tmp, token;
unsigned int eh = IS_ENABLED(CONFIG_PPC64);
token = WRLOCK_TOKEN;
__asm__ __volatile__(
"1: lwarx %0,0,%2,%[eh]\n\
cmpwi 0,%0,0\n\
bne- 2f\n"
" stwcx. %1,0,%2\n\
bne- 1b\n"
PPC_ACQUIRE_BARRIER
"2:" : "=&r" (tmp)
: "r" (token), "r" (&rw->lock), [eh] "n" (eh)
: "cr0", "memory");
return tmp;
}
static inline void arch_read_lock(arch_rwlock_t *rw)
{
while (1) {
if (likely(__arch_read_trylock(rw) > 0))
break;
do {
HMT_low();
if (is_shared_processor())
splpar_rw_yield(rw);
} while (unlikely(rw->lock < 0));
HMT_medium();
}
}
static inline void arch_write_lock(arch_rwlock_t *rw)
{
while (1) {
if (likely(__arch_write_trylock(rw) == 0))
break;
do {
HMT_low();
if (is_shared_processor())
splpar_rw_yield(rw);
} while (unlikely(rw->lock != 0));
HMT_medium();
}
}
static inline int arch_read_trylock(arch_rwlock_t *rw)
{
return __arch_read_trylock(rw) > 0;
}
static inline int arch_write_trylock(arch_rwlock_t *rw)
{
return __arch_write_trylock(rw) == 0;
}
static inline void arch_read_unlock(arch_rwlock_t *rw)
{
long tmp;
__asm__ __volatile__(
"# read_unlock\n\t"
PPC_RELEASE_BARRIER
"1: lwarx %0,0,%1\n\
addic %0,%0,-1\n"
" stwcx. %0,0,%1\n\
bne- 1b"
: "=&r"(tmp)
: "r"(&rw->lock)
: "cr0", "xer", "memory");
}
static inline void arch_write_unlock(arch_rwlock_t *rw)
{
__asm__ __volatile__("# write_unlock\n\t"
PPC_RELEASE_BARRIER: : :"memory");
rw->lock = 0;
}
#define arch_spin_relax(lock) spin_yield(lock)
#define arch_read_relax(lock) rw_yield(lock)
#define arch_write_relax(lock) rw_yield(lock)
#endif /* _ASM_POWERPC_SIMPLE_SPINLOCK_H */
|