summaryrefslogtreecommitdiffstats
path: root/arch/arm/include/asm/spinlock.h
blob: f8b8965666e9b14842786742f48ccdef49000802 (plain)
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
#ifndef __ASM_SPINLOCK_H
#define __ASM_SPINLOCK_H

#if __LINUX_ARM_ARCH__ < 6
#error SMP not supported on pre-ARMv6 CPUs
#endif

#include <asm/processor.h>

/*
 * sev and wfe are ARMv6K extensions.  Uniprocessor ARMv6 may not have the K
 * extensions, so when running on UP, we have to patch these instructions away.
 */
#define ALT_SMP(smp, up)					\
	"9998:	" smp "\n"					\
	"	.pushsection \".alt.smp.init\", \"a\"\n"	\
	"	.long	9998b\n"				\
	"	" up "\n"					\
	"	.popsection\n"

#ifdef CONFIG_THUMB2_KERNEL
#define SEV		ALT_SMP("sev.w", "nop.w")
/*
 * For Thumb-2, special care is needed to ensure that the conditional WFE
 * instruction really does assemble to exactly 4 bytes (as required by
 * the SMP_ON_UP fixup code).   By itself "wfene" might cause the
 * assembler to insert a extra (16-bit) IT instruction, depending on the
 * presence or absence of neighbouring conditional instructions.
 *
 * To avoid this unpredictableness, an approprite IT is inserted explicitly:
 * the assembler won't change IT instructions which are explicitly present
 * in the input.
 */
#define WFE(cond)	ALT_SMP(		\
	"it " cond "\n\t"			\
	"wfe" cond ".n",			\
						\
	"nop.w"					\
)
#else
#define SEV		ALT_SMP("sev", "nop")
#define WFE(cond)	ALT_SMP("wfe" cond, "nop")
#endif

static inline void dsb_sev(void)
{
#if __LINUX_ARM_ARCH__ >= 7
	__asm__ __volatile__ (
		"dsb\n"
		SEV
	);
#else
	__asm__ __volatile__ (
		"mcr p15, 0, %0, c7, c10, 4\n"
		SEV
		: : "r" (0)
	);
#endif
}

/*
 * ARMv6 ticket-based spin-locking.
 *
 * A memory barrier is required after we get a lock, and before we
 * release it, because V6 CPUs are assumed to have weakly ordered
 * memory.
 */

#define arch_spin_unlock_wait(lock) \
	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)

#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)

static inline void arch_spin_lock(arch_spinlock_t *lock)
{
	unsigned long tmp;
	u32 newval;
	arch_spinlock_t lockval;

	__asm__ __volatile__(
"1:	ldrex	%0, [%3]\n"
"	add	%1, %0, %4\n"
"	strex	%2, %1, [%3]\n"
"	teq	%2, #0\n"
"	bne	1b"
	: "=&r" (lockval), "=&r" (newval), "=&r" (tmp)
	: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
	: "cc");

	while (lockval.tickets.next != lockval.tickets.owner) {
		wfe();
		lockval.tickets.owner = ACCESS_ONCE(lock->tickets.owner);
	}

	smp_mb();
}

static inline int arch_spin_trylock(arch_spinlock_t *lock)
{
	unsigned long contended, res;
	u32 slock;

	do {
		__asm__ __volatile__(
		"	ldrex	%0, [%3]\n"
		"	mov	%2, #0\n"
		"	subs	%1, %0, %0, ror #16\n"
		"	addeq	%0, %0, %4\n"
		"	strexeq	%2, %0, [%3]"
		: "=&r" (slock), "=&r" (contended), "=r" (res)
		: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
		: "cc");
	} while (res);

	if (!contended) {
		smp_mb();
		return 1;
	} else {
		return 0;
	}
}

static inline void arch_spin_unlock(arch_spinlock_t *lock)
{
	smp_mb();
	lock->tickets.owner++;
	dsb_sev();
}

static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
	struct __raw_tickets tickets = ACCESS_ONCE(lock->tickets);
	return tickets.owner != tickets.next;
}

static inline int arch_spin_is_contended(arch_spinlock_t *lock)
{
	struct __raw_tickets tickets = ACCESS_ONCE(lock->tickets);
	return (tickets.next - tickets.owner) > 1;
}
#define arch_spin_is_contended	arch_spin_is_contended

