ptr_ring.h 9.8 KB
Newer Older
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
/*
 *	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 ____cacheline_aligned_in_smp;
	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 */
	void **queue;
};

/* Note: callers invoking this in a loop must use a compiler barrier,
46 47 48
 * 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.
49 50 51 52 53 54 55 56
 */
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)
{
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
	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;
98 99 100
}

/* Note: callers invoking this in a loop must use a compiler barrier,
101
 * for example cpu_relax(). Callers must hold producer_lock.
102 103 104
 */
static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
{
105
	if (unlikely(!r->size) || r->queue[r->producer])
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
		return -ENOSPC;

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

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.
162 163
 * 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.
164 165 166
 */
static inline void *__ptr_ring_peek(struct ptr_ring *r)
{
167 168 169
	if (likely(r->size))
		return r->queue[r->consumer];
	return NULL;
170 171
}

172 173 174 175 176
/* 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)
177 178 179 180
{
	return !__ptr_ring_peek(r);
}

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
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;
}

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
/* Must only be called after __ptr_ring_peek returned !NULL */
static inline void __ptr_ring_discard_one(struct ptr_ring *r)
{
	r->queue[r->consumer++] = NULL;
	if (unlikely(r->consumer >= r->size))
		r->consumer = 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 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;
}

/* 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; \
})

333 334 335 336 337
static inline void **__ptr_ring_init_queue_alloc(int size, gfp_t gfp)
{
	return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp);
}

338 339
static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp)
{
340
	r->queue = __ptr_ring_init_queue_alloc(size, gfp);
341 342 343 344 345 346 347 348 349 350 351
	if (!r->queue)
		return -ENOMEM;

	r->size = size;
	r->producer = r->consumer = 0;
	spin_lock_init(&r->producer_lock);
	spin_lock_init(&r->consumer_lock);

	return 0;
}

352 353 354
static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue,
					   int size, gfp_t gfp,
					   void (*destroy)(void *))
355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371
{
	int producer = 0;
	void **old;
	void *ptr;

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

	r->size = size;
	r->producer = producer;
	r->consumer = 0;
	old = r->queue;
	r->queue = queue;

372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388
	return old;
}

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)->producer_lock, flags);

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

389 390 391 392 393 394 395
	spin_unlock_irqrestore(&(r)->producer_lock, flags);

	kfree(old);

	return 0;
}

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
static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
					   int size,
					   gfp_t gfp, void (*destroy)(void *))
{
	unsigned long flags;
	void ***queues;
	int i;

	queues = kmalloc(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])->producer_lock, flags);
		queues[i] = __ptr_ring_swap_queue(rings[i], queues[i],
						  size, gfp, destroy);
		spin_unlock_irqrestore(&(rings[i])->producer_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;
}

438
static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *))
439
{
440 441 442 443 444
	void *ptr;

	if (destroy)
		while ((ptr = ptr_ring_consume(r)))
			destroy(ptr);
445 446 447 448
	kfree(r->queue);
}

#endif /* _LINUX_PTR_RING_H  */