summaryrefslogtreecommitdiffstats
path: root/include/linux/ptr_ring.h
blob: 37b4bb2545b32dc82633df6b76e629b9999f900b (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
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
/*
 *	Definitions for the 'struct ptr_ring' datastructure.
 *
 *	Author:
 *		Michael S. Tsirkin <mst@redhat.com>
 *
 *	Copyright (C) 2016 Red Hat, Inc.
 *
 *	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 is a limited-size FIFO maintaining pointers in FIFO order, with
 *	one CPU producing entries and another consuming entries from a FIFO.
 *
 *	This implementation tries to minimize cache-contention when there is a
 *	single producer and a single consumer CPU.
 */

#ifndef _LINUX_PTR_RING_H
#define _LINUX_PTR_RING_H 1

#ifdef __KERNEL__
#include <linux/spinlock.h>
#include <linux/cache.h>
#include <linux/types.h>
#include <linux/compiler.h>
#include <linux/cache.h>
#include <linux/slab.h>
#include <asm/errno.h>
#endif

struct ptr_ring {
	int producer ____cacheline_aligned_in_smp;
	spinlock_t producer_lock;
	int consumer_head ____cacheline_aligned_in_smp; /* next valid entry */
	int consumer_tail; /* next entry to invalidate */
	spinlock_t consumer_lock;
	/* Shared consumer/producer data */
	/* Read-only by both the producer and the consumer */
	int size ____cacheline_aligned_in_smp; /* max entries in queue */
	int batch; /* number of entries to consume in a batch */
	void **queue;
};

/* Note: callers invoking this in a loop must use a compiler barrier,
 * for example cpu_relax().  If ring is ever resized, callers must hold
 * producer_lock - see e.g. ptr_ring_full.  Otherwise, if callers don't hold
 * producer_lock, the next call to __ptr_ring_produce may fail.
 */
static inline bool __ptr_ring_full(struct ptr_ring *r)
{
	return r->queue[r->producer];
}

static inline bool ptr_ring_full(struct ptr_ring *r)
{
	bool ret;

	spin_lock(&r->producer_lock);
	ret = __ptr_ring_full(r);
	spin_unlock(&r->producer_lock);

	return ret;
}

static inline bool ptr_ring_full_irq(struct ptr_ring *r)
{
	bool ret;

	spin_lock_irq(&r->producer_lock);
	ret = __ptr_ring_full(r);
	spin_unlock_irq(&r->producer_lock);

	return ret;
}

static inline bool ptr_ring_full_any(struct ptr_ring *r)
{
	unsigned long flags;
	bool ret;

	spin_lock_irqsave(&r->producer_lock, flags);
	ret = __ptr_ring_full(r);
	spin_unlock_irqrestore(&r->producer_lock, flags);

	return ret;
}

static inline bool ptr_ring_full_bh(struct ptr_ring *r)
{
	bool ret;

	spin_lock_bh(&r->producer_lock);
	ret = __ptr_ring_full(r);
	spin_unlock_bh(&r->producer_lock);

	return ret;
}

/* Note: callers invoking this in a loop must use a compiler barrier,
 * for example cpu_relax(). Callers must hold producer_lock.
 */
static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
{
	if (unlikely(!r->size) || r->queue[r->producer])
		return -ENOSPC;

	r->queue[r->producer++] = ptr;
	if (unlikely(r->producer >= r->size))
		r->producer = 0;
	return 0;
}

/*
 * Note: resize (below) nests producer lock within consumer lock, so if you
 * consume in interrupt or BH context, you must disable interrupts/BH when
 * calling this.
 */
static inline int ptr_ring_produce(struct ptr_ring *r, void *ptr)
{
	int ret;

	spin_lock(&r->producer_lock);
	ret = __ptr_ring_produce(r, ptr);
	spin_unlock(&r->producer_lock);

	return ret;
}

static inline int ptr_ring_produce_irq(struct ptr_ring *r, void *ptr)
{
	int ret;

	spin_lock_irq(&r->producer_lock);
	ret = __ptr_ring_produce(r, ptr);
	spin_unlock_irq(&r->producer_lock);

	return ret;
}

static inline int ptr_ring_produce_any(struct ptr_ring *r, void *ptr)
{
	unsigned long flags;
	int ret;

	spin_lock_irqsave(&r->producer_lock, flags);
	ret = __ptr_ring_produce(r, ptr);
	spin_unlock_irqrestore(&r->producer_lock, flags);

	return ret;
}

static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr)
{
	int ret;

	spin_lock_bh(&r->producer_lock);
	ret = __ptr_ring_produce(r, ptr);
	spin_unlock_bh(&r->producer_lock);

	return ret;
}

/* Note: callers invoking this in a loop must use a compiler barrier,
 * for example cpu_relax(). Callers must take consumer_lock
 * if they dereference the pointer - see e.g. PTR_RING_PEEK_CALL.
 * If ring is never resized, and if the pointer is merely
 * tested, there's no need to take the lock - see e.g.  __ptr_ring_empty.
 */
static inline void *__ptr_ring_peek(struct ptr_ring *r)
{
	if (likely(r->size))
		return r->queue[r->consumer_head];
	return NULL;
}

