summaryrefslogtreecommitdiffstats
path: root/kernel/srcu.c
blob: b6b9ea2eb51c289672c3bec1699552e92c556940 (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
/*
 * Sleepable Read-Copy Update mechanism for mutual exclusion.
 *
 * This program 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 of the License, or
 * (at your option) any later version.
 *
 * 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, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 *
 * Copyright (C) IBM Corporation, 2006
 *
 * Author: Paul McKenney <paulmck@us.ibm.com>
 *
 * For detailed explanation of Read-Copy Update mechanism see -
 * 		Documentation/RCU/ *.txt
 *
 */

#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
#include <linux/preempt.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/delay.h>
#include <linux/srcu.h>

static int init_srcu_struct_fields(struct srcu_struct *sp)
{
	sp->completed = 0;
	mutex_init(&sp->mutex);
	sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array);
	return sp->per_cpu_ref ? 0 : -ENOMEM;
}

#ifdef CONFIG_DEBUG_LOCK_ALLOC

int __init_srcu_struct(struct srcu_struct *sp, const char *name,
		       struct lock_class_key *key)
{
	/* Don't re-initialize a lock while it is held. */
	debug_check_no_locks_freed((void *)sp, sizeof(*sp));
	lockdep_init_map(&sp->dep_map, name, key, 0);
	return init_srcu_struct_fields(sp);
}
EXPORT_SYMBOL_GPL(__init_srcu_struct);

#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */

/**
 * init_srcu_struct - initialize a sleep-RCU structure
 * @sp: structure to initialize.
 *
 * Must invoke this on a given srcu_struct before passing that srcu_struct
 * to any other function.  Each srcu_struct represents a separate domain
 * of SRCU protection.
 */
int init_srcu_struct(struct srcu_struct *sp)
{
	return init_srcu_struct_fields(sp);
}
EXPORT_SYMBOL_GPL(init_srcu_struct);

#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */

/*
 * Returns approximate number of readers active on the specified rank
 * of per-CPU counters.  Also snapshots each counter's value in the
 * corresponding element of sp->snap[] for later use validating
 * the sum.
 */
static unsigned long srcu_readers_active_idx(struct srcu_struct *sp, int idx)
{
	int cpu;
	unsigned long sum = 0;
	unsigned long t;

	for_each_possible_cpu(cpu) {
		t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]);
		sum += t;
		sp->snap[cpu] = t;
	}
	return sum & SRCU_REF_MASK;
}

/*
 * To be called from the update side after an index flip.  Returns true
 * if the modulo sum of the counters is stably zero, false if there is
 * some possibility of non-zero.
 */
static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
{
	int cpu;

	/*
	 * Note that srcu_readers_active_idx() can incorrectly return
	 * zero even though there is a pre-existing reader throughout.
	 * To see this, suppose that task A is in a very long SRCU
	 * read-side critical section that started on CPU 0, and that
	 * no other reader exists, so that the modulo sum of the counters
	 * is equal to one.  Then suppose that task B starts executing
	 * srcu_readers_active_idx(), summing up to CPU 1, and then that
	 * task C starts reading on CPU 0, so that its increment is not
	 * summed, but finishes reading on CPU 2, so that its decrement
	 * -is- summed.  Then when task B completes its sum, it will
	 * incorrectly get zero, despite the fact that task A has been
	 * in its SRCU read-side critical section the whole time.
	 *
	 * We therefore do a validation step should srcu_readers_active_idx()
	 * return zero.
	 */
	if (srcu_readers_active_idx(sp, idx) != 0)
		return false;

	/*
	 * Since the caller recently flipped ->completed, we can see at
	 * most one increment of each CPU's counter from this point
	 * forward.  The reason for this is that the reader CPU must have
	 * fetched the index before srcu_readers_active_idx checked
	 * that CPU's counter, but not yet incremented its counter.
	 * Its eventual counter increment will follow the read in
	 * srcu_readers_active_idx(), and that increment is immediately
	 * followed by smp_mb() B.  Because smp_mb() D is between
	 * the ->completed flip and srcu_readers_active_idx()'s read,
	 * that CPU's subsequent load of ->completed must see the new
	 * value, and therefore increment the counter in the other rank.
	 */
	smp_mb(); /* A */

