summaryrefslogtreecommitdiff
path: root/include/linux/seqlock.h
blob: cf87a24c0f92f1963081c93d7b0cce2356025358 (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
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
#ifndef __LINUX_SEQLOCK_H
#define __LINUX_SEQLOCK_H
/*
 * Reader/writer consistent mechanism without starving writers. This type of
 * lock for data where the reader wants a consistent set of information
 * and is willing to retry if the information changes. There are two types
 * of readers:
 * 1. Sequence readers which never block a writer but they may have to retry
 *    if a writer is in progress by detecting change in sequence number.
 *    Writers do not wait for a sequence reader.
 * 2. Locking readers which will wait if a writer or another locking reader
 *    is in progress. A locking reader in progress will also block a writer
 *    from going forward. Unlike the regular rwlock, the read lock here is
 *    exclusive so that only one locking reader can get it.
 *
 * This is not as cache friendly as brlock. Also, this may not work well
 * for data that contains pointers, because any writer could
 * invalidate a pointer that a reader was following.
 *
 * Expected non-blocking reader usage:
 * 	do {
 *	    seq = read_seqbegin(&foo);
 * 	...
 *      } while (read_seqretry(&foo, seq));
 *
 *
 * On non-SMP the spin locks disappear but the writer still needs
 * to increment the sequence variables because an interrupt routine could
 * change the state of the data.
 *
 * Based on x86_64 vsyscall gettimeofday 
 * by Keith Owens and Andrea Arcangeli
 */

#include <linux/spinlock.h>
#include <linux/preempt.h>
#include <linux/lockdep.h>
#include <asm/processor.h>

/*
 * Version using sequence counter only.
 * This can be used when code has its own mutex protecting the
 * updating starting before the write_seqcountbeqin() and ending
 * after the write_seqcount_end().
 */
typedef struct seqcount {
	unsigned sequence;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lockdep_map dep_map;
#endif
} seqcount_t;

static inline void __seqcount_init(seqcount_t *s, const char *name,
					  struct lock_class_key *key)
{
	/*
	 * Make sure we are not reinitializing a held lock:
	 */
	lockdep_init_map(&s->dep_map, name, key, 0);
	s->sequence = 0;
}

#ifdef CONFIG_DEBUG_LOCK_ALLOC
# define SEQCOUNT_DEP_MAP_INIT(lockname) \
		.dep_map = { .name = #lockname } \

# define seqcount_init(s)				\
	do {						\
		static struct lock_class_key __key;	\
		__seqcount_init((s), #s, &__key);	\
	} while (0)

static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
{
	seqcount_t *l = (seqcount_t *)s;
	unsigned long flags;

	local_irq_save(flags);
	seqcount_acquire_read(&l->dep_map, 0, 0, _RET_IP_);
	seqcount_release(&l->dep_map, 1, _RET_IP_);
	local_irq_restore(flags);
}

#else
# define SEQCOUNT_DEP_MAP_INIT(lockname)
# define seqcount_init(s) __seqcount_init(s, NULL, NULL)
# define seqcount_lockdep_reader_access(x)
#endif

#define SEQCNT_ZERO(lockname) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(lockname)}


/**
 * __read_seqcount_begin - begin a seq-read critical section (without barrier)
 * @s: pointer to seqcount_t
 * Returns: count to be passed to read_seqcount_retry
 *
 * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb()
 * barrier. Callers should ensure that smp_rmb() or equivalent ordering is
 * provided before actually loading any of the variables that are to be
 * protected in this critical section.
 *
 * Use carefully, only in critical code, and comment how the barrier is
 * provided.
 */
static inline unsigned __read_seqcount_begin(const seqcount_t *s)
{
	unsigned ret;

repeat:
	ret = ACCESS_ONCE(s->sequence);
	if (unlikely(ret & 1)) {
		cpu_relax();
		goto repeat;
	}
	return ret;
}

/**
 * read_seqcount_begin_no_lockdep - start seq-read critical section w/o lockdep
 * @s: pointer to seqcount_t
 * Returns: count to be passed to read_seqcount_retry
 *
 * read_seqcount_begin_no_lockdep opens a read critical section of the given
 * seqcount, but without any lockdep checking. Validity of the critical
 * section is tested by checking read_seqcount_retry function.
 */
static inline unsigned read_seqcount_begin_no_lockdep(const seqcount_t *s)
{
	unsigned ret = __read_seqcount_begin(s);
	smp_rmb();
	return ret;
}