/* Note: callers invoking this in a loop must use a compiler barrier,
 * for example cpu_relax(). Callers must take consumer_lock
 * if the ring is ever resized - see e.g. ptr_ring_empty.
 */
static inline bool __ptr_ring_empty(struct ptr_ring *r)
{
	return !__ptr_ring_peek(r);
}

static inline bool ptr_ring_empty(struct ptr_ring *r)
{
	bool ret;

	spin_lock(&r->consumer_lock);
	ret = __ptr_ring_empty(r);
	spin_unlock(&r->consumer_lock);

	return ret;
}

static inline bool ptr_ring_empty_irq(struct ptr_ring *r)
{
	bool ret;

	spin_lock_irq(&r->consumer_lock);
	ret = __ptr_ring_empty(r);
	spin_unlock_irq(&r->consumer_lock);

	return ret;
}

static inline bool ptr_ring_empty_any(struct ptr_ring *r)
{
	unsigned long flags;
	bool ret;

	spin_lock_irqsave(&r->consumer_lock, flags);
	ret = __ptr_ring_empty(r);
	spin_unlock_irqrestore(&r->consumer_lock, flags);

	return ret;
}

static inline bool ptr_ring_empty_bh(struct ptr_ring *r)
{
	bool ret;

	spin_lock_bh(&r->consumer_lock);
	ret = __ptr_ring_empty(r);
	spin_unlock_bh(&r->consumer_lock);

	return ret;
}

/* Must only be called after __ptr_ring_peek returned !NULL */
static inline void __ptr_ring_discard_one(struct ptr_ring *r)
{
	/* Fundamentally, what we want to do is update consumer
	 * index and zero out the entry so producer can reuse it.
	 * Doing it naively at each consume would be as simple as:
	 *       r->queue[r->consumer++] = NULL;
	 *       if (unlikely(r->consumer >= r->size))
	 *               r->consumer = 0;
	 * but that is suboptimal when the ring is full as producer is writing
	 * out new entries in the same cache line.  Defer these updates until a
	 * batch of entries has been consumed.
	 */
	int head = r->consumer_head++;

	/* Once we have processed enough entries invalidate them in
	 * the ring all at once so producer can reuse their space in the ring.
	 * We also do this when we reach end of the ring - not mandatory
	 * but helps keep the implementation simple.
	 */
	if (unlikely(r->consumer_head - r->consumer_tail >= r->batch ||
		     r->consumer_head >= r->size)) {
		/* Zero out entries in the reverse order: this way we touch the
		 * cache line that producer might currently be reading the last;
		 * producer won't make progress and touch other cache lines
		 * besides the first one until we write out all entries.
		 */
		while (likely(head >= r->consumer_tail))
			r->queue[head--] = NULL;
		r->consumer_tail = r->consumer_head;
	}
	if (unlikely(r->consumer_head >= r->size)) {
		r->consumer_head = 0;
		r->consumer_tail = 0;
	}
}

static inline void *__ptr_ring_consume(struct ptr_ring *r)
{
	void *ptr;

	ptr = __ptr_ring_peek(r);
	if (ptr)
		__ptr_ring_discard_one(r);

	return ptr;
}

static inline int __ptr_ring_consume_batched(struct ptr_ring *r,
					     void **array, int n)
{
	void *ptr;
	int i;

	for (i = 0; i < n; i++) {
		ptr = __ptr_ring_consume(r);
		if (!ptr)
			break;
		array[i] = ptr;
	}

	return i;
}

/*
 * Note: resize (below) nests producer lock within consumer lock, so if you
 * call this in interrupt or BH context, you must disable interrupts/BH when
 * producing.
 */
static inline void *ptr_ring_consume(struct ptr_ring *r)
{
	void *ptr;

	spin_lock(&r->consumer_lock);
	ptr = __ptr_ring_consume(r);
	spin_unlock(&r->consumer_lock);

	return ptr;
}

static inline void *ptr_ring_consume_irq(struct ptr_ring *r)
{
	void *ptr;