	/*
	 * Now, we check the ->snap array that srcu_readers_active_idx()
	 * filled in from the per-CPU counter values. Since
	 * __srcu_read_lock() increments the upper bits of the per-CPU
	 * counter, an increment/decrement pair will change the value
	 * of the counter.  Since there is only one possible increment,
	 * the only way to wrap the counter is to have a huge number of
	 * counter decrements, which requires a huge number of tasks and
	 * huge SRCU read-side critical-section nesting levels, even on
	 * 32-bit systems.
	 *
	 * All of the ways of confusing the readings require that the scan
	 * in srcu_readers_active_idx() see the read-side task's decrement,
	 * but not its increment.  However, between that decrement and
	 * increment are smb_mb() B and C.  Either or both of these pair
	 * with smp_mb() A above to ensure that the scan below will see
	 * the read-side tasks's increment, thus noting a difference in
	 * the counter values between the two passes.
	 *
	 * Therefore, if srcu_readers_active_idx() returned zero, and
	 * none of the counters changed, we know that the zero was the
	 * correct sum.
	 *
	 * Of course, it is possible that a task might be delayed
	 * for a very long time in __srcu_read_lock() after fetching
	 * the index but before incrementing its counter.  This
	 * possibility will be dealt with in __synchronize_srcu().
	 */
	for_each_possible_cpu(cpu)
		if (sp->snap[cpu] !=
		    ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]))
			return false;  /* False zero reading! */
	return true;
}

/**
 * srcu_readers_active - returns approximate number of readers.
 * @sp: which srcu_struct to count active readers (holding srcu_read_lock).
 *
 * Note that this is not an atomic primitive, and can therefore suffer
 * severe errors when invoked on an active srcu_struct.  That said, it
 * can be useful as an error check at cleanup time.
 */
static int srcu_readers_active(struct srcu_struct *sp)
{
	return srcu_readers_active_idx(sp, 0) + srcu_readers_active_idx(sp, 1);
}

/**
 * cleanup_srcu_struct - deconstruct a sleep-RCU structure
 * @sp: structure to clean up.
 *
 * Must invoke this after you are finished using a given srcu_struct that
 * was initialized via init_srcu_struct(), else you leak memory.
 */
void cleanup_srcu_struct(struct srcu_struct *sp)
{
	int sum;

	sum = srcu_readers_active(sp);
	WARN_ON(sum);  /* Leakage unless caller handles error. */
	if (sum != 0)
		return;
	free_percpu(sp->per_cpu_ref);
	sp->per_cpu_ref = NULL;
}
EXPORT_SYMBOL_GPL(cleanup_srcu_struct);

/*
 * Counts the new reader in the appropriate per-CPU element of the
 * srcu_struct.  Must be called from process context.
 * Returns an index that must be passed to the matching srcu_read_unlock().
 */
int __srcu_read_lock(struct srcu_struct *sp)
{
	int idx;

	preempt_disable();
	idx = rcu_dereference_index_check(sp->completed,
					  rcu_read_lock_sched_held()) & 0x1;
	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) +=
		SRCU_USAGE_COUNT + 1;
	smp_mb(); /* B */  /* Avoid leaking the critical section. */
	preempt_enable();
	return idx;
}
EXPORT_SYMBOL_GPL(__srcu_read_lock);

/*
 * Removes the count for the old reader from the appropriate per-CPU
 * element of the srcu_struct.  Note that this may well be a different
 * CPU than that which was incremented by the corresponding srcu_read_lock().
 * Must be called from process context.
 */
void __srcu_read_unlock(struct srcu_struct *sp, int idx)
{
	preempt_disable();
	smp_mb(); /* C */  /* Avoid leaking the critical section. */
	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) -= 1;
	preempt_enable();
}
EXPORT_SYMBOL_GPL(__srcu_read_unlock);

/*
 * We use an adaptive strategy for synchronize_srcu() and especially for
 * synchronize_srcu_expedited().  We spin for a fixed time period
 * (defined below) to allow SRCU readers to exit their read-side critical
 * sections.  If there are still some readers after 10 microseconds,
 * we repeatedly block for 1-millisecond time periods.  This approach
 * has done well in testing, so there is no need for a config parameter.
 */
#define SYNCHRONIZE_SRCU_READER_DELAY 5

static void wait_idx(struct srcu_struct *sp, int idx, bool expedited)
{
	int trycount = 0;

	/*
	 * If a reader fetches the index before the ->completed increment,
	 * but increments its counter after srcu_readers_active_idx_check()
	 * sums it, then smp_mb() D will pair with __srcu_read_lock()'s
	 * smp_mb() B to ensure that the SRCU read-side critical section
	 * will see any updates that the current task performed before its
	 * call to synchronize_srcu(), or to synchronize_srcu_expedited(),
	 * as the case may be.
	 */
	smp_mb(); /* D */

	/*
	 * SRCU read-side critical sections are normally short, so wait
	 * a small amount of time before possibly blocking.
	 */
	if (!srcu_readers_active_idx_check(sp, idx)) {
		udelay(SYNCHRONIZE_SRCU_READER_DELAY);
		while (!srcu_readers_active_idx_check(sp, idx)) {
			if (expedited && ++ trycount < 10)
				udelay(SYNCHRONIZE_SRCU_READER_DELAY);
			else
				schedule_timeout_interruptible(1);
		}
	}

