summaryrefslogtreecommitdiffstats
path: root/arch/arm64/include/asm/spinlock.h
blob: 89206b568cd42365090a8be788da1bbd35466f72 (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
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
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
/*
 * Copyright (C) 2012 ARM Ltd.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program 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 this program.  If not, see <http://www.gnu.org/licenses/>.
 */
#ifndef __ASM_SPINLOCK_H
#define __ASM_SPINLOCK_H

#include <asm/lse.h>
#include <asm/spinlock_types.h>
#include <asm/processor.h>

/*
 * Spinlock implementation.
 *
 * The memory barriers are implicit with the load-acquire and store-release
 * instructions.
 */
static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
{
	unsigned int tmp;
	arch_spinlock_t lockval;
	u32 owner;

	/*
	 * Ensure prior spin_lock operations to other locks have completed
	 * on this CPU before we test whether "lock" is locked.
	 */
	smp_mb();
	owner = READ_ONCE(lock->owner) << 16;

	asm volatile(
"	sevl\n"
"1:	wfe\n"
"2:	ldaxr	%w0, %2\n"
	/* Is the lock free? */
"	eor	%w1, %w0, %w0, ror #16\n"
"	cbz	%w1, 3f\n"
	/* Lock taken -- has there been a subsequent unlock->lock transition? */
"	eor	%w1, %w3, %w0, lsl #16\n"
"	cbz	%w1, 1b\n"
	/*
	 * The owner has been updated, so there was an unlock->lock
	 * transition that we missed. That means we can rely on the
	 * store-release of the unlock operation paired with the
	 * load-acquire of the lock operation to publish any of our
	 * previous stores to the new lock owner and therefore don't
	 * need to bother with the writeback below.
	 */
"	b	4f\n"
"3:\n"
	/*
	 * Serialise against any concurrent lockers by writing back the
	 * unlocked lock value
	 */
	ARM64_LSE_ATOMIC_INSN(
	/* LL/SC */
"	stxr	%w1, %w0, %2\n"
"	nop\n"
"	nop\n",
	/* LSE atomics */
"	mov	%w1, %w0\n"
"	cas	%w0, %w0, %2\n"
"	eor	%w1, %w1, %w0\n")
	/* Somebody else wrote to the lock, GOTO 10 and reload the value */
"	cbnz	%w1, 2b\n"
"4:"
	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
	: "r" (owner)
	: "memory");
}

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

static inline void arch_spin_lock(arch_spinlock_t *lock)
{
	unsigned int tmp;
	arch_spinlock_t lockval, newval;

	asm volatile(
	/* Atomically increment the next ticket. */
	ARM64_LSE_ATOMIC_INSN(
	/* LL/SC */
"	prfm	pstl1strm, %3\n"
"1:	ldaxr	%w0, %3\n"
"	add	%w1, %w0, %w5\n"
"	stxr	%w2, %w1, %3\n"
"	cbnz	%w2, 1b\n",
	/* LSE atomics */
"	mov	%w2, %w5\n"
"	ldadda	%w2, %w0, %3\n"
"	nop\n"
"	nop\n"
"	nop\n"
	)

	/* Did we get the lock? */
"	eor	%w1, %w0, %w0, ror #16\n"
"	cbz	%w1, 3f\n"
	/*
	 * No: spin on the owner. Send a local event to avoid missing an
	 * unlock before the exclusive load.
	 */
"	sevl\n"
"2:	wfe\n"
"	ldaxrh	%w2, %4\n"
"	eor	%w1, %w2, %w0, lsr #16\n"
"	cbnz	%w1, 2b\n"
	/* We got the lock. Critical section starts here. */
"3:"
	: "=&r" (lockval), "=&r" (newval), "=&r" (tmp), "+Q" (*lock)
	: "Q" (lock->owner), "I" (1 << TICKET_SHIFT)
	: "memory");
}

static inline int arch_spin_trylock(arch_spinlock_t *lock)
{
	unsigned int tmp;
	arch_spinlock_t lockval;

	asm volatile(ARM64_LSE_ATOMIC_INSN(
	/* LL/SC */
	"	prfm	pstl1strm, %2\n"
	"1:	ldaxr	%w0, %2\n"
	"	eor	%w1, %w0, %w0, ror #16\n"
	"	cbnz	%w1, 2f\n"
	"	add	%w0, %w0, %3\n"
	"	stxr	%w1, %w0, %2\n"
	"	cbnz	%w1, 1b\n"
	"2:",
	/* LSE atomics */
	"	ldr	%w0, %2\n"
	"	eor	%w1, %w0, %w0, ror #16\n"
	"	cbnz	%w1, 1f\n"
	"	add	%w1, %w0, %3\n"
	"	casa	%w0, %w1, %2\n"
	"	and	%w1, %w1, #0xffff\n"
	"	eor	%w1, %w1, %w0, lsr #16\n"
	"1:")
	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
	: "I" (1 << TICKET_SHIFT)
	: "memory");

	return !tmp;
}

static inline void arch_spin_unlock(arch_spinlock_t *lock)
{
	unsigned long tmp;

	asm volatile(ARM64_LSE_ATOMIC_INSN(
	/* LL/SC */
	"	ldrh	%w1, %0\n"
	"	add	%w1, %w1, #1\n"
	"	stlrh	%w1, %0",
	/* LSE atomics */
	"	mov	%w1, #1\n"
	"	nop\n"
	"	staddlh	%w1, %0")
	: "=Q" (lock->owner), "=&r" (tmp)
	:
	: "memory");
}

static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
{
	return lock.owner == lock.next;
}

static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
	smp_mb(); /* See arch_spin_unlock_wait */
	return !arch_spin_value_unlocked(READ_ONCE(*lock));
}

static inline int arch_spin_is_contended(arch_spinlock_t *lock)
{
	arch_spinlock_t lockval = READ_ONCE(*lock);
	return (lockval.next - lockval.owner) > 1;
}
#define arch_spin_is_contended	arch_spin_is_contended