	spin_lock_irq(&r->consumer_lock);
	ptr = __ptr_ring_consume(r);
	spin_unlock_irq(&r->consumer_lock);

	return ptr;
}

static inline void *ptr_ring_consume_any(struct ptr_ring *r)
{
	unsigned long flags;
	void *ptr;

	spin_lock_irqsave(&r->consumer_lock, flags);
	ptr = __ptr_ring_consume(r);
	spin_unlock_irqrestore(&r->consumer_lock, flags);

	return ptr;
}

static inline void *ptr_ring_consume_bh(struct ptr_ring *r)
{
	void *ptr;

	spin_lock_bh(&r->consumer_lock);
	ptr = __ptr_ring_consume(r);
	spin_unlock_bh(&r->consumer_lock);

	return ptr;
}

static inline int ptr_ring_consume_batched(struct ptr_ring *r,
					   void **array, int n)
{
	int ret;

	spin_lock(&r->consumer_lock);
	ret = __ptr_ring_consume_batched(r, array, n);
	spin_unlock(&r->consumer_lock);

	return ret;
}

static inline int ptr_ring_consume_batched_irq(struct ptr_ring *r,
					       void **array, int n)
{
	int ret;

	spin_lock_irq(&r->consumer_lock);
	ret = __ptr_ring_consume_batched(r, array, n);
	spin_unlock_irq(&r->consumer_lock);

	return ret;
}

static inline int ptr_ring_consume_batched_any(struct ptr_ring *r,
					       void **array, int n)
{
	unsigned long flags;
	int ret;

	spin_lock_irqsave(&r->consumer_lock, flags);
	ret = __ptr_ring_consume_batched(r, array, n);
	spin_unlock_irqrestore(&r->consumer_lock, flags);

	return ret;
}

static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r,
					      void **array, int n)
{
	int ret;

	spin_lock_bh(&r->consumer_lock);
	ret = __ptr_ring_consume_batched(r, array, n);
	spin_unlock_bh(&r->consumer_lock);

	return ret;
}

/* Cast to structure type and call a function without discarding from FIFO.
 * Function must return a value.
 * Callers must take consumer_lock.
 */
#define __PTR_RING_PEEK_CALL(r, f) ((f)(__ptr_ring_peek(r)))

#define PTR_RING_PEEK_CALL(r, f) ({ \
	typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
	\
	spin_lock(&(r)->consumer_lock); \
	__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
	spin_unlock(&(r)->consumer_lock); \
	__PTR_RING_PEEK_CALL_v; \
})

#define PTR_RING_PEEK_CALL_IRQ(r, f) ({ \
	typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
	\
	spin_lock_irq(&(r)->consumer_lock); \
	__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
	spin_unlock_irq(&(r)->consumer_lock); \
	__PTR_RING_PEEK_CALL_v; \
})

#define PTR_RING_PEEK_CALL_BH(r, f) ({ \
	typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
	\
	spin_lock_bh(&(r)->consumer_lock); \
	__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
	spin_unlock_bh(&(r)->consumer_lock); \
	__PTR_RING_PEEK_CALL_v; \
})

#define PTR_RING_PEEK_CALL_ANY(r, f) ({ \
	typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
	unsigned long __PTR_RING_PEEK_CALL_f;\
	\
	spin_lock_irqsave(&(r)->consumer_lock, __PTR_RING_PEEK_CALL_f); \
	__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
	spin_unlock_irqrestore(&(r)->consumer_lock, __PTR_RING_PEEK_CALL_f); \
	__PTR_RING_PEEK_CALL_v; \
})

static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp)
{
	return kcalloc(size, sizeof(void *), gfp);
}

static inline void __ptr_ring_set_size(struct ptr_ring *r, int size)
{
	r->size = size;
	r->batch = SMP_CACHE_BYTES * 2 / sizeof(*(r->queue));
	/* We need to set batch at least to 1 to make logic
	 * in __ptr_ring_discard_one work correctly.
	 * Batching too much (because ring is small) would cause a lot of
	 * burstiness. Needs tuning, for now disable batching.
	 */
	if (r->batch > r->size / 2 || !r->batch)
		r->batch = 1;
}

static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp)
{
	r->queue = __ptr_ring_init_queue_alloc(size, gfp);
	if (!r->queue)
		return -ENOMEM;