	/*
	 * The following smp_mb() E pairs with srcu_read_unlock()'s
	 * smp_mb C to ensure that if srcu_readers_active_idx_check()
	 * sees srcu_read_unlock()'s counter decrement, then any
	 * of the current task's subsequent code will happen after
	 * that SRCU read-side critical section.
	 *
	 * It also ensures the order between the above waiting and
	 * the next flipping.
	 */
	smp_mb(); /* E */
}

/*
 * Flip the readers' index by incrementing ->completed, then wait
 * until there are no more readers using the counters referenced by
 * the old index value.  (Recall that the index is the bottom bit
 * of ->completed.)
 *
 * Of course, it is possible that a reader might be delayed for the
 * full duration of flip_idx_and_wait() between fetching the
 * index and incrementing its counter.  This possibility is handled
 * by the next __synchronize_srcu() invoking wait_idx() for such readers
 * before starting a new grace period.
 */
static void flip_idx_and_wait(struct srcu_struct *sp, bool expedited)
{
	int idx;

	idx = sp->completed++ & 0x1;
	wait_idx(sp, idx, expedited);
}

/*
 * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
 */
static void __synchronize_srcu(struct srcu_struct *sp, bool expedited)
{
	rcu_lockdep_assert(!lock_is_held(&sp->dep_map) &&
			   !lock_is_held(&rcu_bh_lock_map) &&
			   !lock_is_held(&rcu_lock_map) &&
			   !lock_is_held(&rcu_sched_lock_map),
			   "Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section");

	mutex_lock(&sp->mutex);

	/*
	 * Suppose that during the previous grace period, a reader
	 * picked up the old value of the index, but did not increment
	 * its counter until after the previous instance of
	 * __synchronize_srcu() did the counter summation and recheck.
	 * That previous grace period was OK because the reader did
	 * not start until after the grace period started, so the grace
	 * period was not obligated to wait for that reader.
	 *
	 * However, the current SRCU grace period does have to wait for
	 * that reader.  This is handled by invoking wait_idx() on the
	 * non-active set of counters (hence sp->completed - 1).  Once
	 * wait_idx() returns, we know that all readers that picked up
	 * the old value of ->completed and that already incremented their
	 * counter will have completed.
	 *
	 * But what about readers that picked up the old value of
	 * ->completed, but -still- have not managed to increment their
	 * counter?  We do not need to wait for those readers, because
	 * they will have started their SRCU read-side critical section
	 * after the current grace period starts.
	 *
	 * Because it is unlikely that readers will be preempted between
	 * fetching ->completed and incrementing their counter, wait_idx()
	 * will normally not need to wait.
	 */
	wait_idx(sp, (sp->completed - 1) & 0x1, expedited);

	/*
	 * Now that wait_idx() has waited for the really old readers,
	 * invoke flip_idx_and_wait() to flip the counter and wait
	 * for current SRCU readers.
	 */
	flip_idx_and_wait(sp, expedited);

	mutex_unlock(&sp->mutex);
}

/**
 * synchronize_srcu - wait for prior SRCU read-side critical-section completion
 * @sp: srcu_struct with which to synchronize.
 *
 * Flip the completed counter, and wait for the old count to drain to zero.
 * As with classic RCU, the updater must use some separate means of
 * synchronizing concurrent updates.  Can block; must be called from
 * process context.
 *
 * Note that it is illegal to call synchronize_srcu() from the corresponding
 * SRCU read-side critical section; doing so will result in deadlock.
 * However, it is perfectly legal to call synchronize_srcu() on one
 * srcu_struct from some other srcu_struct's read-side critical section.
 */
void synchronize_srcu(struct srcu_struct *sp)
{
	__synchronize_srcu(sp, 0);
}
EXPORT_SYMBOL_GPL(synchronize_srcu);

/**
 * synchronize_srcu_expedited - Brute-force SRCU grace period
 * @sp: srcu_struct with which to synchronize.
 *
 * Wait for an SRCU grace period to elapse, but be more aggressive about
 * spinning rather than blocking when waiting.
 *
 * Note that it is illegal to call this function while holding any lock
 * that is acquired by a CPU-hotplug notifier.  It is also illegal to call
 * synchronize_srcu_expedited() from the corresponding SRCU read-side
 * critical section; doing so will result in deadlock.  However, it is
 * perfectly legal to call synchronize_srcu_expedited() on one srcu_struct
 * from some other srcu_struct's read-side critical section, as long as
 * the resulting graph of srcu_structs is acyclic.
 */
void synchronize_srcu_expedited(struct srcu_struct *sp)
{
	__synchronize_srcu(sp, 1);
}
EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);

/**
 * srcu_batches_completed - return batches completed.
 * @sp: srcu_struct on which to report batch completion.
 *
 * Report the number of batches, correlated with, but not necessarily
 * precisely the same as, the number of grace periods that have elapsed.
 */

long srcu_batches_completed(struct srcu_struct *sp)
{
	return sp->completed;
}
EXPORT_SYMBOL_GPL(srcu_batches_completed);