/**
 * read_seqcount_begin - begin a seq-read critical section
 * @s: pointer to seqcount_t
 * Returns: count to be passed to read_seqcount_retry
 *
 * read_seqcount_begin opens a read critical section of the given seqcount.
 * Validity of the critical section is tested by checking read_seqcount_retry
 * function.
 */
static inline unsigned read_seqcount_begin(const seqcount_t *s)
{
	seqcount_lockdep_reader_access(s);
	return read_seqcount_begin_no_lockdep(s);
}

/**
 * raw_seqcount_begin - begin a seq-read critical section
 * @s: pointer to seqcount_t
 * Returns: count to be passed to read_seqcount_retry
 *
 * raw_seqcount_begin opens a read critical section of the given seqcount.
 * Validity of the critical section is tested by checking read_seqcount_retry
 * function.
 *
 * Unlike read_seqcount_begin(), this function will not wait for the count
 * to stabilize. If a writer is active when we begin, we will fail the
 * read_seqcount_retry() instead of stabilizing at the beginning of the
 * critical section.
 */
static inline unsigned raw_seqcount_begin(const seqcount_t *s)
{
	unsigned ret = ACCESS_ONCE(s->sequence);

	seqcount_lockdep_reader_access(s);
	smp_rmb();
	return ret & ~1;
}

/**
 * __read_seqcount_retry - end a seq-read critical section (without barrier)
 * @s: pointer to seqcount_t
 * @start: count, from read_seqcount_begin
 * Returns: 1 if retry is required, else 0
 *
 * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb()
 * barrier. Callers should ensure that smp_rmb() or equivalent ordering is
 * provided before actually loading any of the variables that are to be
 * protected in this critical section.
 *
 * Use carefully, only in critical code, and comment how the barrier is
 * provided.
 */
static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start)
{
	return unlikely(s->sequence != start);
}

/**
 * read_seqcount_retry - end a seq-read critical section
 * @s: pointer to seqcount_t
 * @start: count, from read_seqcount_begin
 * Returns: 1 if retry is required, else 0
 *
 * read_seqcount_retry closes a read critical section of the given seqcount.
 * If the critical section was invalid, it must be ignored (and typically
 * retried).
 */
static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
{
	smp_rmb();
	return __read_seqcount_retry(s, start);
}


/*
 * Sequence counter only version assumes that callers are using their
 * own mutexing.
 */
static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass)
{
	s->sequence++;
	smp_wmb();
	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
}

static inline void write_seqcount_begin(seqcount_t *s)
{
	write_seqcount_begin_nested(s, 0);
}

static inline void write_seqcount_end(seqcount_t *s)
{
	seqcount_release(&s->dep_map, 1, _RET_IP_);
	smp_wmb();
	s->sequence++;
}

/**
 * write_seqcount_barrier - invalidate in-progress read-side seq operations
 * @s: pointer to seqcount_t
 *
 * After write_seqcount_barrier, no read-side seq operations will complete
 * successfully and see data older than this.
 */
static inline void write_seqcount_barrier(seqcount_t *s)
{
	smp_wmb();
	s->sequence+=2;
}

typedef struct {
	struct seqcount seqcount;
	spinlock_t lock;
} seqlock_t;

/*
 * These macros triggered gcc-3.x compile-time problems.  We think these are
 * OK now.  Be cautious.
 */
#define __SEQLOCK_UNLOCKED(lockname)			\
	{						\
		.seqcount = SEQCNT_ZERO(lockname),	\
		.lock =	__SPIN_LOCK_UNLOCKED(lockname)	\
	}

#define seqlock_init(x)					\
	do {						\
		seqcount_init(&(x)->seqcount);		\
		spin_lock_init(&(x)->lock);		\
	} while (0)

#define DEFINE_SEQLOCK(x) \
		seqlock_t x = __SEQLOCK_UNLOCKED(x)