/*
 * Write lock implementation.
 *
 * Write locks set bit 31. Unlocking, is done by writing 0 since the lock is
 * exclusively held.
 *
 * The memory barriers are implicit with the load-acquire and store-release
 * instructions.
 */

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

	asm volatile(ARM64_LSE_ATOMIC_INSN(
	/* LL/SC */
	"	sevl\n"
	"1:	wfe\n"
	"2:	ldaxr	%w0, %1\n"
	"	cbnz	%w0, 1b\n"
	"	stxr	%w0, %w2, %1\n"
	"	cbnz	%w0, 2b\n"
	"	nop",
	/* LSE atomics */
	"1:	mov	%w0, wzr\n"
	"2:	casa	%w0, %w2, %1\n"
	"	cbz	%w0, 3f\n"
	"	ldxr	%w0, %1\n"
	"	cbz	%w0, 2b\n"
	"	wfe\n"
	"	b	1b\n"
	"3:")
	: "=&r" (tmp), "+Q" (rw->lock)
	: "r" (0x80000000)
	: "memory");
}

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

	asm volatile(ARM64_LSE_ATOMIC_INSN(
	/* LL/SC */
	"1:	ldaxr	%w0, %1\n"
	"	cbnz	%w0, 2f\n"
	"	stxr	%w0, %w2, %1\n"
	"	cbnz	%w0, 1b\n"
	"2:",
	/* LSE atomics */
	"	mov	%w0, wzr\n"
	"	casa	%w0, %w2, %1\n"
	"	nop\n"
	"	nop")
	: "=&r" (tmp), "+Q" (rw->lock)
	: "r" (0x80000000)
	: "memory");

	return !tmp;
}

static inline void arch_write_unlock(arch_rwlock_t *rw)
{
	asm volatile(ARM64_LSE_ATOMIC_INSN(
	"	stlr	wzr, %0",
	"	swpl	wzr, wzr, %0")
	: "=Q" (rw->lock) :: "memory");
}

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

/*
 * Read lock implementation.
 *
 * It exclusively loads the lock value, increments it and stores the new value
 * back if positive and the CPU still exclusively owns the location. If the
 * value is negative, the lock is already held.
 *
 * During unlocking there may be multiple active read locks but no write lock.
 *
 * The memory barriers are implicit with the load-acquire and store-release
 * instructions.
 *
 * Note that in UNDEFINED cases, such as unlocking a lock twice, the LL/SC
 * and LSE implementations may exhibit different behaviour (although this
 * will have no effect on lockdep).
 */
static inline void arch_read_lock(arch_rwlock_t *rw)
{
	unsigned int tmp, tmp2;

	asm volatile(
	"	sevl\n"
	ARM64_LSE_ATOMIC_INSN(
	/* LL/SC */
	"1:	wfe\n"
	"2:	ldaxr	%w0, %2\n"
	"	add	%w0, %w0, #1\n"
	"	tbnz	%w0, #31, 1b\n"
	"	stxr	%w1, %w0, %2\n"
	"	nop\n"
	"	cbnz	%w1, 2b",
	/* LSE atomics */
	"1:	wfe\n"
	"2:	ldxr	%w0, %2\n"
	"	adds	%w1, %w0, #1\n"
	"	tbnz	%w1, #31, 1b\n"
	"	casa	%w0, %w1, %2\n"
	"	sbc	%w0, %w1, %w0\n"
	"	cbnz	%w0, 2b")
	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
	:
	: "cc", "memory");
}

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

	asm volatile(ARM64_LSE_ATOMIC_INSN(
	/* LL/SC */
	"1:	ldxr	%w0, %2\n"
	"	sub	%w0, %w0, #1\n"
	"	stlxr	%w1, %w0, %2\n"
	"	cbnz	%w1, 1b",
	/* LSE atomics */
	"	movn	%w0, #0\n"
	"	nop\n"
	"	nop\n"
	"	staddl	%w0, %2")
	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
	:
	: "memory");
}

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

	asm volatile(ARM64_LSE_ATOMIC_INSN(
	/* LL/SC */
	"	mov	%w1, #1\n"
	"1:	ldaxr	%w0, %2\n"
	"	add	%w0, %w0, #1\n"
	"	tbnz	%w0, #31, 2f\n"
	"	stxr	%w1, %w0, %2\n"
	"	cbnz	%w1, 1b\n"
	"2:",
	/* LSE atomics */
	"	ldr	%w0, %2\n"
	"	adds	%w1, %w0, #1\n"
	"	tbnz	%w1, #31, 1f\n"
	"	casa	%w0, %w1, %2\n"
	"	sbc	%w1, %w1, %w0\n"
	"	nop\n"
	"1:")
	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
	:
	: "cc", "memory");

	return !tmp2;
}

/* 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()

/*
 * Accesses appearing in program order before a spin_lock() operation
 * can be reordered with accesses inside the critical section, by virtue
 * of arch_spin_lock being constructed using acquire semantics.
 *
 * In cases where this is problematic (e.g. try_to_wake_up), an
 * smp_mb__before_spinlock() can restore the required ordering.
 */
#define smp_mb__before_spinlock()	smp_mb()

#endif /* __ASM_SPINLOCK_H */