	__ptr_ring_set_size(r, size);
	r->producer = r->consumer_head = r->consumer_tail = 0;
	spin_lock_init(&r->producer_lock);
	spin_lock_init(&r->consumer_lock);

	return 0;
}

/*
 * Return entries into ring. Destroy entries that don't fit.
 *
 * Note: this is expected to be a rare slow path operation.
 *
 * Note: producer lock is nested within consumer lock, so if you
 * resize you must make sure all uses nest correctly.
 * In particular if you consume ring in interrupt or BH context, you must
 * disable interrupts/BH when doing so.
 */
static inline void ptr_ring_unconsume(struct ptr_ring *r, void **batch, int n,
				      void (*destroy)(void *))
{
	unsigned long flags;
	int head;

	spin_lock_irqsave(&r->consumer_lock, flags);
	spin_lock(&r->producer_lock);

	if (!r->size)
		goto done;

	/*
	 * Clean out buffered entries (for simplicity). This way following code
	 * can test entries for NULL and if not assume they are valid.
	 */
	head = r->consumer_head - 1;
	while (likely(head >= r->consumer_tail))
		r->queue[head--] = NULL;
	r->consumer_tail = r->consumer_head;

	/*
	 * Go over entries in batch, start moving head back and copy entries.
	 * Stop when we run into previously unconsumed entries.
	 */
	while (n) {
		head = r->consumer_head - 1;
		if (head < 0)
			head = r->size - 1;
		if (r->queue[head]) {
			/* This batch entry will have to be destroyed. */
			goto done;
		}
		r->queue[head] = batch[--n];
		r->consumer_tail = r->consumer_head = head;
	}

done:
	/* Destroy all entries left in the batch. */
	while (n)
		destroy(batch[--n]);
	spin_unlock(&r->producer_lock);
	spin_unlock_irqrestore(&r->consumer_lock, flags);
}

static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue,
					   int size, gfp_t gfp,
					   void (*destroy)(void *))
{
	int producer = 0;
	void **old;
	void *ptr;

	while ((ptr = __ptr_ring_consume(r)))
		if (producer < size)
			queue[producer++] = ptr;
		else if (destroy)
			destroy(ptr);

	__ptr_ring_set_size(r, size);
	r->producer = producer;
	r->consumer_head = 0;
	r->consumer_tail = 0;
	old = r->queue;
	r->queue = queue;

	return old;
}

/*
 * Note: producer lock is nested within consumer lock, so if you
 * resize you must make sure all uses nest correctly.
 * In particular if you consume ring in interrupt or BH context, you must
 * disable interrupts/BH when doing so.
 */
static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
				  void (*destroy)(void *))
{
	unsigned long flags;
	void **queue = __ptr_ring_init_queue_alloc(size, gfp);
	void **old;

	if (!queue)
		return -ENOMEM;

	spin_lock_irqsave(&(r)->consumer_lock, flags);
	spin_lock(&(r)->producer_lock);

	old = __ptr_ring_swap_queue(r, queue, size, gfp, destroy);

	spin_unlock(&(r)->producer_lock);
	spin_unlock_irqrestore(&(r)->consumer_lock, flags);

	kfree(old);

	return 0;
}

/*
 * Note: producer lock is nested within consumer lock, so if you
 * resize you must make sure all uses nest correctly.
 * In particular if you consume ring in interrupt or BH context, you must
 * disable interrupts/BH when doing so.
 */
static inline int ptr_ring_resize_multiple(struct ptr_ring **rings,
					   unsigned int nrings,
					   int size,
					   gfp_t gfp, void (*destroy)(void *))
{
	unsigned long flags;
	void ***queues;
	int i;

	queues = kmalloc_array(nrings, sizeof(*queues), gfp);
	if (!queues)
		goto noqueues;

	for (i = 0; i < nrings; ++i) {
		queues[i] = __ptr_ring_init_queue_alloc(size, gfp);
		if (!queues[i])
			goto nomem;
	}

	for (i = 0; i < nrings; ++i) {
		spin_lock_irqsave(&(rings[i])->consumer_lock, flags);
		spin_lock(&(rings[i])->producer_lock);
		queues[i] = __ptr_ring_swap_queue(rings[i], queues[i],
						  size, gfp, destroy);
		spin_unlock(&(rings[i])->producer_lock);
		spin_unlock_irqrestore(&(rings[i])->consumer_lock, flags);
	}

	for (i = 0; i < nrings; ++i)
		kfree(queues[i]);

	kfree(queues);

	return 0;

nomem:
	while (--i >= 0)
		kfree(queues[i]);

	kfree(queues);

noqueues:
	return -ENOMEM;
}

static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *))
{
	void *ptr;

	if (destroy)
		while ((ptr = ptr_ring_consume(r)))
			destroy(ptr);
	kfree(r->queue);
}

#endif /* _LINUX_PTR_RING_H  */
OpenPOWER on IntegriCloud