/*
 * Read side functions for starting and finalizing a read side section.
 */
static inline unsigned read_seqbegin(const seqlock_t *sl)
{
	return read_seqcount_begin(&sl->seqcount);
}

static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
{
	return read_seqcount_retry(&sl->seqcount, start);
}

/*
 * Lock out other writers and update the count.
 * Acts like a normal spin_lock/unlock.
 * Don't need preempt_disable() because that is in the spin_lock already.
 */
static inline void write_seqlock(seqlock_t *sl)
{
	spin_lock(&sl->lock);
	write_seqcount_begin(&sl->seqcount);
}

static inline void write_sequnlock(seqlock_t *sl)
{
	write_seqcount_end(&sl->seqcount);
	spin_unlock(&sl->lock);
}

static inline void write_seqlock_bh(seqlock_t *sl)
{
	spin_lock_bh(&sl->lock);
	write_seqcount_begin(&sl->seqcount);
}

static inline void write_sequnlock_bh(seqlock_t *sl)
{
	write_seqcount_end(&sl->seqcount);
	spin_unlock_bh(&sl->lock);
}

static inline void write_seqlock_irq(seqlock_t *sl)
{
	spin_lock_irq(&sl->lock);
	write_seqcount_begin(&sl->seqcount);
}

static inline void write_sequnlock_irq(seqlock_t *sl)
{
	write_seqcount_end(&sl->seqcount);
	spin_unlock_irq(&sl->lock);
}

static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
{
	unsigned long flags;

	spin_lock_irqsave(&sl->lock, flags);
	write_seqcount_begin(&sl->seqcount);
	return flags;
}

#define write_seqlock_irqsave(lock, flags)				\
	do { flags = __write_seqlock_irqsave(lock); } while (0)

static inline void
write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
{
	write_seqcount_end(&sl->seqcount);
	spin_unlock_irqrestore(&sl->lock, flags);
}

/*
 * A locking reader exclusively locks out other writers and locking readers,
 * but doesn't update the sequence number. Acts like a normal spin_lock/unlock.
 * Don't need preempt_disable() because that is in the spin_lock already.
 */
static inline void read_seqlock_excl(seqlock_t *sl)
{
	spin_lock(&sl->lock);
}

static inline void read_sequnlock_excl(seqlock_t *sl)
{
	spin_unlock(&sl->lock);
}

/**
 * read_seqbegin_or_lock - begin a sequence number check or locking block
 * @lock: sequence lock
 * @seq : sequence number to be checked
 *
 * First try it once optimistically without taking the lock. If that fails,
 * take the lock. The sequence number is also used as a marker for deciding
 * whether to be a reader (even) or writer (odd).
 * N.B. seq must be initialized to an even number to begin with.
 */
static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq)
{
	if (!(*seq & 1))	/* Even */
		*seq = read_seqbegin(lock);
	else			/* Odd */
		read_seqlock_excl(lock);
}

static inline int need_seqretry(seqlock_t *lock, int seq)
{
	return !(seq & 1) && read_seqretry(lock, seq);
}

static inline void done_seqretry(seqlock_t *lock, int seq)
{
	if (seq & 1)
		read_sequnlock_excl(lock);
}

static inline void read_seqlock_excl_bh(seqlock_t *sl)
{
	spin_lock_bh(&sl->lock);
}

static inline void read_sequnlock_excl_bh(seqlock_t *sl)
{
	spin_unlock_bh(&sl->lock);
}

static inline void read_seqlock_excl_irq(seqlock_t *sl)
{
	spin_lock_irq(&sl->lock);
}

static inline void read_sequnlock_excl_irq(seqlock_t *sl)
{
	spin_unlock_irq(&sl->lock);
}

static inline unsigned long __read_seqlock_excl_irqsave(seqlock_t *sl)
{
	unsigned long flags;

	spin_lock_irqsave(&sl->lock, flags);
	return flags;
}

#define read_seqlock_excl_irqsave(lock, flags)				\
	do { flags = __read_seqlock_excl_irqsave(lock); } while (0)

static inline void
read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags)
{
	spin_unlock_irqrestore(&sl->lock, flags);
}

#endif /* __LINUX_SEQLOCK_H */