/*
 * RWLOCKS
 *
 *
 * Write locks are easy - we just set bit 31.  When unlocking, we can
 * just write zero since the lock is exclusively held.
 */

static inline void arch_write_lock(arch_rwlock_t *rw)
{
	unsigned long tmp;

	__asm__ __volatile__(
"1:	ldrex	%0, [%1]\n"
"	teq	%0, #0\n"
	WFE("ne")
"	strexeq	%0, %2, [%1]\n"
"	teq	%0, #0\n"
"	bne	1b"
	: "=&r" (tmp)
	: "r" (&rw->lock), "r" (0x80000000)
	: "cc");

	smp_mb();
}

static inline int arch_write_trylock(arch_rwlock_t *rw)
{
	unsigned long tmp;

	__asm__ __volatile__(
"	ldrex	%0, [%1]\n"
"	teq	%0, #0\n"
"	strexeq	%0, %2, [%1]"
	: "=&r" (tmp)
	: "r" (&rw->lock), "r" (0x80000000)
	: "cc");

	if (tmp == 0) {
		smp_mb();
		return 1;
	} else {
		return 0;
	}
}

static inline void arch_write_unlock(arch_rwlock_t *rw)
{
	smp_mb();

	__asm__ __volatile__(
	"str	%1, [%0]\n"
	:
	: "r" (&rw->lock), "r" (0)
	: "cc");

	dsb_sev();
}

/* write_can_lock - would write_trylock() succeed? */
#define arch_write_can_lock(x)		((x)->lock == 0)

/*
 * Read locks are a bit more hairy:
 *  - Exclusively load the lock value.
 *  - Increment it.
 *  - Store new lock value if positive, and we still own this location.
 *    If the value is negative, we've already failed.
 *  - If we failed to store the value, we want a negative result.
 *  - If we failed, try again.
 * Unlocking is similarly hairy.  We may have multiple read locks
 * currently active.  However, we know we won't have any write
 * locks.
 */
static inline void arch_read_lock(arch_rwlock_t *rw)
{
	unsigned long tmp, tmp2;

	__asm__ __volatile__(
"1:	ldrex	%0, [%2]\n"
"	adds	%0, %0, #1\n"
"	strexpl	%1, %0, [%2]\n"
	WFE("mi")
"	rsbpls	%0, %1, #0\n"
"	bmi	1b"
	: "=&r" (tmp), "=&r" (tmp2)
	: "r" (&rw->lock)
	: "cc");

	smp_mb();
}

static inline void arch_read_unlock(arch_rwlock_t *rw)
{
	unsigned long tmp, tmp2;

	smp_mb();

	__asm__ __volatile__(
"1:	ldrex	%0, [%2]\n"
"	sub	%0, %0, #1\n"
"	strex	%1, %0, [%2]\n"
"	teq	%1, #0\n"
"	bne	1b"
	: "=&r" (tmp), "=&r" (tmp2)
	: "r" (&rw->lock)
	: "cc");

	if (tmp == 0)
		dsb_sev();
}

static inline int arch_read_trylock(arch_rwlock_t *rw)
{
	unsigned long tmp, tmp2 = 1;

	__asm__ __volatile__(
"	ldrex	%0, [%2]\n"
"	adds	%0, %0, #1\n"
"	strexpl	%1, %0, [%2]\n"
	: "=&r" (tmp), "+r" (tmp2)
	: "r" (&rw->lock)
	: "cc");

	smp_mb();
	return tmp2 == 0;
}

/* read_can_lock - would read_trylock() succeed? */
#define arch_read_can_lock(x)		((x)->lock < 0x80000000)

#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)

#define arch_spin_relax(lock)	cpu_relax()
#define arch_read_relax(lock)	cpu_relax()
#define arch_write_relax(lock)	cpu_relax()

#endif /* __ASM_SPINLOCK_H */
OpenPOWER on IntegriCloud